Awesome Drug Discovery

Computational methods for identifying and developing new drug candidates.

Drug discovery is the process by which new candidate medications are identified, designed, and developed using experimental, computational, and informational techniques to address complex challenges in biology, chemistry, and medicine. — Wikipedia

Contents

• Databases and Chemical Libraries
  • General Compound Libraries
  • Natural Product Libraries
  • Bioactivity Databases
• Target and Protein Data
  • Protein Structures
  • Binding Site and Pocket Detection
  • Protein Engineering and Modeling
• Network Pharmacology
• Ligand Design and Optimization
  • Pharmacophore Modeling
  • QSAR and Descriptor Tools
  • Descriptor and Featurization Tools
  • Molecular Property Prediction
  • Fragment-Based Drug Design
• Virtual Screening and Docking
• Interaction Analysis and Visualization
• Molecular Dynamics and Simulation
  • Engines
  • Topology and Force Field Tools
  • Analysis Tools
• Synthesis and Retrosynthesis Planning
• Specialized Modalities
  • PROTACs and Ternary Complexes
  • Peptide Design
• Machine Learning and AI
  • Chemistry-focused ML Frameworks
  • Pretrained Models
  • Molecule Standardization
• Utility and Workflow Tools
• Learning Resources
  • Free Courses
  • Blogs
  • Instructional Notebooks
• Labs and Research Groups

Databases and Chemical Libraries

General Compound Libraries

• DrugBank - Comprehensive data on approved and investigational drugs.
• ZINC - Free compounds for screening.
• ChemSpider - Chemical structures and data.
• DrugSpaceX - Chemical and biological spaces.
• Mcule - Virtual screening platform with purchasable compounds.
• Otava Chemicals - Screening compounds and building blocks.
• Vitas-M Laboratory - Chemical libraries for HTS and lead discovery.
• Eximed - 60k+ compounds for virtual screening.
• OTAVA NP-like Library - Screening compounds for prompt delivery.
• Ambinter - 40M+ compounds for HTS, building blocks, and a wide selection of fragments and natural products.
• VAST Chemical Space - 4.6 billion synthetically accessible compounds for virtual screening and hit expansion.

Natural Product Libraries

• ZINC15 Natural Products - 200k+ natural compounds.
• COCONUT - 400k+ natural products.
• LOTUS - Annotated molecular data with sourcing organisms.
• NPASS - 94k activity-species links.
• ANPDB - 27k+ African medicinal plant compounds.
• SANCDB - Natural compounds from the plant and marine life in and around South Africa.
• CMNPD - 31k+ marine natural products.
• The Natural Products Atlas - An open-access database for microbial natural products structures and metadata.
• BIAdb - A database for benzylisoquinoline alkaloids.
• IMPPAT - Phytochemicals from Indian medicinal plants.
• NP-MRD - 280k+ NMR-based NP studies.
• IBS Natural Compounds - 60k+ compounds.
• PhytoHub - Dietary phytochemicals and metabolites.
• Dr. Duke's Phytochemical DB - Plant compounds and uses.
• CyanoMetDB - Over 3,000 cyanobacterial metabolites.
• Seaweed Metabolite DB - Marine algae compounds.
• FooDB - A comprehensive resource on food constituents.

Bioactivity Databases

• ChEMBL - Bioactivity and ADMET data.
• SureChEMBL - Patent chemistry search.
• BindingDB - Binding affinities for biomolecules.
• PubChem - Structures, properties, and bioassays.
• PDBbind - Protein-ligand affinity data.
• BRENDA - Enzyme properties and functions.
• ExCAPE-DB - A large-scale chemogenomics database.
• Therapeutics Data Commons - AI/ML-ready datasets and learning tasks for therapeutics.
• Therapeutic Target Database (TTD) - Drug targets with linked diseases and compounds.
• Aircheck Datasets - Curated DEL datasets for AI‑driven drug discovery, enabling benchmarking and model development.
• canSAR - Integrative cancer knowledgebase aggregating molecular, genetic, and structural data for drug target identification.
• CDD Vault - Hosted informatics platform providing public access to aggregated drug discovery data.
• ClinicalTrials.gov - Comprehensive registry and results database for clinical studies involving human participants.
• CovalentInDB (CIDB) - A comprehensive database dedicated to covalent inhibitors, targets, and experimental data.
• HSADab - Database of binding thermodynamics, structures, and docking data for human serum albumin.

