Fdog goes assembly

.github/workflows/github_build.yml

@@ -41,6 +41,11 @@ jobs:
         pwd
         pip install .
         path=$(fdog.setup -d ./ --getSourcepath); for i in $(less $path/data/dependencies.txt); do sudo apt-get install -y -qq $i; done
+        path=$(fdog.setup -d ./ --getSourcepath); ls $path/data/
+        echo "#########################################"
+        pwd
+        ls
+        echo "#########################################"
         echo "TEST fdog.setup"
         fdog.setup -d /home/runner/work/fDOG/fDOG/dt --woFAS
         echo "TEST fdog.checkData"
@@ -49,6 +54,8 @@ jobs:
         fdog.showTaxa
         echo "TEST fdog.run"
         fdog.run --seqFile infile.fa --jobName test --refspec HUMAN@9606@qfo24_02 --fasOff --group mammalia
+        echo "TEST fdog.assembly"
+        fdog.assembly --gene test --refSpec HUMAN@9606@qfo24_02 --augustus --augustusRefSpec human --coregroupPath core_orthologs/ --out test_assembly --fasoff
         mkdir seeds
         path=$(fdog.setup -d ./ --getSourcepath); a="1 2 3"; for i in ${a[@]}; do cp $path/data/infile.fa seeds/$i.fa; done
         echo "TEST fdogs.run"

.gitignore

@@ -128,8 +128,16 @@ dmypy.json
 # Pyre type checker
 .pyre/
 
+# DS_store
+**/.DS_Store
+/fdog/.DS_Store
+/fdog/data/.DS_Store
+/fdog/bin/.DS_Store
+/fdog/setup/.DS_Store
+
 #Hannah
 /fdog/data/core_orthologs/
 /fdog/data/assembly_dir/
 /fdog/fdog_goes_assembly/tmp/ 
 taxdump*
+.DS_Store

MANIFEST.in

@@ -1 +1 @@
-recursive-include fDOG *
+recursive-include fdog/data *

README.md

@@ -4,6 +4,8 @@
 [![License: GPL v3](https://img.shields.io/badge/License-GPLv3-blue.svg)](https://www.gnu.org/licenses/gpl-3.0)
 ![Github Build](https://github.com/BIONF/fDOG/workflows/build/badge.svg)
 
+# Poster fDOG - Assembly
+https://github.com/BIONF/fDOG/blob/gh-pages/www/Poster_fDOG_Assembly.pdf
 # Table of Contents
 * [How to install](#how-to-install)
      * [Install the fDOG package](#install-the-fdog-package)

fdog/.gitignore

@@ -0,0 +1,143 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# DS_store
+**/.DS_Store
+/fdog/.DS_Store
+/fdog/data/.DS_Store
+/fdog/bin/.DS_Store
+/fdog/setup/.DS_Store
+
+#Hannah
+/fdog/data/core_orthologs/
+/fdog/data/assembly_dir/
+/fdog/fdog_goes_assembly/tmp/ 
+taxdump*
+/fdog/fDOGassembly.py

