Improve Monomer Input Schema

AutoREACTER/detectors/detector.py

@@ -8,6 +8,15 @@
 the simulation.
 """
 
+import warnings
+
+warnings.warn(
+    """This script is deprecated and will be modified in future versions. Within v0.2, the whole package will primaraliy 
+    support on jupyter notebook and the CLI is removed. Please use the notebook version for now and refer to the README for how to use the package.""",
+    DeprecationWarning,
+    stacklevel=2
+)
+
 import json
 
 # Attempt to import detector modules. Handles different import paths depending on

AutoREACTER/reaction_template_builder/run_reaction_template_pipeline.py

@@ -16,40 +16,6 @@
 - Implement duplicate reaction detection and handling.
 """
 
-
-"""TODO (Reaction Template Pipeline):
-from dataclasses import dataclass
-from typing import Literal
-
-@dataclass(slots=True, frozen=True)
-class MonomerRole:
-    spec: MoleculeSpec
-    functionality_type: str
-    fg_name: str
-    fg_smarts_1: str
-    fg_count_1: int
-    fg_smarts_2: str | None = None
-    fg_count_2: int | None = None
-
-@dataclass(slots=True, frozen=True)
-class ReactionDefinition:
-    reaction_name: str
-    reaction_smarts: str
-    same_reactants: bool
-    delete_atom: bool
-    references: dict
-    monomer_1: MonomerRole
-    monomer_2: MonomerRole | None = None
-"""
-
-
-"""
-def withdraw(balance, amount):
-    if amount > balance:
-        raise InsufficientFundsError(amount - balance, f"Cannot withdraw {amount}, only {balance} available.")
-    return balance - amount
-"""
-
 """
 TODO: Preserve stable reaction_id for each reaction (never renumber).
 Maintain a seq_id mapping for the current filtered set (continuous 1..N) for UI/export.

examples/example_1.ipynb

@@ -23,6 +23,7 @@
     "from AutoREACTER.cache import GetCacheDir, RunDirectoryManager, RetentionCleanup\n",
     "from AutoREACTER.detectors.functional_groups_detector import FunctionalGroupsDetector\n",
     "from AutoREACTER.detectors.reaction_detector import ReactionDetector\n",
+    "from AutoREACTER.detectors.non_monomer_detector import NonReactantsDetector\n",
     "from AutoREACTER.reaction_template_builder.run_reaction_template_pipeline import ReactionTemplatePipeline\n",
     "from rdkit import Chem\n",
     "from rdkit.Chem import Draw\n",
@@ -31,9 +32,10 @@
     "Initialization()\n",
     "input_parser = InputParser()\n",
     "\n",
+    "input_parser = InputParser()\n",
     "cache_dir = GetCacheDir().staging_dir\n",
     "dated_cache_dir = RunDirectoryManager.make_dated_run_dir(cache_dir, chdir_to=\"none\")\n",
-    "# future use\n",
+    "# #future use\n",
     "# RunDirectoryManager.copy_into_run(cache_dir, dated_cache_dir)\n",
     "\n",
     "\n"
@@ -105,15 +107,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Detector must be called after the inputs are validated, because it operates on validated MonomerEntry objects (validated_inputs.monomers)\n",
+    "# Run the detector only after the inputs have been validated, as it consumes validated_inputs.monomers to execute the detection workflow.\n",
     "functional_groups_detector = FunctionalGroupsDetector()\n",
-    "functional_groups, functional_groups_imgs = \n",
+    "functional_groups, functional_groups_imgs = \\\n",
     "    functional_groups_detector.functional_groups_detector(\n",
     "        validated_inputs.monomers\n",
-    "    )\n",
-    "\n",
-    "for fg_img in functional_groups_imgs:\n",
-    "    print(fg_img.indexes_to_highlight)"
+    "    )"
    ]
   },
   {
@@ -135,6 +134,7 @@
    "outputs": [],
    "source": [
     "reaction_detector = ReactionDetector()\n",
+    "non_monomer_detector = NonReactantsDetector()\n",
     "reaction_instances = reaction_detector.reaction_detector(functional_groups)\n",
     "img = reaction_detector.create_reaction_image_grid(reaction_instances)\n",
     "img"
@@ -150,6 +150,28 @@
     "selected_reactions = reaction_detector.reaction_selection(reaction_instances)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c811c031",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "non_reactants_list = non_monomer_detector.non_monomer_detector(validated_inputs, selected_reactions)\n",
+    "img_non_reactants = non_monomer_detector.non_reactants_to_visualization(non_reactants_list)\n",
+    "img_non_reactants"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "00d75b1a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "updated_inputs = non_monomer_detector.non_reactant_selection(validated_inputs, non_reactants_list)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,

