Refactor Pathway Management to Use pathlib

examples/config_files/ES.yaml

@@ -1,6 +1,6 @@
 exp_name: "ES_EXAMPLE_CONFIG"
 
-init_pop_path: ".../.../path_to_seed_compounds.tsv"
+init_pop_path: "data/seed_compounds.csv"
 init_pop_size: 100
 standardize: True
 
@@ -11,4 +11,4 @@ generations: 100
 algorithm: "ES"
 elitist: True
 
-output_path: ".../output_dir_path/"
+output_path: "output_dir_path/"

examples/config_files/GA.yaml

@@ -1,7 +1,7 @@
 exp_name: "GA_EXAMPLE_CONFIG"
 
-init_pop_path: ".../.../path_to_seed_compounds.tsv"
-init_pop_size: 100
+init_pop_path: "data/seed_compounds.csv"
+init_pop_size: 11
 standardize: True
 
 max_rules_by_iter: 22949
@@ -10,4 +10,4 @@ tolerance: 0.1
 generations: 100
 algorithm: "GA"
 
-output_path: ".../output_dir_path/"
+output_path: "output_dir_path/"

examples/config_files/IBEA.yaml

@@ -1,6 +1,6 @@
 exp_name: "IBEA_EXAMPLE_CONFIG"
 
-init_pop_path: ".../.../path_to_seed_compounds.tsv"
+init_pop_path: "data/seed_compounds.csv"
 init_pop_size: 100
 standardize: True
 
@@ -11,4 +11,4 @@ generations: 100
 algorithm: "IBEA"
 kappa: 1.0
 
-output_path: ".../output_dir_path/"
+output_path: "output_dir_path/"

examples/config_files/NSGAII.yaml

@@ -1,13 +1,13 @@
 exp_name: "NSGAII_EXAMPLE_CONFIG"
 
-init_pop_path: ".../.../path_to_seed_compounds.tsv"
-init_pop_size: 100
+init_pop_path: "data/seed_compounds.csv"
+init_pop_size: 11
 standardize: True
 
 max_rules_by_iter: 22949
 tolerance: 0.1
 
-generations: 100
+generations: 10
 algorithm: "NSGAII"
 
-output_path: ".../output_dir_path/"
+output_path: "output_dir_path/"

examples/config_files/NSGAIII.yaml

@@ -1,6 +1,6 @@
 exp_name: "NSGAIII_EXAMPLE_CONFIG"
 
-init_pop_path: ".../.../path_to_seed_compounds.tsv"
+init_pop_path: "data/seed_compounds.csv"
 init_pop_size: 100
 standardize: True
 
@@ -10,4 +10,4 @@ tolerance: 0.1
 generations: 100
 algorithm: "NSGAIII"
 
-output_path: ".../output_dir_path/"
+output_path: "output_dir_path/"

examples/config_files/SA.yaml

@@ -1,6 +1,6 @@
 exp_name: "SA_EXAMPLE_CONFIG"
 
-init_pop_path: ".../.../path_to_seed_compounds.tsv"
+init_pop_path: "data/seed_compounds.csv"
 init_pop_size: 100
 standardize: True
 
@@ -13,4 +13,4 @@ temperature: 1.0
 minimum_temperature: 0.000001
 alpha: 0.95
 
-output_path: ".../output_dir_path/"
+output_path: "output_dir_path/"

examples/config_files/SPEA2.yaml

@@ -1,6 +1,6 @@
 exp_name: "SPEA2_EXAMPLE_CONFIG"
 
-init_pop_path: ".../.../path_to_seed_compounds.tsv"
+init_pop_path: "data/seed_compounds.csv"
 init_pop_size: 100
 standardize: True
 
@@ -10,4 +10,4 @@ tolerance: 0.1
 generations: 100
 algorithm: "SPEA2"
 
