diff --git a/README.md b/README.md
index ad7acd7..7808759 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,6 @@
# OptiMHC
-**An optimum rescoring pipeline for immunopeptidomics data that significantly enhances peptide identification performance.**
+**An optimized rescoring pipeline for immunopeptidomics data that significantly enhances peptide identification performance.**
OptiMHC integrates multiple rescoring features with machine learning-based rescoring to maximize the number of confidently identified peptides from mass spectrometry experiments.
@@ -240,12 +240,6 @@ Here are some examples:
-### GUI (Experimental)
-
-```bash
-optimhc gui
-```
-
### Full CLI Help
```bash
diff --git a/docs/api/core.md b/docs/api/core.md
index 744a49c..e5aa4c1 100644
--- a/docs/api/core.md
+++ b/docs/api/core.md
@@ -24,12 +24,6 @@
options:
members: true
-## Logging
-
-::: optimhc.core.logging_helper
- options:
- members: true
-
## Utilities
::: optimhc.utils
diff --git a/docs/api/features.md b/docs/api/features.md
index 99f852a..6b92874 100644
--- a/docs/api/features.md
+++ b/docs/api/features.md
@@ -2,54 +2,54 @@
## Base Class
-::: optimhc.feature_generator.base_feature_generator
+::: optimhc.feature.base_feature_generator
options:
members: true
## Basic
-::: optimhc.feature_generator.basic
+::: optimhc.feature.basic
options:
members: true
## Spectral Similarity
-::: optimhc.feature_generator.spectral_similarity
+::: optimhc.feature.spectral_similarity
options:
members: true
## DeepLC
-::: optimhc.feature_generator.DeepLC
+::: optimhc.feature.deeplc
options:
members: true
## Overlapping Peptide
-::: optimhc.feature_generator.overlapping_peptide
+::: optimhc.feature.overlapping_peptide
options:
members: true
## PWM
-::: optimhc.feature_generator.PWM
+::: optimhc.feature.pwm
options:
members: true
## MHCflurry
-::: optimhc.feature_generator.mhcflurry
+::: optimhc.feature.mhcflurry
options:
members: true
## NetMHCpan
-::: optimhc.feature_generator.netMHCpan
+::: optimhc.feature.netmhcpan
options:
members: true
## NetMHCIIpan
-::: optimhc.feature_generator.netMHCIIpan
+::: optimhc.feature.netmhciipan
options:
members: true
diff --git a/docs/development/index.md b/docs/development/index.md
index cfe6391..63e4f42 100644
--- a/docs/development/index.md
+++ b/docs/development/index.md
@@ -20,7 +20,7 @@ uv sync --locked --group dev
Alternatively, using pip:
```bash
-pip install -e ".[gui]"
+pip install -e .
pip install pytest ruff pre-commit
```
@@ -42,7 +42,7 @@ uv run ruff format . # Format
uv run ruff format --check . # Check without modifying
```
-Configuration: `line-length = 99`, rules `["E", "F", "I"]` (pycodestyle errors, pyflakes, isort). `E501` (line too long) is ignored. Ruff excludes `docs/`, `examples/`, and `optimhc/gui/`.
+Configuration: `line-length = 99`, rules `["E", "F", "I"]` (pycodestyle errors, pyflakes, isort). `E501` (line too long) is ignored. Ruff excludes `docs/` and `examples/`.
## Pre-commit Hooks
diff --git a/docs/getting-started/installation.md b/docs/getting-started/installation.md
index 50611e4..926650d 100644
--- a/docs/getting-started/installation.md
+++ b/docs/getting-started/installation.md
@@ -71,7 +71,4 @@ netMHCIIpan -v # Should print the version number
optimhc --help
```
-You should see the available commands: `pipeline`, `experiment`, and `gui`.
-
-!!! note "GUI"
- The Streamlit GUI is currently under development.
+You should see the available commands: `pipeline` and `experiment`.
diff --git a/docs/index.md b/docs/index.md
index 73ce52c..041865c 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -1,6 +1,6 @@
# OptiMHC
-**An optimum rescoring pipeline for immunopeptidomics data that significantly enhances peptide identification performance.**
+**An optimized rescoring pipeline for immunopeptidomics data that significantly enhances peptide identification performance.**
OptiMHC integrates multiple rescoring features with machine learning-based rescoring to maximize the number of confidently identified peptides from mass spectrometry experiments.
diff --git a/optimhc/cli.py b/optimhc/cli.py
index 2f7c589..fae3e67 100644
--- a/optimhc/cli.py
+++ b/optimhc/cli.py
@@ -1,27 +1,55 @@
-import importlib.util
import json
import logging
-import os
-import sys
import click
+from optimhc import __version__
from optimhc.core import Pipeline
from optimhc.core.config import Config
-logging.basicConfig(
- level=logging.INFO,
- format="%(asctime)s %(levelname)s %(name)s: %(message)s",
- handlers=[logging.StreamHandler()],
-)
-
logger = logging.getLogger(__name__)
+LOG_MAPPING = {
+ "DEBUG": logging.DEBUG,
+ "INFO": logging.INFO,
+ "WARNING": logging.WARNING,
+ "ERROR": logging.ERROR,
+ "CRITICAL": logging.CRITICAL,
+}
+
+
+def setup_logging(level: str = "INFO") -> None:
+ if level not in LOG_MAPPING:
+ raise ValueError(f"Invalid log level: {level}")
+ logging.basicConfig(
+ level=LOG_MAPPING[level],
+ format="%(asctime)s [%(levelname)s] %(name)s - %(message)s",
+ datefmt="%Y-%m-%d %H:%M:%S",
+ force=True,
+ )
+
+ # mhctools attaches its own INFO-level handlers to its loggers
+ # https://github.com/openvax/mhctools/blob/master/mhctools/logging.conf
+ for name in [
+ "mhctools",
+ "mhctools.base_commandline_predictor",
+ "mhctools.netmhc",
+ "mhctools.netmhciipan",
+ "mhctools.process_helpers",
+ "mhctools.cleanup_context",
+ ]:
+ lg = logging.getLogger(name)
+ lg.handlers.clear()
+ lg.disabled = True
+ lg.propagate = False
+ lg.setLevel(logging.CRITICAL)
+
@click.group()
+@click.version_option(version=__version__, prog_name="optimhc")
def cli():
"""
- optiMHC - A high-performance rescoring pipeline for immunopeptidomics data.
+ OptiMHC - A optimized rescoring pipeline for immunopeptidomics data.
"""
pass
@@ -106,13 +134,8 @@ def pipeline(
model,
):
"""Run the optiMHC pipeline with the specified configuration."""
- # Load configuration
- if config:
- pipeline_config = Config(config)
- else:
- pipeline_config = Config()
+ pipeline_config = Config(config) if config else Config()
- # Override with command-line parameters
if inputtype:
pipeline_config["inputType"] = inputtype
if inputfile:
@@ -143,10 +166,9 @@ def pipeline(
if model:
pipeline_config["rescore"]["model"] = model
- # Run pipeline
+ setup_logging(pipeline_config["logLevel"])
pipeline_config.validate()
- pipeline = Pipeline(pipeline_config)
- pipeline.run()
+ Pipeline(pipeline_config).run()
@cli.command()
@@ -158,63 +180,10 @@ def pipeline(
)
def experiment(config):
"""Run multiple experiments with different feature combinations."""
- # Load configuration
pipeline_config = Config(config)
+ setup_logging(pipeline_config["logLevel"])
- # Run experiments
- pipeline = Pipeline(pipeline_config)
- pipeline.run_experiments()
-
-
-@cli.command()
-def gui():
- """Launch the optiMHC GUI."""
- if importlib.util.find_spec("streamlit") is None:
- print("Error: Streamlit is not installed. Install GUI dependencies with:")
- print("pip install optimhc[gui]")
- return
-
- import subprocess
-
- # Get the path to the GUI app
- gui_path = os.path.join(os.path.dirname(__file__), "gui", "app.py")
-
- if not os.path.exists(gui_path):
- print(f"Error: GUI application not found at {gui_path}")
- return
-
- # Create a temporary launcher script that uses the correct imports
- import tempfile
-
- launcher_content = """
-import os
-import sys
-import streamlit
-
-# Add the root directory to the path
-sys.path.insert(0, '{}')
-
-# Import the app module properly
-from optimhc.gui.app import main
-
-if __name__ == "__main__":
- main()
- """.format(os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))
-
- fd, temp_path = tempfile.mkstemp(suffix=".py")
- with os.fdopen(fd, "w") as f:
- f.write(launcher_content)
-
- # Launch Streamlit with the temporary script
- print("Starting optiMHC GUI...")
- try:
- subprocess.run([sys.executable, "-m", "streamlit", "run", temp_path])
- finally:
- # Clean up the temporary file
- try:
- os.unlink(temp_path)
- except OSError:
- pass
+ Pipeline(pipeline_config).run_experiments()
if __name__ == "__main__":
diff --git a/optimhc/core/config.py b/optimhc/core/config.py
index a88fabf..89c6d18 100644
--- a/optimhc/core/config.py
+++ b/optimhc/core/config.py
@@ -59,11 +59,15 @@ def load_config(config_path):
Load and parse a configuration file using YAML.
Merges loaded config with default configuration.
- Parameters:
- config_path (str): Path to the YAML configuration file.
+ Parameters
+ ----------
+ config_path : str
+ Path to the YAML configuration file.
- Returns:
- dict: A dictionary containing all configurations.
+ Returns
+ -------
+ dict
+ A dictionary containing all configurations.
"""
logger.info(f"Loading configuration from {config_path}")
with open(config_path, "r") as f:
diff --git a/optimhc/core/feature_generation.py b/optimhc/core/feature_generation.py
index d83fff6..e9cf448 100644
--- a/optimhc/core/feature_generation.py
+++ b/optimhc/core/feature_generation.py
@@ -1,30 +1,12 @@
-"""
-feature_generation.py
-
-Implements feature generation logic for optiMHC, supporting multiple feature generators
-(Basic, OverlappingPeptide, PWM, MHCflurry, NetMHCpan, NetMHCIIpan, DeepLC, SpectralSimilarity, etc.).
-"""
-
import gc
import logging
-import os
-import re
-
-from optimhc.feature_generator.netMHCIIpan import NetMHCIIpanFeatureGenerator
-# The reason why we need to import the feature generators here is that
-# the package 'mhctools' affect the logging configuration of optiMHC.
-# TODO: find a better way to handle this.
-from optimhc.feature_generator.netMHCpan import NetMHCpanFeatureGenerator
+import optimhc.feature # noqa: F401 -- triggers generator registration
+from optimhc.feature.factory import feature_generator_factory
logger = logging.getLogger(__name__)
-# TODO: refactor the code to pass config as a parameter to the generators
-# TODO: factory method for feature generators
-# TODO: for allele-specific generators, we need to test the validation of the allele input first
-
-
def generate_features(psms, config):
"""
Generate features from different generators according to the configuration.
@@ -35,321 +17,21 @@ def generate_features(psms, config):
A container object holding PSMs and relevant data.
config : dict
Configuration dictionary loaded from YAML or CLI.
-
- Returns
- -------
- None
- Features are added in-place to the PsmContainer.
-
- Examples
- --------
- >>> generate_features(psms, config)
"""
- remove_modification = True
- remove_pre_nxt_aa = config["removePreNxtAA"]
- n_processes = config["numProcesses"]
- show_progress = config["showProgress"]
- mod_dict = config.get("modificationMap", None)
- if mod_dict == {}:
- mod_dict = None
feature_generators = config.get("featureGenerator", None)
- allele = config.get("allele", None)
- unique_peptides = list(set(psms.peptides))
-
- if feature_generators is not None:
- for generator_config in feature_generators:
- if not isinstance(generator_config, dict):
- logger.warning("Feature generator config is not a dictionary, skipping...")
- continue
-
- generator_type = generator_config.get("name")
- logger.info(f"Generating features with {generator_type}...")
- generator_params = generator_config.get("params", {})
-
- if generator_type == "OverlappingPeptide":
- from optimhc.feature_generator.overlapping_peptide import (
- OverlappingPeptideFeatureGenerator,
- assign_brother_aggregated_feature,
- )
-
- overlapping_peptide = OverlappingPeptideFeatureGenerator(
- unique_peptides,
- min_overlap_length=generator_params.get("minOverlapLength", 8),
- min_length=generator_params.get("minLength", 8),
- max_length=generator_params.get("maxLength", 25),
- remove_pre_nxt_aa=remove_pre_nxt_aa,
- remove_modification=remove_modification,
- )
- overlapping_features = overlapping_peptide.generate_features()
- full_data = overlapping_peptide.get_full_data()
-
- psms.add_metadata(
- full_data[["Peptide", "contig_member_count", "ContigSequence"]],
- psms_key=psms.peptide_column,
- metadata_key="Peptide",
- source="OverlappingPeptide",
- )
- psms.add_features(
- overlapping_features,
- psms_key=psms.peptide_column,
- feature_key=overlapping_peptide.id_column,
- source="OverlappingPeptide",
- )
- score = generator_params.get("overlappingScore", None)
- if score:
- assign_brother_aggregated_feature(
- psms,
- feature_columns=score,
- overlapping_source="OverlappingPeptide",
- source_name="ContigFeatures",
- )
-
- del overlapping_peptide, overlapping_features, full_data
- gc.collect()
-
- elif generator_type == "Basic":
- from optimhc.feature_generator.basic import BasicFeatureGenerator
-
- basic_generator = BasicFeatureGenerator(
- psms.psms[psms.peptide_column].tolist(),
- remove_pre_nxt_aa=remove_pre_nxt_aa,
- remove_modification=remove_modification,
- )
- basic_features = basic_generator.generate_features()
- psms.add_features_by_index(
- basic_features[basic_generator.feature_columns], source="Basic"
- )
-
- del basic_generator, basic_features
- gc.collect()
-
- elif generator_type == "PWM":
- from optimhc.feature_generator.PWM import PWMFeatureGenerator
-
- pwm_generator = PWMFeatureGenerator(
- unique_peptides,
- alleles=allele,
- mhc_class=generator_params.get("class", "I"),
- remove_modification=remove_modification,
- remove_pre_nxt_aa=remove_pre_nxt_aa,
- )
- pwm_features = pwm_generator.generate_features()
- psms.add_features(
- pwm_features,
- psms_key=psms.peptide_column,
- feature_key=pwm_generator.id_column,
- source="PWM",
- )
-
- del pwm_generator, pwm_features
- gc.collect()
-
- elif generator_type == "MHCflurry":
- from optimhc.feature_generator.mhcflurry import (
- MHCflurryFeatureGenerator,
- )
-
- mhcflurry_generator = MHCflurryFeatureGenerator(
- unique_peptides,
- alleles=allele,
- remove_pre_nxt_aa=remove_pre_nxt_aa,
- remove_modification=remove_modification,
- )
- mhcflurry_features = mhcflurry_generator.generate_features()
- psms.add_features(
- mhcflurry_features,
- psms_key=psms.peptide_column,
- feature_key=mhcflurry_generator.id_column,
- source="MHCflurry",
- )
-
- del mhcflurry_generator, mhcflurry_features
- gc.collect()
-
- elif generator_type == "NetMHCpan":
- # from optimhc.feature_generator.netMHCpan import NetMHCpanFeatureGenerator
- netmhcpan_generator = NetMHCpanFeatureGenerator(
- unique_peptides,
- alleles=allele,
- mode=generator_params.get("mode", "best"),
- remove_pre_nxt_aa=remove_pre_nxt_aa,
- remove_modification=remove_modification,
- n_processes=n_processes,
- show_progress=show_progress,
- )
- netmhcpan_features = netmhcpan_generator.generate_features()
- psms.add_features(
- netmhcpan_features,
- psms_key=psms.peptide_column,
- feature_key=netmhcpan_generator.id_column,
- source="NetMHCpan",
- )
-
- del netmhcpan_generator, netmhcpan_features
- gc.collect()
-
- elif generator_type == "NetMHCIIpan":
- # from optimhc.feature_generator.netMHCIIpan import NetMHCIIpanFeatureGenerator
- netmhciipan_generator = NetMHCIIpanFeatureGenerator(
- unique_peptides,
- alleles=allele,
- mode=generator_params.get("mode", "best"),
- remove_pre_nxt_aa=remove_pre_nxt_aa,
- remove_modification=remove_modification,
- n_processes=n_processes,
- show_progress=show_progress,
- )
- netmhciipan_features = netmhciipan_generator.generate_features()
- psms.add_features(
- netmhciipan_features,
- psms_key=psms.peptide_column,
- feature_key=netmhciipan_generator.id_column,
- source="NetMHCIIpan",
- )
-
- del netmhciipan_generator, netmhciipan_features
- gc.collect()
-
- elif generator_type == "DeepLC":
- from optimhc.feature_generator.DeepLC import DeepLCFeatureGenerator
-
- deeplc_generator = DeepLCFeatureGenerator(
- psms,
- calibration_criteria_column=generator_params.get("calibrationCriteria"),
- lower_score_is_better=generator_params.get("lowerIsBetter"),
- calibration_set_size=generator_params.get("calibrationSize", 0.1),
- processes=n_processes,
- # TODO: Check here carefully
- # Since DeepLC is GPU-based,
- # the processes here is not the same meaning as the n_processes in multi-threading
- model_path=generator_params.get("model_path", None),
- remove_pre_nxt_aa=remove_pre_nxt_aa,
- mod_dict=mod_dict,
- )
- deeplc_features = deeplc_generator.generate_features()
- psms.add_features_by_index(
- deeplc_features[deeplc_generator.feature_columns], source="DeepLC"
- )
-
- del deeplc_generator, deeplc_features
- gc.collect()
-
- elif generator_type == "SpectralSimilarity":
- from optimhc.feature_generator.spectral_similarity import (
- SpectralSimilarityFeatureGenerator,
- )
-
- # Match PSMs with the spectra
- mzML_dir = generator_params.get("mzmlDir", None)
- if mzML_dir is None:
- logger.error(
- "mzML_dir is not provided for SpectralSimilarity feature generator."
- )
- continue
-
- pattern = generator_params.get("spectrumIdPattern", None)
- mz_file_names = []
- spectrum_ids = psms.spectrum_ids
-
- if pattern:
- logger.info(
- f"Using pattern: {pattern} to extract mzML file names from spectrum IDs."
- )
- for spectrum_id in spectrum_ids:
- mz_file_names.append(re.match(pattern, spectrum_id).group(1))
- logger.info(f"mzML file names: {list(set(mz_file_names))}")
- else:
- logger.info("Spectrum ID pattern is not provided.")
- if psms.ms_data_file_column is not None:
- logger.info(
- f"Trying to extract mzML file names from {psms.ms_data_file_column}"
- )
- logger.info(
- f"MS data file format: {set(psms.psms[psms.ms_data_file_column])}"
- )
-
- for ms_data_file in psms.psms[psms.ms_data_file_column]:
- mz_file_basename = os.path.basename(ms_data_file).split(".")[0]
- if mz_file_basename.endswith(".mzML"):
- mz_file_basename = mz_file_basename[:-5]
- elif mz_file_basename.endswith("mzML"):
- mz_file_basename = mz_file_basename[:-4]
- mz_file_names.append(mz_file_basename)
-
- logger.info(f"mzML file names: {list(set(mz_file_names))}")
- else:
- logger.info("MS data file information is not provided.")
- logger.info(
- r"Trying to use the default pattern: (.+?)\.\d+\.\d+\.\d+ to extract mzML file names from spectrum IDs."
- )
- for spectrum_id in spectrum_ids:
- mz_file_names.append(
- re.match(r"(.+?)\.\d+\.\d+\.\d+", spectrum_id).group(1)
- )
-
- mz_file_paths = [
- os.path.join(mzML_dir, f"{mz_file}.mzML") for mz_file in mz_file_names
- ]
- mz_file_paths_set = set(mz_file_paths)
- logger.info(f"mz_file_paths: {mz_file_paths_set}")
-
- for mz_file_path in mz_file_paths_set:
- if not os.path.exists(mz_file_path):
- logger.error(f"mzML file not found: {mz_file_path}")
- continue
-
- model_type = generator_params.get("model", None)
- if model_type is None:
- logger.error(
- "Model type is not provided for SpectralSimilarity feature generator."
- )
- raise ValueError(
- "Model type is required for SpectralSimilarity feature generator."
- )
-
- collision_energy = generator_params.get("collisionEnergy", None)
- instrument = generator_params.get("instrument", None)
- fragmentation_type = generator_params.get("fragmentationType", None)
- spectral_similarity_generator = SpectralSimilarityFeatureGenerator(
- spectrum_ids=psms.spectrum_ids,
- peptides=psms.peptides,
- charges=psms.charges,
- scan_ids=psms.scan_ids,
- mz_file_paths=mz_file_paths,
- model_type=generator_params.get("model"),
- collision_energies=(
- [collision_energy] * len(psms.peptides) if collision_energy else None
- ),
- instruments=([instrument] * len(psms.peptides) if instrument else None),
- fragmentation_types=(
- [fragmentation_type] * len(psms.peptides) if fragmentation_type else None
- ),
- remove_pre_nxt_aa=remove_pre_nxt_aa,
- mod_dict=mod_dict,
- url=generator_params.get("url"),
- ssl=generator_params.get("ssl", True),
- top_n=generator_params.get("numTopPeaks", 36),
- tolerance_ppm=generator_params.get("tolerance", 20),
- )
-
- spectral_similarity_features = spectral_similarity_generator.generate_features()
- psms.add_features(
- spectral_similarity_features,
- psms_key=[
- psms.spectrum_column,
- psms.peptide_column,
- psms.charge_column,
- ],
- feature_key=spectral_similarity_generator.id_column,
- source="SpectralSimilarity",
- )
- del (
- spectral_similarity_generator,
- spectral_similarity_features,
- mz_file_paths,
- mz_file_names,
- )
- gc.collect()
-
- else:
- logger.warning(f"Unknown feature generator: {generator_type}, skipping...")
+ if not feature_generators:
+ return
+
+ for generator_config in feature_generators:
+ if not isinstance(generator_config, dict):
+ logger.warning("Feature generator config is not a dictionary, skipping...")
+ continue
+
+ name = generator_config.get("name")
+ params = generator_config.get("params", {})
+
+ logger.info(f"Generating features with {name}...")
+ generator_cls = feature_generator_factory.get_generator(name)
+ generator = generator_cls.from_config(psms, config, params)
+ generator.apply(psms, source=name)
+ gc.collect()
diff --git a/optimhc/core/logging_helper.py b/optimhc/core/logging_helper.py
deleted file mode 100644
index 100cfc3..0000000
--- a/optimhc/core/logging_helper.py
+++ /dev/null
@@ -1,110 +0,0 @@
-import logging
-
-
-def setup_loggers(log_file=None, log_level="INFO"):
- """
- Create or update all loggers so that each logger has a StreamHandler and optionally a FileHandler.
- This ensures all log messages are displayed in the console and optionally saved to a file.
-
- Parameters
- ----------
- log_file : str, optional
- Path to the log file. If None, no file logging is set up.
- log_level : str, optional
- Logging level (DEBUG, INFO, WARNING, ERROR). Default is "INFO".
- """
- # Disable mhctools logging, avoid the warning message when multiprocessing
- for logger_name in [
- "mhctools",
- "mhctools.base_commandline_predictor",
- "mhctools.netmhc",
- "mhctools.netmhciipan",
- ]:
- logger = logging.getLogger(logger_name)
- logger.disabled = True
- logger.propagate = False
- logger.setLevel(logging.CRITICAL)
-
- loggers = [logging.getLogger(name) for name in logging.root.manager.loggerDict]
- level = getattr(logging, log_level.upper(), logging.INFO)
-
- # debug_logging()
-
- for lg in loggers:
- if lg.name.startswith("mhctools"):
- continue
-
- lg.disabled = False
- has_stream_handler = any(
- isinstance(handler, logging.StreamHandler) for handler in lg.handlers
- )
- if not has_stream_handler:
- console_handler = logging.StreamHandler()
- console_handler.setLevel(level)
- formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
- console_handler.setFormatter(formatter)
- lg.addHandler(console_handler)
-
- if log_file:
- has_file_handler = any(
- isinstance(handler, logging.FileHandler) for handler in lg.handlers
- )
- if not has_file_handler:
- file_handler = logging.FileHandler(log_file, mode="a")
- file_handler.setLevel(level)
- formatter = logging.Formatter(
- "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
- )
- file_handler.setFormatter(formatter)
- lg.addHandler(file_handler)
-
- lg.propagate = False
- lg.setLevel(level)
-
- if lg.name.startswith("optimhc"):
- lg.disabled = False
-
- root_logger = logging.getLogger()
- root_logger.disabled = False
- root_logger.setLevel(level)
-
-
-def debug_logging():
- """
- Print debugging information for all loggers that start with 'optimhc' and
- the root logger. This helps verify that logger configurations are set properly.
- """
- print("\n=== Debugging Loggers ===\n")
- loggers = [logging.getLogger(name) for name in logging.root.manager.loggerDict.keys()]
- for lg in loggers:
- if lg.name.startswith("optimhc"):
- print(f"Logger Name: {lg.name}")
- print(f" - Effective Level: {logging.getLevelName(lg.getEffectiveLevel())}")
- print(f" - Explicit Level: {logging.getLevelName(lg.level)} (default: NOTSET)")
- print(f" - Propagate: {lg.propagate}")
- print(f" - Disabled: {lg.disabled}")
-
- if lg.handlers:
- for handler in lg.handlers:
- print(f" Handler: {type(handler).__name__}")
- print(f" - Level: {logging.getLevelName(handler.level)}")
- print(f" - Formatter: {handler.formatter}")
- if isinstance(handler, logging.FileHandler):
- print(f" - Log File: {handler.baseFilename}")
- print(f" - Stream: {getattr(handler, 'stream', None)}")
- else:
- print(" No handlers attached to the logger.")