Target and Protein Data

Protein Structures

• RCSB PDB - Repository for macromolecular structures.
• PDBe - European counterpart to RCSB PDB.
• OPM - Orientation of proteins in membranes.
• UniProt - Protein sequences, structures, and functions.
• InterPro - Protein classification and domain prediction.
• AlphaFold DB - Predicted structures from AlphaFold.
• Proteopedia - Interactive protein visualizations.
• Pfam - Collection of protein families represented by multiple sequence alignments and hidden Markov models.
• Human Protein Atlas - Spatial mapping of all human proteins across tissues and cells.

Binding Site and Pocket Detection

• PrankWeb - Pocket prediction and analysis.
• CASTp - Pocket geometry and volume analysis.
• CavityPlus - Pocket detection and druggability.
• CaverWeb - Tunnel and channel detection.
• PASSer - Allosteric site prediction.
• Pocket Binding Site Prediction - ML-based tool for predicting binding pockets and active sites on protein structures.
• Protplex - Semantic search engine for the PDB enabling multidimensional queries on structures and binding pockets.

Protein Engineering and Modeling

• DynaMut - Predicts mutation-induced stability changes.
• SWISS-MODEL - A fully automated protein structure homology-modeling server.
• MODELLER - A software for homology or comparative modeling of protein structures.
• PDBFixer - Repairs PDB files by adding missing atoms, residues, and hydrogens for MD simulations.
• OpenFold Portal - Cloud portal for predicting 3D protein structures using the open-source OpenFold model.
• RFdiffusion - Open-source method for de novo protein design using structure-guided diffusion models.
• Melodia - Python library for analyzing and comparing protein structure shapes via differential geometry.

Network Pharmacology

• GeneCards - Human gene database with genomic, proteomic, and clinical data.
• SwissTargetPrediction - Predicts targets of small molecules via similarity-based screening.
• STITCH - Integrates chemical–protein interactions across organisms.
• STRING - A database of known and predicted protein–protein interactions.
• Cytoscape - Visualizes and analyzes molecular interaction networks.
• Open Targets - Integrative platform for therapeutic target identification.
• OmicsNet - Builds multi-omics networks for systems biology.
• DisGeNET - Curated gene–disease associations for network analysis.
• PharmMapper - Identifies potential targets via reverse pharmacophore mapping.
• ChEA3 - Transcription factor enrichment tool integrating ChIP-seq, co-expression, and perturbation datasets.
• miRDB - Predicts functional microRNA targets using machine learning and high-throughput data.
• Venny 2.1 - A web tool for comparing lists using Venn diagrams.
• OMIM - Authoritative compendium of human genes and their relationship to genetic variation and phenotypic expression.
• PharmGKB - Pharmacogenomics resource exploring genetic variation impacts on drug response and molecular targets.
• Polypharmacology Browser PPB3 - Deep learning tool predicting off-target effects and polypharmacology for bioactive molecules.
• Drug-Target Interaction Explorer - Dashboard for exploring and visualizing drug-target interaction networks.

Ligand Design and Optimization

Pharmacophore Modeling

• Pharmit - Interactive pharmacophore modeling.

QSAR and Descriptor Tools

• QSAR Toolbox - Hazard assessment and QSAR.
• OCHEM - QSAR model building and prediction.
• ChemMaster - QSAR and cheminformatics suite.
• 3D-QSAR - Web resources for 3D QSAR modeling.
• QSAR-Co - Robust multitarget QSAR modeling.
• QSPRpred - Open-source Python toolkit for building, reproducing, and deploying QSAR/QSPR models.
• DataWarrior - Free software for chemical analysis, QSAR, and visualization.
• KNIME - Workflow platform for cheminformatics and ML integration.
• pyADA - Assesses the applicability domain of molecular fingerprints via similarity-based thresholds for QSAR validation.

