{"id":13573413,"url":"https://github.com/benb111/awesome-small-molecule-ml","last_synced_at":"2025-04-04T12:30:57.596Z","repository":{"id":39568703,"uuid":"440886380","full_name":"benb111/awesome-small-molecule-ml","owner":"benb111","description":"A curated list of resources for machine learning for small-molecule drug discovery","archived":false,"fork":false,"pushed_at":"2023-11-25T15:02:21.000Z","size":104,"stargazers_count":176,"open_issues_count":1,"forks_count":27,"subscribers_count":16,"default_branch":"main","last_synced_at":"2024-05-19T18:18:56.401Z","etag":null,"topics":["awesome","awesome-list","bioinformatics","cheminformatics","drug-discovery","machine-learning"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"cc0-1.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/benb111.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2021-12-22T14:33:49.000Z","updated_at":"2024-05-07T18:48:24.000Z","dependencies_parsed_at":"2024-01-03T07:01:20.167Z","dependency_job_id":null,"html_url":"https://github.com/benb111/awesome-small-molecule-ml","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/benb111%2Fawesome-small-molecule-ml","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/benb111%2Fawesome-small-molecule-ml/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/benb111%2Fawesome-small-molecule-ml/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/benb111%2Fawesome-small-molecule-ml/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/benb111","download_url":"https://codeload.github.com/benb111/awesome-small-molecule-ml/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247179506,"owners_count":20897054,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["awesome","awesome-list","bioinformatics","cheminformatics","drug-discovery","machine-learning"],"created_at":"2024-08-01T15:00:34.608Z","updated_at":"2025-04-04T12:30:52.588Z","avatar_url":"https://github.com/benb111.png","language":null,"funding_links":[],"categories":["See Also","Uncategorized","Other Lists","Related awesome lists"],"sub_categories":["Uncategorized","TeX Lists","Force Fields","Books","De novo molecular structure elucidation from MS/MS spectra \u003ca id=\"de-novo-molecular-structure-elucidation-from-msms-spectra\"\u003e\u003c/a\u003e"],"readme":"# Awesome Small Molecule Machine Learning [![Awesome](https://awesome.re/badge.svg)](https://awesome.re)\n\nA curated list of awesome papers, data sets, frameworks, packages, blogs, and other resources related to machine learning for small-molecule drug discovery. Please [contribute](CONTRIBUTING.md)!\n\n\n## Contents\n\n* [Papers](#papers)\n    * [Survey papers and books](#papers-surveys)\n    * [Representation, transfer, and few-shot learning](#papers-representation)\n    * [Generative algorithms](#papers-generative-algorithms)\n    * [Hit finding and potency prediciton](#papers-hit-finding)\n    * [ADME and toxicity prediction](#papers-adme-tox)\n    * [Synthetic accessability and retrosynthetic planning](#papers-synthetic-accessibility)\n    * [DNA-encoded libraries (DELs)](#dels)\n    * [Visualization and interpretability](#papers-viz)\n    * [MS/MS prediction](#papers-msms)\n* [Data sets](#data-sets)\n* [Frameworks, Libraries, and Software Tools](#frameworks)\n* [Blogs](#blogs)\n* [Twitter](#twitter)\n* [Related lists](#related-lists)\n\n\n## Papers\n\n\u003ca id=\"papers-surveys\"\u003e\u003c/a\u003e\n### Survey papers and books\n\n* Walters and Barzilay, 2021. [Critical assessment of AI in drug discovery](https://doi.org/10.1080/17460441.2021.1915982).\n* White, 2021. [Deep Learning for Molecules and Materials](https://dmol.pub/).\n* Coley, 2020. [Defining and Exploring Chemical Spaces](https://dspace.mit.edu/handle/1721.1/131238).\n* Chuang et al, 2020. [Learning Molecular Representations for Medicinal Chemistry](https://pubs.acs.org/doi/10.1021/acs.jmedchem.0c00385).