- print("")
-
- root_logger = logging.getLogger()
- print("Root Logger:")
- print(f" - Level: {logging.getLevelName(root_logger.level)}")
- print(f" - Handlers: {len(root_logger.handlers)}")
- for handler in root_logger.handlers:
- print(f" Handler: {type(handler).__name__}")
- print(f" - Level: {logging.getLevelName(handler.level)}")
- print(f" - Formatter: {handler.formatter}")
- if isinstance(handler, logging.FileHandler):
- print(f" - Log File: {handler.baseFilename}")
- print(f" - Stream: {getattr(handler, 'stream', None)}")
- print("\n=== End of Logger Debugging ===\n")
diff --git a/optimhc/core/pipeline.py b/optimhc/core/pipeline.py
index 32b5653..ab4fad8 100644
--- a/optimhc/core/pipeline.py
+++ b/optimhc/core/pipeline.py
@@ -15,7 +15,6 @@
from optimhc.core.config import Config
from optimhc.core.feature_generation import generate_features
-from optimhc.core.logging_helper import setup_loggers
from optimhc.parser import read_pepxml, read_pin
from optimhc.rescore import mokapot
from optimhc.rescore.model import RandomForestPercolatorModel, XGBoostPercolatorModel
@@ -67,7 +66,6 @@ def __init__(self, config):
self.experiment = self.config.get("experimentName", "optimhc_experiment")
self.output_dir = os.path.join(self.config["outputDir"], self.experiment)
os.makedirs(self.output_dir, exist_ok=True)
- setup_loggers(os.path.join(self.output_dir, "log"), self.config.get("logLevel", "INFO"))
self.visualization_enabled = self.config.get("visualization", True)
self.save_models = self.config.get("saveModels", True)
diff --git a/optimhc/feature/__init__.py b/optimhc/feature/__init__.py
new file mode 100644
index 0000000..c69db0c
--- /dev/null
+++ b/optimhc/feature/__init__.py
@@ -0,0 +1,27 @@
+from optimhc.feature.base_feature_generator import BaseFeatureGenerator
+from optimhc.feature.basic import BasicFeatureGenerator
+from optimhc.feature.deeplc import DeepLCFeatureGenerator
+from optimhc.feature.factory import feature_generator_factory
+from optimhc.feature.mhcflurry import MHCflurryFeatureGenerator
+from optimhc.feature.netmhciipan import NetMHCIIpanFeatureGenerator
+from optimhc.feature.netmhcpan import NetMHCpanFeatureGenerator
+from optimhc.feature.overlapping_peptide import (
+ OverlappingPeptideFeatureGenerator,
+)
+from optimhc.feature.pwm import PWMFeatureGenerator
+from optimhc.feature.spectral_similarity import (
+ SpectralSimilarityFeatureGenerator,
+)
+
+__all__ = [
+ "feature_generator_factory",
+ "BaseFeatureGenerator",
+ "BasicFeatureGenerator",
+ "PWMFeatureGenerator",
+ "OverlappingPeptideFeatureGenerator",
+ "MHCflurryFeatureGenerator",
+ "NetMHCpanFeatureGenerator",
+ "NetMHCIIpanFeatureGenerator",
+ "DeepLCFeatureGenerator",
+ "SpectralSimilarityFeatureGenerator",
+]
diff --git a/optimhc/feature/base_feature_generator.py b/optimhc/feature/base_feature_generator.py
new file mode 100644
index 0000000..8d9424f
--- /dev/null
+++ b/optimhc/feature/base_feature_generator.py
@@ -0,0 +1,80 @@
+from abc import ABC, abstractmethod
+from typing import List
+
+import pandas as pd
+
+from optimhc.psm_container import PsmContainer
+
+
+class BaseFeatureGenerator(ABC):
+ """Abstract base class for all feature generators in the rescoring pipeline.
+
+ Subclasses must implement:
+ - ``feature_columns`` -- names of generated feature columns
+ - ``id_column`` -- merge key column(s)
+ - ``generate_features()`` -- pure computation, returns a DataFrame
+ - ``from_config()`` -- construct an instance from pipeline config
+
+ The default ``apply()`` merges features by peptide column.
+ Override it for index-based merges, composite keys, or post-processing.
+ """
+
+ @property
+ @abstractmethod
+ def feature_columns(self) -> List[str]:
+ """Return a list of feature column names produced by this generator."""
+ ...
+
+ @property
+ @abstractmethod
+ def id_column(self) -> List[str]:
+ """Return the column(s) used as merge key(s) with the PsmContainer."""
+ ...
+
+ @abstractmethod
+ def generate_features(self) -> pd.DataFrame:
+ """Generate features and return them as a DataFrame."""
+ ...
+
+ @classmethod
+ def from_config(
+ cls,
+ psms: PsmContainer,
+ config: dict,
+ params: dict,
+ ) -> "BaseFeatureGenerator":
+ """Construct a generator instance from pipeline configuration.
+
+ Parameters
+ ----------
+ psms : PsmContainer
+ The PSM container with all current data.
+ config : dict
+ The full pipeline configuration.
+ params : dict
+ Generator-specific parameters from
+ ``config["featureGenerator"][i]["params"]``.
+ """
+ raise NotImplementedError(f"{cls.__name__} must implement from_config()")
+
+ def apply(self, psms: PsmContainer, source: str) -> None:
+ """Generate features and merge them into the PsmContainer.
+
+ The default implementation merges by peptide column using
+ ``add_features()``. Override for different merge strategies
+ (index-based, composite key) or additional post-processing.
+
+ Parameters
+ ----------
+ psms : PsmContainer
+ The PSM container to add features to (modified in-place).
+ source : str
+ Name of this feature source (e.g. ``"Basic"``, ``"PWM"``).
+ """
+ features = self.generate_features()
+ psms.add_features(
+ features,
+ psms_key=psms.peptide_column,
+ feature_key=self.id_column,
+ source=source,
+ )
diff --git a/optimhc/feature_generator/basic.py b/optimhc/feature/basic.py
similarity index 85%
rename from optimhc/feature_generator/basic.py
rename to optimhc/feature/basic.py
index 2d29472..2e0fde3 100644
--- a/optimhc/feature_generator/basic.py
+++ b/optimhc/feature/basic.py
@@ -1,5 +1,3 @@
-# feature_generator/basic.py
-
import logging
from typing import List
@@ -7,7 +5,8 @@
from scipy.stats import entropy # Import entropy from scipy
from optimhc import utils
-from optimhc.feature_generator.base_feature_generator import BaseFeatureGenerator
+from optimhc.feature.base_feature_generator import BaseFeatureGenerator
+from optimhc.feature.factory import feature_generator_factory
logger = logging.getLogger(__name__)
@@ -85,11 +84,15 @@ def _preprocess_peptide(self, peptide: str) -> str:
"""
Preprocess peptide sequence by removing adjacent amino acids and modifications.
- Parameters:
- peptide (str): Original peptide sequence.
+ Parameters
+ ----------
+ peptide : str
+ Original peptide sequence.
- Returns:
- str: Preprocessed peptide sequence.
+ Returns
+ -------
+ str
+ Preprocessed peptide sequence.
"""
if self.remove_pre_nxt_aa:
peptide = utils.strip_flanking_and_charge(peptide)
@@ -101,11 +104,15 @@ def _shannon_entropy(self, sequence: str) -> float:
"""
Calculate the Shannon entropy of a peptide sequence.
- Parameters:
- sequence (str): Peptide sequence.
+ Parameters
+ ----------
+ sequence : str
+ Peptide sequence.
- Returns:
- float: Shannon entropy value.
+ Returns
+ -------
+ float
+ Shannon entropy value.
"""
if len(sequence) == 0:
return 0.0
@@ -162,3 +169,18 @@ def generate_features(self) -> pd.DataFrame:
logger.info(f"Generated basic features for {len(features_df)} peptides.")
return features_df
+
+ @classmethod
+ def from_config(cls, psms, config, params):
+ return cls(
+ peptides=psms.peptides,
+ remove_pre_nxt_aa=config["removePreNxtAA"],
+ remove_modification=True,
+ )
+
+ def apply(self, psms, source):
+ features = self.generate_features()
+ psms.add_features_by_index(features[self.feature_columns], source=source)
+
+
+feature_generator_factory.register_generator("Basic", BasicFeatureGenerator)
diff --git a/optimhc/feature_generator/DeepLC.py b/optimhc/feature/deeplc.py
similarity index 92%
rename from optimhc/feature_generator/DeepLC.py
rename to optimhc/feature/deeplc.py
index 0060e8a..348f791 100644
--- a/optimhc/feature_generator/DeepLC.py
+++ b/optimhc/feature/deeplc.py
@@ -1,4 +1,3 @@
-# feature_generator/DeepLC.py
# TODO: Use koina for prediction
import logging
@@ -9,7 +8,8 @@
from deeplc import DeepLC
from optimhc import utils
-from optimhc.feature_generator.base_feature_generator import BaseFeatureGenerator
+from optimhc.feature.base_feature_generator import BaseFeatureGenerator
+from optimhc.feature.factory import feature_generator_factory
from optimhc.psm_container import PsmContainer
logger = logging.getLogger(__name__)
@@ -78,28 +78,30 @@ def __init__(
DeepLC retraining is on by default. Add ``deeplc_retrain: False`` as a keyword argument to
disable retraining.
- Parameters:
- psms: PsmContainer
+ Parameters
+ ----------
+ psms : PsmContainer
PSMs to generate features for.
- calibration_criteria_column: str
+ calibration_criteria_column : str
Column name in the PSMs DataFrame to use for DeepLC calibration.
- lower_score_is_better
- Whether a lower PSM score denotes a better matching PSM. Default: False
- calibration_set_size: int or float
+ lower_score_is_better : bool
+ Whether a lower PSM score denotes a better matching PSM. Default: False.
+ calibration_set_size : int or float
Amount of best PSMs to use for DeepLC calibration. If this value is lower
than the number of available PSMs, all PSMs will be used. (default: 0.15)
- processes: {int, None}
+ processes : int or None
Number of processes to use in DeepLC. Defaults to 1.
- model_path: str
+ model_path : str
Path to the DeepLC model. If None, the default model will be used.
- remove_pre_nxt_aa: bool
+ remove_pre_nxt_aa : bool
Whether to remove the first and last amino acids from the peptide sequence.
- Default: True
- mod_dict: dict
- Dictionary of modifications to be used for DeepLC. If None, no modifications will be used.
- *args: list
+ Default: True.
+ mod_dict : dict
+ Dictionary of modifications to be used for DeepLC. If None, no modifications
+ will be used.
+ *args : list
Additional positional arguments are passed to DeepLC.
- kwargs: dict
+ **kwargs : dict
Additional keyword arguments are passed to DeepLC.
"""
self.psms = psms
@@ -456,3 +458,26 @@ def save_raw_predictions(self, file_path: str, **kwargs) -> None:
logger.info(f"Raw predictions saved to {file_path}")
else:
logger.warning("Raw predictions have not been generated yet.")
+
+ @classmethod
+ def from_config(cls, psms, config, params):
+ mod_dict = config.get("modificationMap", None)
+ if mod_dict == {}:
+ mod_dict = None
+ return cls(
+ psms=psms,
+ calibration_criteria_column=params.get("calibrationCriteria"),
+ lower_score_is_better=params.get("lowerIsBetter"),
+ calibration_set_size=params.get("calibrationSize", 0.1),
+ processes=config.get("numProcesses", 1),
+ model_path=params.get("model_path", None),
+ remove_pre_nxt_aa=config["removePreNxtAA"],
+ mod_dict=mod_dict,
+ )
+
+ def apply(self, psms, source):
+ features = self.generate_features()
+ psms.add_features_by_index(features[self.feature_columns], source=source)
+
+
+feature_generator_factory.register_generator("DeepLC", DeepLCFeatureGenerator)
diff --git a/optimhc/feature/factory.py b/optimhc/feature/factory.py
new file mode 100644
index 0000000..561c0c8
--- /dev/null
+++ b/optimhc/feature/factory.py
@@ -0,0 +1,37 @@
+import logging
+from typing import Dict, List, Type
+
+from optimhc.feature.base_feature_generator import BaseFeatureGenerator
+
+logger = logging.getLogger(__name__)
+
+
+class FeatureGeneratorFactory:
+ """Registry and factory for feature generators.
+
+ Each generator module registers itself at import time by calling
+ ``feature_generator_factory.register_generator(name, cls)``.
+ The orchestrator retrieves generators by name via ``get_generator(name)``.
+ """
+
+ def __init__(self):
+ self._registry: Dict[str, Type[BaseFeatureGenerator]] = {}
+
+ def register_generator(self, name: str, generator_class: Type[BaseFeatureGenerator]):
+ """Register a feature generator class under *name*."""
+ self._registry[name] = generator_class
+
+ def get_generator(self, name: str) -> Type[BaseFeatureGenerator]:
+ """Return the generator class registered under *name*."""
+ if name not in self._registry:
+ raise ValueError(
+ f"Unknown feature generator: '{name}'. Available: {sorted(self._registry.keys())}"
+ )
+ return self._registry[name]
+
+ def list_generators(self) -> List[str]:
+ """Return sorted list of registered generator names."""
+ return sorted(self._registry.keys())
+
+
+feature_generator_factory = FeatureGeneratorFactory()
diff --git a/optimhc/feature_generator/mhcflurry.py b/optimhc/feature/mhcflurry.py
similarity index 95%
rename from optimhc/feature_generator/mhcflurry.py
rename to optimhc/feature/mhcflurry.py
index 1cc3b30..d151f06 100644
--- a/optimhc/feature_generator/mhcflurry.py
+++ b/optimhc/feature/mhcflurry.py
@@ -5,7 +5,8 @@
from mhcflurry import Class1PresentationPredictor
from optimhc import utils
-from optimhc.feature_generator.base_feature_generator import BaseFeatureGenerator
+from optimhc.feature.base_feature_generator import BaseFeatureGenerator
+from optimhc.feature.factory import feature_generator_factory
logger = logging.getLogger(__name__)
@@ -338,3 +339,15 @@ def predictions_to_dataframe(self) -> pd.DataFrame:
if self.predictions is None:
raise ValueError("No predictions available. Please run 'generate_features' first.")
return self.predictions
+
+ @classmethod
+ def from_config(cls, psms, config, params):
+ return cls(
+ peptides=list(set(psms.peptides)),
+ alleles=config.get("allele", []),
+ remove_pre_nxt_aa=config["removePreNxtAA"],
+ remove_modification=True,
+ )
+
+
+feature_generator_factory.register_generator("MHCflurry", MHCflurryFeatureGenerator)
diff --git a/optimhc/feature_generator/netMHCIIpan.py b/optimhc/feature/netmhciipan.py
similarity index 97%
rename from optimhc/feature_generator/netMHCIIpan.py
rename to optimhc/feature/netmhciipan.py
index b65db9d..336fc5e 100644
--- a/optimhc/feature_generator/netMHCIIpan.py
+++ b/optimhc/feature/netmhciipan.py
@@ -1,5 +1,3 @@
-# feature_generator/netMHCIIpan.py
-
# TODO: set 'BA' and 'EL' as optional parameters for the user to choose the prediction method.
import logging
@@ -12,7 +10,8 @@
from tqdm import tqdm
from optimhc import utils
-from optimhc.feature_generator.base_feature_generator import BaseFeatureGenerator
+from optimhc.feature.base_feature_generator import BaseFeatureGenerator
+from optimhc.feature.factory import feature_generator_factory
logger = logging.getLogger(__name__)
@@ -647,3 +646,18 @@ def save_raw_predictions(self, file_path: str, **kwargs) -> None:
logger.info(f"Raw prediction results saved to: {file_path}")
else:
logger.warning("No raw prediction results available to save.")
+
+ @classmethod
+ def from_config(cls, psms, config, params):
+ return cls(
+ peptides=list(set(psms.peptides)),
+ alleles=config.get("allele", []),
+ mode=params.get("mode", "best"),
+ remove_pre_nxt_aa=config["removePreNxtAA"],
+ remove_modification=True,
+ n_processes=config.get("numProcesses", 1),
+ show_progress=config.get("showProgress", False),
+ )
+
+
+feature_generator_factory.register_generator("NetMHCIIpan", NetMHCIIpanFeatureGenerator)
diff --git a/optimhc/feature_generator/netMHCpan.py b/optimhc/feature/netmhcpan.py
similarity index 97%
rename from optimhc/feature_generator/netMHCpan.py
rename to optimhc/feature/netmhcpan.py
index 089bd6d..7816da6 100644
--- a/optimhc/feature_generator/netMHCpan.py
+++ b/optimhc/feature/netmhcpan.py
@@ -1,5 +1,3 @@
-# feature_generators/netmhcpan_feature_generator.py
-
# TODO: Except 'best' mode, the other modes seems to be not working properly. We need to investigate this issue.
import logging
@@ -12,6 +10,7 @@
from tqdm import tqdm
from optimhc import utils
+from optimhc.feature.factory import feature_generator_factory
from .base_feature_generator import BaseFeatureGenerator
@@ -674,3 +673,18 @@ def predictions_to_dataframe(self) -> pd.DataFrame:
# logger.info(f"Generated best allele information for {len(best_allele_df)} peptides.")
# return best_allele_df
+
+ @classmethod
+ def from_config(cls, psms, config, params):
+ return cls(
+ peptides=list(set(psms.peptides)),
+ alleles=config.get("allele", []),
+ mode=params.get("mode", "best"),
+ remove_pre_nxt_aa=config["removePreNxtAA"],
+ remove_modification=True,
+ n_processes=config.get("numProcesses", 1),
+ show_progress=config.get("showProgress", False),
+ )
+
+
+feature_generator_factory.register_generator("NetMHCpan", NetMHCpanFeatureGenerator)
diff --git a/optimhc/feature_generator/numba_utils.py b/optimhc/feature/numba_utils.py
similarity index 100%
rename from optimhc/feature_generator/numba_utils.py
rename to optimhc/feature/numba_utils.py
diff --git a/optimhc/feature_generator/overlapping_peptide.py b/optimhc/feature/overlapping_peptide.py
similarity index 89%
rename from optimhc/feature_generator/overlapping_peptide.py
rename to optimhc/feature/overlapping_peptide.py
index 42d4f04..d50faef 100644
--- a/optimhc/feature_generator/overlapping_peptide.py
+++ b/optimhc/feature/overlapping_peptide.py
@@ -1,5 +1,3 @@
-# feature_generator/overlapping_peptide.py
-
import logging
from collections import defaultdict
from typing import Dict, List, Tuple, Union
@@ -11,7 +9,8 @@
from tqdm import tqdm
from optimhc import utils
-from optimhc.feature_generator.base_feature_generator import BaseFeatureGenerator
+from optimhc.feature.base_feature_generator import BaseFeatureGenerator
+from optimhc.feature.factory import feature_generator_factory
from optimhc.psm_container import PsmContainer
logger = logging.getLogger(__name__)
@@ -688,111 +687,43 @@ def get_full_data(self) -> pd.DataFrame:
self.full_data = self.overlap_data.merge(full_data_df, on="clean_peptide", how="left")
return self.full_data
+ @classmethod
+ def from_config(cls, psms, config, params):
+ instance = cls(
+ peptides=list(set(psms.peptides)),
+ min_overlap_length=params.get("minOverlapLength", 8),
+ min_length=params.get("minLength", 8),
+ max_length=params.get("maxLength", 25),
+ remove_pre_nxt_aa=config["removePreNxtAA"],
+ remove_modification=True,
+ )
+ instance._overlapping_score = params.get("overlappingScore", None)
+ return instance
+
+ def apply(self, psms, source):
+ features = self.generate_features()
+ full_data = self.get_full_data()
+
+ psms.add_metadata(
+ full_data[["Peptide", "contig_member_count", "ContigSequence"]],
+ psms_key=psms.peptide_column,
+ metadata_key="Peptide",
+ source=source,
+ )
+ psms.add_features(
+ features,
+ psms_key=psms.peptide_column,
+ feature_key=self.id_column,
+ source=source,
+ )
-'''
-# TODO: test
-
-def assign_brother_aggregated_feature(
- psms: PsmContainer,
- feature_columns: Union[str, List[str]],
- overlapping_source: str,
- source_name: str = 'OverlappingGroupFeatures'
-) -> None:
- """
- Assign aggregated features based on brother peptides to the PSMs.
-
- For PSMs with the same ContigSequence (brother peptides), compute the mean of specified features
- and assign these aggregated features back to each PSM in the group.
- If a PSM does not have a ContigSequence (no brothers), its new features will be set to the original values.
-
- Metadata in the PSM container:
- {
- "source_name": {
- "metadata_field_1": "value1",
- "metadata_field_2": "value2"
- }
- }
-
- Parameters:
- psms (PsmContainer): PSM container containing the peptides and features.
- feature_columns (Union[str, List[str]]): Name of the feature column(s) to aggregate.
- overlapping_source (str): Source name of the overlapping peptide features.
- source_name (str): Name of the new feature source.
-
- Returns:
- None
- """
- if isinstance(feature_columns, str):
- feature_columns = [feature_columns]
- psms_df = psms.psms
-
- if psms.metadata_column is None:
- raise ValueError("The PSMs do not contain metadata.")
- metadata = psms_df[psms.metadata_column]
- print(metadata)
-
-
- def get_overlapping_data(x):
- try:
- return x.get(overlapping_source, {})
- except AttributeError:
- logger.error(f"Metadata for PSM {x} is not a dictionary.")
- return {}
-
- def get_contig_sequence(x):
- try:
- return x.get('ContigSequence', None)
- except AttributeError:
- logger.error(f"Invalid metadata for PSM {x}.")
- return None
-
- overlapping_data = metadata.apply(get_overlapping_data)
- contig_sequences = overlapping_data.apply(get_contig_sequence)
- print(overlapping_data)
- print(contig_sequences)
-
- psms_df['ContigSequence'] = contig_sequences
-
- for feature in feature_columns:
- if feature not in psms_df.columns:
- raise ValueError(f"Feature column '{feature}' not found in PSMs.")
-
- grouped_mean = psms_df.groupby('ContigSequence')[feature_columns].mean().reset_index()
- #grouped_sum = psms_df.groupby('ContigSequence')[feature_columns].sum().reset_index()
-
- """
- grouped = grouped_mean.merge(grouped_sum,
- on='ContigSequence',
- suffixes=('_brother_mean', '_brother_sum'))
- """
- psms_with_agg = psms_df.merge(grouped_mean,
- on='ContigSequence',
- how='left',
- suffixes=('', '_brother_mean'))
-
-
- # use the original feature values if the aggregated values are missing
- for feature in feature_columns:
- mean_feature = feature + '_brother_mean'
- sum_feature = feature + '_brother_sum'
- psms_with_agg[mean_feature].fillna(psms_with_agg[feature], inplace=True)
- psms_with_agg[sum_feature].fillna(psms_with_agg[feature], inplace=True)
-
-
- agg_feature_columns = []
- for feature in feature_columns:
- mean_feature = feature + '_brother_mean'
- sum_feature = feature + '_brother_sum'
- agg_feature_columns.append(mean_feature)
- agg_feature_columns.append(sum_feature)
-
- new_features_df = psms_with_agg[agg_feature_columns]
- new_features_df.columns = agg_feature_columns
-
- psms.add_features_by_index(new_features_df, source=source_name)
-
-
-'''
+ if self._overlapping_score:
+ assign_brother_aggregated_feature(
+ psms,
+ feature_columns=self._overlapping_score,
+ overlapping_source=source,
+ source_name="ContigFeatures",
+ )
def assign_brother_aggregated_feature(
@@ -880,3 +811,8 @@ def get_contig_sequence(x):
new_features_df = psms_with_agg[agg_feature_columns]
psms.add_features_by_index(features_df=new_features_df, source=source_name)
+
+
+feature_generator_factory.register_generator(
+ "OverlappingPeptide", OverlappingPeptideFeatureGenerator
+)
diff --git a/optimhc/feature_generator/PWM.py b/optimhc/feature/pwm.py
similarity index 98%
rename from optimhc/feature_generator/PWM.py
rename to optimhc/feature/pwm.py
index 84b541d..913298c 100644
--- a/optimhc/feature_generator/PWM.py
+++ b/optimhc/feature/pwm.py
@@ -1,5 +1,3 @@
-# feature_generator/PWM.py
-
import logging
import os
from typing import Dict, List, Optional, Tuple, Union
@@ -8,7 +6,8 @@
import pandas as pd
from optimhc import utils
-from optimhc.feature_generator.base_feature_generator import BaseFeatureGenerator
+from optimhc.feature.base_feature_generator import BaseFeatureGenerator
+from optimhc.feature.factory import feature_generator_factory
logger = logging.getLogger(__name__)
@@ -700,3 +699,16 @@ def feature_columns(self) -> List[str]:
feature_columns.append(f"N_Flank_PWM_Score_{allele}")
feature_columns.append(f"C_Flank_PWM_Score_{allele}")
return feature_columns
+
+ @classmethod
+ def from_config(cls, psms, config, params):
+ return cls(
+ peptides=list(set(psms.peptides)),
+ alleles=config.get("allele", []),
+ mhc_class=params.get("class", "I"),
+ remove_modification=True,
+ remove_pre_nxt_aa=config["removePreNxtAA"],
+ )
+
+
+feature_generator_factory.register_generator("PWM", PWMFeatureGenerator)
diff --git a/optimhc/feature_generator/spectral_similarity.py b/optimhc/feature/spectral_similarity.py
similarity index 75%
rename from optimhc/feature_generator/spectral_similarity.py
rename to optimhc/feature/spectral_similarity.py
index 698452f..9f3a273 100644
--- a/optimhc/feature_generator/spectral_similarity.py
+++ b/optimhc/feature/spectral_similarity.py
@@ -1,5 +1,3 @@
-# feature_generator/spectral_similarity.py
-
import logging
from typing import Dict, List, Optional, Tuple
@@ -8,8 +6,9 @@
from koinapy import Koina
from optimhc import utils
-from optimhc.feature_generator.base_feature_generator import BaseFeatureGenerator
-from optimhc.feature_generator.numba_utils import align_peaks, compute_similarity_features
+from optimhc.feature.base_feature_generator import BaseFeatureGenerator
+from optimhc.feature.factory import feature_generator_factory
+from optimhc.feature.numba_utils import align_peaks, compute_similarity_features
from optimhc.parser import extract_mzml_data
logger = logging.getLogger(__name__)
@@ -25,18 +24,30 @@ class SpectralSimilarityFeatureGenerator(BaseFeatureGenerator):
3. Align experimental and predicted spectra
4. Calculate similarity metrics as features
- Parameters:
- peptides (List[str]): List of peptide sequences
- charges (List[int]): List of charge states
- scan_ids (List[int]): List of scan IDs
- mz_file_paths (List[str]): List of mzML file paths
- model_type (str): Prediction model type, either "HCD" or "CID"
- collision_energies (List[float]): List of collision energies, required when model_type is "HCD"
- remove_pre_nxt_aa (bool): Whether to remove preceding and next amino acids, default is True
- remove_modification (bool): Whether to remove modifications, default is True
- url (str): Koina server URL, default is "koina.wilhelmlab.org:443"
- top_n (int): Number of top peaks to use for alignment, default is 12
- tolerance_ppm (float): Mass tolerance for alignment in ppm, default is 20
+ Parameters
+ ----------
+ peptides : list of str
+ List of peptide sequences.