Descriptor and Featurization Tools

• RDKit - Open-source cheminformatics toolkit with descriptor, fingerprint, and molecular manipulation support.
• PaDEL-Descriptor - Java tool for calculating molecular descriptors and fingerprints.
• Mordred - Python library with 1800+ molecular descriptors.
• CDK - Java cheminformatics library with descriptor calculators.
• alvaDesc - Commercial software for molecular descriptors and fingerprints.
• MolFeat - Python package for molecular featurization and embeddings.
• Dragon - Commercial molecular descriptor calculator (widely cited).
• ChemDescriptor - Open-source tool for generating chemical descriptors and fingerprints, supporting cheminformatics workflows.

Molecular Property Prediction

• SwissADME - Drug-likeness and PK.
• pkCSM - ADMET property prediction.
• DeepPK - DL-based pharmacokinetics.
• admetSAR 2.0 - Comprehensive ADMET.
• ADMETlab 2.0 - PK, toxicity and drug-likeness.
• ProTox-II - Toxicity predictions.
• PreADMET - PK property predictions.
• FAF-Drugs - ADMET filtering.
• Admetboost - ML-based ADMET prediction.
• MetaPredict - Predict molecular properties from structure.
• ADMET-AI - A web-based tool for predicting ADMET properties based on Chemprop-RDKit models trained on datasets from the TDC.

Fragment-Based Drug Design

• SwissSidechain - Fragment and linker library for small molecule design.
• BoBER - Bioisosteric replacements for lead optimization.
• FragBuilder - Python API for building peptide-like and small molecule fragments.
• SeeSAR - Fragment growing and linking software (free academic version).
• Enamine Fragment Libraries - Large curated collection of diverse fragments for FBDD.
• FragmentFinder - Computational tool for identifying and matching structural fragments in drug discovery workflows.

Virtual Screening and Docking

• OpenBabel - Format conversion and ligand prep.
• Meeko - Prepares ligands/receptors for AutoDock by assigning partial charges and atom types.
• MolScrub - Enumerates tautomers, pH states, and conformers for docking and structure-based modeling.
• MGLTools - Structure preparation.
• AutoDockTools - AutoDock GUI.
• AutoDock Vina - Popular docking software.
• AutoDock-GPU - GPU-accelerated version of AutoDock for faster ligand-receptor docking.
• DiffDock - Deep learning-based docking tool that predicts ligand poses directly from protein structures using diffusion models.
• EasyDockVina2 - Vina automation.
• Webina - Web-based Vina.
• Smina - Vina fork with extra features.
• Gnina - CNN-scoring docking.
• EasyDock - Vina/Smina pipeline.
• HADDOCK - Flexible docking suite.
• PandaDock - Python docking tool.
• ZDOCK - Protein-protein docking.
• ClusPro - Protein-protein docking server.
• pyDockWEB - Electrostatics-based docking.
• SwissDock - Web docking for beginners.
• MzDOCK - GUI docking pipeline.
• Uni-Mol Docking V2 - AI-assisted docking.
• Vina on Colab - Run Vina in Google Colab.
• MetalDock - A Python-based tool designed for the docking of metal-organic compounds to proteins, DNA, or other biomolecules.
• Chopdock - Molecular docking and cheminformatics tool for structural interaction analysis and fragment-based design.
• Boltzmann Maps - Web application for structure-guided drug design using pre-computed water and chemical fragment maps.

Interaction Analysis and Visualization

• PLIP - Protein-ligand interaction profiling.
• posecheck-fast - High-throughput docking pose validation with symmetry-corrected RMSD and lightweight distance and clash filters.
• GetContacts - Compute and visualize noncovalent interactions from structures and MD trajectories.
• LigPlot+ - 2D interaction diagrams.
• Discovery Studio Visualizer - Advanced visualization.
• PyMOL - Python-based molecular visualization software.
• UCSF ChimeraX - A molecular visualization program with emphasis on structural biology.
• Avogadro - Cross-platform molecular editor and visualizer featuring an extensible plugin system.
• xyzrender - CLI for producing publication-quality molecular graphics, GIFs, and SVGs from coordinate files.
• pymol-sifts - PyMOL plugin for integrating and visually mapping SIFTS structural and sequence data.

Molecular Dynamics and Simulation

Engines

• GROMACS - Fast, scalable MD engine optimized for biomolecular simulations and energy minimization.
• OpenMM - Flexible MD toolkit with GPU acceleration and Python bindings.
• LAMMPS - Classical MD simulator for materials science and soft matter.
• NAMD - Highly parallel MD engine tailored for large biomolecular systems.
• AMBER - Suite for biomolecular simulations and free energy calculations.
• Desmond - GPU-accelerated MD engine for high-performance simulations.