fdog/addAssembly.py

@@ -0,0 +1,124 @@
+import fdog.libs.addtaxon as addTaxon_fn
+import fdog.libs.tree as tree_fn
+import fdog.libs.zzz as general_fn
+import sys
+import os
+import argparse
+
+def check_fasta(file):
+    nHeader = general_fn.count_line(file, '>', True)
+    nSeq = general_fn.count_line(file, '>', False)
+    if not nHeader == nSeq:
+        return(1)
+    nPipe = general_fn.count_line(file, '|', True)
+    if nPipe > 0:
+        return(1)
+    return(0)
+
+def check_path(path):
+    if not os.path.exists(path):
+        return False
+    else:
+        if os.path.isfile(path):
+            return "File"
+        else:
+            return "Path"
+
+def parse_file(path):
+    file = open(path, "r")
+    lines = file.readlines()
+    id_dict = {}
+    for line in lines:
+        line = line.rstrip()
+        ncbi, name = line.split("\t")
+        id_dict[ncbi] = name
+    file.close()
+    return id_dict
+
+
+def main():
+    print("#################################")
+    #################### handle user input #####################################
+    version = '0.0.3'
+    ################### initialize parser ######################################
+    parser = argparse.ArgumentParser(description='You are running fdog.addAssembly version ' + str(version) + '.')
+    ################## required arguments ######################################
+    required = parser.add_argument_group('Required arguments')
+    required.add_argument('--fasta', help='Path to fasta file or folder', action='store', default='', required=True)
+    required.add_argument('--out', help='Path to output folder.', action='store', default='', required=True)
+    required.add_argument('--ncbi', help='NCBI ID of species or a mapping file (tab separated) containing the NCBI ID and the corresponding file name placed in the folder given by --fasta. ', action='store', default='', required=True)
+    required.add_argument('--ver', help='Version', action='store', default='', required=True)
+    optional = parser.add_argument_group('Optional arguments')
+    optional.add_argument('--link', help='links fasta files instead of copying them', action='store_true', default = False)
+
+    args = parser.parse_args()
+    fasta = args.fasta
+    if check_path(fasta) == False:
+        print("%s does not exists. Exiting ..."%(fasta))
+        sys.exit()
+    else:
+        format = check_path(fasta)
+    out_folder = args.out
+    out_folder = os.path.abspath(out_folder) + '/'
+    os.system('mkdir %s >/dev/null 2>&1' % (out_folder))
+    ncbi = args.ncbi
+    ver = args.ver
+    ln = args.link
+    id_dict = {}
+
+    if check_path(ncbi) == False:
+        if ncbi.isdigit() and format == "File":
+            id_dict[ncbi] = fasta
+        else:
+            print("%s is no file or digit. Exiting ..."%(ncbi))
+            sys.exit()
+    elif check_path(ncbi) == "File":
+        print("Parsing mapping file ...")
+        id_dict = parse_file(ncbi)
+        print("... done")
+    else:
+        print("%s is no file or digit. Exiting ..."%(ncbi))
+        sys.exit()
+    #print(format)
+    #print(fasta)
+    if format == "File":
+        fa = id_dict[ncbi]
+        if check_fasta(fa):
+            name = addTaxon_fn.generate_spec_name(ncbi, "", ver)
+            if ln == False:
+                assembly_folder = out_folder + name
+                os.system('mkdir %s >/dev/null 2>&1' % (assembly_folder))
+                os.system("cp %s %s/%s.fa" %(fa, assembly_folder, name))
+            else:
+                assembly_folder = out_folder + name
+                os.system('mkdir %s >/dev/null 2>&1' % (assembly_folder))
+                os.system("ln %s %s/%s.fa" %(fa, assembly_folder, name))
+        else:
+            print("%s Fasta format not valid or header includes |"%(fa))
+
+    else:
+        for sp in id_dict:
+            print("Adding species %s"%(sp))
+            #print(id_dict)
+            fa = id_dict[sp]
+            fasta = os.path.abspath(fasta) + '/'
+            #print(fa)
+            #print(fasta)
+            fasta_path = fasta + fa
+            if check_fasta(fasta_path):
+                name = addTaxon_fn.generate_spec_name(sp, "", ver)
+                if ln == False:
+                    assembly_folder = out_folder + name
+                    os.system('mkdir %s >/dev/null 2>&1' % (assembly_folder))
+                    os.system("cp %s %s/%s.fa" %(fasta_path, assembly_folder, name))
+                else:
+                    assembly_folder = out_folder + name
+                    os.system('mkdir %s >/dev/null 2>&1' % (assembly_folder))
+                    os.system("ln -s %s %s/%s.fa" %(fasta_path, assembly_folder, name))
+            else:
+                print("%s Fasta format not valid or header includes |"%(fasta_path))
+
+    print("DONE, files can be found: %s"%(out_folder))
+
+if __name__ == '__main__':
+    main()