+ charges : list of int
+ List of charge states.
+ scan_ids : list of int
+ List of scan IDs.
+ mz_file_paths : list of str
+ List of mzML file paths.
+ model_type : str
+ Prediction model type, either "HCD" or "CID".
+ collision_energies : list of float
+ List of collision energies, required when model_type is "HCD".
+ remove_pre_nxt_aa : bool
+ Whether to remove preceding and next amino acids, default is True.
+ remove_modification : bool
+ Whether to remove modifications, default is True.
+ url : str
+ Koina server URL, default is "koina.wilhelmlab.org:443".
+ top_n : int
+ Number of top peaks to use for alignment, default is 12.
+ tolerance_ppm : float
+ Mass tolerance for alignment in ppm, default is 20.
"""
def __init__(
@@ -89,7 +100,7 @@ def __init__(
)
self.df["processed_peptide"] = self.df["peptide"].apply(self._preprocess_peptide)
- logger.info(f"Recevied {len(self.df)} PSMs for spectral similarity feature generation")
+ logger.info(f"Received {len(self.df)} PSMs for spectral similarity feature generation")
@property
def id_column(self) -> List[str]:
@@ -118,8 +129,10 @@ def input_df(self) -> pd.DataFrame:
"""
Return the generated features as a DataFrame.
- Returns:
- pd.DataFrame: DataFrame containing the generated features
+ Returns
+ -------
+ pd.DataFrame
+ DataFrame containing the generated features.
"""
return self.df
@@ -304,38 +317,40 @@ def _predict_theoretical_spectra(
else:
raise ValueError(f"Unsupported model type: {self.model_type}")
- # Save the raw prediction results
- self._raw_predictions = predictions.copy()
-
- # Convert prediction results to a suitable format
- pred_df = predictions.copy()
- pred_df.rename(
- columns={
- "peptide_sequences": "processed_peptide",
- "precursor_charges": "charge",
- "intensities": "pred_intensity",
- "mz": "pred_mz",
- },
- inplace=True,
- )
+ # Save the raw prediction results
+ self._raw_predictions = predictions.copy()
+
+ # Convert prediction results to a suitable format
+ pred_df = predictions.copy()
+ pred_df.rename(
+ columns={
+ "peptide_sequences": "processed_peptide",
+ "precursor_charges": "charge",
+ "intensities": "pred_intensity",
+ "mz": "pred_mz",
+ },
+ inplace=True,
+ )
- # Group by peptide and charge, convert predicted mz and intensity to lists
- grouped_df = (
- pred_df.groupby(["processed_peptide", "charge"])
- .agg({"pred_intensity": list, "pred_mz": list, "annotation": list})
- .reset_index()
- )
+ # Group by peptide and charge, convert predicted mz and intensity to lists
+ grouped_df = (
+ pred_df.groupby(["processed_peptide", "charge"])
+ .agg({"pred_intensity": list, "pred_mz": list, "annotation": list})
+ .reset_index()
+ )
- logger.info(f"Successfully predicted {len(grouped_df)} theoretical spectra")
- return grouped_df
+ logger.info(f"Successfully predicted {len(grouped_df)} theoretical spectra")
+ return grouped_df
@property
def raw_predictions(self) -> pd.DataFrame:
"""
Returns the raw prediction results from Koina.
- Returns:
- pd.DataFrame: Raw prediction results DataFrame
+ Returns
+ -------
+ pd.DataFrame
+ Raw prediction results DataFrame.
"""
if self._raw_predictions is None:
if self.results is None:
@@ -346,8 +361,10 @@ def get_raw_predictions(self) -> pd.DataFrame:
"""
Get the raw prediction results DataFrame from Koina.
- Returns:
- pd.DataFrame: Raw prediction results DataFrame
+ Returns
+ -------
+ pd.DataFrame
+ Raw prediction results DataFrame.
"""
return self.raw_predictions
@@ -355,9 +372,12 @@ def save_raw_predictions(self, file_path: str, **kwargs) -> None:
"""
Save the raw prediction results to a file.
- Parameters:
- file_path (str): Path to save the file
- **kwargs: Other parameters passed to pandas.DataFrame.to_csv
+ Parameters
+ ----------
+ file_path : str
+ Path to save the file.
+ **kwargs
+ Other parameters passed to ``pandas.DataFrame.to_csv``.
"""
if "index" not in kwargs:
kwargs["index"] = False
@@ -415,20 +435,27 @@ def _align_spectra_all_peaks(
"""
Align experimental and predicted spectra using ppm tolerance.
- Parameters:
- exp_mz (List[float]): Experimental m/z values
- exp_intensity (List[float]): Experimental intensity values
- pred_mz (List[float]): Predicted m/z values
- pred_intensity (List[float]): Predicted intensity values
- pred_annotation (Optional[List[str]]): Predicted fragment annotations
-
- Returns:
- Tuple[np.ndarray, np.ndarray, np.ndarray, Dict]:
- - Aligned experimental intensity vector
- - Predicted intensity vector
- - Matching index pairs as int array of shape (N, 2),
- where column 0 is pred_idx and column 1 is exp_idx (-1 = no match)
- - Additional info including original sorted arrays
+ Parameters
+ ----------
+ exp_mz : list of float
+ Experimental m/z values.
+ exp_intensity : list of float
+ Experimental intensity values.
+ pred_mz : list of float
+ Predicted m/z values.
+ pred_intensity : list of float
+ Predicted intensity values.
+ pred_annotation : list of str, optional
+ Predicted fragment annotations.
+
+ Returns
+ -------
+ tuple of (np.ndarray, np.ndarray, np.ndarray, dict)
+ - Aligned experimental intensity vector
+ - Predicted intensity vector
+ - Matching index pairs as int array of shape (N, 2),
+ where column 0 is pred_idx and column 1 is exp_idx (-1 = no match)
+ - Additional info including original sorted arrays
"""
# Sort both experimental and predicted spectra by m/z
exp_mz_sorted, exp_intensity_sorted, _ = self._sort_spectrum_by_mz(exp_mz, exp_intensity)
@@ -479,19 +506,25 @@ def _get_top_peaks_vectors(
top_n: int,
) -> Tuple[np.ndarray, np.ndarray, np.ndarray]:
"""
- Extract top N peaks based on predicted intensity for similarity calculation
+ Extract top N peaks based on predicted intensity for similarity calculation.
- Parameters:
- aligned_exp_intensity (np.ndarray): Aligned experimental intensity vector
- aligned_pred_intensity (np.ndarray): Aligned predicted intensity vector
- matched_indices (np.ndarray): Matching index pairs, shape (N, 2)
- top_n (int): Number of top peaks to extract
+ Parameters
+ ----------
+ aligned_exp_intensity : np.ndarray
+ Aligned experimental intensity vector.
+ aligned_pred_intensity : np.ndarray
+ Aligned predicted intensity vector.
+ matched_indices : np.ndarray
+ Matching index pairs, shape (N, 2).
+ top_n : int
+ Number of top peaks to extract.
- Returns:
- Tuple[np.ndarray, np.ndarray, np.ndarray]:
- - Top N experimental intensity vector
- - Top N predicted intensity vector
- - Top N matching index pairs, shape (top_n, 2)
+ Returns
+ -------
+ tuple of (np.ndarray, np.ndarray, np.ndarray)
+ - Top N experimental intensity vector
+ - Top N predicted intensity vector
+ - Top N matching index pairs, shape (top_n, 2)
"""
num_peaks = min(top_n, len(aligned_pred_intensity))
top_pred_indices = np.argsort(-aligned_pred_intensity)[:num_peaks]
@@ -586,10 +619,12 @@ def _calculate_similarity_features(
def _generate_features(self) -> pd.DataFrame:
"""
- Generate spectral similarity features
+ Generate spectral similarity features.
- Returns:
- pd.DataFrame: DataFrame containing generated features
+ Returns
+ -------
+ pd.DataFrame
+ DataFrame containing generated features.
"""
psm_df = self.df.copy()
pred_spectra_df = self._predict_theoretical_spectra(
@@ -790,3 +825,99 @@ def get_full_data(self) -> pd.DataFrame:
results and raw data used in feature generation.
"""
return self.results
+
+ @staticmethod
+ def _resolve_mzml_paths(psms, params):
+ """Resolve per-PSM mzML file paths from config and PsmContainer."""
+ import os
+ import re
+
+ mzml_dir = params.get("mzmlDir", None)
+ if mzml_dir is None:
+ raise ValueError("mzmlDir is required for SpectralSimilarity feature generator.")
+
+ pattern = params.get("spectrumIdPattern", None)
+ mz_file_names = []
+ spectrum_ids = psms.spectrum_ids
+
+ if pattern:
+ logger.info(f"Using pattern: {pattern} to extract mzML file names from spectrum IDs.")
+ for spectrum_id in spectrum_ids:
+ mz_file_names.append(re.match(pattern, spectrum_id).group(1))
+ logger.info(f"mzML file names: {list(set(mz_file_names))}")
+ else:
+ logger.info("Spectrum ID pattern is not provided.")
+ if psms.ms_data_file_column is not None:
+ logger.info(f"Trying to extract mzML file names from {psms.ms_data_file_column}")
+ logger.info(f"MS data file format: {set(psms.psms[psms.ms_data_file_column])}")
+ for ms_data_file in psms.psms[psms.ms_data_file_column]:
+ mz_file_basename = os.path.basename(ms_data_file).split(".")[0]
+ if mz_file_basename.endswith(".mzML"):
+ mz_file_basename = mz_file_basename[:-5]
+ elif mz_file_basename.endswith("mzML"):
+ mz_file_basename = mz_file_basename[:-4]
+ mz_file_names.append(mz_file_basename)
+ logger.info(f"mzML file names: {list(set(mz_file_names))}")
+ else:
+ logger.info("MS data file information is not provided.")
+ logger.info(
+ r"Trying to use the default pattern: (.+?)\.\d+\.\d+\.\d+ "
+ "to extract mzML file names from spectrum IDs."
+ )
+ for spectrum_id in spectrum_ids:
+ mz_file_names.append(re.match(r"(.+?)\.\d+\.\d+\.\d+", spectrum_id).group(1))
+
+ mz_file_paths = [os.path.join(mzml_dir, f"{mz_file}.mzML") for mz_file in mz_file_names]
+ for mz_file_path in set(mz_file_paths):
+ if not os.path.exists(mz_file_path):
+ logger.error(f"mzML file not found: {mz_file_path}")
+
+ return mz_file_paths
+
+ @classmethod
+ def from_config(cls, psms, config, params):
+ mz_file_paths = cls._resolve_mzml_paths(psms, params)
+ mod_dict = config.get("modificationMap", None)
+ if mod_dict == {}:
+ mod_dict = None
+
+ model_type = params.get("model", None)
+ if model_type is None:
+ raise ValueError("Model type is required for SpectralSimilarity feature generator.")
+
+ n = len(psms.peptides)
+ collision_energy = params.get("collisionEnergy", None)
+ instrument = params.get("instrument", None)
+ fragmentation_type = params.get("fragmentationType", None)
+
+ return cls(
+ spectrum_ids=psms.spectrum_ids,
+ peptides=psms.peptides,
+ charges=psms.charges,
+ scan_ids=psms.scan_ids,
+ mz_file_paths=mz_file_paths,
+ model_type=model_type,
+ collision_energies=[collision_energy] * n if collision_energy else None,
+ instruments=[instrument] * n if instrument else None,
+ fragmentation_types=[fragmentation_type] * n if fragmentation_type else None,
+ remove_pre_nxt_aa=config["removePreNxtAA"],
+ mod_dict=mod_dict,
+ url=params.get("url"),
+ ssl=params.get("ssl", True),
+ top_n=params.get("numTopPeaks", 36),
+ tolerance_ppm=params.get("tolerance", 20),
+ )
+
+ def apply(self, psms, source):
+ features = self.generate_features()
+ psms.add_features(
+ features,
+ psms_key=[psms.spectrum_column, psms.peptide_column, psms.charge_column],
+ feature_key=self.id_column,
+ source=source,
+ )
+
+
+feature_generator_factory.register_generator(
+ "SpectralSimilarity", SpectralSimilarityFeatureGenerator
+)
diff --git a/optimhc/feature_generator/__init__.py b/optimhc/feature_generator/__init__.py
deleted file mode 100644
index 7d30ecc..0000000
--- a/optimhc/feature_generator/__init__.py
+++ /dev/null
@@ -1,3 +0,0 @@
-import warnings
-
-warnings.filterwarnings("ignore")
diff --git a/optimhc/feature_generator/base_feature_generator.py b/optimhc/feature_generator/base_feature_generator.py
deleted file mode 100644
index 7cac35c..0000000
--- a/optimhc/feature_generator/base_feature_generator.py
+++ /dev/null
@@ -1,35 +0,0 @@
-# feature_generators/base_feature_generator.py
-
-from abc import ABC, abstractmethod
-from typing import List
-
-import pandas as pd
-
-
-class BaseFeatureGenerator(ABC):
- """
- Abstract base class for all feature generators in the rescoring pipeline.
- """
-
- @property
- @abstractmethod
- def feature_columns(self) -> List[str]:
- """
- Returns a list of feature names generated by the feature generator.
- """
- pass
-
- @property
- @abstractmethod
- def id_column(self) -> List[str]:
- """
- Returns the column or columns used as key or keys to merge features with PSMs.
- """
- pass
-
- @abstractmethod
- def generate_features(self) -> pd.DataFrame:
- """
- Generates features.
- """
- pass
diff --git a/optimhc/gui/__init__.py b/optimhc/gui/__init__.py
deleted file mode 100644
index a750dbc..0000000
--- a/optimhc/gui/__init__.py
+++ /dev/null
@@ -1,5 +0,0 @@
-"""
-optiMHC GUI module for Streamlit-based interface.
-"""
-
-__all__ = ["app"]
diff --git a/optimhc/gui/app.py b/optimhc/gui/app.py
deleted file mode 100644
index 91db588..0000000
--- a/optimhc/gui/app.py
+++ /dev/null
@@ -1,76 +0,0 @@
-"""
-Main application for the optiMHC GUI.
-"""
-
-import streamlit as st
-import os
-import sys
-from pathlib import Path
-
-# Add optiMHC root to path if needed
-optimhc_root = str(Path(__file__).parent.parent.parent)
-if optimhc_root not in sys.path:
- sys.path.append(optimhc_root)
-
-# Import style utilities
-from optimhc.gui.style import set_page_config, apply_custom_css, footer
-
-# Import page modules
-from optimhc.gui.pages import home, configure, run, results
-
-
-def main():
- """
- Main application entry point.
- """
- # Set up page config
- set_page_config()
-
- # Apply custom CSS
- apply_custom_css()
-
- # Initialize session state for navigation
- if "page" not in st.session_state:
- st.session_state.page = "home"
-
- # Sidebar navigation
- st.sidebar.title("Navigation")
-
- # Navigation buttons
- if st.sidebar.button("Home", use_container_width=True):
- st.session_state.page = "home"
- st.rerun()
-
- if st.sidebar.button("Configure", use_container_width=True):
- st.session_state.page = "configure"
- st.rerun()
-
- if st.sidebar.button("Run Pipeline", use_container_width=True):
- st.session_state.page = "run"
- st.rerun()
-
- if st.sidebar.button("Results", use_container_width=True):
- st.session_state.page = "results"
- st.rerun()
-
- # Version info in sidebar
- st.sidebar.markdown("---")
- from optimhc import __version__
- st.sidebar.info(f"optiMHC v{__version__}")
-
- # Render the selected page
- if st.session_state.page == "home":
- home.render()
- elif st.session_state.page == "configure":
- configure.render()
- elif st.session_state.page == "run":
- run.render()
- elif st.session_state.page == "results":
- results.render()
-
- # Footer
- footer()
-
-
-if __name__ == "__main__":
- main()
diff --git a/optimhc/gui/components/__init__.py b/optimhc/gui/components/__init__.py
deleted file mode 100644
index 1338c94..0000000
--- a/optimhc/gui/components/__init__.py
+++ /dev/null
@@ -1,14 +0,0 @@
-"""
-GUI components for the optiMHC Streamlit interface.
-"""
-
-__all__ = [
- "config_form",
- "file_upload",
- "log_viewer",
- "pipeline_control",
- "results_viewer",
- "feature_generator_form",
- "rescore_form",
- "modification_map"
-]
diff --git a/optimhc/gui/components/config_form.py b/optimhc/gui/components/config_form.py
deleted file mode 100644
index 1344885..0000000
--- a/optimhc/gui/components/config_form.py
+++ /dev/null
@@ -1,399 +0,0 @@
-"""
-Configuration form component for optiMHC GUI.
-"""
-
-import os
-import streamlit as st
-import yaml
-from typing import Dict, Any, List, Optional
-import json
-
-# Import optiMHC config defaults
-from optimhc.core.config import DEFAULT_CONFIG
-
-
-def feature_generator_form(existing_generators: List[Dict[str, Any]] = None) -> List[Dict[str, Any]]:
- """
- Create a form for configuring feature generators.
-
- Args:
- existing_generators: List of existing feature generator configurations
-
- Returns:
- List of feature generator configurations
- """
- if existing_generators is None:
- existing_generators = []
-
- feature_generators = []
-
- # Known feature generators and their parameters
- generator_options = {
- "Basic": {},
- "PWM": {"class": ["I", "II"]},
- "MHCflurry": {},
- "NetMHCpan": {},
- "NetMHCIIpan": {},
- "DeepLC": {
- "calibrationCriteria": ["expect", "xcorr", "hyperscore"],
- "lowerIsBetter": [True, False],
- "calibrationSize": [0.1, 0.2, 0.3]
- },
- "SpectralSimilarity": {
- "model": ["AlphaPeptDeep_ms2_generic", "AlphaPeptDeep_ms2_HCD", "AlphaPeptDeep_ms2_CID"],
- "instrument": ["LUMOS", "QE", "VELOS", "FUSION"],
- "numTopPeaks": [10, 20, 36, 50]
- },
- "OverlappingPeptide": {
- "minOverlapLength": [7, 8, 9],
- "minLength": [7, 8, 9],
- "maxLength": [15, 20, 25],
- "overlappingScore": ["expect", "xcorr", "hyperscore"]
- }
- }
-
- st.subheader("Feature Generators")
-
- # Use session state to keep track of the number of generators
- if "num_generators" not in st.session_state:
- st.session_state.num_generators = max(1, len(existing_generators))
-
- # Add/remove generator controls outside of the form
- col1, col2 = st.columns([1, 5])
- with col1:
- if st.button("➕ Add Generator", key="add_generator"):
- st.session_state.num_generators += 1
- st.rerun()
- with col2:
- if st.session_state.num_generators > 1 and st.button("➖ Remove Last Generator", key="remove_generator"):
- st.session_state.num_generators -= 1
- st.rerun()
-
- # Generate forms for each feature generator
- for i in range(st.session_state.num_generators):
- with st.expander(f"Feature Generator {i+1}", expanded=True):
- existing_gen = {} if i >= len(existing_generators) else existing_generators[i]
-
- # Feature generator name
- generator_name = st.selectbox(
- "Generator Type",
- options=list(generator_options.keys()),
- key=f"gen_type_{i}",
- index=list(generator_options.keys()).index(existing_gen.get("name", "Basic")) if existing_gen.get("name") in generator_options else 0
- )
-
- # Feature generator parameters
- params = {}
- if generator_options[generator_name]:
- st.markdown("**Parameters:**")
- for param_name, param_options in generator_options[generator_name].items():
- existing_params = existing_gen.get("params", {})
- existing_value = existing_params.get(param_name)
-
- # Handle different parameter types
- if isinstance(param_options, list):
- if all(isinstance(x, bool) for x in param_options):
- param_value = st.checkbox(
- param_name,
- value=existing_value if existing_value is not None else param_options[0],
- key=f"gen_{i}_{param_name}"
- )
- elif all(isinstance(x, (int, float)) for x in param_options):
- param_value = st.number_input(
- param_name,
- value=existing_value if existing_value is not None else param_options[0],
- key=f"gen_{i}_{param_name}"
- )
- else:
- param_value = st.selectbox(
- param_name,
- options=param_options,
- index=param_options.index(existing_value) if existing_value in param_options else 0,
- key=f"gen_{i}_{param_name}"
- )
- else:
- param_value = st.text_input(
- param_name,
- value=str(existing_value) if existing_value is not None else "",
- key=f"gen_{i}_{param_name}"
- )
-
- params[param_name] = param_value
-
- # Add to list of generators
- generator_config = {"name": generator_name}
- if params:
- generator_config["params"] = params
-
- feature_generators.append(generator_config)
-
- return feature_generators
-
-
-def rescore_form(existing_rescore: Dict[str, Any] = None) -> Dict[str, Any]:
- """
- Create a form for rescoring settings.
-
- Args:
- existing_rescore: Existing rescore configuration
-
- Returns:
- Rescore configuration dictionary
- """
- if existing_rescore is None:
- existing_rescore = DEFAULT_CONFIG["rescore"]
-
- st.subheader("Rescoring Settings")
-
- rescore_model = st.selectbox(
- "Rescoring Model",
- options=["Percolator", "XGBoost", "RandomForest"],
- index=["Percolator", "XGBoost", "RandomForest"].index(existing_rescore.get("model", "Percolator")),
- help="Model to use for rescoring"
- )
-
- test_fdr = st.number_input(
- "Test FDR",
- min_value=0.001,
- max_value=0.1,
- value=float(existing_rescore.get("testFDR", 0.01)),
- step=0.001,
- format="%.3f",
- help="FDR threshold for testing"
- )
-
- num_jobs = st.number_input(
- "Number of Jobs",
- min_value=1,
- max_value=32,
- value=int(existing_rescore.get("numJobs", 1)),
- help="Number of parallel jobs for model training"
- )
-
- return {
- "model": rescore_model,
- "testFDR": test_fdr,
- "numJobs": num_jobs
- }
-
-
-def config_form(existing_config: Dict[str, Any] = None) -> Dict[str, Any]:
- """
- Create a form for configuring the pipeline.
-
- Args:
- existing_config: Existing configuration dictionary
-
- Returns:
- Configuration dictionary
- """
- if existing_config is None:
- existing_config = DEFAULT_CONFIG
-
- st.subheader("Basic Settings")
-
- experiment_name = st.text_input(
- "Experiment Name",
- value=existing_config.get("experimentName", ""),
- help="Name of the experiment"
- )
-
- input_type = st.selectbox(
- "Input Type",
- options=["pepxml", "pin"],
- index=["pepxml", "pin"].index(existing_config.get("inputType", "pepxml")),
- help="Type of input file"
- )
-
- # For GUI, we'll handle input files differently than the direct file paths
- input_files = existing_config.get("inputFile", [])
- if isinstance(input_files, str):
- input_files = [input_files]
-
- input_files_str = st.text_area(
- "Input Files",
- value="\n".join(input_files) if input_files else "",
- height=100,
- help="One file path per line. Use file uploader to add files."
- )
-
- input_files = [f for f in input_files_str.strip().split("\n") if f]
-
- decoy_prefix = st.text_input(
- "Decoy Prefix",
- value=existing_config.get("decoyPrefix", "DECOY_"),
- help="Prefix used to identify decoy sequences"
- )
-
- output_dir = st.text_input(
- "Output Directory",
- value=existing_config.get("outputDir", "./results"),
- help="Directory where results will be saved"
- )
-
- # Allele settings
- st.subheader("Allele Settings")
-
- alleles = existing_config.get("allele", [])
- if isinstance(alleles, str):
- alleles = [alleles]
-
- alleles_str = st.text_area(
- "Alleles",
- value="\n".join(alleles) if alleles else "",
- height=100,
- help="One allele per line, e.g., HLA-A*02:01"
- )
-
- alleles = [a for a in alleles_str.strip().split("\n") if a]
-
- # Performance settings
- st.subheader("Performance Settings")
-
- col1, col2 = st.columns(2)
-
- with col1:
- num_processes = st.number_input(
- "Number of Processes",
- min_value=1,
- max_value=64,
- value=int(existing_config.get("numProcesses", 4)),
- help="Number of parallel processes"
- )
-
- with col2:
- show_progress = st.checkbox(
- "Show Progress",
- value=existing_config.get("showProgress", True),
- help="Show progress bars during processing"
- )
-
- col1, col2 = st.columns(2)
-
- with col1:
- visualization = st.checkbox(
- "Enable Visualization",
- value=existing_config.get("visualization", True),
- help="Generate visualizations of results"
- )
-
- with col2:
- remove_pre_nxt_aa = st.checkbox(
- "Remove Pre/Next Amino Acids",
- value=existing_config.get("removePreNxtAA", False),
- help="Remove pre/post neighboring amino acids in sequence processing"
- )
-
- log_level = st.selectbox(
- "Log Level",
- options=["DEBUG", "INFO", "WARNING", "ERROR"],
- index=["DEBUG", "INFO", "WARNING", "ERROR"].index(existing_config.get("logLevel", "INFO")),
- help="Logging verbosity level"
- )
-
- # Advanced sections
-
- # Feature generators
- feature_generators = feature_generator_form(existing_config.get("featureGenerator", []))
-
- # Rescoring
- rescore = rescore_form(existing_config.get("rescore", {}))
-
- # Combine all settings
- config = {
- "experimentName": experiment_name,
- "inputType": input_type,
- "inputFile": input_files,
- "decoyPrefix": decoy_prefix,
- "outputDir": output_dir,
- "allele": alleles,
- "numProcesses": num_processes,
- "showProgress": show_progress,
- "visualization": visualization,
- "removePreNxtAA": remove_pre_nxt_aa,
- "logLevel": log_level,
- "featureGenerator": feature_generators,
- "rescore": rescore
- }
-
- return config
-
-
-def render_config_summary(config: Dict[str, Any]):
- """
- Render a summary of the configuration as a YAML code block.
