Merge pull request #24 from MoleculeResolver/spr/main/f034bebf

Add docs website

.gitignore

@@ -5,4 +5,5 @@ __pycache__/
 moleculeresolver/molecule_cache.*
 .venv/
 *.db*
-debug.log
+debug.log
+*build/

.readthedocs.yaml

@@ -0,0 +1,22 @@
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the OS, Python version, and other tools you might need
+build:
+  os: ubuntu-24.04
+  tools:
+    python: "3.13"
+
+# Build documentation in the "docs/" directory with Sphinx
+sphinx:
+   configuration: docs/source/conf.py
+
+# Optionally, but recommended,
+# declare the Python requirements required to build your documentation
+# See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
+python:
+   install:
+   - requirements: docs/requirements.txt
+

.spr.yml

@@ -0,0 +1,12 @@
+githubRepoOwner: MoleculeResolver
+githubRepoName: molecule-resolver
+githubHost: github.com
+githubRemote: origin
+githubBranch: main
+requireChecks: true
+requireApproval: true
+mergeMethod: rebase
+mergeQueue: false
+forceFetchTags: false
+showPrTitlesInStack: false
+branchPushIndividually: false

docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = source
+BUILDDIR      = build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/make.bat

@@ -0,0 +1,35 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=source
+set BUILDDIR=build
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.https://www.sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd

docs/requirements.txt

@@ -0,0 +1 @@
+sphinx-autoapi>=3.4.0

docs/source/conf.py

@@ -0,0 +1,28 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# For the full list of built-in configuration values, see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+# -- Project information -----------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
+
+project = 'MoleculeResolver'
+copyright = '2025, Simon Muller and Kobi Felton'
+author = 'Simon Muller and Kobi Felton'
+release = '0.3.2'
+
+# -- General configuration ---------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
+
+extensions = ['autoapi.extension']
+
+templates_path = ['_templates']
+exclude_patterns = []
+
+autoapi_dirs = ['../../moleculeresolver']
+
+# -- Options for HTML output -------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
+
+html_theme = 'alabaster'
+html_static_path = ['_static']

docs/source/index.rst

@@ -0,0 +1,17 @@
+.. MoleculeResolver documentation master file, created by
+   sphinx-quickstart on Mon Jan 13 19:01:52 2025.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+MoleculeResolver documentation
+==============================
+
+Add your content using ``reStructuredText`` syntax. See the
+`reStructuredText <https://www.sphinx-doc.org/en/master/usage/restructuredtext/index.html>`_
+documentation for details.
+
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Contents:
+

molecule_test_set/benchmark_molecule_names.json

@@ -0,0 +1,102 @@
+[
+    "Acetic Acid",
+    "Acetone",
+    "Acetylene",
+    "Acetylsalicylic Acid",
+    "Adenine",
+    "Adenosine Triphosphate",
+    "Adipic Acid",
+    "Aluminum(III) Oxide",
+    "Ammonia",
+    "Ascorbic Acid",
+    "Aspartame",
+    "Benzene",
+    "Benzoic Acid",
+    "Biphenyl ",
+    "Butane",
+    "Butene",
+    "Butyric Acid",
+    "Caffeine",
+    "Calcium Carbonate",
+    "Calcium Oxide",
+    "Calcium Sulfate",
+    "Carbon Dioxide",
+    "Carbon Monoxide",
+    "Chloroform",
+    "Chlorophyll",
+    "Cholesterol",
+    "Citric Acid",
+    "Cocaine",
+    "Cytosine",
+    "DDT",
+    "DEET",
+    "R-12",
+    "Dopamine",
+    "Adrenaline",
+    "Ethane",
+    "Ethylene",
+    "Ether",
+    "Ethanol",
+    "Ethylenediaminetetraacetic Acid",
+    "Fluoxetine",
+    "Formaldehyde",
+    "Formic Acid",
+    "Glucose",
+    "Glycerol",
+    "Guanine",
+    "Hydrochloric Acid",
+    "Hydrogen Peroxide",
+    "Hydrogen Sulfide",
+    "Ibuprofen",
+    "Indigo",
+    "Insulin",
+    "Iron(III) Oxide",
+    "Isooctane",
+    "Isoprene",
+    "l-Dopa",
+    "Methane",
+    "Methyl Alcohol",
+    "Methylphenidate",
+    "Monosodium Glutamate",
+    "Morphine",
+    "Naphthalene",
+    "Nicotine",
+    "Nitric Acid",
+    "Nitric Oxide",
+    "Nitrogen Dioxide",
+    "Nitrous Oxide",
+    "Nitroglycerin",
+    "Norethindrone",
+    "Penicillin",
+    "Phenol",
+    "Phosphoric Acid",
+    "Piperine",
+    "Potassium Carbonate",
+    "Potassium Nitrate",
+    "Propane",
+    "Propylene",
+    "Quinine",
+    "Saccharin",
+    "Silicon Dioxide",
+    "Sodium Bicarbonate",
+    "Sodium Carbonate",
+    "Sodium Chloride",
+    "Sodium Hydroxide",
+    "Sodium Hypochlorite",
+    "Strychnine",
+    "Styrene",
+    "Sucrose",
+    "Sulfuric Acid",
+    "Tetrafluoroethylene",
+    "Tetrahydrocannabinol",
+    "Thymine",
+    "Trinitrotoluene",
+    "Toluene",
+    "Triuranium Octaoxide",
+    "Uracil",
+    "Urea",
+    "Vanillin",
+    "Vinyl Chloride",
+    "Water",
+    "Xylene"
+]

molecule_test_set/get_data_generate_identifiers.py

@@ -0,0 +1,35 @@
+
+import json
+import os
+from moleculeresolver import MoleculeResolver
+from rdkit import Chem
+
+with open('benchmark_molecule_names.json', 'r') as f:
+    benchmark_molecule_names = json.load(f)
+
+if not os.path.exists('benchmark_component_molecules.json'):
+
+    benchmark_component_molecules = {}
+    with MoleculeResolver(available_service_API_keys={"chemeo": 'YOUR_KEY'}, molecule_cache_db_path='molecule_cache.db') as mr:
+        mr._available_services.remove('cts')
+        temp = mr.find_multiple_molecules_parallelized(benchmark_molecule_names, [['name']] * len(benchmark_molecule_names))
+
+        for name, molecule in zip(benchmark_molecule_names, temp, strict=True):
+            molecule.found_molecules = []
+            molecule = molecule.__dict__
+            mol = Chem.MolFromSmiles(molecule['SMILES'])
+            pubchem_cid = [v.strip() for v in molecule['additional_information'].split(';') if 'pubchem' in v]
+            if pubchem_cid:
+                pubchem_cid = int(pubchem_cid[0].split(':')[-1])
+            else:
+                pubchem_cid = None
+
+            molecule['pubchem_cid'] = pubchem_cid
+            molecule['formula'] = Chem.rdMolDescriptors.CalcMolFormula(mol)
+            molecule['hill_formula'] = mr.to_hill_formula(mol)
+            molecule['inchi'] = Chem.MolToInchi(mol)
+            molecule['inchikey'] = Chem.InchiToInchiKey(molecule['inchi'])
+            benchmark_component_molecules[name] = molecule
+
+    with open('benchmark_component_molecules.json', 'w') as f:
+        json.dump(benchmark_component_molecules, f, indent=4)