Topology and Force Field Tools

• CGenFF - CHARMM force field parametrization of drug-like molecules.
• SwissParam - Rapid generation of CHARMM-compatible parameters for small organic molecules.
• ATB - Automated topology builder and repository for classical force field parameters.
• CHARMM-GUI - Web-based interface for building complex biomolecular systems and generating MD input files.
• LigParGen - Automated OPLS-AA parameter generator for organic ligands.

Analysis Tools

• MD DaVis - Interactive visualization and analysis of MD trajectories.
• iMODS - Normal Mode Analysis toolkit using internal coordinates.
• MolAiCal - Web-based platform for binding free energy calculations using MM/PBSA and MM/GBSA methods.
• gmx_MMPBSA - Port of AMBER MMPBSA.py for GROMACS.
• VMD - Large biomolecular systems visualization and analysis using 3D graphics and scripting.
• Grace - 2D plotting tool for Unix-like systems with advanced graphing, fitting, and analysis features.
• CPPTRAJ - Fast, parallelizable trajectory analysis from AMBER.
• MDAnalysis - Open-source Python library for analyzing MD simulations.
• CABS-flex 3.0 - Web server for rapid simulation of protein and peptide structural flexibility using coarse-grained models.
• cmd-viewer - Tool for visualizing and analyzing MD simulation trajectories and structural data.
• Pharmacon - Open-source toolkit for molecular dynamics simulation analysis in medicinal chemistry.

Synthesis and Retrosynthesis Planning

• Spaya - AI-driven retrosynthesis engine with route ranking and synthetic feasibility scoring.
• AiZynthFinder - Monte Carlo tree search-based retrosynthesis using trained neural networks.
• ASKCOS - Synthesis route prediction with ML, developed by MIT.
• IBM RoboRXN - Automated reaction prediction using transformer models.
• MANIFOLD - Search engine for synthetically accessible molecules and building blocks.
• onepot.ai - AI-enabled molecular editor and synthesis planning platform with an encrypted structure environment.

Specialized Modalities

PROTACs and Ternary Complexes

• PROTAC-db - Curated database of PROTAC molecules, targets, and linkers for degrader design.
• PROsettaC - Structure-based modeling of ternary complexes for targeted protein degradation.

Peptide Design

• PepDraw - Peptide visualization with annotated physicochemical properties.
• PEP-SiteFinder - Predicts peptide-binding sites on protein structures using drug-like ligand mapping.
• PEP-FOLD3 - De novo peptide structure prediction framework.

Machine Learning and AI

Chemistry-focused ML Frameworks

• DeepChem - Open-source deep learning framework for chemistry and biology.
• scikit-mol - Open-source toolkit bridging RDKit and scikit-learn for molecular ML workflows.
• Chemprop - Directed message passing neural networks for molecular property prediction.
• ChemML - Machine learning and informatics suite for analyzing, mining, and modeling chemical and materials data.
• Oloren ChemEngine - Unified API for molecular property prediction with uncertainty quantification, interpretability, and model tuning.
• TorchDrug - A machine learning library for drug discovery with support for GNNs and molecular datasets.
• DGL-LifeSci - Graph deep learning toolkit for life sciences using the Deep Graph Library.
• iChem - Python cheminformatics package for molecular comparisons, fingerprints, and chemical data analysis.
• LigandForge - ML-based structure-guided de novo ligand generation and optimization for hit identification.

Pretrained Models

• MolBERT - Transformer-based molecular representation learning.
• ChemBERTa - Pretrained BERT-like models for molecules from SMILES.
• Chai-1 - Multi-modal foundation model for biomolecular structure prediction of proteins, nucleic acids, and ligands.
• ESM3 - Generative biology foundation model for designing novel proteins across sequence, structure, and function.
• ESMc - A family of open protein language foundation models for sequence generation and design.
• Uni-Mol - 3D molecular representation learning framework.
• Boltz-2 - A foundation model that jointly predicts structure and binding affinity, rivaling physics-based FEP methods in accuracy.
• Zatom - AI-driven generative chemistry platform for discovering and analyzing molecular structures.