-
- Args:
- config: Configuration dictionary
- """
- st.subheader("Configuration Summary")
-
- # Create a simplified copy of the configuration to display
- display_config = config.copy()
-
- # Convert to YAML string
- config_yaml = yaml.dump(display_config, default_flow_style=False, sort_keys=False)
-
- # Display as a code block with syntax highlighting
- st.code(config_yaml, language="yaml")
-
-
-def validate_config(config: Dict[str, Any]) -> List[str]:
- """
- Validate configuration for obvious errors.
-
- Args:
- config: Configuration dictionary
-
- Returns:
- List of error messages, empty if configuration is valid
- """
- errors = []
-
- # Check required fields
- required_fields = ["experimentName", "inputType", "inputFile", "outputDir", "allele"]
- for field in required_fields:
- if field not in config or not config[field]:
- errors.append(f"Missing required field: {field}")
-
- # Check inputType
- if config.get("inputType") not in ["pepxml", "pin"]:
- errors.append("Input type must be 'pepxml' or 'pin'")
-
- # Check feature generators
- generators = config.get("featureGenerator", [])
- if not generators:
- errors.append("At least one feature generator is required")
-
- # Check if SpectralSimilarity has required parameters
- for gen in generators:
- if gen.get("name") == "SpectralSimilarity":
- params = gen.get("params", {})
- # Check instrument
- instrument = params.get("instrument")
- if instrument and instrument not in ["QE", "LUMOS", "TIMSTOF", "SCIEXTOF"]:
- errors.append(f"Invalid instrument '{instrument}' for SpectralSimilarity. Must be one of: QE, LUMOS, TIMSTOF, SCIEXTOF")
-
- # Check mzML directory
- if "mzmlDir" not in params:
- errors.append("SpectralSimilarity requires 'mzmlDir' parameter")
-
- # Check spectrum ID pattern
- if "spectrumIdPattern" not in params:
- errors.append("SpectralSimilarity requires 'spectrumIdPattern' parameter to extract mzML filenames from spectrum IDs")
-
- # Check rescore settings
- rescore = config.get("rescore", {})
- if not rescore or "model" not in rescore:
- errors.append("Rescore model is required")
-
- if "testFDR" in rescore and (rescore["testFDR"] <= 0 or rescore["testFDR"] > 1):
- errors.append("Test FDR must be between 0 and 1")
-
- # Check modification map format
- mod_map = config.get("modificationMap", {})
- for mass, unimod in mod_map.items():
- if not unimod.startswith("UNIMOD:"):
- errors.append(f"Invalid UNIMOD format for mass {mass}: {unimod}. Must start with 'UNIMOD:'")
-
- return errors
diff --git a/optimhc/gui/components/feature_generator_form.py b/optimhc/gui/components/feature_generator_form.py
deleted file mode 100644
index 44e7e1d..0000000
--- a/optimhc/gui/components/feature_generator_form.py
+++ /dev/null
@@ -1,267 +0,0 @@
-"""
-Feature generator form component for optiMHC GUI.
-"""
-
-import streamlit as st
-from typing import Dict, Any, List
-
-def feature_generator_form(existing_generators: List[Dict[str, Any]] = None) -> List[Dict[str, Any]]:
- """
- Create a form for configuring feature generators.
-
- Args:
- existing_generators: List of existing feature generator configurations
-
- Returns:
- List of feature generator configurations
- """
- if existing_generators is None:
- existing_generators = []
-
- # Convert existing generators to a dict for easier lookup
- existing_gen_dict = {}
- for gen in existing_generators:
- existing_gen_dict[gen["name"]] = gen.get("params", {})
-
- feature_generators = []
-
- st.subheader("Feature Generators")
-
- # Determine the MHC class from existing configuration
- # Look for PWM first as it has explicit class parameter
- mhc_class = None
- for gen in existing_generators:
- if gen["name"] == "PWM" and "params" in gen and "class" in gen["params"]:
- mhc_class = gen["params"]["class"]
- break
-
- # If PWM not found, infer from presence of NetMHCIIpan
- if mhc_class is None:
- if any(gen["name"] == "NetMHCIIpan" for gen in existing_generators):
- mhc_class = "II"
- else:
- mhc_class = "I" # Default to class I
-
- # MHC class selection
- mhc_class = st.radio(
- "MHC Class",
- options=["I", "II"],
- index=0 if mhc_class == "I" else 1,
- horizontal=True,
- help="Select MHC class for appropriate feature generators."
- )
-
- st.markdown("---")
- st.markdown("Select which feature generators to use in the pipeline:")
-
- # Basic feature generator (always available)
- if st.checkbox("Basic", value="Basic" in existing_gen_dict or not existing_generators, key="basic_gen"):
- feature_generators.append({"name": "Basic"})
-
- # PWM feature generator (class parameter set automatically based on MHC class selection)
- if st.checkbox("PWM", value="PWM" in existing_gen_dict, key="pwm_gen"):
- feature_generators.append({
- "name": "PWM",
- "params": {"class": mhc_class}
- })
-
- # Class I specific generators
- if mhc_class == "I":
- # MHCflurry (class I only)
- if st.checkbox("MHCflurry", value="MHCflurry" in existing_gen_dict, key="mhcflurry_gen"):
- feature_generators.append({"name": "MHCflurry"})
-
- # NetMHCpan (class I only)
- if st.checkbox("NetMHCpan", value="NetMHCpan" in existing_gen_dict, key="netmhcpan_gen"):
- feature_generators.append({"name": "NetMHCpan"})
-
- # Class II specific generators
- else: # mhc_class == "II"
- # NetMHCIIpan (class II only)
- if st.checkbox("NetMHCIIpan", value="NetMHCIIpan" in existing_gen_dict, key="netmhciipan_gen"):
- feature_generators.append({"name": "NetMHCIIpan"})
-
- # DeepLC feature generator (available for both classes)
- if st.checkbox("DeepLC", value="DeepLC" in existing_gen_dict, key="deeplc_gen"):
- deeplc_params = {}
-
- col1, col2 = st.columns(2)
- with col1:
- calibration_criteria = st.text_input(
- "Calibration Criteria",
- value=existing_gen_dict.get("DeepLC", {}).get("calibrationCriteria", "expect"),
- key="deeplc_calibration_criteria",
- help="Criteria for calibration (e.g., expect, xcorr, hyperscore)"
- )
- deeplc_params["calibrationCriteria"] = calibration_criteria
-
- with col2:
- lower_is_better = st.checkbox(
- "Lower Is Better",
- value=existing_gen_dict.get("DeepLC", {}).get("lowerIsBetter", True),
- key="deeplc_lower_is_better",
- help="Whether lower values of the calibration criteria are better (True for expect, False for xcorr/hyperscore)"
- )
- deeplc_params["lowerIsBetter"] = lower_is_better
-
- calibration_size = st.slider(
- "Calibration Size",
- min_value=0.05,
- max_value=0.5,
- value=float(existing_gen_dict.get("DeepLC", {}).get("calibrationSize", 0.1)),
- step=0.05,
- key="deeplc_calibration_size",
- help="Fraction of PSMs to use for calibration (0.05-0.5)"
- )
- deeplc_params["calibrationSize"] = calibration_size
-
- feature_generators.append({"name": "DeepLC", "params": deeplc_params})
-
- # SpectralSimilarity feature generator (with AlphaPeptDeep as default)
- if st.checkbox("SpectralSimilarity", value="SpectralSimilarity" in existing_gen_dict or not existing_generators, key="spectra_similarity_gen"):
- ss_params = {}
-
- st.markdown("#### SpectralSimilarity Settings")
-
- model = st.selectbox(
- "Model",
- options=["AlphaPeptDeep_ms2_generic"],
- index=["AlphaPeptDeep_ms2_generic"].index(
- existing_gen_dict.get("SpectralSimilarity", {}).get("model", "AlphaPeptDeep_ms2_generic")
- ),
- key="spectra_similarity_model",
- help="Prediction model for theoretical spectra"
- )
- ss_params["model"] = model
-
- instrument = st.selectbox(
- "Instrument",
- options=["QE", "LUMOS", "TIMSTOF", "SCIEXTOF"],
- index=["QE", "LUMOS", "TIMSTOF", "SCIEXTOF"].index(
- existing_gen_dict.get("SpectralSimilarity", {}).get("instrument", "LUMOS")
- ),
- key="spectra_similarity_instrument",
- help="Available instruments: QE, LUMOS, TIMSTOF, SCIEXTOF"
- )
- ss_params["instrument"] = instrument
-
- # mzML directory path
- mzml_dir = st.text_input(
- "mzML Directory Path",
- value=existing_gen_dict.get("SpectralSimilarity", {}).get("mzmlDir", "./data"),
- key="spectra_similarity_mzml_dir",
- help="Path to directory containing mzML files"
- )
- if mzml_dir:
- ss_params["mzmlDir"] = mzml_dir
-
- # Spectrum ID pattern
- spectrum_id_pattern = st.text_input(
- "Spectrum ID Pattern",
- value=existing_gen_dict.get("SpectralSimilarity", {}).get("spectrumIdPattern", "(.+?)\\.\\d+\\.\\d+\\.\\d+"),
- key="spectra_similarity_spectrum_id_pattern",
- help="Regular expression pattern to extract mzML filename from spectrum IDs. Default pattern: (.+?)\\.\\d+\\.\\d+\\.\\d+"
- )
- if spectrum_id_pattern:
- ss_params["spectrumIdPattern"] = spectrum_id_pattern
-
- collision_energy = st.number_input(
- "Collision Energy",
- min_value=20,
- max_value=40,
- value=int(existing_gen_dict.get("SpectralSimilarity", {}).get("collisionEnergy", 28)),
- key="spectra_similarity_collision_energy",
- help="Collision energy used during acquisition (typical range: 25-30)"
- )
- ss_params["collisionEnergy"] = collision_energy
-
- tolerance = st.slider(
- "Tolerance (ppm)",
- min_value=10,
- max_value=50,
- value=int(existing_gen_dict.get("SpectralSimilarity", {}).get("tolerance", 20)),
- step=5,
- key="spectra_similarity_tolerance",
- help="Mass tolerance in ppm for peak matching (10-50 ppm)"
- )
- ss_params["tolerance"] = tolerance
-
- num_top_peaks = st.slider(
- "Number of Top Peaks",
- min_value=10,
- max_value=100,
- value=int(existing_gen_dict.get("SpectralSimilarity", {}).get("numTopPeaks", 36)),
- step=2,
- key="spectra_similarity_num_top_peaks",
- help="Number of most intense peaks to consider for matching"
- )
- ss_params["numTopPeaks"] = num_top_peaks
-
- url = st.text_input(
- "API URL",
- value=existing_gen_dict.get("SpectralSimilarity", {}).get("url", "koina.wilhelmlab.org:443"),
- key="spectra_similarity_url",
- help="AlphaPept API URL (default: koina.wilhelmlab.org:443)"
- )
- if url:
- ss_params["url"] = url
-
- feature_generators.append({"name": "SpectralSimilarity", "params": ss_params})
-
- # OverlappingPeptide feature generator
- if st.checkbox("OverlappingPeptide", value="OverlappingPeptide" in existing_gen_dict, key="overlapping_peptide_gen"):
- op_params = {}
-
- st.markdown("#### OverlappingPeptide Settings")
-
- col1, col2 = st.columns(2)
- with col1:
- min_overlap_length = st.number_input(
- "Min Overlap Length",
- min_value=5,
- max_value=15,
- value=int(existing_gen_dict.get("OverlappingPeptide", {}).get("minOverlapLength", 7)),
- key="op_min_overlap_length",
- help="Minimum number of amino acids that must overlap"
- )
- op_params["minOverlapLength"] = min_overlap_length
-
- with col2:
- overlapping_score = st.text_input(
- "Overlapping Score",
- value=existing_gen_dict.get("OverlappingPeptide", {}).get("overlappingScore", "expect"),
- key="op_overlapping_score",
- help="Score to use for overlapping peptides (e.g., expect, xcorr, hyperscore)"
- )
- op_params["overlappingScore"] = overlapping_score
-
- col1, col2 = st.columns(2)
- with col1:
- min_length = st.number_input(
- "Min Length",
- min_value=5,
- max_value=15,
- value=int(existing_gen_dict.get("OverlappingPeptide", {}).get("minLength", 7 if mhc_class == "I" else 9)),
- key="op_min_length",
- help="Minimum peptide length to consider"
- )
- op_params["minLength"] = min_length
-
- with col2:
- max_length = st.number_input(
- "Max Length",
- min_value=10,
- max_value=50,
- value=int(existing_gen_dict.get("OverlappingPeptide", {}).get("maxLength", 20 if mhc_class == "I" else 30)),
- key="op_max_length",
- help="Maximum peptide length to consider"
- )
- op_params["maxLength"] = max_length
-
- feature_generators.append({"name": "OverlappingPeptide", "params": op_params})
-
- # Warning if no generators selected
- if not feature_generators:
- st.warning("Please select at least one feature generator.")
-
- return feature_generators
diff --git a/optimhc/gui/components/file_upload.py b/optimhc/gui/components/file_upload.py
deleted file mode 100644
index f830666..0000000
--- a/optimhc/gui/components/file_upload.py
+++ /dev/null
@@ -1,159 +0,0 @@
-"""
-File upload component for optiMHC GUI.
-"""
-
-import os
-import streamlit as st
-import yaml
-import tempfile
-from typing import Dict, Any, Optional, Tuple
-from optimhc.gui.utils import load_config_from_yaml
-
-
-def config_file_uploader() -> Optional[Dict[str, Any]]:
- """
- Display a file uploader for configuration files.
-
- Returns:
- Configuration dictionary if a file is uploaded, None otherwise
- """
- uploaded_file = st.file_uploader(
- "Upload configuration file",
- type=["yaml", "yml"],
- help="Upload a YAML configuration file"
- )
-
- if uploaded_file is not None:
- try:
- config = yaml.safe_load(uploaded_file)
- st.success(f"Configuration file '{uploaded_file.name}' loaded successfully")
- return config
- except Exception as e:
- st.error(f"Error loading configuration file: {str(e)}")
- return None
-
- return None
-
-
-def input_path_field(input_type: str, value: str = "", placeholder: str = "") -> str:
- """
- Display an input field for file paths.
-
- Args:
- input_type: Type of input (pepxml, pin, mzML directory)
- value: Current value
- placeholder: Placeholder text
-
- Returns:
- String containing file paths, one per line
- """
- if input_type.lower() in ["pepxml", "pin"]:
- help_text = f"Enter the full path to your {input_type} files, one per line"
- elif input_type.lower() == "mzml":
- help_text = "Enter the full path to your mzML directory"
- else:
- help_text = "Enter file paths, one per line"
-
- paths = st.text_area(
- f"{input_type} File Paths",
- value=value,
- placeholder=placeholder,
- height=100,
- help=help_text,
- key=f"{input_type.lower()}_paths"
- )
-
- return paths
-
-
-def yaml_example(example_type: str = "class_i") -> str:
- """
- Return an example YAML configuration by reading from example files.
-
- Args:
- example_type: Type of example (class_i or class_ii)
-
- Returns:
- Example YAML configuration as a string
- """
- # Get the path to the examples directory
- current_dir = os.path.dirname(
- os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
- )
- examples_dir = os.path.join(current_dir, "examples")
-
- # Determine which example file to read
- if example_type.lower() == "class_i":
- example_file = os.path.join(examples_dir, "classI_example.yaml")
- default_config = """
-experimentName: class_I_example
-inputType: pepxml
-inputFile:
- - ./data/YE_20180428_SK_HLA_A0202_3Ips_a50mio_R1_01.pep.xml
-decoyPrefix: DECOY_
-outputDir: ./examples/results/class_I_example
-visualization: True
-removePreNxtAA: False
-numProcesses: 4
-showProgress: True
-modificationMap:
- "147.035385": "UNIMOD:35" # Oxidation (M)
- "160.030649": "UNIMOD:4" # Carbamidomethyl (C)
-allele:
- - HLA-A*02:02
-featureGenerator:
- - name: Basic
- - name: PWM
- params:
- class: I
- - name: MHCflurry
- - name: NetMHCpan
-rescore:
- testFDR: 0.01
- model: Percolator
- numJobs: 4
-"""
- else: # class_ii
- example_file = os.path.join(examples_dir, "classII_example.yaml")
- default_config = """
-experimentName: class_II_example
-inputType: pepxml
-inputFile:
- - ./data/AG20201214_FAIMS_DPB0101_DPA0201_93e6_1hr.pep.xml
-decoyPrefix: DECOY_
-outputDir: ./examples/results/class_II_example
-visualization: True
-removePreNxtAA: False
-numProcesses: 4
-showProgress: True
-modificationMap:
- "147.035385": "UNIMOD:35" # Oxidation (M)
- "160.030649": "UNIMOD:4" # Carbamidomethyl (C)
-allele:
- - HLA-DPA1*02:01-DPB1*01:01
-featureGenerator:
- - name: Basic
- - name: PWM
- params:
- class: II
- - name: NetMHCIIpan
-rescore:
- testFDR: 0.01
- model: Percolator
- numJobs: 4
-"""
-
- try:
- if not os.path.exists(example_file):
- st.warning(f"Example file not found: {example_file}, using default configuration")
- return default_config
-
- with open(example_file, 'r') as f:
- content = f.read()
- if not content:
- st.warning(f"Example file is empty: {example_file}, using default configuration")
- return default_config
- return content
- except Exception as e:
- st.warning(f"Error reading example file: {str(e)}, using default configuration")
- return default_config
diff --git a/optimhc/gui/components/log_viewer.py b/optimhc/gui/components/log_viewer.py
deleted file mode 100644
index c1719ce..0000000
--- a/optimhc/gui/components/log_viewer.py
+++ /dev/null
@@ -1,250 +0,0 @@
-"""
-Log viewer component for optiMHC GUI.
-"""
-
-import os
-from typing import List, Optional
-import streamlit as st
-
-
-def display_logs(logs: List[str]):
- """
- Display logs as read-only text with auto-scrolling.
-
- Args:
- logs: List of log messages
- """
- if not logs:
- st.info("No logs to display yet...")
- return
-
- # Join logs with newlines
- log_text = "\n".join(logs)
-
- # Use a container with custom CSS to create a taller scrollable area
- log_container = st.container()
-
- with log_container:
- # Add custom CSS for taller log area with scrollbar
- st.markdown("""
-
- """, unsafe_allow_html=True)
-
- # Use st.code for read-only display
- st.code(log_text, language="plain")
-
- # Add JavaScript to auto-scroll to bottom
- # This ensures the latest logs are always visible
- auto_scroll_js = """
-
- """
- st.components.v1.html(auto_scroll_js, height=0)
-
-
-def find_pipeline_log_file() -> Optional[str]:
- """
- Find the pipeline log file based on configuration.
-
- Returns:
- Path to the log file or None if not found
- """
- # Try to get output directory and experiment name from config
- output_dir = None
- experiment_name = None
-
- if "config" in st.session_state:
- config = st.session_state.config
- output_dir = config.get("outputDir")
- experiment_name = config.get("experimentName")
-
- # First, check if we already know the log file path from pipeline execution
- if "pipeline_log_path" in st.session_state and st.session_state.pipeline_log_path:
- log_path = st.session_state.pipeline_log_path
- if os.path.exists(log_path):
- return log_path
-
- # Next, try to find log file in the expected pipeline output directory
- if output_dir and experiment_name:
- experiment_dir = os.path.join(output_dir, experiment_name)
- if os.path.exists(experiment_dir):
- # Pipeline's default log file
- log_path = os.path.join(experiment_dir, "log")
- if os.path.exists(log_path):
- return log_path
-
- # Look for any log files in the experiment directory
- for root, _, files in os.walk(experiment_dir):
- for file in files:
- if file.endswith(".log") or file == "log":
- return os.path.join(root, file)
-
- # If no log in experiment directory, search the main output directory
- if output_dir and os.path.exists(output_dir):
- log_files = []
- for root, _, files in os.walk(output_dir):
- log_files.extend([os.path.join(root, f) for f in files
- if f.endswith(".log") or f == "log"])
-
- if log_files:
- # Return the most recently modified log file
- return max(log_files, key=os.path.getmtime)
-
- return None
-
-
-def read_log_file(log_path, max_lines=1000):
- """
- Read log content from file.
-
- Args:
- log_path: Path to the log file
- max_lines: Maximum number of lines to read
-
- Returns:
- List of log lines
- """
- try:
- if not os.path.exists(log_path):
- return []
-
- with open(log_path, 'r', encoding='utf-8') as f:
- lines = f.readlines()
- # Return the last max_lines lines
- return [line.rstrip() for line in lines[-max_lines:]]
- except Exception as e:
- print(f"Error reading log file: {str(e)}")
- return []
-
-
-def update_logs():
- """
- Update logs from the log file.
-
- Returns:
- True if logs were updated, False otherwise
- """
- # Find the log file
- log_path = find_pipeline_log_file()
- if not log_path:
- return False
-
- # Read the log file
- logs = read_log_file(log_path)
- if not logs:
- return False
-
- # Update session state
- st.session_state.logs = logs
- return True
-
-
-def log_viewer(process=None):
- """
- Simple log viewer with manual refresh button.
-
- Args:
- process: Optional subprocess to monitor for status
- """
- st.subheader("Log Output")
-
- # Status indicator if process is provided
- if process:
- if process.poll() is None:
- st.caption("📋 Process is running...")
- else:
- ret_code = process.poll()
- if ret_code == 0:
- st.caption("✅ Process completed successfully. Return code: 0")
- else:
- st.caption(f"⚠️ Process completed with errors. Return code: {ret_code}")
-
- # Find log file
- log_path = find_pipeline_log_file()
-
- # Controls row
- col1, col2, col3 = st.columns([2, 1, 1])
-
- with col1:
- if log_path:
- st.caption(f"Log file: {log_path}")
- else:
- st.caption("No log file found")
-
- with col2:
- # Clear logs button
- if st.button("Clear Logs"):
- st.session_state.logs = []
- st.rerun()
-
- with col3:
- # Refresh button
- if st.button("Refresh Logs"):
- update_logs()
- st.rerun()
-
- # Debug info (collapsed)
- with st.expander("Debug Info", expanded=False):
- log_path = find_pipeline_log_file() or "Not found"
- log_exists = "Yes" if log_path != "Not found" and os.path.exists(log_path) else "No"
- log_size = "0" if log_path == "Not found" or not os.path.exists(log_path) else str(os.path.getsize(log_path))
-
- process_info = ""
- if process:
- process_info = f"""
-Process PID: {process.pid}
-Process Return Code: {process.poll()}
-Has stdout: {"Yes" if hasattr(process, 'stdout') and process.stdout else "No"}
-"""
-
- st.code(f"""{process_info}
-Log Count: {len(st.session_state.logs) if "logs" in st.session_state else 0}
-Log File: {log_path}
-Log File Exists: {log_exists}
-Log File Size: {log_size} bytes
- """)
-
- # Initialize logs if needed
- if "logs" not in st.session_state:
- st.session_state.logs = []
- # Try to load logs the first time
- update_logs()
-
- # Display the logs
- display_logs(st.session_state.logs)
diff --git a/optimhc/gui/components/modification_map.py b/optimhc/gui/components/modification_map.py
deleted file mode 100644
index 6a61af0..0000000
--- a/optimhc/gui/components/modification_map.py
+++ /dev/null
@@ -1,102 +0,0 @@
-"""
-Modification map component for optiMHC GUI.
-"""
-
-import streamlit as st
-from typing import Dict, Any, Optional
-
-def modification_map_form(existing_map: Optional[Dict[str, str]] = None) -> Dict[str, str]:
- """
- Create a form for modification map configuration.
-
- Args:
- existing_map: Existing modification map configuration
-
- Returns:
- Modification map dictionary mapping masses to UNIMOD values
- """
- if existing_map is None:
- existing_map = {
- "147.035385": "UNIMOD:35", # Oxidation (M) - Full modified residue mass
- "160.030649": "UNIMOD:4", # Carbamidomethyl (C) - Full modified residue mass
- "166.998359": "UNIMOD:21" # Phospho (S) - Full modified residue mass
- }
-
- st.subheader("Modification Map")
-
- st.markdown("""
- Specify the mapping from modification masses to UNIMOD identifiers.
- The mass value should be the FULL modified residue mass (amino acid + modification) as found in pepXML parameters.
- All modifications need to be explicitly encoded in the sequence (e.g., C[UNIMOD:4] for carbamidomethylated cysteine).
- """)
-
- # Create a container for the dynamic map
- modification_map = {}
-
- # Use session state to track number of modification entries
- if "num_modifications" not in st.session_state:
- st.session_state.num_modifications = len(existing_map)
- st.session_state.modification_masses = list(existing_map.keys())
- st.session_state.modification_values = list(existing_map.values())
-
- # Add/remove modification controls
- col1, col2 = st.columns([1, 5])
- with col1:
- if st.button("➕ Add Modification", key="add_modification"):
- st.session_state.num_modifications += 1
- st.session_state.modification_masses.append("")
- st.session_state.modification_values.append("UNIMOD:")
- st.rerun()
- with col2:
- if st.session_state.num_modifications > 0 and st.button("➖ Remove Last Modification", key="remove_modification"):
- st.session_state.num_modifications -= 1
- if st.session_state.modification_masses:
- st.session_state.modification_masses.pop()
- if st.session_state.modification_values:
- st.session_state.modification_values.pop()
- st.rerun()
-
- # Create a table-like interface for modifications
- if st.session_state.num_modifications > 0:
- col1, col2 = st.columns(2)
- with col1:
- st.markdown("**Mass (Residue+Modification)**")
- with col2:
- st.markdown("**UNIMOD Identifier**")
-
- for i in range(st.session_state.num_modifications):
- col1, col2 = st.columns(2)
- with col1:
- mass = st.text_input(
- "Mass",
- value=st.session_state.modification_masses[i] if i < len(st.session_state.modification_masses) else "",
- key=f"mod_mass_{i}",
- label_visibility="collapsed"
- )
- st.session_state.modification_masses[i] = mass
-
- with col2:
- unimod = st.text_input(
- "UNIMOD",
- value=st.session_state.modification_values[i] if i < len(st.session_state.modification_values) else "UNIMOD:",
- key=f"mod_unimod_{i}",
- label_visibility="collapsed"
- )
- st.session_state.modification_values[i] = unimod
-
- # Add to modification map
- if mass and unimod:
- modification_map[mass] = unimod
-
- # Information about common modifications
- with st.expander("Common Modifications (Note: Values are examples, check your pepXML)", expanded=False):
- st.markdown("""
- | Mass (Full) | UNIMOD ID | Modification | Target Residues |
- |------|-----------|--------------|--------------|
- | 147.035385 | UNIMOD:35 | Oxidation | M |
- | 160.030649 | UNIMOD:4 | Carbamidomethyl | C |
-
- Note: These are full masses (amino acid + modification). You must check your pepXML file parameters to find the exact masses used in your data.