\n* Walters and Barzilay, 2020. [Applications of Deep Learning in Molecule Generation and Molecular Property Prediction](https://pubs.acs.org/doi/10.1021/acs.accounts.0c00699).\n* Cai et al, 2020. [Transfer Learning for Drug Discovery](https://doi.org/10.1021/acs.jmedchem.9b02147).\n\n\n\u003ca id=\"papers-representation\"\u003e\u003c/a\u003e\n### Representation, transfer learning, and few-shot learning\n\n* Krenn et al, 2022. [SELFIES and the future of molecular string representations](https://arxiv.org/abs/2204.00056).\n* Wang et al, 2022. [Molecular Contrastive Learning of Representations via Graph Neural Networks](https://arxiv.org/pdf/2102.10056.pdf). [[Code](https://github.com/yuyangw/MolCLR)]\n* Ahmad et al, 2021. [ChemBERTa-2: Towards Chemical Foundation Models](https://cloud.ml.jku.at/s/dZ7CwqBkHX97C6S). [[Code](https://github.com/seyonechithrananda/bert-loves-chemistry)]\n* Satorras et al, 2021. [E(n) Equivariant Graph Neural Networks](https://arxiv.org/abs/2102.09844). [[Code](https://github.com/vgsatorras/egnn)]\n* Stanley et al, 2021. [FS-Mol: A Few-Shot Learning Dataset of Molecules](https://openreview.net/forum?id=701FtuyLlAd). [[Code](https://github.com/microsoft/FS-Mol)]\n* Townshend et al, 2021. [ATOM3D: Tasks On Molecules in Three Dimensions](https://arxiv.org/abs/2012.04035).\n* Xue et al, 2021. [X-MOL: large-scale pre-training for molecular understanding and diverse molecular analysis](https://www.biorxiv.org/content/10.1101/2020.12.23.424259v2.full). [[Code](https://github.com/bm2-lab/X-MOL)]\n* Ying et al, 2021. [Do Transformers Really Perform Bad for Graph Representation? (Graphormer paper)](https://arxiv.org/abs/2106.05234). [[Code](https://github.com/microsoft/Graphormer)]\n* Chuang and Keiser, 2020. [Attention-Based Learning on Molecular Ensembles](https://arxiv.org/abs/2011.12820).\n* Li and Fourches, 2020. [Inductive transfer learning for molecular activity prediction: Next-Gen QSAR Models with MolPMoFiT](https://jcheminf.biomedcentral.com/articles/10.1186/s13321-020-00430-x). [[Code](https://github.com/XinhaoLi74/MolPMoFiT)]\n* Maziarka et al, 2020. [Molecule Attention Transformer](https://arxiv.org/pdf/2002.08264.pdf). [[Code](https://github.com/ardigen/MAT)]\n* Nguyen et al., 2020. [Meta-Learning GNN Initializations for Low-Resource Molecular Property Prediction\n](https://arxiv.org/pdf/2003.05996.pdf) [[Code](https://github.com/GSK-AI/meta-learning-qsar)]\n* Rong et al., 2020. [Self-Supervised Graph Transformer on Large-Scale Molecular Data (GROVER paper)](https://arxiv.org/abs/2007.02835). [[Code](https://github.com/tencent-ailab/grover)]\n* Hu et al, 2019. [Strategies for Pre-training Graph Neural Networks](https://arxiv.org/abs/1905.12265). [[Code](https://github.com/snap-stanford/pretrain-gnns)]\n* Yang et al, 2019. [Analyzing Learned Molecular Representations for Property Prediction (Chemprop)](https://pubs.acs.org/doi/10.1021/acs.jcim.9b00237). [[Code](https://github.com/chemprop/chemprop)]\n* Feinberg et al, 2018. [PotentialNet for Molecular Property Prediction](https://pubs.acs.org/doi/abs/10.1021/acscentsci.8b00507).\n* Altae-Tran et al, 2017. [Low Data Drug Discovery with One-Shot Learning](https://pubs.acs.org/doi/abs/10.1021/acscentsci.6b00367).\n\n\n\u003ca id=\"papers-generative-algorithms\"\u003e\u003c/a\u003e\n### Generative algorithms\n\n* Bengio et al, 2021. [Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation](https://arxiv.org/abs/2106.04399). [[Code](https://github.com/bengioe/gflownet)]\n* Berenger and Tsuda, 2021. [Molecular generation by Fast Assembly of (Deep)SMILES fragments](https://jcheminf.biomedcentral.com/articles/10.1186/s13321-021-00566-4). [[Code](https://github.com/UnixJunkie/FASMIFRA)]\n* Gao et al, 2021. [Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular Design](https://arxiv.org/abs/2110.06389). [[Code](https://github.com/wenhao-gao/SynNet)]\n* Takeuchi et al, 2021. [R-group replacement database for medicinal chemistry](https://www.future-science.com/doi/10.2144/fsoa-2021-0062).