Molecule Standardization

• MolVS - Molecule validation and standardization library based on RDKit.
• cleanmol - Python library for cleaning, standardizing, and preparing molecular structures for cheminformatics workflows.

Utility and Workflow Tools

• ProteinsPlus - A web-based platform designed to assist life scientists in analyzing and working with protein structures.
• OPSIN - Convert IUPAC names to chemical structures.
• OSRA - Extract chemical structures from images.
• ChemPlot - Chemical space visualization.
• ChemDB - Chemoinformatics portal with compound data and tools.
• Screening Explorer - Analyze screening datasets and hit distributions.
• spyrmsd - Python tool for symmetry-corrected RMSD calculations using graph isomorphism.
• NERDD - Curated drug discovery resources.
• LigBuilder3 - De novo ligand design.
• ChemMine Tools - Web-based cheminformatics toolkit for compound analysis.
• MayaChemTools - Perl/Python scripts for cheminformatics.
• Click2Drug - CADD software and databases directory.
• Galaxy Europe - Galaxy instance for cheminformatics.
• CADD Vault - CADD resources repository.
• HEDGEHOG - Stage-based evaluation pipeline for generative molecular design with filters, retrosynthesis checks, docking, pose validation, and reports.
• BioMoDes - Biomolecular structure prediction and modeling tools.
• PlayMolecule - Interactive molecular modeling and simulation platform.
• Ertl Molecular - Cheminformatics tools for medicinal chemists, including scaffold analysis, ring replacement, and property calculators.
• Datagrok - Environment for working with chemical data, covering full-range of tasks from data access to de novo design.
• AssayCurveFit - Web application for processing dose-response data and generating IC50/EC50 curve fits.
• AssayCurveFit (GitHub) - Source repository for IC50/EC50 calculation from biochemical assays.
• biopipelines - Modular Python framework for automated computational protein and ligand engineering workflows on SLURM clusters.
• CHEESE - AI-driven interactive tool for analyzing chemical spaces and optimizing hit compounds.
• chembl_webresource_client - Official Python client library for programmatic access to the ChEMBL database API.
• ChemIllusion MCP - Model Context Protocol server providing language models with tools for generating and analyzing molecular data.
• ComProScanner - Pipeline for automated large-scale profiling and screening of chemical compounds against protein targets.
• NAMI - Computational tool for clustering and evaluating differences across molecular datasets.
• Neurosnap - Web platform providing no-code interfaces to bioinformatics and ML tools including AlphaFold.
• PyChem-Pro - Pure-Python desktop application for molecular visualization, geometry optimization, and cheminformatics.
• rdkit-agent - Agent-first cheminformatics CLI powered by RDKit WASM for structure validation and format conversion.

Learning Resources

Free Courses

• TMP Chem Lectures - Recorded lectures from a leading cheminformatics summer school.
• Strasbourg Summer School in Chemoinformatics - Summer school lectures.
• BIGCHEM - Online course on big data applications in chemistry.
• Drug Discovery Course - Foundations of drug discovery and development.
• drugdesign.org - Free courses on drug design and cheminformatics.
• Learn CADD - An interactive, visual, first-principles guide to computer-aided drug design.
• Cheminformatics OLCC - Intercollegiate course on cheminformatics theory and coding.
• Python For Cheminformatics Docking - Python tutorials for molecular docking via RCSB.
• DDA CDD Workshop - Workshop on generative and computational drug design.
• MDTutorials - Step-by-step tutorials for MD simulations using GROMACS.
• Resources for Learning Bioinformatics - Curated collection of tutorials and materials for bioinformatics and computational biology.
• Synthesis Workshop - Open-access video podcast on advanced organic synthesis and medicinal chemistry.
• AI for Chemistry (ai4chem Book) - An open-access book and interactive guide to machine learning and AI in chemistry.
• AI for Chemistry Course - Lecture slides, Jupyter notebooks, and exercises for machine learning in chemistry.
• CCAS Training Materials - Training resources for computer-assisted synthesis tools, reaction modeling, and machine learning.
• ML in Chemistry (CHEM 542) - Rutgers University course materials covering machine learning applications in chemical sciences.