- """)
-
- return modification_map
diff --git a/optimhc/gui/components/pipeline_control.py b/optimhc/gui/components/pipeline_control.py
deleted file mode 100644
index 8dc4726..0000000
--- a/optimhc/gui/components/pipeline_control.py
+++ /dev/null
@@ -1,177 +0,0 @@
-"""
-Pipeline control component for optiMHC GUI.
-"""
-
-import os
-import subprocess
-import sys
-import tempfile
-import time
-from typing import Dict, Any, Optional, Tuple
-import streamlit as st
-import yaml
-
-from optimhc.gui.utils import create_temp_config_file, run_pipeline_command
-
-
-def pipeline_status_indicator(running: bool = False, success: Optional[bool] = None):
- """
- Display a status indicator for the pipeline.
-
- Args:
- running: Whether the pipeline is currently running
- success: Whether the pipeline completed successfully
- """
- if running:
- st.info("Pipeline is running...")
- elif success is not None:
- if success:
- st.success("Pipeline completed successfully")
- else:
- st.error("Pipeline failed")
- else:
- st.info("Pipeline not yet started")
-
-
-def pipeline_control_panel(config: Dict[str, Any]):
- """
- Create a control panel for running the pipeline.
-
- Args:
- config: Configuration dictionary
- """
- st.subheader("Pipeline Control")
-
- # Initialize session state
- if "pipeline_running" not in st.session_state:
- st.session_state.pipeline_running = False
-
- if "pipeline_process" not in st.session_state:
- st.session_state.pipeline_process = None
-
- if "pipeline_start_time" not in st.session_state:
- st.session_state.pipeline_start_time = None
-
- if "pipeline_config_path" not in st.session_state:
- st.session_state.pipeline_config_path = None
-
- # Display status
- col1, col2 = st.columns([1, 3])
-
- with col1:
- if st.session_state.pipeline_running:
- pipeline_status_indicator(running=True)
- else:
- if st.session_state.pipeline_process is not None:
- return_code = st.session_state.pipeline_process.poll()
- pipeline_status_indicator(success=(return_code == 0))
- else:
- pipeline_status_indicator()
-
- with col2:
- if st.session_state.pipeline_start_time:
- elapsed_time = time.time() - st.session_state.pipeline_start_time
- st.text(f"Running for: {int(elapsed_time // 60)}m {int(elapsed_time % 60)}s")
-
- # Control buttons
- start_disabled = st.session_state.pipeline_running
- stop_disabled = not st.session_state.pipeline_running
-
- col1, col2 = st.columns(2)
-
- with col1:
- if st.button("Start Pipeline", disabled=start_disabled, key="start_pipeline"):
- # Check if the configuration is valid
- if not config.get("experimentName"):
- st.error("Experiment name is required")
- return
-
- if not config.get("inputFile"):
- st.error("At least one input file is required")
- return
-
- if not config.get("allele"):
- st.error("At least one allele is required")
- return
-
- if not config.get("featureGenerator"):
- st.error("At least one feature generator is required")
- return
-
- # Create a temporary configuration file
- config_path = create_temp_config_file(config)
- st.session_state.pipeline_config_path = config_path
-
- # Run the pipeline as a subprocess
- st.session_state.pipeline_process = run_pipeline_command(config_path)
- st.session_state.pipeline_running = True
- st.session_state.pipeline_start_time = time.time()
-
- # Initialize logs
- if "logs" not in st.session_state:
- st.session_state.logs = []
-
- # Rerun to update UI
- st.rerun()
-
- with col2:
- if st.button("Stop Pipeline", disabled=stop_disabled, key="stop_pipeline"):
- if st.session_state.pipeline_process:
- # Terminate the process
- st.session_state.pipeline_process.terminate()
- st.session_state.pipeline_running = False
-
- # Wait for process to terminate
- try:
- st.session_state.pipeline_process.wait(timeout=5)
- except subprocess.TimeoutExpired:
- # Force kill if it doesn't terminate gracefully
- st.session_state.pipeline_process.kill()
-
- st.warning("Pipeline was stopped by user")
-
- # No longer need to cleanup config file since it's part of the output
-
- # Rerun to update UI
- st.rerun()
-
- # Save configuration button
- if st.button("Save Configuration to File"):
- # Create a download button for the configuration
- config_yaml = yaml.dump(config, default_flow_style=False)
-
- # Use streamlit's download button
- filename = f"{config.get('experimentName', 'optimhc_config')}.yaml"
- st.download_button(
- label="Download Configuration File",
- data=config_yaml,
- file_name=filename,
- mime="text/yaml"
- )
-
-
-def check_pipeline_status():
- """
- Check the status of a running pipeline.
-
- Returns:
- Tuple of (running, return_code)
- """
- running = st.session_state.get("pipeline_running", False)
- process = st.session_state.get("pipeline_process", None)
-
- if process is None:
- return False, None
-
- # Check if process is still running
- return_code = process.poll()
-
- if return_code is not None and running:
- # Process has completed
- st.session_state.pipeline_running = False
-
- # No longer need to cleanup config file since it's part of the output
-
- return False, return_code
-
- return running, return_code
diff --git a/optimhc/gui/components/rescore_form.py b/optimhc/gui/components/rescore_form.py
deleted file mode 100644
index e30b540..0000000
--- a/optimhc/gui/components/rescore_form.py
+++ /dev/null
@@ -1,55 +0,0 @@
-"""
-Rescoring form component for optiMHC GUI.
-"""
-
-import streamlit as st
-from typing import Dict, Any
-
-# Import optiMHC config defaults
-from optimhc.core.config import DEFAULT_CONFIG
-
-def rescore_form(existing_rescore: Dict[str, Any] = None) -> Dict[str, Any]:
- """
- Create a form for rescoring settings.
-
- Args:
- existing_rescore: Existing rescore configuration
-
- Returns:
- Rescore configuration dictionary
- """
- if existing_rescore is None:
- existing_rescore = DEFAULT_CONFIG["rescore"]
-
- st.subheader("Rescoring Settings")
-
- rescore_model = st.selectbox(
- "Rescoring Model",
- options=["Percolator", "XGBoost", "RandomForest"],
- index=["Percolator", "XGBoost", "RandomForest"].index(existing_rescore.get("model", "Percolator")),
- help="Model to use for rescoring"
- )
-
- test_fdr = st.number_input(
- "Test FDR",
- min_value=0.001,
- max_value=0.1,
- value=float(existing_rescore.get("testFDR", 0.01)),
- step=0.001,
- format="%.3f",
- help="FDR threshold for testing"
- )
-
- num_jobs = st.number_input(
- "Number of Jobs",
- min_value=1,
- max_value=32,
- value=int(existing_rescore.get("numJobs", 1)),
- help="Number of parallel jobs for model training"
- )
-
- return {
- "model": rescore_model,
- "testFDR": test_fdr,
- "numJobs": num_jobs
- }
diff --git a/optimhc/gui/components/results_viewer.py b/optimhc/gui/components/results_viewer.py
deleted file mode 100644
index 05be9e7..0000000
--- a/optimhc/gui/components/results_viewer.py
+++ /dev/null
@@ -1,248 +0,0 @@
-"""
-Results viewer component for optiMHC GUI.
-"""
-
-import os
-import glob
-import base64
-from typing import List, Dict, Any, Optional
-import streamlit as st
-import pandas as pd
-import plotly.express as px
-from pathlib import Path
-
-from optimhc.gui.utils import scan_output_directory
-
-
-def get_image_as_base64(file_path):
- """
- Get image file as base64 string.
-
- Args:
- file_path: Path to image file
-
- Returns:
- Base64 encoded image
- """
- with open(file_path, "rb") as image_file:
- return base64.b64encode(image_file.read()).decode()
-
-
-def display_image(file_path, caption=None):
- """
- Display an image with caption.
-
- Args:
- file_path: Path to image file
- caption: Optional caption for the image
- """
- try:
- # Use HTML to have more control over image sizing
- img_format = file_path.split('.')[-1].lower()
- img_base64 = get_image_as_base64(file_path)
- html = f'
'
-
- if caption:
- html = f'{html}{caption}
'
-
- st.markdown(html, unsafe_allow_html=True)
- except Exception as e:
- st.error(f"Error displaying image {os.path.basename(file_path)}: {str(e)}")
-
-
-def display_csv(file_path, caption=None):
- """
- Display a CSV file as a dataframe.
-
- Args:
- file_path: Path to CSV file
- caption: Optional caption for the table
- """
- try:
- # Determine file type and use appropriate reader
- if file_path.endswith('.csv'):
- df = pd.read_csv(file_path)
- elif file_path.endswith('.tsv'):
- df = pd.read_csv(file_path, sep='\t')
- elif file_path.endswith('.xlsx'):
- df = pd.read_excel(file_path)
- else:
- st.warning(f"Unsupported file format: {os.path.basename(file_path)}")
- return
-
- if caption:
- st.markdown(f"**{caption}**")
-
- # Display dataframe with pagination if large
- if len(df) > 100:
- # Add pagination controls
- page_size = st.slider(f"Rows per page for {os.path.basename(file_path)}", 10, 100, 50)
- page = st.number_input(f"Page for {os.path.basename(file_path)}", min_value=1, max_value=max(1, len(df) // page_size + 1), value=1)
-
- start_idx = (page - 1) * page_size
- end_idx = min(start_idx + page_size, len(df))
-
- st.dataframe(df.iloc[start_idx:end_idx])
- st.text(f"Showing rows {start_idx+1}-{end_idx} of {len(df)}")
- else:
- st.dataframe(df)
-
- # Option to download the file
- csv_data = df.to_csv(index=False).encode('utf-8')
- st.download_button(
- label=f"Download {os.path.basename(file_path)}",
- data=csv_data,
- file_name=os.path.basename(file_path),
- mime="text/csv"
- )
- except Exception as e:
- st.error(f"Error displaying data from {os.path.basename(file_path)}: {str(e)}")
-
-
-def results_viewer(output_dir: str):
- """
- Display results from the output directory, focusing only on figures.
-
- Args:
- output_dir: Path to the output directory
- """
- st.subheader("Results Visualization")
-
- if not os.path.exists(output_dir):
- st.warning(f"Output directory '{output_dir}' does not exist yet")
- return
-
- # Check if there's an experiment name in the session state
- experiment_name = None
- if "config" in st.session_state:
- experiment_name = st.session_state.config.get("experimentName")
-
- # Look for figures in experiment subdirectory if it exists
- if experiment_name:
- experiment_dir = os.path.join(output_dir, experiment_name)
- if os.path.exists(experiment_dir):
- # Update output_dir to use the experiment directory
- output_dir = experiment_dir
-
- # Check for figures subfolder
- figures_dir = os.path.join(output_dir, "figures")
- has_figures_subdir = os.path.exists(figures_dir) and os.path.isdir(figures_dir)
-
- # Get all figure files
- figure_files = []
-
- # First check figures subdirectory if it exists
- if has_figures_subdir:
- figure_files = glob.glob(os.path.join(figures_dir, "*.png"))
- figure_files.extend(glob.glob(os.path.join(figures_dir, "*.jpg")))
- figure_files.extend(glob.glob(os.path.join(figures_dir, "*.svg")))
- figure_files.extend(glob.glob(os.path.join(figures_dir, "*.pdf")))
-
- # If no figures found in subfolder (or none exists), check main directory
- if not figure_files:
- figure_files = glob.glob(os.path.join(output_dir, "*.png"))
- figure_files.extend(glob.glob(os.path.join(output_dir, "*.jpg")))
- figure_files.extend(glob.glob(os.path.join(output_dir, "*.svg")))
- figure_files.extend(glob.glob(os.path.join(output_dir, "*.pdf")))
-
- # Show figures
- if figure_files:
- figure_count = len(figure_files)
-
- # Show information about found figures
- st.caption(f"Found {figure_count} figures in {figures_dir if has_figures_subdir else output_dir}")
-
- # Create a selector for figures if there are more than one
- if figure_count > 1:
- # Sort figures by name for consistency
- figure_files.sort()
- figure_names = [os.path.basename(f) for f in figure_files]
-
- # Figure selection dropdown
- selected_figure = st.selectbox(
- "Select figure to view:",
- figure_names,
- key="figure_selector"
- )
-
- selected_index = figure_names.index(selected_figure)
-
- # Display the selected figure
- st.markdown("### Selected Figure")
- display_image(figure_files[selected_index], caption=selected_figure)
-
- # Show thumbnail gallery with 3 columns
- st.markdown("### All Figures")
-
- # Use columns for gallery display
- cols = st.columns(min(3, figure_count))
- for i, file_path in enumerate(figure_files):
- with cols[i % 3]:
- try:
- img_format = file_path.split('.')[-1].lower()
- if img_format in ['png', 'jpg', 'jpeg', 'svg']:
- img_base64 = get_image_as_base64(file_path)
- html = f''
- st.markdown(html, unsafe_allow_html=True)
- st.caption(os.path.basename(file_path))
- else:
- # For non-image formats like PDF
- st.info(f"{os.path.basename(file_path)} (PDF file)")
- except Exception as e:
- st.error(f"Error with image {os.path.basename(file_path)}")
- else:
- # Just show the single figure
- display_image(figure_files[0], caption=os.path.basename(figure_files[0]))
- else:
- st.info(f"No figures found in the output directory. Run the pipeline to generate results.")
-
- # Refresh button
- if st.button("Refresh Results", key="refresh_results_btn"):
- st.rerun()
-
-
-def results_summary(output_dir: str):
- """
- Display a summary of results.
-
- Args:
- output_dir: Path to the output directory
- """
- if not os.path.exists(output_dir):
- return
-
- # Look for summary statistics
- summary_files = glob.glob(os.path.join(output_dir, "**/summary*.csv"), recursive=True)
- summary_files.extend(glob.glob(os.path.join(output_dir, "**/stats*.csv"), recursive=True))
-
- if not summary_files:
- return
-
- st.subheader("Results Summary")
-
- try:
- # Use the first summary file found
- df = pd.read_csv(summary_files[0])
-
- # Display key statistics
- cols = st.columns(3)
-
- if 'total_psms' in df.columns:
- with cols[0]:
- st.metric("Total PSMs", df['total_psms'].iloc[0])
-
- if 'target_psms' in df.columns:
- with cols[1]:
- st.metric("Target PSMs", df['target_psms'].iloc[0])
-
- if 'decoy_psms' in df.columns:
- with cols[2]:
- st.metric("Decoy PSMs", df['decoy_psms'].iloc[0])
-
- # Generate a simple chart if possible
- if {'fdr', 'target_psms'}.issubset(df.columns):
- st.subheader("FDR vs. Target PSMs")
- fig = px.line(df, x='fdr', y='target_psms', title='PSMs at different FDR thresholds')
- st.plotly_chart(fig, use_container_width=True)
- except Exception as e:
- st.error(f"Error generating results summary: {str(e)}")
diff --git a/optimhc/gui/pages/__init__.py b/optimhc/gui/pages/__init__.py
deleted file mode 100644
index 0be9679..0000000
--- a/optimhc/gui/pages/__init__.py
+++ /dev/null
@@ -1,10 +0,0 @@
-"""
-Page modules for the optiMHC Streamlit interface.
-"""
-
-__all__ = [
- "home",
- "configure",
- "run",
- "results"
-]
diff --git a/optimhc/gui/pages/configure.py b/optimhc/gui/pages/configure.py
deleted file mode 100644
index 1fb7b07..0000000
--- a/optimhc/gui/pages/configure.py
+++ /dev/null
@@ -1,308 +0,0 @@
-"""
-Configuration page for the optiMHC GUI.
-"""
-
-import streamlit as st
-import os
-import yaml
-from typing import Dict, Any
-
-from optimhc.gui.style import main_header, sub_header, info_box, warning_box
-from optimhc.gui.components.config_form import validate_config, render_config_summary
-from optimhc.gui.components.file_upload import config_file_uploader, input_path_field, yaml_example
-from optimhc.gui.components.feature_generator_form import feature_generator_form
-from optimhc.gui.components.rescore_form import rescore_form
-from optimhc.gui.components.modification_map import modification_map_form
-
-
-def render():
- """
- Render the configuration page.
- """
- main_header("Configure Pipeline")
-
- st.markdown("""
- Configure your optiMHC pipeline by filling out the form below, or upload an existing configuration file.
- """)
-
- # Initialize session state for configuration
- if "config" not in st.session_state:
- st.session_state.config = {}
-
- # File upload option and example buttons
- col1, col2, col3 = st.columns([2, 1, 1])
-
- with col1:
- uploaded_config = config_file_uploader()
-
- if uploaded_config:
- # Validate configuration
- errors = validate_config(uploaded_config)
-
- if errors:
- for error in errors:
- st.error(error)
- else:
- # Save configuration to session state
- st.session_state.config = uploaded_config
-
- # Handle modification map in session state for the form
- if "modificationMap" in uploaded_config and uploaded_config["modificationMap"]:
- st.session_state.num_modifications = len(uploaded_config["modificationMap"])
- st.session_state.modification_masses = list(uploaded_config["modificationMap"].keys())
- st.session_state.modification_values = list(uploaded_config["modificationMap"].values())
-
- st.success("Configuration loaded successfully!")
- st.rerun()
-
- with col2:
- if st.button("Load Class I Example", use_container_width=True):
- example_config = yaml.safe_load(yaml_example("class_i"))
- # Ensure modification map is included
- if "modificationMap" not in example_config or not example_config["modificationMap"]:
- example_config["modificationMap"] = {
- "147.035385": "UNIMOD:35", # Oxidation (M) - full modified residue mass
- "160.030649": "UNIMOD:4" # Carbamidomethyl (C) - full modified residue mass
- }
- st.session_state.config = example_config
- # Also update the modification map in session state for the form
- st.session_state.num_modifications = len(example_config["modificationMap"])
- st.session_state.modification_masses = list(example_config["modificationMap"].keys())
- st.session_state.modification_values = list(example_config["modificationMap"].values())
- st.success("Class I example configuration loaded!")
- st.rerun()
-
- with col3:
- if st.button("Load Class II Example", use_container_width=True):
- example_config = yaml.safe_load(yaml_example("class_ii"))
- # Ensure modification map is included
- if "modificationMap" not in example_config or not example_config["modificationMap"]:
- example_config["modificationMap"] = {
- "147.035385": "UNIMOD:35", # Oxidation (M) - full modified residue mass
- "160.030649": "UNIMOD:4" # Carbamidomethyl (C) - full modified residue mass
- }
- st.session_state.config = example_config
- # Also update the modification map in session state for the form
- st.session_state.num_modifications = len(example_config["modificationMap"])
- st.session_state.modification_masses = list(example_config["modificationMap"].keys())
- st.session_state.modification_values = list(example_config["modificationMap"].values())
- st.success("Class II example configuration loaded!")
- st.rerun()
-
- # Setup configuration tabs
- tabs = st.tabs(["Basic Settings", "Feature Generators", "Rescoring", "Summary"])
-
- # Tab 1: Basic Settings
- with tabs[0]:
- st.subheader("Basic Settings")
-
- # Experiment name
- experiment_name = st.text_input(
- "Experiment Name",
- value=st.session_state.config.get("experimentName", ""),
- placeholder="my_experiment",
- help="Name of the experiment"
- )
-
- # Input type and files
- col1, col2 = st.columns(2)
- with col1:
- input_type = st.selectbox(
- "Input Type",
- options=["pepxml", "pin"],
- index=["pepxml", "pin"].index(st.session_state.config.get("inputType", "pepxml")),
- help="Type of input file"
- )
-
- with col2:
- decoy_prefix = st.text_input(
- "Decoy Prefix",
- value=st.session_state.config.get("decoyPrefix", "DECOY_"),
- help="Prefix used to identify decoy sequences"
- )
-
- # Input files - use direct path input
- input_files = st.session_state.config.get("inputFile", [])
- if isinstance(input_files, str):
- input_files = [input_files]
-
- input_files_str = input_path_field(
- input_type,
- value="\n".join(input_files) if input_files else "",
- placeholder="../examples/data/YE_20180428_SK_HLA_A0202_3Ips_a50mio_R1_01.pep.xml"
- )
-
- # Output directory
- output_dir = st.text_input(
- "Output Directory",
- value=st.session_state.config.get("outputDir", "../examples/results"),
- placeholder="../examples/results/my_experiment",
- help="Directory where results will be saved"
- )
-
- # Allele settings
- st.subheader("Allele Settings")
-
- alleles = st.session_state.config.get("allele", [])
- if isinstance(alleles, str):
- alleles = [alleles]
-
- alleles_str = st.text_area(
- "Alleles",
- value="\n".join(alleles) if alleles else "",
- placeholder="HLA-A*02:01\nHLA-B*07:02",
- height=100,
- help="One allele per line, e.g., HLA-A*02:01 for class I or HLA-DPA1*02:01-DPB1*01:01 for class II"
- )
-
- # Modification map
- st.subheader("Modification Map")
- st.markdown("Maps full modified residue masses to UNIMOD identifiers.")
- modification_map = modification_map_form(st.session_state.config.get("modificationMap", {}))
-
- # Performance settings
- st.subheader("Performance Settings")
-
- col1, col2 = st.columns(2)
-
- with col1:
- num_processes = st.number_input(
- "Number of Processes",
- min_value=1,
- max_value=64,
- value=int(st.session_state.config.get("numProcesses", 4)),
- help="Number of parallel processes"
- )
-
- with col2:
- show_progress = st.checkbox(
- "Show Progress",
- value=st.session_state.config.get("showProgress", True),
- help="Show progress bars during processing"
- )
-
- col1, col2 = st.columns(2)
-
- with col1:
- visualization = st.checkbox(
- "Enable Visualization",
- value=st.session_state.config.get("visualization", True),
- help="Generate visualizations of results"
- )
-
- with col2:
- remove_pre_nxt_aa = st.checkbox(
- "Remove Pre/Next Amino Acids",
- value=st.session_state.config.get("removePreNxtAA", False),
- help="Remove pre/post neighboring amino acids in sequence processing"
- )
-
- log_level = st.selectbox(
- "Log Level",
- options=["DEBUG", "INFO", "WARNING", "ERROR"],
- index=["DEBUG", "INFO", "WARNING", "ERROR"].index(st.session_state.config.get("logLevel", "INFO")),
- help="Logging verbosity level"
- )
-
- # Save basic settings
- if st.button("Save Basic Settings", key="save_basic"):
- # Process input fields
- input_files = [f for f in input_files_str.strip().split("\n") if f]
- alleles = [a for a in alleles_str.strip().split("\n") if a]
-
- # Update configuration
- st.session_state.config.update({
- "experimentName": experiment_name,
- "inputType": input_type,
- "inputFile": input_files,
- "decoyPrefix": decoy_prefix,
- "outputDir": output_dir,
- "allele": alleles,
- "modificationMap": modification_map,
- "numProcesses": num_processes,
- "showProgress": show_progress,
- "visualization": visualization,
- "removePreNxtAA": remove_pre_nxt_aa,
- "logLevel": log_level
- })
-
- st.success("Basic settings saved!")
- st.rerun()
-
- # Tab 2: Feature Generators
- with tabs[1]:
- # Feature generators configuration
- feature_generators = feature_generator_form(st.session_state.config.get("featureGenerator", []))
-
- # Save feature generators
- if st.button("Save Feature Generators", key="save_features"):
- st.session_state.config["featureGenerator"] = feature_generators
- st.success("Feature generators saved!")
-
- # Tab 3: Rescoring
- with tabs[2]:
- # Rescoring configuration
- rescore_config = rescore_form(st.session_state.config.get("rescore", {}))
-
- # Save rescoring settings
- if st.button("Save Rescoring Settings", key="save_rescore"):
- st.session_state.config["rescore"] = rescore_config
- st.success("Rescoring settings saved!")
-
- # Tab 4: Summary
- with tabs[3]:
- # Full configuration summary
- if st.session_state.config:
- st.subheader("Configuration Summary")
-
- # Display configuration summary
- render_config_summary(st.session_state.config)
-
- # Validate configuration
- errors = validate_config(st.session_state.config)
-
- if errors:
- st.error("Configuration has errors:")
- for error in errors:
- st.error(f"- {error}")
- else:
- st.success("Configuration is valid!")
-
- # Option to download configuration
- if st.button("Download Configuration as YAML"):
- # Create YAML content
- config_yaml = yaml.dump(st.session_state.config, default_flow_style=False)
-
- # Use streamlit's download button
- filename = f"{st.session_state.config.get('experimentName', 'optimhc_config')}.yaml"
- st.download_button(
- label="Download Configuration File",
- data=config_yaml,
- file_name=filename,
- mime="text/yaml"
- )
- else:
- st.warning("No configuration has been saved yet. Please fill out and save the forms in the other tabs.")
-
- # Navigation buttons
- st.markdown("---")
- col1, col2 = st.columns(2)
-
- with col1:
- if st.button("← Back to Home"):
- st.session_state.page = "home"
- st.rerun()
-
- with col2:
- if st.button("Continue to Run →"):
- # Check if we have a valid configuration
- if not st.session_state.config:
- warning_box("Please configure the pipeline first.")
- else:
- errors = validate_config(st.session_state.config)
- if errors:
- for error in errors:
- st.error(error)
- else:
- st.session_state.page = "run"
- st.rerun()
diff --git a/optimhc/gui/pages/home.py b/optimhc/gui/pages/home.py
deleted file mode 100644
index b91b833..0000000
--- a/optimhc/gui/pages/home.py
+++ /dev/null
@@ -1,75 +0,0 @@
-"""
-Home page for the optiMHC GUI.