\n* Imrie et al, 2020. [Deep Generative Models for 3D Linker Design](https://pubs.acs.org/doi/10.1021/acs.jcim.9b01120). [[Code](https://github.com/oxpig/DeLinker)]\n* Jin et al, 2020. [Hierarchical Generation of Molecular Graphs using Structural Motifs](https://arxiv.org/abs/2002.03230). [[Code](https://github.com/wengong-jin/hgraph2graph)]\n* Polishchuk, 2020. [CReM: chemically reasonable mutations framework for structure generation](https://jcheminf.biomedcentral.com/articles/10.1186/s13321-020-00431-w). [[Code](https://github.com/DrrDom/crem)]\n* Brown, 2019. [GuacaMol: Benchmarking Models for de Novo Molecular Design](https://doi.org/10.1021/acs.jcim.8b00839). [[Code](https://github.com/BenevolentAI/guacamol)]\n* Popova et al, 2019. [MolecularRNN: Generating realistic molecular graphs with optimized properties\n](https://arxiv.org/abs/1905.13372).\n* You et al, 2019. [Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation](https://arxiv.org/abs/1806.02473). [[Code](https://github.com/bowenliu16/rl_graph_generation)]\n* Zhou et al, 2019. [Optimization of Molecules via Deep Reinforcement Learning](https://doi.org/10.1038/s41598-019-47148-x). [[Code (official version)](https://github.com/google-research/google-research/tree/master/mol_dqn)] [[PyTorch implementation](https://github.com/aksub99/MolDQN-pytorch)]\n* Jin et al, 2018. [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://arxiv.org/abs/1802.04364). [[Code](https://github.com/wengong-jin/icml18-jtnn)]\n* Merk et al, 2018. [De Novo Design of Bioactive Small Molecules by Artificial Intelligence](https://pubmed.ncbi.nlm.nih.gov/29319225/).\n\n\n\u003ca id=\"papers-hit-finding\"\u003e\u003c/a\u003e\n### Hit finding and potency prediciton\n\n* Stärk et al, 2022. [EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction](https://arxiv.org/abs/2202.05146). [[Code](https://github.com/HannesStark/EquiBind)]\n* Bender et al, 2021. [A practical guide to large-scale docking](https://www.nature.com/articles/s41596-021-00597-z).\n* García-Ortegón et al, 2021. [DOCKSTRING: easy molecular docking yields better benchmarks for ligand design](https://arxiv.org/abs/2110.15486). [[Code](https://github.com/dockstring/dockstring)] [[Data](https://figshare.com/s/95f2fed733dec170b998)]\n* Graff et al, 2021. [Accelerating high-throughput virtual screening through molecular pool-based active learning](https://pubs.rsc.org/en/content/articlelanding/2021/sc/d0sc06805e). [[Code](https://github.com/coleygroup/molpal)]\n* Gentile et al, 2020. [Deep Docking: A Deep Learning Platform for Augmentation of Structure Based Drug Discovery](https://pubs.acs.org/doi/10.1021/acscentsci.0c00229). [[Code](https://github.com/jamesgleave/Deep-Docking-NonAutomated)]\n* Cáceres et al, 2020. [Adding Stochastic Negative Examples into Machine Learning Improves Molecular Bioactivity Prediction](https://pubs.acs.org/doi/10.1021/acs.jcim.0c00565).\n* Lin et al, 2019. [Ultra-large library docking for discovering new chemotypes](https://www.nature.com/articles/s41586-019-0917-9).\n\n\n\u003ca id=\"papers-adme-tox\"\u003e\u003c/a\u003e\n### ADME and toxicity prediction\n\n* Fradkin et al, 2022. [A Graph Neural Network Approach to Molecule Carcinogenicity Prediction](https://www.biorxiv.org/content/10.1101/2021.11.10.468094v1.abstract).\n* Karim et al, 2021. [CardioTox net: a robust predictor for hERG channel blockade based on deep learning meta-feature ensembles](https://jcheminf.biomedcentral.com/articles/10.1186/s13321-021-00541-z). [[Code](https://github.com/Abdulk084/CardioTox)]\n* Siramshetty et al, 2021. [Validating ADME QSAR Models Using Marketed Drugs](https://journals.sagepub.com/doi/10.1177/24725552211017520).