examples/example_1_inputs_count_mode.json

@@ -1,39 +1,53 @@
 {
-  "simulation_name": "Example_Count_Mode",
-  "temperature": [300, 400, 500],
-  "density": 0.8,
-
-  "composition": {
-    "method": "counts",
-    "targets": [
-      {"tag": "10k"},
-      {"tag": "100k"}
-    ]
-  },
-
-  "monomers": [ 
-    {
-      "name": "tmc",
-      "smiles": "ClC(=O)c1cc(cc(c1)C(Cl)=O)C(Cl)=O",
-      "count": {
-        "10k": 220,
-        "100k": 2200
-      }
-    },
-    {
-      "name": "mpd",
-      "smiles": "C1=CC(=CC(=C1)N)N",
-      "count": {
-        "10k": 220,
-        "100k": 2200
-      }
+
+    "simulation_name": "Example_Count_Mode",
+
+    "replicas": {
+        "temperatures": [300, 400, 500],
+        "density": [0.8],
+        "method": "counts",
+
+        "systems": [
+
+            {
+                "tag": "10k",
+
+                "monomer_counts": {
+                    "tmc": 220,
+                    "mpd": 220,
+                    "ethanol": 110
+                }
+            },
+
+            {
+                "tag": "100k",
+
+                "monomer_counts": {
+                    "tmc": 2200,
+                    "mpd": 2200,
+                    "ethanol": 1100
+                }
+            }
+
+        ]
     },
-    {
-      "smiles": "CCO",
-      "count": {
-        "10k": 110,
-        "100k": 1100
-      }
-    }
-  ]
+
+    "monomers": [
+
+        {
+            "name": "tmc",
+            "smiles": "ClC(=O)c1cc(cc(c1)C(Cl)=O)C(Cl)=O"
+        },
+
+        {
+            "name": "mpd",
+            "smiles": "C1=CC(=CC(=C1)N)N"
+        },
+
+        {
+            "name": "ethanol",
+            "smiles": "CCO"
+        }
+
+    ]
 }

examples/example_1_inputs_count_mode_FF.json

@@ -1,39 +1,44 @@
 {
   "simulation_name": "Example_Count_Mode",
-  "temperature": [300, 400, 500],
-  "density": 0.8,
-  "force_field": "PCFF",
-  "composition": {
+
+  "replicas": {
+    "temperatures": [300, 400, 500],
+    "density": [0.8],
     "method": "counts",
-    "targets": [
-      {"tag": "10k"},
-      {"tag": "100k"}
+
+    "systems": [
+      {
+        "tag": "10k",
+        "monomer_counts": {
+          "tmc": 220,
+          "mpd": 220,
+          "data_3": 110
+        }
+      },
+      {
+        "tag": "100k",
+        "monomer_counts": {
+          "tmc": 2200,
+          "mpd": 2200,
+          "data_3": 1100
+        }
+      }
     ]
   },
-
-  "monomers": [ 
+
+  "force_field": "PCFF",
+
+  "monomers": [
     {
       "name": "tmc",
-      "smiles": "ClC(=O)c1cc(cc(c1)C(Cl)=O)C(Cl)=O",
-      "count": {
-        "10k": 220,
-        "100k": 2200
-      }
+      "smiles": "ClC(=O)c1cc(cc(c1)C(Cl)=O)C(Cl)=O"
     },
     {
       "name": "mpd",
-      "smiles": "C1=CC(=CC(=C1)N)N",
-      "count": {
-        "10k": 220,
-        "100k": 2200
-      }
+      "smiles": "C1=CC(=CC(=C1)N)N"
     },
     {
-      "smiles": "CCO",
-      "count": {
-        "10k": 110,
-        "100k": 1100
-      }
+      "smiles": "CCO"
     }
   ]
-}
+}

examples/example_1_inputs_count_mode_with_non_monomers.json

@@ -0,0 +1,46 @@
+{
+
+    "simulation_name": "Example_Count_Mode",
+
+    "replicas": {
+        "temperatures": [300, 400, 500],
+        "density": [0.8],
+        "method": "counts",
+
+        "systems": [
+
+            {
+                "tag": "10k",
+
+                "monomer_counts": {
+                    "tmc": 220,
+                    "mpd": 220
+                }
+            },
+
+            {
+                "tag": "100k",
+
+                "monomer_counts": {
+                    "tmc": 2200,
+                    "mpd": 2200
+                }
+            }
+
+        ]
+    },
+
+    "monomers": [
+
+        {
+            "name": "tmc",
+            "smiles": "ClC(=O)c1cc(cc(c1)C(Cl)=O)C(Cl)=O"
+        },
+
+        {
+            "name": "mpd",
+            "smiles": "C1=CC(=CC(=C1)N)N"
+        }
+
+    ]
+}