-"""
-
-import streamlit as st
-from optimhc.gui.style import main_header, sub_header, info_box
-
-
-def render():
- """
- Render the home page.
- """
- main_header("Welcome to optiMHC")
-
- st.markdown("""
- optiMHC is a high-performance rescoring pipeline for immunopeptidomics data, designed to enhance
- peptide identification by integrating multiple feature generators and machine learning-based rescoring.
- """)
-
- # Feature overview
- sub_header("Features")
-
- col1, col2 = st.columns(2)
-
- with col1:
- st.markdown("""
- - **Multiple Feature Generators**
- - Basic sequence features
- - Position Weight Matrix (PWM)
- - MHC binding prediction (MHCflurry, NetMHCpan)
- - Chromatographic retention time (DeepLC)
- - Spectrum similarity
- - Overlapping peptides
-
- - **Machine Learning Rescoring**
- - Percolator
- - XGBoost
- - Random Forest
- """)
-
- with col2:
- st.markdown("""
- - **Flexible Configuration**
- - YAML-based configuration
- - Command-line interface
- - Python API
-
- - **Comprehensive Visualization**
- - ROC curves
- - Score distributions
- - FDR vs. identifications
- - Feature importance
- """)
-
- # Quick start guide
- sub_header("Quick Start")
-
- st.markdown("""
- To get started with optiMHC:
-
- 1. Go to the **Configure** page to set up your pipeline parameters
- 2. Upload your input files or specify their paths
- 3. Run the pipeline from the **Run** page
- 4. View your results in the **Results** page
- """)
-
- # Warning about GUI being in development
- info_box("""
- Note: This GUI is currently in development. For advanced use cases or troubleshooting,
- please refer to the command-line interface or the documentation.
- """)
-
- # Footer
- st.markdown("---")
- st.markdown("optiMHC is developed and maintained by Zixiang Shang. For more information, please visit the [GitHub repository](https://github.com/5h4ng/optiMHC).")
diff --git a/optimhc/gui/pages/results.py b/optimhc/gui/pages/results.py
deleted file mode 100644
index 7e7163c..0000000
--- a/optimhc/gui/pages/results.py
+++ /dev/null
@@ -1,125 +0,0 @@
-"""
-Results page for the optiMHC GUI.
-"""
-
-import streamlit as st
-import os
-import glob
-from typing import Dict, Any, List
-
-from optimhc.gui.style import main_header, sub_header, info_box, warning_box
-from optimhc.gui.components.results_viewer import results_viewer
-
-
-def find_figure_files(output_dir: str, experiment_name: str = None) -> List[str]:
- """
- Find all figure files in the output directory or its figures subdirectory.
-
- Args:
- output_dir: Path to the output directory
- experiment_name: Optional experiment name subdirectory
-
- Returns:
- List of paths to figure files
- """
- figure_files = []
-
- # If experiment name is provided, look in that subdirectory
- if experiment_name:
- experiment_dir = os.path.join(output_dir, experiment_name)
- if os.path.exists(experiment_dir):
- # Look for figures subfolder inside experiment directory
- figures_dir = os.path.join(experiment_dir, "figures")
- if os.path.exists(figures_dir) and os.path.isdir(figures_dir):
- figure_files = glob.glob(os.path.join(figures_dir, "*.png"))
- figure_files.extend(glob.glob(os.path.join(figures_dir, "*.jpg")))
- figure_files.extend(glob.glob(os.path.join(figures_dir, "*.svg")))
- figure_files.extend(glob.glob(os.path.join(figures_dir, "*.pdf")))
-
- # If no figures found in subfolder, look in experiment directory
- if not figure_files:
- figure_files = glob.glob(os.path.join(experiment_dir, "*.png"))
- figure_files.extend(glob.glob(os.path.join(experiment_dir, "*.jpg")))
- figure_files.extend(glob.glob(os.path.join(experiment_dir, "*.svg")))
- figure_files.extend(glob.glob(os.path.join(experiment_dir, "*.pdf")))
-
- # If no figures found in experiment directory or no experiment name,
- # check main output directory
- if not figure_files:
- # Check for figures subfolder in main directory
- figures_dir = os.path.join(output_dir, "figures")
- if os.path.exists(figures_dir) and os.path.isdir(figures_dir):
- figure_files = glob.glob(os.path.join(figures_dir, "*.png"))
- figure_files.extend(glob.glob(os.path.join(figures_dir, "*.jpg")))
- figure_files.extend(glob.glob(os.path.join(figures_dir, "*.svg")))
- figure_files.extend(glob.glob(os.path.join(figures_dir, "*.pdf")))
-
- # If still no figures, check main directory
- if not figure_files:
- figure_files = glob.glob(os.path.join(output_dir, "*.png"))
- figure_files.extend(glob.glob(os.path.join(output_dir, "*.jpg")))
- figure_files.extend(glob.glob(os.path.join(output_dir, "*.svg")))
- figure_files.extend(glob.glob(os.path.join(output_dir, "*.pdf")))
-
- return figure_files
-
-
-def render():
- """
- Render the results page focusing on figure visualization.
- """
- main_header("Results Visualization")
-
- # Check if we have a configuration
- if "config" not in st.session_state or not st.session_state.config:
- warning_box("No configuration available. Please configure and run the pipeline first.")
-
- if st.button("Go to Configuration"):
- st.session_state.page = "configure"
- st.rerun()
- return
-
- # Get output directory and experiment name from configuration
- output_dir = st.session_state.config.get("outputDir", "./results")
- experiment_name = st.session_state.config.get("experimentName", "")
-
- # Allow user to change the output directory
- output_dir = st.text_input("Output Directory", value=output_dir)
-
- # Check if directory exists
- if not os.path.exists(output_dir):
- warning_box(f"Output directory '{output_dir}' does not exist. Please run the pipeline first or check the directory path.")
-
- # Show navigation buttons
- col1, col2 = st.columns(2)
- with col1:
- if st.button("← Back to Run Pipeline"):
- st.session_state.page = "run"
- st.rerun()
- with col2:
- if st.button("Go to Home"):
- st.session_state.page = "home"
- st.rerun()
- return
-
- # Show experiment details if available
- if experiment_name:
- sub_header(f"Experiment: {experiment_name}")
-
- # Display results using our results_viewer component
- # The component will handle finding the appropriate figure files
- results_viewer(output_dir)
-
- # Navigation buttons
- st.markdown("---")
- col1, col2 = st.columns(2)
-
- with col1:
- if st.button("← Back to Run"):
- st.session_state.page = "run"
- st.rerun()
-
- with col2:
- if st.button("Back to Home"):
- st.session_state.page = "home"
- st.rerun()
diff --git a/optimhc/gui/pages/run.py b/optimhc/gui/pages/run.py
deleted file mode 100644
index ee4f4f2..0000000
--- a/optimhc/gui/pages/run.py
+++ /dev/null
@@ -1,62 +0,0 @@
-"""
-Run page for the optiMHC GUI.
-"""
-
-import streamlit as st
-import os
-import time
-from typing import Dict, Any
-
-from optimhc.gui.style import main_header, sub_header, info_box, warning_box
-from optimhc.gui.components.pipeline_control import pipeline_control_panel, check_pipeline_status
-from optimhc.gui.components.log_viewer import log_viewer
-from optimhc.gui.components.config_form import render_config_summary
-
-
-def render():
- """
- Render the run page.
- """
- main_header("Run Pipeline")
-
- # Check if we have a configuration
- if "config" not in st.session_state or not st.session_state.config:
- warning_box("No configuration available. Please configure the pipeline first.")
-
- if st.button("Go to Configuration"):
- st.session_state.page = "configure"
- st.rerun()
- return
-
- # Display configuration summary
- with st.expander("Configuration Summary", expanded=False):
- render_config_summary(st.session_state.config)
-
- # Pipeline control panel
- pipeline_control_panel(st.session_state.config)
-
- # Separator
- st.markdown("---")
-
- # Check pipeline status
- running, return_code = check_pipeline_status()
-
- # Show log viewer if process exists
- if "pipeline_process" in st.session_state and st.session_state.pipeline_process:
- log_viewer(st.session_state.pipeline_process)
-
- # Navigation buttons
- col1, col2 = st.columns(2)
-
- with col1:
- if st.button("← Back to Configure"):
- st.session_state.page = "configure"
- st.rerun()
-
- with col2:
- # Only enable results button if pipeline has completed
- results_disabled = running or ("pipeline_process" not in st.session_state)
-
- if st.button("View Results →", disabled=results_disabled):
- st.session_state.page = "results"
- st.rerun()
diff --git a/optimhc/gui/style.py b/optimhc/gui/style.py
deleted file mode 100644
index d83b7aa..0000000
--- a/optimhc/gui/style.py
+++ /dev/null
@@ -1,161 +0,0 @@
-"""
-Styling utilities for the optiMHC Streamlit interface.
-"""
-
-import streamlit as st
-
-
-def apply_custom_css():
- """
- Apply custom CSS styling to the Streamlit app.
- """
- st.markdown("""
-
- """, unsafe_allow_html=True)
-
-
-def set_page_config():
- """
- Set up the Streamlit page configuration with theme and layout settings.
- """
- st.set_page_config(
- page_title="optiMHC",
- page_icon="🧬",
- layout="wide",
- initial_sidebar_state="expanded",
- )
-
-
-def main_header(text):
- """
- Display a main header with custom styling.
-
- Args:
- text: Header text to display
- """
- st.markdown(f'{text}
', unsafe_allow_html=True)
-
-
-def sub_header(text):
- """
- Display a sub-header with custom styling.
-
- Args:
- text: Sub-header text to display
- """
- st.markdown(f'', unsafe_allow_html=True)
-
-
-def info_box(text):
- """
- Display an information box with custom styling.
-
- Args:
- text: Information text to display
- """
- st.markdown(f'{text}
', unsafe_allow_html=True)
-
-
-def success_box(text):
- """
- Display a success box with custom styling.
-
- Args:
- text: Success message to display
- """
- st.markdown(f'{text}
', unsafe_allow_html=True)
-
-
-def warning_box(text):
- """
- Display a warning box with custom styling.
-
- Args:
- text: Warning message to display
- """
- st.markdown(f'{text}
', unsafe_allow_html=True)
-
-
-def error_box(text):
- """
- Display an error box with custom styling.
-
- Args:
- text: Error message to display
- """
- st.markdown(f'{text}
', unsafe_allow_html=True)
-
-
-def footer():
- """
- Display a footer with copyright and version information.
- """
- from optimhc import __version__ as version
-
- st.markdown(
- f'',
- unsafe_allow_html=True
- )
diff --git a/optimhc/gui/utils.py b/optimhc/gui/utils.py
deleted file mode 100644
index 53831fc..0000000
--- a/optimhc/gui/utils.py
+++ /dev/null
@@ -1,243 +0,0 @@
-"""
-Utility functions for the optiMHC GUI.
-"""
-
-import os
-import subprocess
-import sys
-import tempfile
-from pathlib import Path
-import yaml
-import json
-import streamlit as st
-import pandas as pd
-from typing import Dict, List, Any, Optional, Union
-
-
-def load_config_from_yaml(file_path: str) -> Dict[str, Any]:
- """
- Load configuration from a YAML file.
-
- Args:
- file_path: Path to the YAML configuration file
-
- Returns:
- Dictionary containing the configuration
- """
- try:
- with open(file_path, 'r') as f:
- config = yaml.safe_load(f)
- return config
- except Exception as e:
- st.error(f"Error loading configuration file: {str(e)}")
- return {}
-
-
-def save_config_to_yaml(config: Dict[str, Any], file_path: str) -> bool:
- """
- Save configuration to a YAML file.
-
- Args:
- config: Configuration dictionary
- file_path: Path to save the YAML file
-
- Returns:
- True if successful, False otherwise
- """
- try:
- with open(file_path, 'w') as f:
- yaml.dump(config, f, default_flow_style=False)
- return True
- except Exception as e:
- st.error(f"Error saving configuration file: {str(e)}")
- return False
-
-
-def create_temp_config_file(config: Dict[str, Any]) -> str:
- """
- Create a temporary configuration file.
-
- Args:
- config: Configuration dictionary
-
- Returns:
- Path to the temporary file
- """
- fd, temp_path = tempfile.mkstemp(suffix='.yaml')
- with os.fdopen(fd, 'w') as f:
- yaml.dump(config, f, default_flow_style=False)
- return temp_path
-
-
-def run_pipeline_command(config_path: str) -> subprocess.Popen:
- """
- Run the optiMHC pipeline as a subprocess.
-
- Args:
- config_path: Path to the configuration file
-
- Returns:
- Subprocess object
- """
- # Load configuration to access output directory and experiment name
- config = {}
- try:
- with open(config_path, 'r') as f:
- config = yaml.safe_load(f)
-
- # Store config in session state for log finding
- st.session_state.config = config
- except Exception as e:
- print(f"Error loading configuration: {str(e)}")
-
- # Identify where logs will be stored based on pipeline conventions
- output_dir = config.get("outputDir", "")
- experiment_name = config.get("experimentName", "")
-
- # The actual log file that the pipeline will create
- if output_dir and experiment_name:
- experiment_dir = os.path.join(output_dir, experiment_name)
- os.makedirs(experiment_dir, exist_ok=True)
- pipeline_log_path = os.path.join(experiment_dir, "log")
-
- # Store the expected log file path in session state
- st.session_state.pipeline_log_path = pipeline_log_path
- else:
- st.session_state.pipeline_log_path = None
-
- # Reset log position counter
- st.session_state.log_position = 0
-
- # Set environment variables to ensure output is not buffered
- my_env = os.environ.copy()
- my_env["PYTHONUNBUFFERED"] = "1" # Prevent Python from buffering output
- my_env["PYTHONIOENCODING"] = "utf-8" # Ensure UTF-8 encoding
-
- # Run the pipeline command
- cmd = [sys.executable, "-u", "-m", "optimhc", "pipeline", "--config", config_path]
- process = subprocess.Popen(
- cmd,
- stdout=subprocess.PIPE,
- stderr=subprocess.STDOUT,
- text=True,
- bufsize=1, # Line buffered
- universal_newlines=True,
- env=my_env
- )
-
- # Start a thread to read and print output (for debugging)
- def monitor_output():
- try:
- for line in iter(process.stdout.readline, ''):
- print(line.strip()) # Print to console for debugging
- except Exception as e:
- print(f"Error in monitor thread: {str(e)}")
-
- # Start thread in daemon mode so it won't block program exit
- import threading
- monitor_thread = threading.Thread(target=monitor_output, daemon=True)
- monitor_thread.start()
-
- return process
-
-
-def scan_output_directory(output_dir: str) -> Dict[str, List[str]]:
- """
- Scan the output directory for results.
-
- Args:
- output_dir: Path to the output directory
-
- Returns:
- Dictionary with lists of files grouped by type
- """
- if not os.path.exists(output_dir):
- return {
- 'figures': [],
- 'tables': [],
- 'logs': [],
- 'other': []
- }
-
- result_files = {
- 'figures': [],
- 'tables': [],
- 'logs': [],
- 'other': []
- }
-
- for root, _, files in os.walk(output_dir):
- for file in files:
- file_path = os.path.join(root, file)
- if file.endswith(('.png', '.jpg', '.jpeg', '.svg', '.pdf')):
- result_files['figures'].append(file_path)
- elif file.endswith(('.csv', '.tsv', '.xlsx')):
- result_files['tables'].append(file_path)
- elif file.endswith('.log'):
- result_files['logs'].append(file_path)
- else:
- result_files['other'].append(file_path)
-
- return result_files
-
-
-def get_config_summary(config: Dict[str, Any]) -> Dict[str, Any]:
- """
- Create a summary of the configuration for display.
-
- Args:
- config: Configuration dictionary
-
- Returns:
- Dictionary with summarized configuration
- """
- summary = {
- 'Experiment Name': config.get('experimentName', 'N/A'),
- 'Input Type': config.get('inputType', 'N/A'),
- 'Output Directory': config.get('outputDir', 'N/A'),
- 'Alleles': ', '.join(config.get('allele', [])) if config.get('allele') else 'N/A',
- 'Feature Generators': [gen.get('name') for gen in config.get('featureGenerator', [])]
- if config.get('featureGenerator') else 'N/A',
- 'Rescoring Model': config.get('rescore', {}).get('model', 'N/A') if config.get('rescore') else 'N/A',
- 'Modification Map': f"{len(config.get('modificationMap', {}))} modifications"
- if config.get('modificationMap') else 'Default'
- }
- return summary
-
-
-def parse_feature_generator_json(json_str: str) -> Optional[Dict[str, Any]]:
- """
- Parse JSON string for feature generator configuration.
-
- Args:
- json_str: JSON string to parse
-
- Returns:
- Dictionary containing the feature generator configuration or None if invalid
- """
- try:
- return json.loads(json_str)
- except json.JSONDecodeError:
- return None
-
-
-def format_log_message(message: str, level: str = "INFO") -> str:
- """
- Format a log message for display.
-
- Args:
- message: Log message to format
- level: Log level
-
- Returns:
- Formatted log message
- """
- level_colors = {
- "DEBUG": "gray",
- "INFO": "black",
- "WARNING": "orange",
- "ERROR": "red",
- "CRITICAL": "crimson"
- }
- color = level_colors.get(level, "black")
- return f'[{level}] {message}'
diff --git a/optimhc/psm_container.py b/optimhc/psm_container.py
index f8e0b27..6aa1e5a 100644
--- a/optimhc/psm_container.py
+++ b/optimhc/psm_container.py
@@ -69,7 +69,7 @@ def __init__(
protein_column: str,
rescoring_features: Dict[str, List[str]],
hit_rank_column: Optional[str] = None,
- charge_column: Optional[int] = None,
+ charge_column: Optional[str] = None,
retention_time_column: Optional[str] = None,
calculated_mass_column: Optional[str] = None,
metadata_column: Optional[str] = None,
@@ -144,13 +144,13 @@ def check_rescoring_features(features: Dict[str, List[str]]):
logger.info("PsmContainer initialized with %d PSM entries.", len(self._psms))
if self.ms_data_file_column:
logger.info(
- "PSMs originated from %d MS data file(S).",
+ "PSMs originated from %d MS data file(s).",
len(self._psms[ms_data_file_column].unique()),
)
logger.info("target psms: %d", len(self.target_psms))
logger.info("decoy psms: %d", len(self.decoy_psms))
logger.info("unique peptides: %d", len(np.unique(self.peptides)))
- logger.info("rescoing features: %s", rescoring_features)
+ logger.info("rescoring features: %s", rescoring_features)
@property
def psms(self) -> pd.DataFrame:
diff --git a/pyproject.toml b/pyproject.toml
index 2faa19b..234f742 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -34,13 +34,6 @@ dependencies = [
"numba>=0.64.0",
]
-[project.optional-dependencies]
-gui = [
- "streamlit>=1.24.0",
- "plotly>=5.13.0",
- "watchdog>=3.0.0",
-]
-
[dependency-groups]
dev = [
"pytest>=8.4.0",
@@ -62,7 +55,7 @@ include = ["optimhc*"]
optimhc = ["PWMs*"]
[tool.ruff]
-exclude = ["docs", "examples", "optimhc/gui/"]
+exclude = ["docs", "examples"]
line-length = 99
target-version = "py311"
diff --git a/tests/feature_generator/__init__.py b/tests/feature/__init__.py
similarity index 100%
rename from tests/feature_generator/__init__.py
rename to tests/feature/__init__.py
diff --git a/tests/feature_generator/test_spectral_similarity.py b/tests/feature/test_spectral_similarity.py
similarity index 96%
rename from tests/feature_generator/test_spectral_similarity.py
rename to tests/feature/test_spectral_similarity.py
index 60fe8b1..b9829a3 100644
--- a/tests/feature_generator/test_spectral_similarity.py
+++ b/tests/feature/test_spectral_similarity.py
@@ -2,7 +2,7 @@
import numpy as np
-from optimhc.feature_generator.spectral_similarity import SpectralSimilarityFeatureGenerator
+from optimhc.feature.spectral_similarity import SpectralSimilarityFeatureGenerator
def _make_generator(tolerance_ppm=20.0, top_n=36):
diff --git a/uv.lock b/uv.lock
index 11824bf..e7479df 100644
--- a/uv.lock
+++ b/uv.lock
@@ -1,5 +1,5 @@
version = 1
-revision = 3
+revision = 2
requires-python = ">=3.10, <3.13"
resolution-markers = [
"python_full_version >= '3.12'",
@@ -17,22 +17,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/18/a6/907a406bb7d359e6a63f99c313846d9eec4f7e6f7437809e03aa00fa3074/absl_py-2.4.0-py3-none-any.whl", hash = "sha256:88476fd881ca8aab94ffa78b7b6c632a782ab3ba1cd19c9bd423abc4fb4cd28d", size = 135750, upload-time = "2026-01-28T10:17:04.19Z" },
]
-[[package]]
-name = "altair"
-version = "6.0.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
- { name = "jinja2" },
- { name = "jsonschema" },
- { name = "narwhals" },
- { name = "packaging" },
- { name = "typing-extensions" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/f7/c0/184a89bd5feba14ff3c41cfaf1dd8a82c05f5ceedbc92145e17042eb08a4/altair-6.0.0.tar.gz", hash = "sha256:614bf5ecbe2337347b590afb111929aa9c16c9527c4887d96c9bc7f6640756b4", size = 763834, upload-time = "2025-11-12T08:59:11.519Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/db/33/ef2f2409450ef6daa61459d5de5c08128e7d3edb773fefd0a324d1310238/altair-6.0.0-py3-none-any.whl", hash = "sha256:09ae95b53d5fe5b16987dccc785a7af8588f2dca50de1e7a156efa8a461515f8", size = 795410, upload-time = "2025-11-12T08:59:09.804Z" },
-]
-
[[package]]
name = "annotated-types"
version = "0.7.0"
@@ -78,15 +62,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/2b/03/13dde6512ad7b4557eb792fbcf0c653af6076b81e5941d36ec61f7ce6028/astunparse-1.6.3-py2.py3-none-any.whl", hash = "sha256:c2652417f2c8b5bb325c885ae329bdf3f86424075c4fd1a128674bc6fba4b8e8", size = 12732, upload-time = "2019-12-22T18:12:11.297Z" },
]
-[[package]]
-name = "attrs"
-version = "25.4.0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/6b/5c/685e6633917e101e5dcb62b9dd76946cbb57c26e133bae9e0cd36033c0a9/attrs-25.4.0.tar.gz", hash = "sha256:16d5969b87f0859ef33a48b35d55ac1be6e42ae49d5e853b597db70c35c57e11", size = 934251, upload-time = "2025-10-06T13:54:44.725Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/3a/2a/7cc015f5b9f5db42b7d48157e23356022889fc354a2813c15934b7cb5c0e/attrs-25.4.0-py3-none-any.whl", hash = "sha256:adcf7e2a1fb3b36ac48d97835bb6d8ade15b8dcce26aba8bf1d14847b57a3373", size = 67615, upload-time = "2025-10-06T13:54:43.17Z" },
-]
-
[[package]]
name = "biopython"
version = "1.86"
@@ -123,24 +98,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/a9/13/00db03b01e54070d5b0ec9c71eef86e61afa733d9af76e5b9b09f5dc9165/biopython-1.86-cp312-cp312-win_amd64.whl", hash = "sha256:35a6b9c5dcdfb5c2631a313a007f3f41a7d72573ba2b68c962e10ea92096ff3b", size = 2733610, upload-time = "2025-10-28T21:32:34.99Z" },
]
-[[package]]
-name = "blinker"