\n* Göller et al, 2020. [Bayer’s in silico ADMET platform: a journey of machine learning over the past two decades](https://doi.org/10.1016/j.drudis.2020.07.001).\n* Ryu et al, 2020. [DeepHIT: a deep learning framework for prediction of hERG-induced cardiotoxicity](https://doi.org/10.1093/bioinformatics/btaa075). [[Code](https://bitbucket.org/krictai/deephit/src/master/)]\n* Cai et al, 2019. [Deep Learning-Based Prediction of Drug-Induced Cardiotoxicity](https://pubs.acs.org/doi/10.1021/acs.jcim.8b00769). [[Code](https://github.com/ChengF-Lab/deephERG)]\n* Ogura et al, 2019. [Support Vector Machine model for hERG inhibitory activities based on the integrated hERG database using descriptor selection by NSGA-II](https://www.nature.com/articles/s41598-019-47536-3). [[Data](https://drugdesign.riken.jp/hERGdb/)]\n* Lombardo et al, 2018. [In Silico Absorption, Distribution, Metabolism, Excretion, and Pharmacokinetics (ADME-PK): Utility and Best Practices](https://pubs.acs.org/doi/10.1021/acs.jmedchem.7b00487).\n\n\n\u003ca id=\"papers-synthetic-accessibility\"\u003e\u003c/a\u003e\n### Synthetic accessability and retrosynthetic planning\n\n* Fortunato et al, 2020. [Data augmentation and pretraining for template-based retrosynthetic prediction in computer-aided synthesis planning](https://pubs.acs.org/doi/10.1021/acs.jcim.0c00403).\n* Koch et al, 2020. [Reinforcement Learning for Bioretrosynthesis](https://pubs.acs.org/doi/10.1021/acssynbio.9b00447).\n* Somnath et al, 2020. [Learning Graph Models for Retrosynthesis Prediction](https://arxiv.org/abs/2006.07038).\n* Dai et al, 2019. [Retrosynthesis Prediction with Conditional Graph Logic Network](https://arxiv.org/abs/2001.01408). [[Code](https://github.com/Hanjun-Dai/GLN)]\n* Coley et al, 2018. [SCScore: Synthetic Complexity Learned from a Reaction Corpus](https://pubs.acs.org/doi/10.1021/acs.jcim.7b00622). [[Code](https://github.com/connorcoley/scscore)] [[DeepChem implementation](https://github.com/deepchem/deepchem/blob/master/deepchem/models/scscore.py)]\n\n\n\u003ca id=\"dels\"\u003e\u003c/a\u003e\n### DNA-encoded libraries (DELs)\n* Lim et al, 2022. [Machine Learning on DNA-Encoded Library Count Data Using an Uncertainty-Aware Probabilistic Loss Function](https://pubs.acs.org/doi/10.1021/acs.jcim.2c00041). [[Code](https://github.com/coleygroup/del_qsar)]\n* McCloskey et al, 2020. [Machine Learning on DNA-Encoded Libraries: A New Paradigm for Hit Finding](https://pubs.acs.org/doi/10.1021/acs.jmedchem.0c00452).\n\n\u003ca id=\"papers-viz\"\u003e\u003c/a\u003e\n### Visualization and interpretability\n\n* Humer et al, 2021. [ChemInformatics Model Explorer (CIME): Exploratory analysis of chemical model explanations](https://chemrxiv.org/engage/chemrxiv/article-details/61a6579f568d33caaa4bff69). [[Code](https://github.com/jku-vds-lab/cime)]\n* Matveieva and Polishchuk, 2021. [Benchmarks for interpretation of QSAR models](https://jcheminf.biomedcentral.com/articles/10.1186/s13321-021-00519-x). [[Code](https://github.com/ci-lab-cz/ibenchmark)]\n* Atsushi et al, 2019. [Integrating the Structure–Activity Relationship Matrix Method with Molecular Grid Maps and Activity Landscape Models for Medicinal Chemistry Applications](https://pubs.acs.org/doi/10.1021/acsomega.9b00595).\n* Naveja and Medina-Franco, 2019. [Finding Constellations in Chemical Space Through Core Analysis](https://www.frontiersin.org/articles/10.3389/fchem.2019.00510/full).