-output_path: ".../output_dir_path/"
+output_path: "output_dir_path/"

examples/data/seed_compounds.csv

@@ -0,0 +1,12 @@
+compound_id	smiles
+id_0	N=C(O)NC(O)C(=O)O
+id_1	Nc1ncnc2c1ncn2C1OC(COP(=O)(O)OC(=O)c2cccc(O)c2O)C(O)C1O
+id_2	CC1(O)OCC(O)C1(O)O
+id_3	CC1(O)OCC(O)C1=O
+id_4	CC(C)(COP(=O)(O)OP(=O)(O)OCC1OC(n2cnc3c(N)ncnc32)C(O)C1OP(=O)(O)O)C(O)C(O)=NCCC(O)=NCCSC(=O)CC(O)CCC(=O)O
+id_5	CC(C)(O)C(O)C(=O)O
+id_6	CCC(C)(O)C(O)C(=O)O
+id_7	N=C(N)N=C(O)c1nc(Cl)c(N2CCCCCC2)nc1N
+id_8	O=C(O)C(O)CO
+id_9	CC(C)(CO)C(O)C(=O)O
+id_10	CC(C)(CO)C(O)C(O)=NCCC(=O)O

examples/example.ipynb

@@ -0,0 +1,143 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "id": "initial_id",
+   "metadata": {
+    "collapsed": true,
+    "ExecuteTime": {
+     "end_time": "2025-02-12T12:51:01.579361Z",
+     "start_time": "2025-02-12T12:51:00.188Z"
+    }
+   },
+   "source": [
+    "from rdkit.Chem.QED import qed\n",
+    "from reactea import evaluation_functions_wrapper\n",
+    "\n",
+    "# EVALUATION FUNCTIONS\n",
+    "\n",
+    "# evaluation function returning the number of rings a molecule\n",
+    "def number_of_rings(mol):\n",
+    "    ri = mol.GetRingInfo()\n",
+    "    n_rings = len(ri.AtomRings())\n",
+    "    return n_rings\n",
+    "\n",
+    "n_rigs_feval = evaluation_functions_wrapper(number_of_rings,\n",
+    "                                            maximize=False,\n",
+    "                                            worst_fitness=100,\n",
+    "                                            name='n_rings')\n",
+    "\n",
+    "# evaluation function returning the drug-likeliness score (QED) of a molecule\n",
+    "def qed_score(mol):\n",
+    "    return qed(mol)\n",
+    "\n",
+    "qed_feval = evaluation_functions_wrapper(qed_score,\n",
+    "                                         maximize=True,\n",
+    "                                         worst_fitness=0.0,\n",
+    "                                         name='qed')\n",
+    "\n",
+    "# CASE STUDY\n",
+    "\n",
+    "from reactea import case_study_wrapper\n",
+    "\n",
+    "# SINGLE OBJECTIVE CASE STUDY\n",
+    "# case study to optimize a single objective `f1` (minimize number of rings in a molecule)\n",
+    "minimize_rings = case_study_wrapper(n_rigs_feval,\n",
+    "                                    multi_objective=False,\n",
+    "                                    name='minimize_rings')\n",
+    "\n",
+    "# SINGLE-OBJECTIVE CASE STUDY WITH MULTIPLE EVALUATION FUNCTIONS\n",
+    "# case study to optimize a single objective but with multiple evaluation functions `f1` and `f2` (minimize number of rings in a molecule and maximize qed)\n",
+    "# the number of evaluation functions must be the same as the number of values in weights and the sum of the weights must be 1\n",
+    "minimize_rings_maximize_qed = case_study_wrapper([n_rigs_feval, qed_feval],\n",
+    "                                                 multi_objective=False,\n",
+    "                                                 name='minimize_rings_maximize_qed',\n",
+    "                                                 weights=[0.3, 0.7])\n",
+    "\n",
+    "# MULTI-OBJECTIVE CASE STUDY\n",
+    "# case study to optimize multiple objectives simultaneous\n",
+    "minimize_rings_maximize_qed_mo = case_study_wrapper([n_rigs_feval, qed_feval],\n",
+    "                                                    multi_objective=True,\n",
+    "                                                    name='minimize_rings_maximize_qed_mo')"
+   ],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[12:51:00] Initializing Normalizer\n"
+     ]
+    }
+   ],
+   "execution_count": 1
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2025-02-12T12:51:33.381067Z",
+     "start_time": "2025-02-12T12:51:01.642195Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "from reactea import run_reactea\n",
+    "\n",
+    "case_study_rings = minimize_rings_maximize_qed_mo\n",
+    "# provide path to configuration file and case study\n",
+    "run_reactea(configs_path = 'config_files/NSGAII.yaml',\n",
+    "            case_study = case_study_rings)"
+   ],
+   "id": "e217633e149b67e5",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running NSGAII\n",
+      "Eval(s)|     Worst      Best    Median   Average   Std Dev|     Worst      Best    Median   Average   Std Dev|\n",
+      "     11|  4.000000  0.000000  0.000000  1.000000  1.348400|  0.041206  0.508241  0.427593  0.370435  0.139558|\n",
+      "     22|  2.000000  0.000000  0.000000  0.545455  0.782030|  0.301591  0.662767  0.456096  0.440253  0.098033|\n",
+      "     33|  3.000000  0.000000  0.000000  0.727273  1.052349|  0.396890  0.788971  0.501522  0.530570  0.110155|\n",
+      "     44|  3.000000  0.000000  0.000000  0.818182  1.113404|  0.456096  0.788971  0.571526  0.564990  0.096966|\n",
+      "     55|  3.000000  0.000000  0.000000  0.727273  1.052349|  0.461845  0.788971  0.571526  0.580778  0.085874|\n",
+      "     66|  3.000000  0.000000  2.000000  1.454545  1.372697|  0.571526  0.788971  0.591504  0.628655  0.068347|\n",
+      "     77|  3.000000  0.000000  1.000000  1.363636  1.226431|  0.571526  0.788971  0.638008  0.649290  0.065461|\n",
+      "     88|  3.000000  0.000000  1.000000  1.363636  1.226431|  0.571526  0.788971  0.638008  0.649290  0.065461|\n",
+      "     99|  3.000000  0.000000  1.000000  1.454545  1.157084|  0.579890  0.788971  0.671357  0.664836  0.062069|\n",
+      "    110|  3.000000  0.000000  2.000000  1.636364  1.226431|  0.579890  0.788971  0.679245  0.677558  0.058601|\n"
+     ]
+    }
+   ],
+   "execution_count": 2
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": null,
+   "source": "",
+   "id": "fdcbdfb72eec84c0"
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