-version = "1.9.0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/21/28/9b3f50ce0e048515135495f198351908d99540d69bfdc8c1d15b73dc55ce/blinker-1.9.0.tar.gz", hash = "sha256:b4ce2265a7abece45e7cc896e98dbebe6cead56bcf805a3d23136d145f5445bf", size = 22460, upload-time = "2024-11-08T17:25:47.436Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/10/cb/f2ad4230dc2eb1a74edf38f1a38b9b52277f75bef262d8908e60d957e13c/blinker-1.9.0-py3-none-any.whl", hash = "sha256:ba0efaa9080b619ff2f3459d1d500c57bddea4a6b424b60a91141db6fd2f08bc", size = 8458, upload-time = "2024-11-08T17:25:46.184Z" },
-]
-
-[[package]]
-name = "cachetools"
-version = "6.2.6"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/39/91/d9ae9a66b01102a18cd16db0cf4cd54187ffe10f0865cc80071a4104fbb3/cachetools-6.2.6.tar.gz", hash = "sha256:16c33e1f276b9a9c0b49ab5782d901e3ad3de0dd6da9bf9bcd29ac5672f2f9e6", size = 32363, upload-time = "2026-01-27T20:32:59.956Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/90/45/f458fa2c388e79dd9d8b9b0c99f1d31b568f27388f2fdba7bb66bbc0c6ed/cachetools-6.2.6-py3-none-any.whl", hash = "sha256:8c9717235b3c651603fff0076db52d6acbfd1b338b8ed50256092f7ce9c85bda", size = 11668, upload-time = "2026-01-27T20:32:58.527Z" },
-]
-
[[package]]
name = "certifi"
version = "2026.2.25"
@@ -480,30 +437,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/1d/33/f1c6a276de27b7d7339a34749cc33fa87f077f921969c47185d34a887ae2/gast-0.7.0-py3-none-any.whl", hash = "sha256:99cbf1365633a74099f69c59bd650476b96baa5ef196fec88032b00b31ba36f7", size = 22966, upload-time = "2025-11-29T15:30:03.983Z" },
]
-[[package]]
-name = "gitdb"
-version = "4.0.12"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
- { name = "smmap" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/72/94/63b0fc47eb32792c7ba1fe1b694daec9a63620db1e313033d18140c2320a/gitdb-4.0.12.tar.gz", hash = "sha256:5ef71f855d191a3326fcfbc0d5da835f26b13fbcba60c32c21091c349ffdb571", size = 394684, upload-time = "2025-01-02T07:20:46.413Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/a0/61/5c78b91c3143ed5c14207f463aecfc8f9dbb5092fb2869baf37c273b2705/gitdb-4.0.12-py3-none-any.whl", hash = "sha256:67073e15955400952c6565cc3e707c554a4eea2e428946f7a4c162fab9bd9bcf", size = 62794, upload-time = "2025-01-02T07:20:43.624Z" },
-]
-
-[[package]]
-name = "gitpython"
-version = "3.1.46"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
- { name = "gitdb" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/df/b5/59d16470a1f0dfe8c793f9ef56fd3826093fc52b3bd96d6b9d6c26c7e27b/gitpython-3.1.46.tar.gz", hash = "sha256:400124c7d0ef4ea03f7310ac2fbf7151e09ff97f2a3288d64a440c584a29c37f", size = 215371, upload-time = "2026-01-01T15:37:32.073Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/6a/09/e21df6aef1e1ffc0c816f0522ddc3f6dcded766c3261813131c78a704470/gitpython-3.1.46-py3-none-any.whl", hash = "sha256:79812ed143d9d25b6d176a10bb511de0f9c67b1fa641d82097b0ab90398a2058", size = 208620, upload-time = "2026-01-01T15:37:30.574Z" },
-]
-
[[package]]
name = "google-pasta"
version = "0.2.0"
@@ -693,18 +626,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/d1/b3/8def84f539e7d2289a02f0524b944b15d7c75dab7628bedf1c4f0992029c/isort-5.13.2-py3-none-any.whl", hash = "sha256:8ca5e72a8d85860d5a3fa69b8745237f2939afe12dbf656afbcb47fe72d947a6", size = 92310, upload-time = "2023-12-13T20:37:23.244Z" },
]
-[[package]]
-name = "jinja2"
-version = "3.1.6"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
- { name = "markupsafe" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/df/bf/f7da0350254c0ed7c72f3e33cef02e048281fec7ecec5f032d4aac52226b/jinja2-3.1.6.tar.gz", hash = "sha256:0137fb05990d35f1275a587e9aee6d56da821fc83491a0fb838183be43f66d6d", size = 245115, upload-time = "2025-03-05T20:05:02.478Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/62/a1/3d680cbfd5f4b8f15abc1d571870c5fc3e594bb582bc3b64ea099db13e56/jinja2-3.1.6-py3-none-any.whl", hash = "sha256:85ece4451f492d0c13c5dd7c13a64681a86afae63a5f347908daf103ce6d2f67", size = 134899, upload-time = "2025-03-05T20:05:00.369Z" },
-]
-
[[package]]
name = "job-pool"
version = "0.2.6"
@@ -726,33 +647,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/7b/91/984aca2ec129e2757d1e4e3c81c3fcda9d0f85b74670a094cc443d9ee949/joblib-1.5.3-py3-none-any.whl", hash = "sha256:5fc3c5039fc5ca8c0276333a188bbd59d6b7ab37fe6632daa76bc7f9ec18e713", size = 309071, upload-time = "2025-12-15T08:41:44.973Z" },
]
-[[package]]
-name = "jsonschema"
-version = "4.26.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
- { name = "attrs" },
- { name = "jsonschema-specifications" },
- { name = "referencing" },
- { name = "rpds-py" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/b3/fc/e067678238fa451312d4c62bf6e6cf5ec56375422aee02f9cb5f909b3047/jsonschema-4.26.0.tar.gz", hash = "sha256:0c26707e2efad8aa1bfc5b7ce170f3fccc2e4918ff85989ba9ffa9facb2be326", size = 366583, upload-time = "2026-01-07T13:41:07.246Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/69/90/f63fb5873511e014207a475e2bb4e8b2e570d655b00ac19a9a0ca0a385ee/jsonschema-4.26.0-py3-none-any.whl", hash = "sha256:d489f15263b8d200f8387e64b4c3a75f06629559fb73deb8fdfb525f2dab50ce", size = 90630, upload-time = "2026-01-07T13:41:05.306Z" },
-]
-
-[[package]]
-name = "jsonschema-specifications"
-version = "2025.9.1"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
- { name = "referencing" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/19/74/a633ee74eb36c44aa6d1095e7cc5569bebf04342ee146178e2d36600708b/jsonschema_specifications-2025.9.1.tar.gz", hash = "sha256:b540987f239e745613c7a9176f3edb72b832a4ac465cf02712288397832b5e8d", size = 32855, upload-time = "2025-09-08T01:34:59.186Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/41/45/1a4ed80516f02155c51f51e8cedb3c1902296743db0bbc66608a0db2814f/jsonschema_specifications-2025.9.1-py3-none-any.whl", hash = "sha256:98802fee3a11ee76ecaca44429fda8a41bff98b00a0f2838151b113f210cc6fe", size = 18437, upload-time = "2025-09-08T01:34:57.871Z" },
-]
-
[[package]]
name = "keras"
version = "3.12.1"
@@ -1244,15 +1138,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/b2/bc/465daf1de06409cdd4532082806770ee0d8d7df434da79c76564d0f69741/namex-0.1.0-py3-none-any.whl", hash = "sha256:e2012a474502f1e2251267062aae3114611f07df4224b6e06334c57b0f2ce87c", size = 5905, upload-time = "2025-05-26T23:17:37.695Z" },
]
-[[package]]
-name = "narwhals"
-version = "2.17.0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/75/59/81d0f4cad21484083466f278e6b392addd9f4205b48d45b5c8771670ebf8/narwhals-2.17.0.tar.gz", hash = "sha256:ebd5bc95bcfa2f8e89a8ac09e2765a63055162837208e67b42d6eeb6651d5e67", size = 620306, upload-time = "2026-02-23T09:44:34.142Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/4b/27/20770bd6bf8fbe1e16f848ba21da9df061f38d2e6483952c29d2bb5d1d8b/narwhals-2.17.0-py3-none-any.whl", hash = "sha256:2ac5307b7c2b275a7d66eeda906b8605e3d7a760951e188dcfff86e8ebe083dd", size = 444897, upload-time = "2026-02-23T09:44:32.006Z" },
-]
-
[[package]]
name = "networkx"
version = "3.2.1"
@@ -1362,13 +1247,6 @@ dependencies = [
{ name = "xgboost" },
]
-[package.optional-dependencies]
-gui = [
- { name = "plotly" },
- { name = "streamlit" },
- { name = "watchdog" },
-]
-
[package.dev-dependencies]
dev = [
{ name = "pre-commit" },
@@ -1389,19 +1267,15 @@ requires-dist = [
{ name = "numba", specifier = ">=0.64.0" },
{ name = "numpy", specifier = "==1.26.4" },
{ name = "pandas", specifier = "==2.2.3" },
- { name = "plotly", marker = "extra == 'gui'", specifier = ">=5.13.0" },
{ name = "pyteomics", specifier = "==4.7.5" },
{ name = "pyyaml", specifier = "==6.0.2" },
{ name = "scikit-learn", specifier = "==1.5.2" },
{ name = "scipy", specifier = "==1.13.1" },
{ name = "seaborn", specifier = "==0.13.2" },
{ name = "setuptools", specifier = ">=61,<82" },
- { name = "streamlit", marker = "extra == 'gui'", specifier = ">=1.24.0" },
{ name = "tqdm", specifier = "==4.67.0" },
- { name = "watchdog", marker = "extra == 'gui'", specifier = ">=3.0.0" },
{ name = "xgboost", specifier = "==1.7.6" },
]
-provides-extras = ["gui"]
[package.metadata.requires-dev]
dev = [
@@ -1559,19 +1433,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/48/31/05e764397056194206169869b50cf2fee4dbbbc71b344705b9c0d878d4d8/platformdirs-4.9.2-py3-none-any.whl", hash = "sha256:9170634f126f8efdae22fb58ae8a0eaa86f38365bc57897a6c4f781d1f5875bd", size = 21168, upload-time = "2026-02-16T03:56:08.891Z" },
]
-[[package]]
-name = "plotly"
-version = "6.5.2"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
- { name = "narwhals" },
- { name = "packaging" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/e3/4f/8a10a9b9f5192cb6fdef62f1d77fa7d834190b2c50c0cd256bd62879212b/plotly-6.5.2.tar.gz", hash = "sha256:7478555be0198562d1435dee4c308268187553cc15516a2f4dd034453699e393", size = 7015695, upload-time = "2026-01-14T21:26:51.222Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/8a/67/f95b5460f127840310d2187f916cf0023b5875c0717fdf893f71e1325e87/plotly-6.5.2-py3-none-any.whl", hash = "sha256:91757653bd9c550eeea2fa2404dba6b85d1e366d54804c340b2c874e5a7eb4a4", size = 9895973, upload-time = "2026-01-14T21:26:47.135Z" },
-]
-
[[package]]
name = "pluggy"
version = "1.6.0"
@@ -1789,19 +1650,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/36/c7/cfc8e811f061c841d7990b0201912c3556bfeb99cdcb7ed24adc8d6f8704/pydantic_core-2.41.5-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:56121965f7a4dc965bff783d70b907ddf3d57f6eba29b6d2e5dabfaf07799c51", size = 2145302, upload-time = "2025-11-04T13:43:46.64Z" },
]
-[[package]]
-name = "pydeck"
-version = "0.9.1"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
- { name = "jinja2" },
- { name = "numpy" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/a1/ca/40e14e196864a0f61a92abb14d09b3d3da98f94ccb03b49cf51688140dab/pydeck-0.9.1.tar.gz", hash = "sha256:f74475ae637951d63f2ee58326757f8d4f9cd9f2a457cf42950715003e2cb605", size = 3832240, upload-time = "2024-05-10T15:36:21.153Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/ab/4c/b888e6cf58bd9db9c93f40d1c6be8283ff49d88919231afe93a6bcf61626/pydeck-0.9.1-py2.py3-none-any.whl", hash = "sha256:b3f75ba0d273fc917094fa61224f3f6076ca8752b93d46faf3bcfd9f9d59b038", size = 6900403, upload-time = "2024-05-10T15:36:17.36Z" },
-]
-
[[package]]
name = "pyensembl"
version = "2.3.13"
@@ -2004,20 +1852,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/0c/e8/4f648c598b17c3d06e8753d7d13d57542b30d56e6c2dedf9c331ae56312e/PyYAML-6.0.2-cp312-cp312-win_amd64.whl", hash = "sha256:7e7401d0de89a9a855c839bc697c079a4af81cf878373abd7dc625847d25cbd8", size = 156338, upload-time = "2024-08-06T20:32:41.93Z" },
]
-[[package]]
-name = "referencing"
-version = "0.37.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
- { name = "attrs" },
- { name = "rpds-py" },
- { name = "typing-extensions" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/22/f5/df4e9027acead3ecc63e50fe1e36aca1523e1719559c499951bb4b53188f/referencing-0.37.0.tar.gz", hash = "sha256:44aefc3142c5b842538163acb373e24cce6632bd54bdb01b21ad5863489f50d8", size = 78036, upload-time = "2025-10-13T15:30:48.871Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/2c/58/ca301544e1fa93ed4f80d724bf5b194f6e4b945841c5bfd555878eea9fcb/referencing-0.37.0-py3-none-any.whl", hash = "sha256:381329a9f99628c9069361716891d34ad94af76e461dcb0335825aecc7692231", size = 26766, upload-time = "2025-10-13T15:30:47.625Z" },
-]
-
[[package]]
name = "requests"
version = "2.32.5"
@@ -2046,70 +1880,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/14/25/b208c5683343959b670dc001595f2f3737e051da617f66c31f7c4fa93abc/rich-14.3.3-py3-none-any.whl", hash = "sha256:793431c1f8619afa7d3b52b2cdec859562b950ea0d4b6b505397612db8d5362d", size = 310458, upload-time = "2026-02-19T17:23:13.732Z" },
]
-[[package]]
-name = "rpds-py"
-version = "0.30.0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/20/af/3f2f423103f1113b36230496629986e0ef7e199d2aa8392452b484b38ced/rpds_py-0.30.0.tar.gz", hash = "sha256:dd8ff7cf90014af0c0f787eea34794ebf6415242ee1d6fa91eaba725cc441e84", size = 69469, upload-time = "2025-11-30T20:24:38.837Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/06/0c/0c411a0ec64ccb6d104dcabe0e713e05e153a9a2c3c2bd2b32ce412166fe/rpds_py-0.30.0-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:679ae98e00c0e8d68a7fda324e16b90fd5260945b45d3b824c892cec9eea3288", size = 370490, upload-time = "2025-11-30T20:21:33.256Z" },
- { url = "https://files.pythonhosted.org/packages/19/6a/4ba3d0fb7297ebae71171822554abe48d7cab29c28b8f9f2c04b79988c05/rpds_py-0.30.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:4cc2206b76b4f576934f0ed374b10d7ca5f457858b157ca52064bdfc26b9fc00", size = 359751, upload-time = "2025-11-30T20:21:34.591Z" },
- { url = "https://files.pythonhosted.org/packages/cd/7c/e4933565ef7f7a0818985d87c15d9d273f1a649afa6a52ea35ad011195ea/rpds_py-0.30.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:389a2d49eded1896c3d48b0136ead37c48e221b391c052fba3f4055c367f60a6", size = 389696, upload-time = "2025-11-30T20:21:36.122Z" },
- { url = "https://files.pythonhosted.org/packages/5e/01/6271a2511ad0815f00f7ed4390cf2567bec1d4b1da39e2c27a41e6e3b4de/rpds_py-0.30.0-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:32c8528634e1bf7121f3de08fa85b138f4e0dc47657866630611b03967f041d7", size = 403136, upload-time = "2025-11-30T20:21:37.728Z" },
- { url = "https://files.pythonhosted.org/packages/55/64/c857eb7cd7541e9b4eee9d49c196e833128a55b89a9850a9c9ac33ccf897/rpds_py-0.30.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f207f69853edd6f6700b86efb84999651baf3789e78a466431df1331608e5324", size = 524699, upload-time = "2025-11-30T20:21:38.92Z" },
- { url = "https://files.pythonhosted.org/packages/9c/ed/94816543404078af9ab26159c44f9e98e20fe47e2126d5d32c9d9948d10a/rpds_py-0.30.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:67b02ec25ba7a9e8fa74c63b6ca44cf5707f2fbfadae3ee8e7494297d56aa9df", size = 412022, upload-time = "2025-11-30T20:21:40.407Z" },
- { url = "https://files.pythonhosted.org/packages/61/b5/707f6cf0066a6412aacc11d17920ea2e19e5b2f04081c64526eb35b5c6e7/rpds_py-0.30.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0c0e95f6819a19965ff420f65578bacb0b00f251fefe2c8b23347c37174271f3", size = 390522, upload-time = "2025-11-30T20:21:42.17Z" },
- { url = "https://files.pythonhosted.org/packages/13/4e/57a85fda37a229ff4226f8cbcf09f2a455d1ed20e802ce5b2b4a7f5ed053/rpds_py-0.30.0-cp310-cp310-manylinux_2_31_riscv64.whl", hash = "sha256:a452763cc5198f2f98898eb98f7569649fe5da666c2dc6b5ddb10fde5a574221", size = 404579, upload-time = "2025-11-30T20:21:43.769Z" },
- { url = "https://files.pythonhosted.org/packages/f9/da/c9339293513ec680a721e0e16bf2bac3db6e5d7e922488de471308349bba/rpds_py-0.30.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:e0b65193a413ccc930671c55153a03ee57cecb49e6227204b04fae512eb657a7", size = 421305, upload-time = "2025-11-30T20:21:44.994Z" },
- { url = "https://files.pythonhosted.org/packages/f9/be/522cb84751114f4ad9d822ff5a1aa3c98006341895d5f084779b99596e5c/rpds_py-0.30.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:858738e9c32147f78b3ac24dc0edb6610000e56dc0f700fd5f651d0a0f0eb9ff", size = 572503, upload-time = "2025-11-30T20:21:46.91Z" },
- { url = "https://files.pythonhosted.org/packages/a2/9b/de879f7e7ceddc973ea6e4629e9b380213a6938a249e94b0cdbcc325bb66/rpds_py-0.30.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:da279aa314f00acbb803da1e76fa18666778e8a8f83484fba94526da5de2cba7", size = 598322, upload-time = "2025-11-30T20:21:48.709Z" },
- { url = "https://files.pythonhosted.org/packages/48/ac/f01fc22efec3f37d8a914fc1b2fb9bcafd56a299edbe96406f3053edea5a/rpds_py-0.30.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:7c64d38fb49b6cdeda16ab49e35fe0da2e1e9b34bc38bd78386530f218b37139", size = 560792, upload-time = "2025-11-30T20:21:50.024Z" },
- { url = "https://files.pythonhosted.org/packages/e2/da/4e2b19d0f131f35b6146425f846563d0ce036763e38913d917187307a671/rpds_py-0.30.0-cp310-cp310-win32.whl", hash = "sha256:6de2a32a1665b93233cde140ff8b3467bdb9e2af2b91079f0333a0974d12d464", size = 221901, upload-time = "2025-11-30T20:21:51.32Z" },
- { url = "https://files.pythonhosted.org/packages/96/cb/156d7a5cf4f78a7cc571465d8aec7a3c447c94f6749c5123f08438bcf7bc/rpds_py-0.30.0-cp310-cp310-win_amd64.whl", hash = "sha256:1726859cd0de969f88dc8673bdd954185b9104e05806be64bcd87badbe313169", size = 235823, upload-time = "2025-11-30T20:21:52.505Z" },
- { url = "https://files.pythonhosted.org/packages/4d/6e/f964e88b3d2abee2a82c1ac8366da848fce1c6d834dc2132c3fda3970290/rpds_py-0.30.0-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:a2bffea6a4ca9f01b3f8e548302470306689684e61602aa3d141e34da06cf425", size = 370157, upload-time = "2025-11-30T20:21:53.789Z" },
- { url = "https://files.pythonhosted.org/packages/94/ba/24e5ebb7c1c82e74c4e4f33b2112a5573ddc703915b13a073737b59b86e0/rpds_py-0.30.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:dc4f992dfe1e2bc3ebc7444f6c7051b4bc13cd8e33e43511e8ffd13bf407010d", size = 359676, upload-time = "2025-11-30T20:21:55.475Z" },
- { url = "https://files.pythonhosted.org/packages/84/86/04dbba1b087227747d64d80c3b74df946b986c57af0a9f0c98726d4d7a3b/rpds_py-0.30.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:422c3cb9856d80b09d30d2eb255d0754b23e090034e1deb4083f8004bd0761e4", size = 389938, upload-time = "2025-11-30T20:21:57.079Z" },
- { url = "https://files.pythonhosted.org/packages/42/bb/1463f0b1722b7f45431bdd468301991d1328b16cffe0b1c2918eba2c4eee/rpds_py-0.30.0-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:07ae8a593e1c3c6b82ca3292efbe73c30b61332fd612e05abee07c79359f292f", size = 402932, upload-time = "2025-11-30T20:21:58.47Z" },
- { url = "https://files.pythonhosted.org/packages/99/ee/2520700a5c1f2d76631f948b0736cdf9b0acb25abd0ca8e889b5c62ac2e3/rpds_py-0.30.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:12f90dd7557b6bd57f40abe7747e81e0c0b119bef015ea7726e69fe550e394a4", size = 525830, upload-time = "2025-11-30T20:21:59.699Z" },
- { url = "https://files.pythonhosted.org/packages/e0/ad/bd0331f740f5705cc555a5e17fdf334671262160270962e69a2bdef3bf76/rpds_py-0.30.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:99b47d6ad9a6da00bec6aabe5a6279ecd3c06a329d4aa4771034a21e335c3a97", size = 412033, upload-time = "2025-11-30T20:22:00.991Z" },
- { url = "https://files.pythonhosted.org/packages/f8/1e/372195d326549bb51f0ba0f2ecb9874579906b97e08880e7a65c3bef1a99/rpds_py-0.30.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:33f559f3104504506a44bb666b93a33f5d33133765b0c216a5bf2f1e1503af89", size = 390828, upload-time = "2025-11-30T20:22:02.723Z" },
- { url = "https://files.pythonhosted.org/packages/ab/2b/d88bb33294e3e0c76bc8f351a3721212713629ffca1700fa94979cb3eae8/rpds_py-0.30.0-cp311-cp311-manylinux_2_31_riscv64.whl", hash = "sha256:946fe926af6e44f3697abbc305ea168c2c31d3e3ef1058cf68f379bf0335a78d", size = 404683, upload-time = "2025-11-30T20:22:04.367Z" },
- { url = "https://files.pythonhosted.org/packages/50/32/c759a8d42bcb5289c1fac697cd92f6fe01a018dd937e62ae77e0e7f15702/rpds_py-0.30.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:495aeca4b93d465efde585977365187149e75383ad2684f81519f504f5c13038", size = 421583, upload-time = "2025-11-30T20:22:05.814Z" },
- { url = "https://files.pythonhosted.org/packages/2b/81/e729761dbd55ddf5d84ec4ff1f47857f4374b0f19bdabfcf929164da3e24/rpds_py-0.30.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:d9a0ca5da0386dee0655b4ccdf46119df60e0f10da268d04fe7cc87886872ba7", size = 572496, upload-time = "2025-11-30T20:22:07.713Z" },
- { url = "https://files.pythonhosted.org/packages/14/f6/69066a924c3557c9c30baa6ec3a0aa07526305684c6f86c696b08860726c/rpds_py-0.30.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:8d6d1cc13664ec13c1b84241204ff3b12f9bb82464b8ad6e7a5d3486975c2eed", size = 598669, upload-time = "2025-11-30T20:22:09.312Z" },
- { url = "https://files.pythonhosted.org/packages/5f/48/905896b1eb8a05630d20333d1d8ffd162394127b74ce0b0784ae04498d32/rpds_py-0.30.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:3896fa1be39912cf0757753826bc8bdc8ca331a28a7c4ae46b7a21280b06bb85", size = 561011, upload-time = "2025-11-30T20:22:11.309Z" },
- { url = "https://files.pythonhosted.org/packages/22/16/cd3027c7e279d22e5eb431dd3c0fbc677bed58797fe7581e148f3f68818b/rpds_py-0.30.0-cp311-cp311-win32.whl", hash = "sha256:55f66022632205940f1827effeff17c4fa7ae1953d2b74a8581baaefb7d16f8c", size = 221406, upload-time = "2025-11-30T20:22:13.101Z" },
- { url = "https://files.pythonhosted.org/packages/fa/5b/e7b7aa136f28462b344e652ee010d4de26ee9fd16f1bfd5811f5153ccf89/rpds_py-0.30.0-cp311-cp311-win_amd64.whl", hash = "sha256:a51033ff701fca756439d641c0ad09a41d9242fa69121c7d8769604a0a629825", size = 236024, upload-time = "2025-11-30T20:22:14.853Z" },
- { url = "https://files.pythonhosted.org/packages/14/a6/364bba985e4c13658edb156640608f2c9e1d3ea3c81b27aa9d889fff0e31/rpds_py-0.30.0-cp311-cp311-win_arm64.whl", hash = "sha256:47b0ef6231c58f506ef0b74d44e330405caa8428e770fec25329ed2cb971a229", size = 229069, upload-time = "2025-11-30T20:22:16.577Z" },
- { url = "https://files.pythonhosted.org/packages/03/e7/98a2f4ac921d82f33e03f3835f5bf3a4a40aa1bfdc57975e74a97b2b4bdd/rpds_py-0.30.0-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:a161f20d9a43006833cd7068375a94d035714d73a172b681d8881820600abfad", size = 375086, upload-time = "2025-11-30T20:22:17.93Z" },
- { url = "https://files.pythonhosted.org/packages/4d/a1/bca7fd3d452b272e13335db8d6b0b3ecde0f90ad6f16f3328c6fb150c889/rpds_py-0.30.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:6abc8880d9d036ecaafe709079969f56e876fcf107f7a8e9920ba6d5a3878d05", size = 359053, upload-time = "2025-11-30T20:22:19.297Z" },
- { url = "https://files.pythonhosted.org/packages/65/1c/ae157e83a6357eceff62ba7e52113e3ec4834a84cfe07fa4b0757a7d105f/rpds_py-0.30.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ca28829ae5f5d569bb62a79512c842a03a12576375d5ece7d2cadf8abe96ec28", size = 390763, upload-time = "2025-11-30T20:22:21.661Z" },
- { url = "https://files.pythonhosted.org/packages/d4/36/eb2eb8515e2ad24c0bd43c3ee9cd74c33f7ca6430755ccdb240fd3144c44/rpds_py-0.30.0-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:a1010ed9524c73b94d15919ca4d41d8780980e1765babf85f9a2f90d247153dd", size = 408951, upload-time = "2025-11-30T20:22:23.408Z" },