\n\n\u003ca id=\"papers-msms\"\u003e\u003c/a\u003e\n### MS/MS prediction\n* Young et al, 2023. [MassFormer: Tandem Mass Spectrum Prediction for Small Molecules using Graph Transformers](https://arxiv.org/abs/2111.04824). [[Code](https://github.com/Roestlab/massformer)] \n* Goldman el al, 2023. [Prefix-Tree Decoding for Predicting Mass Spectra from Molecules](https://arxiv.org/abs/2303.06470). [[Code](https://github.com/samgoldman97/ms-pred)] \n* Hong et al, 2023. [3DMolMS: prediction of tandem mass spectra from 3D molecular conformations](https://academic.oup.com/bioinformatics/article/39/6/btad354/7186501). [[Code](https://github.com/JosieHong/3DMolMS)] \n* Wang et al, 2021. [CFM-ID 4.0: More Accurate ESI-MS/MS Spectral Prediction and Compound Identification](https://pubs.acs.org/doi/10.1021/acs.analchem.1c01465). \n* Wei et al, 2019. [Rapid Prediction of Electron–Ionization Mass Spectrometry Using Neural Networks](https://pubs.acs.org/doi/10.1021/acscentsci.9b00085). [[Code](https://github.com/brain-research/deep-molecular-massspec)] \n\n## Data sets\n* [ADME@NCATS](https://opendata.ncats.nih.gov/adme)\n* [AMED Cardiotoxicity Database](https://drugdesign.riken.jp/hERGdb/)\n* [BindingDB](https://www.bindingdb.org/bind/index.jsp)\n* [ChEMBL](https://www.ebi.ac.uk/chembl/)\n* [DrugBank](https://go.drugbank.com)\n* [DrugMatrix](https://ntp.niehs.nih.gov/data/drugmatrix/)\n* [Enamine Real database](https://enamine.net/compound-collections/real-compounds/real-database)\n* [hERG Central](https://www.cambridgemedchemconsulting.com/news/index_files/81f15972727e1fe70ae7f37514bdab58-362.html)\n* [MoleculeNet](https://moleculenet.org/)\n* [MONA: DB of Mass spec + other readouts](https://mona.fiehnlab.ucdavis.edu/)\n* [NPASS database of natural products](http://bidd.group/NPASS/)\n* [PubChem](https://pubchem.ncbi.nlm.nih.gov/)\n* [The Open Reaction Database](https://docs.open-reaction-database.org/en/latest/)\n* [Therapeutic Data Commons](https://tdcommons.ai/)\n* [Zinc](https://pubs.acs.org/doi/10.1021/acs.jcim.0c00675)\n\n\n\n\u003ca id=\"frameworks\"\u003e\u003c/a\u003e\n## Frameworks, Libraries, and Software Tools\n* [AutoDock Vina](https://autodock-vina.readthedocs.io/en/latest/index.html)\n* [BioPandas](http://rasbt.github.io/biopandas/)\n* [Chemprop](https://github.com/chemprop/chemprop)\n* [DeepChem](https://deepchem.io/) [[Tutorials](https://github.com/deepchem/deepchem/tree/master/examples/tutorials)]\n* [Open Babel](http://openbabel.org/wiki/Main_Page)\n* [pdb-tools](http://www.bonvinlab.org/pdb-tools/)\n* [PyTorch Geometric](https://pytorch-geometric.readthedocs.io/en/latest/)\n* [rd_filters](https://github.com/PatWalters/rd_filters)\n* [Small-World Search](https://sw.docking.org/search.html)\n* [TorchDrug](https://torchdrug.ai/)\n\n\n## Blogs\n* [Hyperparameter Space](http://hyperparameter.space/)\n* [Is Life Worth Living](https://iwatobipen.wordpress.com/)\n* [Practical Cheminformatics](http://practicalcheminformatics.blogspot.com/)\n* [RDKit Blog](https://greglandrum.github.io/rdkit-blog/)\n\n\n## Twitter\n* [Regina Barzilay](https://twitter.com/BarzilayRegina)\n* [Bob the Grumpy Med Chemist](https://twitter.com/med_chemist)\n* [John Chodera](https://twitter.com/jchodera)\n* [Connor W. Coley](https://twitter.com/cwcoley)\n* [Greg Landrum](https://twitter.com/dr_greg_landrum)\n* [pen(Taka)](https://twitter.com/iwatobipen)\n* [Bharath Ramsundar](https://twitter.com/rbhar90)\n* [Marwin Segler](https://twitter.com/marwinsegler)\n* [Patrick Walters](https://twitter.com/wpwalters)\n\n\n## Related lists\n* [Awesome Cheminformatics](https://github.com/hsiaoyi0504/awesome-cheminformatics)\n* [Awesome Drug Discovery](https://github.com/xnuohz/awesome-drug-discovery)\n* [Awesome Explainable Graph Reasoning](https://github.com/AstraZeneca/awesome-explainable-graph-reasoning)\n* [Awesome Python Chemistry](https://github.com/lmmentel/awesome-python-chemistry)\n* [deeplearning-biology](https://github.com/hussius/deeplearning-biology#chemoinformatics-and-drug-discovery-)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbenb111%2Fawesome-small-molecule-ml","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbenb111%2Fawesome-small-molecule-ml","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbenb111%2Fawesome-small-molecule-ml/lists"}