Blogs

• Practical Fragments - Insights into fragment-based drug discovery.
• Practical Cheminformatics - Tools and tips for cheminformatics workflows.
• Neovarsity - Deep-tech blog on cheminformatics and drug discovery applications.
• Cheminformania - Cheminformatics meets deep learning and molecular modeling.
• Daily Dose of Data Science - Digestible data science tutorials and concepts.
• Machine Learning Mastery - Practical ML guides for developers and scientists.
• Chem-Workflows - Jupyter-based chemistry workflows and tutorials.
• Structural Bioinformatics - Guide to structure-based drug design and protein modeling.
• McConnellsMedChem - Medicinal chemistry insights and commentary.
• DrugDiscovery.NET - AI-powered approaches to drug discovery.
• MacinChem - Computational chemistry tools for macOS users.
• Jeremy Monat - Cheminformatics research and academic resources.
• RDKit blog - A rich collection of tutorials, technical tips, and experimental insights from Greg Landrum.
• DeepMedChem - AI-powered insights, tool reviews, and workflows for modern drug discovery.
• The Data Chemist's Handbook - A curated handbook with guidelines, code snippets, and tools for data-driven chemistry.
• Awesome Learning Digital Chemistry - Curated compilation of resources for learning digital chemistry, including courses, tutorials, and books.
• CCAS Data sets, Tools, and Workflows - A repository of datasets and computational workflows for computer-assisted organic synthesis.

Instructional Notebooks

• DeepChem Tutorials - Comprehensive set of tutorials covering deep learning for chemistry, biology, and materials science.
• TeachOpenCADD - Modular Jupyter tutorials for CADD workflows and concepts.
• intro_pharma_ai - Notebook-based introduction to AI applications in pharma.
• Practical Cheminformatics Tutorials - Hands-on Jupyter tutorials for RDKit, SAR, clustering, generative models, and ML pipelines.
• AI/DL for Life Sciences - Interactive notebooks showcasing AI/DL use cases in life sciences.
• Fingerprint Generator Tutorial - RDKit blog tutorial on generating and manipulating molecular fingerprints.
• how-to-train-your-chemeleon - Tutorial and framework for training chemical machine learning models.
• rdkit-tips-and-tricks - Practical snippets and examples for the RDKit cheminformatics toolkit.

Labs and Research Groups

• Carlsson Lab - GPCR modeling, receptor-ligand interactions, MD, docking, and AI for drug discovery. (Uppsala University, Sweden)
• InSiliChem - Computational chemobiology and metalloenzyme design. (Universitat Autònoma de Barcelona, Spain)
• LCBC - Molecular dynamics, free energy calculations, retrosynthesis using machine learning. (Seoul National University, Korea)
• Angelo Raymond Rossi - High-performance computing for computational chemistry and cheminformatics. (University of Connecticut, USA)
• Laboratory of Chemoinformatics - QSAR/QSPR, chemical similarity, and virtual screening. (Université de Strasbourg / CNRS, France)
• Erastova Lab - Molecular modeling of soft matter and biomolecular simulations. (University of Edinburgh, UK)
• The Ballester Group - Developing ML/AI methods for structure-based scoring and virtual screening. (Imperial College London, UK)
• Meiler Lab - Rosetta software, protein design, and ML-based protein engineering. (Vanderbilt / Leipzig University, USA / Germany)
• COMP3D - Develops and applies AI methods to design safe, effective pharmaceuticals and agrochemicals. (University of Vienna, Austria)
• Dral Group - AI-enhanced computational chemistry, quantum chemical methods, and development of MLatom. (Xiamen University, China)
• Bonvin Lab - Computational structural biology, HADDOCK, and integrative modeling. (Utrecht University, Netherlands)
• Volkamer Lab - Binding site analysis and AI-powered virtual screening. (Saarland University, Germany)
• AI Laboratory for Molecular Engineering - PROTACs, molecular glues, and ML for chemistry and life sciences. (Chalmers University, Sweden)
• Loschmidt Labs - PEG - Protein and enzyme engineering, AI-assisted enzyme design. (Masaryk University, Czechia)
• QSAR4U - Cheminformatics tools, QSAR modeling, CReM, and EasyDock. (Palacky University, Czechia)
• LBMD - Computational strategies to understand and engineer biomolecular systems. (KU Leuven, Belgium)