- { url = "https://files.pythonhosted.org/packages/d6/65/ad8dc1784a331fabbd740ef6f71ce2198c7ed0890dab595adb9ea2d775a1/rpds_py-0.30.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f8d1736cfb49381ba528cd5baa46f82fdc65c06e843dab24dd70b63d09121b3f", size = 514622, upload-time = "2025-11-30T20:22:25.16Z" },
- { url = "https://files.pythonhosted.org/packages/63/8e/0cfa7ae158e15e143fe03993b5bcd743a59f541f5952e1546b1ac1b5fd45/rpds_py-0.30.0-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d948b135c4693daff7bc2dcfc4ec57237a29bd37e60c2fabf5aff2bbacf3e2f1", size = 414492, upload-time = "2025-11-30T20:22:26.505Z" },
- { url = "https://files.pythonhosted.org/packages/60/1b/6f8f29f3f995c7ffdde46a626ddccd7c63aefc0efae881dc13b6e5d5bb16/rpds_py-0.30.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:47f236970bccb2233267d89173d3ad2703cd36a0e2a6e92d0560d333871a3d23", size = 394080, upload-time = "2025-11-30T20:22:27.934Z" },
- { url = "https://files.pythonhosted.org/packages/6d/d5/a266341051a7a3ca2f4b750a3aa4abc986378431fc2da508c5034d081b70/rpds_py-0.30.0-cp312-cp312-manylinux_2_31_riscv64.whl", hash = "sha256:2e6ecb5a5bcacf59c3f912155044479af1d0b6681280048b338b28e364aca1f6", size = 408680, upload-time = "2025-11-30T20:22:29.341Z" },
- { url = "https://files.pythonhosted.org/packages/10/3b/71b725851df9ab7a7a4e33cf36d241933da66040d195a84781f49c50490c/rpds_py-0.30.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:a8fa71a2e078c527c3e9dc9fc5a98c9db40bcc8a92b4e8858e36d329f8684b51", size = 423589, upload-time = "2025-11-30T20:22:31.469Z" },
- { url = "https://files.pythonhosted.org/packages/00/2b/e59e58c544dc9bd8bd8384ecdb8ea91f6727f0e37a7131baeff8d6f51661/rpds_py-0.30.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:73c67f2db7bc334e518d097c6d1e6fed021bbc9b7d678d6cc433478365d1d5f5", size = 573289, upload-time = "2025-11-30T20:22:32.997Z" },
- { url = "https://files.pythonhosted.org/packages/da/3e/a18e6f5b460893172a7d6a680e86d3b6bc87a54c1f0b03446a3c8c7b588f/rpds_py-0.30.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:5ba103fb455be00f3b1c2076c9d4264bfcb037c976167a6047ed82f23153f02e", size = 599737, upload-time = "2025-11-30T20:22:34.419Z" },
- { url = "https://files.pythonhosted.org/packages/5c/e2/714694e4b87b85a18e2c243614974413c60aa107fd815b8cbc42b873d1d7/rpds_py-0.30.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:7cee9c752c0364588353e627da8a7e808a66873672bcb5f52890c33fd965b394", size = 563120, upload-time = "2025-11-30T20:22:35.903Z" },
- { url = "https://files.pythonhosted.org/packages/6f/ab/d5d5e3bcedb0a77f4f613706b750e50a5a3ba1c15ccd3665ecc636c968fd/rpds_py-0.30.0-cp312-cp312-win32.whl", hash = "sha256:1ab5b83dbcf55acc8b08fc62b796ef672c457b17dbd7820a11d6c52c06839bdf", size = 223782, upload-time = "2025-11-30T20:22:37.271Z" },
- { url = "https://files.pythonhosted.org/packages/39/3b/f786af9957306fdc38a74cef405b7b93180f481fb48453a114bb6465744a/rpds_py-0.30.0-cp312-cp312-win_amd64.whl", hash = "sha256:a090322ca841abd453d43456ac34db46e8b05fd9b3b4ac0c78bcde8b089f959b", size = 240463, upload-time = "2025-11-30T20:22:39.021Z" },
- { url = "https://files.pythonhosted.org/packages/f3/d2/b91dc748126c1559042cfe41990deb92c4ee3e2b415f6b5234969ffaf0cc/rpds_py-0.30.0-cp312-cp312-win_arm64.whl", hash = "sha256:669b1805bd639dd2989b281be2cfd951c6121b65e729d9b843e9639ef1fd555e", size = 230868, upload-time = "2025-11-30T20:22:40.493Z" },
- { url = "https://files.pythonhosted.org/packages/69/71/3f34339ee70521864411f8b6992e7ab13ac30d8e4e3309e07c7361767d91/rpds_py-0.30.0-pp311-pypy311_pp73-macosx_10_12_x86_64.whl", hash = "sha256:c2262bdba0ad4fc6fb5545660673925c2d2a5d9e2e0fb603aad545427be0fc58", size = 372292, upload-time = "2025-11-30T20:24:16.537Z" },
- { url = "https://files.pythonhosted.org/packages/57/09/f183df9b8f2d66720d2ef71075c59f7e1b336bec7ee4c48f0a2b06857653/rpds_py-0.30.0-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:ee6af14263f25eedc3bb918a3c04245106a42dfd4f5c2285ea6f997b1fc3f89a", size = 362128, upload-time = "2025-11-30T20:24:18.086Z" },
- { url = "https://files.pythonhosted.org/packages/7a/68/5c2594e937253457342e078f0cc1ded3dd7b2ad59afdbf2d354869110a02/rpds_py-0.30.0-pp311-pypy311_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3adbb8179ce342d235c31ab8ec511e66c73faa27a47e076ccc92421add53e2bb", size = 391542, upload-time = "2025-11-30T20:24:20.092Z" },
- { url = "https://files.pythonhosted.org/packages/49/5c/31ef1afd70b4b4fbdb2800249f34c57c64beb687495b10aec0365f53dfc4/rpds_py-0.30.0-pp311-pypy311_pp73-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:250fa00e9543ac9b97ac258bd37367ff5256666122c2d0f2bc97577c60a1818c", size = 404004, upload-time = "2025-11-30T20:24:22.231Z" },
- { url = "https://files.pythonhosted.org/packages/e3/63/0cfbea38d05756f3440ce6534d51a491d26176ac045e2707adc99bb6e60a/rpds_py-0.30.0-pp311-pypy311_pp73-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9854cf4f488b3d57b9aaeb105f06d78e5529d3145b1e4a41750167e8c213c6d3", size = 527063, upload-time = "2025-11-30T20:24:24.302Z" },
- { url = "https://files.pythonhosted.org/packages/42/e6/01e1f72a2456678b0f618fc9a1a13f882061690893c192fcad9f2926553a/rpds_py-0.30.0-pp311-pypy311_pp73-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:993914b8e560023bc0a8bf742c5f303551992dcb85e247b1e5c7f4a7d145bda5", size = 413099, upload-time = "2025-11-30T20:24:25.916Z" },
- { url = "https://files.pythonhosted.org/packages/b8/25/8df56677f209003dcbb180765520c544525e3ef21ea72279c98b9aa7c7fb/rpds_py-0.30.0-pp311-pypy311_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:58edca431fb9b29950807e301826586e5bbf24163677732429770a697ffe6738", size = 392177, upload-time = "2025-11-30T20:24:27.834Z" },
- { url = "https://files.pythonhosted.org/packages/4a/b4/0a771378c5f16f8115f796d1f437950158679bcd2a7c68cf251cfb00ed5b/rpds_py-0.30.0-pp311-pypy311_pp73-manylinux_2_31_riscv64.whl", hash = "sha256:dea5b552272a944763b34394d04577cf0f9bd013207bc32323b5a89a53cf9c2f", size = 406015, upload-time = "2025-11-30T20:24:29.457Z" },
- { url = "https://files.pythonhosted.org/packages/36/d8/456dbba0af75049dc6f63ff295a2f92766b9d521fa00de67a2bd6427d57a/rpds_py-0.30.0-pp311-pypy311_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:ba3af48635eb83d03f6c9735dfb21785303e73d22ad03d489e88adae6eab8877", size = 423736, upload-time = "2025-11-30T20:24:31.22Z" },
- { url = "https://files.pythonhosted.org/packages/13/64/b4d76f227d5c45a7e0b796c674fd81b0a6c4fbd48dc29271857d8219571c/rpds_py-0.30.0-pp311-pypy311_pp73-musllinux_1_2_aarch64.whl", hash = "sha256:dff13836529b921e22f15cb099751209a60009731a68519630a24d61f0b1b30a", size = 573981, upload-time = "2025-11-30T20:24:32.934Z" },
- { url = "https://files.pythonhosted.org/packages/20/91/092bacadeda3edf92bf743cc96a7be133e13a39cdbfd7b5082e7ab638406/rpds_py-0.30.0-pp311-pypy311_pp73-musllinux_1_2_i686.whl", hash = "sha256:1b151685b23929ab7beec71080a8889d4d6d9fa9a983d213f07121205d48e2c4", size = 599782, upload-time = "2025-11-30T20:24:35.169Z" },
- { url = "https://files.pythonhosted.org/packages/d1/b7/b95708304cd49b7b6f82fdd039f1748b66ec2b21d6a45180910802f1abf1/rpds_py-0.30.0-pp311-pypy311_pp73-musllinux_1_2_x86_64.whl", hash = "sha256:ac37f9f516c51e5753f27dfdef11a88330f04de2d564be3991384b2f3535d02e", size = 562191, upload-time = "2025-11-30T20:24:36.853Z" },
-]
-
[[package]]
name = "ruff"
version = "0.15.4"
@@ -2300,15 +2070,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/b7/ce/149a00dd41f10bc29e5921b496af8b574d8413afcd5e30dfa0ed46c2cc5e/six-1.17.0-py2.py3-none-any.whl", hash = "sha256:4721f391ed90541fddacab5acf947aa0d3dc7d27b2e1e8eda2be8970586c3274", size = 11050, upload-time = "2024-12-04T17:35:26.475Z" },
]
-[[package]]
-name = "smmap"
-version = "5.0.2"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/44/cd/a040c4b3119bbe532e5b0732286f805445375489fceaec1f48306068ee3b/smmap-5.0.2.tar.gz", hash = "sha256:26ea65a03958fa0c8a1c7e8c7a58fdc77221b8910f6be2131affade476898ad5", size = 22329, upload-time = "2025-01-02T07:14:40.909Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/04/be/d09147ad1ec7934636ad912901c5fd7667e1c858e19d355237db0d0cd5e4/smmap-5.0.2-py3-none-any.whl", hash = "sha256:b30115f0def7d7531d22a0fb6502488d879e75b260a9db4d0819cfb25403af5e", size = 24303, upload-time = "2025-01-02T07:14:38.724Z" },
-]
-
[[package]]
name = "sqlalchemy"
version = "2.0.47"
@@ -2343,44 +2104,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/15/9f/7c378406b592fcf1fc157248607b495a40e3202ba4a6f1372a2ba6447717/sqlalchemy-2.0.47-py3-none-any.whl", hash = "sha256:e2647043599297a1ef10e720cf310846b7f31b6c841fee093d2b09d81215eb93", size = 1940159, upload-time = "2026-02-24T17:15:07.158Z" },
]
-[[package]]
-name = "streamlit"
-version = "1.54.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
- { name = "altair" },
- { name = "blinker" },
- { name = "cachetools" },
- { name = "click" },
- { name = "gitpython" },
- { name = "numpy" },
- { name = "packaging" },
- { name = "pandas" },
- { name = "pillow" },
- { name = "protobuf" },
- { name = "pyarrow" },
- { name = "pydeck" },
- { name = "requests" },
- { name = "tenacity" },
- { name = "toml" },
- { name = "tornado" },
- { name = "typing-extensions" },
- { name = "watchdog", marker = "sys_platform != 'darwin'" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/be/66/d887ee80ea85f035baee607c60af024994e17ae9b921277fca9675e76ecf/streamlit-1.54.0.tar.gz", hash = "sha256:09965e6ae7eb0357091725de1ce2a3f7e4be155c2464c505c40a3da77ab69dd8", size = 8662292, upload-time = "2026-02-04T16:37:54.734Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/48/1d/40de1819374b4f0507411a60f4d2de0d620a9b10c817de5925799132b6c9/streamlit-1.54.0-py3-none-any.whl", hash = "sha256:a7b67d6293a9f5f6b4d4c7acdbc4980d7d9f049e78e404125022ecb1712f79fc", size = 9119730, upload-time = "2026-02-04T16:37:52.199Z" },
-]
-
-[[package]]
-name = "tenacity"
-version = "9.1.4"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/47/c6/ee486fd809e357697ee8a44d3d69222b344920433d3b6666ccd9b374630c/tenacity-9.1.4.tar.gz", hash = "sha256:adb31d4c263f2bd041081ab33b498309a57c77f9acf2db65aadf0898179cf93a", size = 49413, upload-time = "2026-02-07T10:45:33.841Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/d7/c1/eb8f9debc45d3b7918a32ab756658a0904732f75e555402972246b0b8e71/tenacity-9.1.4-py3-none-any.whl", hash = "sha256:6095a360c919085f28c6527de529e76a06ad89b23659fa881ae0649b867a9d55", size = 28926, upload-time = "2026-02-07T10:45:32.24Z" },
-]
-
[[package]]
name = "tensorboard"
version = "2.20.0"
@@ -2490,15 +2213,6 @@ version = "0.0.0"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/5c/87/75d3fbe15aabd45d9b70702241787cf1f7f30dd9fabcd9bc89d828c7661d/tinytimer-0.0.0.tar.gz", hash = "sha256:6ad13c8f01ab6094e58081a5367ffc4c5831f2d6b29034d2434d8ae106308fa5", size = 2069, upload-time = "2015-03-20T20:00:55.612Z" }
-[[package]]
-name = "toml"
-version = "0.10.2"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/be/ba/1f744cdc819428fc6b5084ec34d9b30660f6f9daaf70eead706e3203ec3c/toml-0.10.2.tar.gz", hash = "sha256:b3bda1d108d5dd99f4a20d24d9c348e91c4db7ab1b749200bded2f839ccbe68f", size = 22253, upload-time = "2020-11-01T01:40:22.204Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/44/6f/7120676b6d73228c96e17f1f794d8ab046fc910d781c8d151120c3f1569e/toml-0.10.2-py2.py3-none-any.whl", hash = "sha256:806143ae5bfb6a3c6e736a764057db0e6a0e05e338b5630894a5f779cabb4f9b", size = 16588, upload-time = "2020-11-01T01:40:20.672Z" },
-]
-
[[package]]
name = "tomli"
version = "2.4.0"
@@ -2535,23 +2249,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/b5/11/87d6d29fb5d237229d67973a6c9e06e048f01cf4994dee194ab0ea841814/tomlkit-0.14.0-py3-none-any.whl", hash = "sha256:592064ed85b40fa213469f81ac584f67a4f2992509a7c3ea2d632208623a3680", size = 39310, upload-time = "2026-01-13T01:14:51.965Z" },
]
-[[package]]
-name = "tornado"
-version = "6.5.5"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/f8/f1/3173dfa4a18db4a9b03e5d55325559dab51ee653763bb8745a75af491286/tornado-6.5.5.tar.gz", hash = "sha256:192b8f3ea91bd7f1f50c06955416ed76c6b72f96779b962f07f911b91e8d30e9", size = 516006, upload-time = "2026-03-10T21:31:02.067Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/59/8c/77f5097695f4dd8255ecbd08b2a1ed8ba8b953d337804dd7080f199e12bf/tornado-6.5.5-cp39-abi3-macosx_10_9_universal2.whl", hash = "sha256:487dc9cc380e29f58c7ab88f9e27cdeef04b2140862e5076a66fb6bb68bb1bfa", size = 445983, upload-time = "2026-03-10T21:30:44.28Z" },
- { url = "https://files.pythonhosted.org/packages/ab/5e/7625b76cd10f98f1516c36ce0346de62061156352353ef2da44e5c21523c/tornado-6.5.5-cp39-abi3-macosx_10_9_x86_64.whl", hash = "sha256:65a7f1d46d4bb41df1ac99f5fcb685fb25c7e61613742d5108b010975a9a6521", size = 444246, upload-time = "2026-03-10T21:30:46.571Z" },
- { url = "https://files.pythonhosted.org/packages/b2/04/7b5705d5b3c0fab088f434f9c83edac1573830ca49ccf29fb83bf7178eec/tornado-6.5.5-cp39-abi3-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:e74c92e8e65086b338fd56333fb9a68b9f6f2fe7ad532645a290a464bcf46be5", size = 447229, upload-time = "2026-03-10T21:30:48.273Z" },
- { url = "https://files.pythonhosted.org/packages/34/01/74e034a30ef59afb4097ef8659515e96a39d910b712a89af76f5e4e1f93c/tornado-6.5.5-cp39-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:435319e9e340276428bbdb4e7fa732c2d399386d1de5686cb331ec8eee754f07", size = 448192, upload-time = "2026-03-10T21:30:51.22Z" },
- { url = "https://files.pythonhosted.org/packages/be/00/fe9e02c5a96429fce1a1d15a517f5d8444f9c412e0bb9eadfbe3b0fc55bf/tornado-6.5.5-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:3f54aa540bdbfee7b9eb268ead60e7d199de5021facd276819c193c0fb28ea4e", size = 448039, upload-time = "2026-03-10T21:30:53.52Z" },
- { url = "https://files.pythonhosted.org/packages/82/9e/656ee4cec0398b1d18d0f1eb6372c41c6b889722641d84948351ae19556d/tornado-6.5.5-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:36abed1754faeb80fbd6e64db2758091e1320f6bba74a4cf8c09cd18ccce8aca", size = 447445, upload-time = "2026-03-10T21:30:55.541Z" },
- { url = "https://files.pythonhosted.org/packages/5a/76/4921c00511f88af86a33de770d64141170f1cfd9c00311aea689949e274e/tornado-6.5.5-cp39-abi3-win32.whl", hash = "sha256:dd3eafaaeec1c7f2f8fdcd5f964e8907ad788fe8a5a32c4426fbbdda621223b7", size = 448582, upload-time = "2026-03-10T21:30:57.142Z" },
- { url = "https://files.pythonhosted.org/packages/2c/23/f6c6112a04d28eed765e374435fb1a9198f73e1ec4b4024184f21faeb1ad/tornado-6.5.5-cp39-abi3-win_amd64.whl", hash = "sha256:6443a794ba961a9f619b1ae926a2e900ac20c34483eea67be4ed8f1e58d3ef7b", size = 448990, upload-time = "2026-03-10T21:30:58.857Z" },
- { url = "https://files.pythonhosted.org/packages/b7/c8/876602cbc96469911f0939f703453c1157b0c826ecb05bdd32e023397d4e/tornado-6.5.5-cp39-abi3-win_arm64.whl", hash = "sha256:2c9a876e094109333f888539ddb2de4361743e5d21eece20688e3e351e4990a6", size = 448016, upload-time = "2026-03-10T21:31:00.43Z" },
-]
-
[[package]]
name = "tqdm"
version = "4.67.0"
@@ -2683,35 +2380,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/78/55/896b06bf93a49bec0f4ae2a6f1ed12bd05c8860744ac3a70eda041064e4d/virtualenv-21.1.0-py3-none-any.whl", hash = "sha256:164f5e14c5587d170cf98e60378eb91ea35bf037be313811905d3a24ea33cc07", size = 5825072, upload-time = "2026-02-27T08:49:27.516Z" },
]
-[[package]]
-name = "watchdog"
-version = "6.0.0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/db/7d/7f3d619e951c88ed75c6037b246ddcf2d322812ee8ea189be89511721d54/watchdog-6.0.0.tar.gz", hash = "sha256:9ddf7c82fda3ae8e24decda1338ede66e1c99883db93711d8fb941eaa2d8c282", size = 131220, upload-time = "2024-11-01T14:07:13.037Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/0c/56/90994d789c61df619bfc5ce2ecdabd5eeff564e1eb47512bd01b5e019569/watchdog-6.0.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:d1cdb490583ebd691c012b3d6dae011000fe42edb7a82ece80965b42abd61f26", size = 96390, upload-time = "2024-11-01T14:06:24.793Z" },
- { url = "https://files.pythonhosted.org/packages/55/46/9a67ee697342ddf3c6daa97e3a587a56d6c4052f881ed926a849fcf7371c/watchdog-6.0.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:bc64ab3bdb6a04d69d4023b29422170b74681784ffb9463ed4870cf2f3e66112", size = 88389, upload-time = "2024-11-01T14:06:27.112Z" },
- { url = "https://files.pythonhosted.org/packages/44/65/91b0985747c52064d8701e1075eb96f8c40a79df889e59a399453adfb882/watchdog-6.0.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:c897ac1b55c5a1461e16dae288d22bb2e412ba9807df8397a635d88f671d36c3", size = 89020, upload-time = "2024-11-01T14:06:29.876Z" },
- { url = "https://files.pythonhosted.org/packages/e0/24/d9be5cd6642a6aa68352ded4b4b10fb0d7889cb7f45814fb92cecd35f101/watchdog-6.0.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:6eb11feb5a0d452ee41f824e271ca311a09e250441c262ca2fd7ebcf2461a06c", size = 96393, upload-time = "2024-11-01T14:06:31.756Z" },
- { url = "https://files.pythonhosted.org/packages/63/7a/6013b0d8dbc56adca7fdd4f0beed381c59f6752341b12fa0886fa7afc78b/watchdog-6.0.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:ef810fbf7b781a5a593894e4f439773830bdecb885e6880d957d5b9382a960d2", size = 88392, upload-time = "2024-11-01T14:06:32.99Z" },
- { url = "https://files.pythonhosted.org/packages/d1/40/b75381494851556de56281e053700e46bff5b37bf4c7267e858640af5a7f/watchdog-6.0.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:afd0fe1b2270917c5e23c2a65ce50c2a4abb63daafb0d419fde368e272a76b7c", size = 89019, upload-time = "2024-11-01T14:06:34.963Z" },
- { url = "https://files.pythonhosted.org/packages/39/ea/3930d07dafc9e286ed356a679aa02d777c06e9bfd1164fa7c19c288a5483/watchdog-6.0.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:bdd4e6f14b8b18c334febb9c4425a878a2ac20efd1e0b231978e7b150f92a948", size = 96471, upload-time = "2024-11-01T14:06:37.745Z" },
- { url = "https://files.pythonhosted.org/packages/12/87/48361531f70b1f87928b045df868a9fd4e253d9ae087fa4cf3f7113be363/watchdog-6.0.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:c7c15dda13c4eb00d6fb6fc508b3c0ed88b9d5d374056b239c4ad1611125c860", size = 88449, upload-time = "2024-11-01T14:06:39.748Z" },
- { url = "https://files.pythonhosted.org/packages/5b/7e/8f322f5e600812e6f9a31b75d242631068ca8f4ef0582dd3ae6e72daecc8/watchdog-6.0.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:6f10cb2d5902447c7d0da897e2c6768bca89174d0c6e1e30abec5421af97a5b0", size = 89054, upload-time = "2024-11-01T14:06:41.009Z" },
- { url = "https://files.pythonhosted.org/packages/30/ad/d17b5d42e28a8b91f8ed01cb949da092827afb9995d4559fd448d0472763/watchdog-6.0.0-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:c7ac31a19f4545dd92fc25d200694098f42c9a8e391bc00bdd362c5736dbf881", size = 87902, upload-time = "2024-11-01T14:06:53.119Z" },
- { url = "https://files.pythonhosted.org/packages/5c/ca/c3649991d140ff6ab67bfc85ab42b165ead119c9e12211e08089d763ece5/watchdog-6.0.0-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:9513f27a1a582d9808cf21a07dae516f0fab1cf2d7683a742c498b93eedabb11", size = 88380, upload-time = "2024-11-01T14:06:55.19Z" },
- { url = "https://files.pythonhosted.org/packages/a9/c7/ca4bf3e518cb57a686b2feb4f55a1892fd9a3dd13f470fca14e00f80ea36/watchdog-6.0.0-py3-none-manylinux2014_aarch64.whl", hash = "sha256:7607498efa04a3542ae3e05e64da8202e58159aa1fa4acddf7678d34a35d4f13", size = 79079, upload-time = "2024-11-01T14:06:59.472Z" },
- { url = "https://files.pythonhosted.org/packages/5c/51/d46dc9332f9a647593c947b4b88e2381c8dfc0942d15b8edc0310fa4abb1/watchdog-6.0.0-py3-none-manylinux2014_armv7l.whl", hash = "sha256:9041567ee8953024c83343288ccc458fd0a2d811d6a0fd68c4c22609e3490379", size = 79078, upload-time = "2024-11-01T14:07:01.431Z" },
- { url = "https://files.pythonhosted.org/packages/d4/57/04edbf5e169cd318d5f07b4766fee38e825d64b6913ca157ca32d1a42267/watchdog-6.0.0-py3-none-manylinux2014_i686.whl", hash = "sha256:82dc3e3143c7e38ec49d61af98d6558288c415eac98486a5c581726e0737c00e", size = 79076, upload-time = "2024-11-01T14:07:02.568Z" },
- { url = "https://files.pythonhosted.org/packages/ab/cc/da8422b300e13cb187d2203f20b9253e91058aaf7db65b74142013478e66/watchdog-6.0.0-py3-none-manylinux2014_ppc64.whl", hash = "sha256:212ac9b8bf1161dc91bd09c048048a95ca3a4c4f5e5d4a7d1b1a7d5752a7f96f", size = 79077, upload-time = "2024-11-01T14:07:03.893Z" },
- { url = "https://files.pythonhosted.org/packages/2c/3b/b8964e04ae1a025c44ba8e4291f86e97fac443bca31de8bd98d3263d2fcf/watchdog-6.0.0-py3-none-manylinux2014_ppc64le.whl", hash = "sha256:e3df4cbb9a450c6d49318f6d14f4bbc80d763fa587ba46ec86f99f9e6876bb26", size = 79078, upload-time = "2024-11-01T14:07:05.189Z" },
- { url = "https://files.pythonhosted.org/packages/62/ae/a696eb424bedff7407801c257d4b1afda455fe40821a2be430e173660e81/watchdog-6.0.0-py3-none-manylinux2014_s390x.whl", hash = "sha256:2cce7cfc2008eb51feb6aab51251fd79b85d9894e98ba847408f662b3395ca3c", size = 79077, upload-time = "2024-11-01T14:07:06.376Z" },
- { url = "https://files.pythonhosted.org/packages/b5/e8/dbf020b4d98251a9860752a094d09a65e1b436ad181faf929983f697048f/watchdog-6.0.0-py3-none-manylinux2014_x86_64.whl", hash = "sha256:20ffe5b202af80ab4266dcd3e91aae72bf2da48c0d33bdb15c66658e685e94e2", size = 79078, upload-time = "2024-11-01T14:07:07.547Z" },
- { url = "https://files.pythonhosted.org/packages/07/f6/d0e5b343768e8bcb4cda79f0f2f55051bf26177ecd5651f84c07567461cf/watchdog-6.0.0-py3-none-win32.whl", hash = "sha256:07df1fdd701c5d4c8e55ef6cf55b8f0120fe1aef7ef39a1c6fc6bc2e606d517a", size = 79065, upload-time = "2024-11-01T14:07:09.525Z" },
- { url = "https://files.pythonhosted.org/packages/db/d9/c495884c6e548fce18a8f40568ff120bc3a4b7b99813081c8ac0c936fa64/watchdog-6.0.0-py3-none-win_amd64.whl", hash = "sha256:cbafb470cf848d93b5d013e2ecb245d4aa1c8fd0504e863ccefa32445359d680", size = 79070, upload-time = "2024-11-01T14:07:10.686Z" },
- { url = "https://files.pythonhosted.org/packages/33/e8/e40370e6d74ddba47f002a32919d91310d6074130fe4e17dabcafc15cbf1/watchdog-6.0.0-py3-none-win_ia64.whl", hash = "sha256:a1914259fa9e1454315171103c6a30961236f508b9b623eae470268bbcc6a22f", size = 79067, upload-time = "2024-11-01T14:07:11.845Z" },
-]
-
[[package]]
name = "werkzeug"
version = "3.1.6"