requirements.txt

@@ -2,7 +2,7 @@ rdkit-pypi==2022.03.1
 numpy==1.21.5
 pandas==1.3.5
 cytoolz==0.11.2
-jmetalpy
+jmetalpy==1.5.5
 PyYAML==6.0
 matplotlib==3.5.1
 chembl_structure_pipeline

src/reactea/__init__.py

@@ -1,5 +1,5 @@
-import os
 import warnings
+from pathlib import Path
 from typing import Union
 
 from rdkit import RDLogger
@@ -9,8 +9,6 @@
 from reactea.optimization.jmetal.ea import ChemicalEA
 from reactea.wrappers import case_study_wrapper, evaluation_functions_wrapper
 
-ROOT_DIR = os.path.dirname(__file__)
-
 
 def run_reactea(configs_path: Union[str, dict],
                 case_study: CaseStudy,
@@ -22,13 +20,16 @@ def run_reactea(configs_path: Union[str, dict],
     if ignore_warnings:
         warnings.filterwarnings("ignore")
 
-    if isinstance(configs_path, str) and os.path.exists(configs_path):
+    configs_path = Path(configs_path)
+    if configs_path.exists():
         configs = Loaders.get_config_from_yaml(configs_path)
-    else:
+    elif isinstance(configs_path, dict):
         configs = configs_path
+    else:
+        raise FileNotFoundError(f"Config file {configs_path} not found.")
 
     # set up output folder
-    output_folder = os.path.join(configs['output_dir'], configs['algorithm'])
+    output_folder = Path(configs['output_dir']) / configs['algorithm']
     configs['output_dir'] = output_folder
 
     # initialize population and initialize population smiles

src/reactea/cli.py

@@ -1,4 +1,3 @@
-import os
 import time
 from datetime import datetime
 
@@ -10,8 +9,6 @@
 from reactea.io_streams import Loaders, Writers
 from reactea.optimization.jmetal.ea import ChemicalEA
 
-DATA_FILES = os.path.dirname(__file__)
-
 
 def setup_configuration_file(args):
     # create dictionary from parser.parse_args()

src/reactea/constants.py

@@ -7,7 +7,7 @@
 from reactea.chem import ChEMBLStandardizer
 from reactea.optimization.comparators import ParetoDominanceComparator
 from reactea.optimization.jmetal.operators import ReactorPseudoCrossover, ReactorMutation
-from reactea.optimization.jmetal.terminators import StoppingByEvaluationsOrImprovement, StoppingByEvaluations
+from reactea.optimization.jmetal.terminators import StoppingByEvaluations
 
 
 class ExperimentConstants: