AI-powered Virtual Screening

This page contains tools (about 1000 links) for structure-based or ligand-based virtual screening, for hit2lead and to predict the 3D structures of chemical compounds, drug repositioning. URLs were cleaned and dead links removed in November 2025

Jump to section:

3D structure prediction for small chemical compounds

  • LoQI: Scalable Low-Energy Molecular Conformer Generation with Quantum Mechanical Accuracy (stereochemistry-aware diffusion model) and ChEMBL3D, which contains over 250 million molecular geometries for 1.8 million drug-like compounds, optimized using AIMNet2 neural network potentials (standalone, 2025)
  • GCLDM: Geometry-Complete Latent Diffusion Model for 3D Molecule Generation (standalone, 2025).
  • EC-Conf: An Ultra-fast Diffusion Model for Molecular conformation Generation with Equivariant Consistency (standalone).
  • RDKIT-clustering-3D: Do Deep Learning Methods Really Perform Better in Molecular Conformation Generation (standalone).
  • smi2sdf3d: 3D diverse conformers generation using rdkit (Python) (standalone).
  • Auto3D: Automatic Generation of the Low-energy 3D Structures with ANI Neural Network Potentials (standalone).
  • CDPKit - CONFORT: High-Quality Conformer Generation (standalone).
  • BCL::Conf Server: generates conformational ensembles of small molecules (online).
  • GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles (standalone).
  • DeepChargePredictor: A web server for predicting QM-based atomic charges via state-of-the-art machine-learning algorithms (online).
  • Molassembler: Molecular graph construction, modification and conformer generation for inorganic and organic molecules (standalone).
  • Machine-learning-meets-pKa: Machine Learning Meets pKa prediction (python tool) (needs RDKIT) (standalone).
  • PrepFlow: A Toolkit for Chemical Library Preparation and Management for Virtual Screening (not 3D per se) (standalone).
  • ACC2: Atomic Charge Calculator II: Web-Based Tool for the Calculation of Partial Atomic Charges (online).
  • Molpro: quantum chemistry package (standalone).
  • CREST: Automated exploration of the low-energy chemical space with fast quantum chemical methods. CREST is an utility/driver program for the xtb program (semiempirical quantum mechanical (SQM) method which is called extended tight binding (xTB)) (standalone).
  • Gypsum-DL: an open-source program for preparing small-molecule libraries for structure-based virtual screening (pKa...) (standalone).
  • OPERA: Open-source QSAR models for pKa prediction using multiple machine learning approaches. Also suite of QSAR models (windows, linux), recent implementation (CATMoS Acute Toxicity Modeling Suite, acute oral toxicity) (standalone).
  • MolTaut: A Tool for the Rapid Generation of Favorable Tautomer in Aqueous Solution (compound preparation) (online).
  • MolTaut: A Tool for the Rapid Generation of Favorable Tautomer in Aqueous Solution (compound preparation) (standalone).
  • Chemaxon: numerous tools for small molecules (standalone).
  • Balloon: tools to predict 3D structure of small molecules (standalone).
  • Frog2: standalone and online.
  • Conformator: a novel method for the Generation of Conformer Ensembles (standalone).
  • DataWarrior: numerous tools (standalone).
  • Knodle: standalone automatic perception.
  • Ambitcli: no 3D but Java application for standardization (standalone).
  • Standardiser: standardize molecules, it requires RDKIt (standalone).
  • Standardized-smiles: Python script to standardize small molecules (use RDKIT) (standalone).
  • Standardize: PubChem chemical structure standardization (online).
  • WebMO: free World Wide Web-based interface to computational chemistry packages (standalone).
  • Q-Chem: comprehensive ab initio quantum chemistry package for accurate predictions of molecular structures, reactivities, and vibrational, electronic and NMR spectra (commercial, standalone).
  • Surflex-Tools: starting with version 4 (standalone).

Structure-based virtual screening and related and AI-based

  • DiffDock-Fine-Tune: Fine-Tuning DiffDock‑L for Allosteric Kinase Docking (standalone 2026)
  • LigandExplorer: An Automated Tool for Ligand Extraction from PDB Structures (standalone 2026)
  • SimDMTA: How Selection Strategies Influence Active Learning in Drug Discovery (standalone 2026)
  • MEHC-Curation: A Python Framework for High-Quality Molecular Dataset Curation (standalone 2026)
  • ProteinDJ: A high-performance and modular protein design pipeline (standalone 2026)
  • DeepTGIN: a novel hybrid multimodal approach using Transformers and graph isomorphism networks for protein-ligand binding affinity prediction (standalone 2024)
  • SMARTDock: A Toolkit for the Automated Development of Target-Specific Scoring Functions Using Bioactivity Data (standalone)
  • RTMScore: Boosting protein–ligand binding pose prediction and virtual screening based on residue–atom distance likelihood potential and graph transformer (standalone)
  • PMH_Bio: Persistent Mayer Homology-Based Machine Learning Models for Protein-Ligand Binding Affinity Prediction (standalone)
  • Boltzina: Efficient and Accurate Virtual Screening via Docking-Guided Binding Prediction with Boltz-2 (standalone 2026)
  • DiffLinker: Equivariant 3D-conditional diffusion model for molecular linker design (standalone)
  • Autofragdiff: Autoregressive fragment-based diffusion for pocket-aware ligand design (standalone)
  • DeepRLI: a multi-objective framework for universal protein–ligand interaction prediction (standalone 2025)
  • UNI-MOL DOCKING V2: towards realistic and accurate binding pose prediction (standalone 2024)
  • WeMol: A Cloud-Based and Zero-Code Platform for AI-Driven Molecular Design and Simulation, molecular similarity, structure-based and AI-enhanced docking, ADMET, molecular generation, MD simulations... (online 2026)
  • BADGER-SBDD: General Binding Affinity Guidance for Diffusion Models in Structure-Based Drug Design (standalone 2026)
  • AI-MCLig: De novo protein ligand design including protein flexibility and conformational adaptation (standalone 2026)
  • Combichem: Efficient Hit-to-Lead Searching of Kinase Inhibitor Chemical Space via Computational Fragment Merging (standalone)
  • DeepFrag2: deep convolutional neural network that guides ligand optimization by extending a ligand with a molecular fragment (standalone)
  • Prompt-to-Pill: Multi-Agent Drug Discovery and Clinical Simulation Pipeline (standalone 2026)
  • MetalloDock: Decoding Metalloprotein–Ligand Interactions via Physics-Aware Deep Learning for Metalloprotein Drug Discovery (standalone 2026)
  • PhoreGen: Pharmacophore-Oriented 3D Molecular Generation (standalone 2025)
  • ShEPhERD: Diffusing shape, electrostatics, and pharmacophores for bioisosteric drug design (standalone)
  • Conglude: Contrastive Geometric Learning Unlocks Unified Structure and Ligand-Based Drug Design (NB: Jan 2025, it may take some months for the code gets available) (standalone 2026)
  • OMTRA: A Multi-Task Generative Model for Structure-Based Drug Design (state-of-the-art performance on pocket-conditioned de novo design and docking) (standalone 2025)
  • ActivityFinder: Toward the Fully Automatic Integration of Structural and Binding Affinity Data (standalone 2026)
  • Meeko: interface for AutoDock (standalone, 2025)
  • basil_dock: a series of Jupyter notebooks designed to perform interactive molecular docking (standalone, 2025)
  • SGEDiff: a subgraph-enriched diffusion model for structure-based 3D molecular generation (standalone, 2025)
  • DiffDock-Pocket: Diffusion for Pocket-Level Docking with Side Chain Flexibility (standalone, 2023)
  • GatorAffinity: Boosting Protein-Ligand Binding Affinity Prediction with Large-Scale Synthetic Structural Data (standalone, 2025)
  • ODesign: A World Model for Biomolecular Interaction Design (design peptides, small molecules, proteins...) (standalone, 2025)
  • OpenFold-3: OF3 aims to be an open-source, bitwise reproduction of AlphaFold3 (AF3) with performance parity across all molecular modalities (even protein-ligand cofolding...beta version) (standalone, 2025)
  • TopMT-GAN: a 3D topology-driven generative model for efficient and diverse structure-based ligand design (standalone, 2025)
  • CovalentLab: One-Shot Rational Design of Covalent Drugs - residue reactivity prediction (standalone, 2025)
  • CovalentLab: One-Shot Rational Design of Covalent Drugs (online, 2025)
  • LigUnity: Hierarchical affinity landscape navigation through learning a shared pocket-ligand space (standalone, 2025)
  • Openpharmacophore: Pharmacophore screening (standalone)
  • SLOGEN: A Structure-based Lead Optimization Model Unifying Fragment Generation and Screening (standalone, 2025)
  • Boltzgen: universal binder design (standalone 2025)
  • GEMS: Resolving data bias improves generalization in binding affinity prediction - re-scoring after docking (standalone 2025)
  • CORDIAL: A generalizable deep learning framework for structure-based protein–ligand affinity ranking (standalone 2025)
  • DockBox2: GNN model to improve binding mode and affinity predictions from docking (standalone 2025)
  • PharmacoForge: pharmacophore generation with diffusion models (standalone 2025)
  • EM-PLA: Environment-aware heterogeneous graph-based multimodal protein–ligand binding affinity prediction (standalone 2025)
  • Alphappimi: A comprehensive deep learning framework for predicting PPI-modulator interactions (standalone 2025)
  • P4ward: An automated modelling platform for Protac ternary complex design (standalone, 2025).
  • FlowDock: Geometric Flow Matching for Generative Protein-Ligand Docking and Affinity Prediction (standalone, 2025).
  • Simpatico: accurate and ultra-fast virtual drug screening with atomic embeddings (standalone, 2025).
  • CoBDock-2: enhancing Blind Docking Performance through Hybrid Feature Selection Combining Ensemble and Multimodel Feature Selection Approaches (standalone, 2025).
  • EquiCPI: SE(3)-Equivariant Geometric Deep Learning for Structure-Aware Prediction of Compound-Protein Interactions (standalone, 2025).
  • Boltz-2: AI model for efficient binding affinity prediction (standalone, 2025).
  • MDRMF: Finding Drug Candidate Hits With a Hundred Samples: Ultra-low Data Screening With Active Learning (standalone, 2025).
  • DrugBaiter: Improved Prediction of Drug–Protein Interactions through Physics-Based Few-Shot Learning (standalone, 2025).
  • IdolPRO: Guided multi-objective generative AI to enhance structure-based drug design (standalone, 2025).
  • E3Docker: a docking server for potential E3 binder discovery (online, 2025).
  • PoLiGenX: Equivariant Diffusion for Structure-Based De Novo Ligand Generation with Latent-Conditioning (Pfizer OpenSource) (standalone).
  • MDRL: A 3D generation framework (ligand side) using diffusion model and reinforcement learning to generate multi-target compounds with desired properties (standalone).
  • Moldrug: algorithm for an automated ligand binding site exploration by 3D aware molecular enumerations (hit2lead) (standalone).
  • Moldina: a fast and accurate search algorithm for simultaneous docking of multiple ligands (standalone).
  • MolSnapper: Conditioning Diffusion for Structure-Based Drug Design (standalone).
  • FEP-SPell-ABFE: An Open-Source Automated Alchemical Absolute Binding Free-Energy Calculation Workflow for Drug Discovery (standalone).
  • iScore: A ML-Based Scoring Function for De Novo Drug Discovery (standalone).
  • HiQBind: PDBBind Optimization to Create a High-Quality Protein-Ligand Binding Dataset for Binding Affinity Prediction (standalone).
  • OpenMMDL: Building, Simulating, and Analyzing Protein–Ligand Systems in OpenMM (standalone).
  • FlowDock: Geometric Flow Matching for Generative Protein-Ligand Docking and Affinity Prediction (standalone).
  • PharmRL: pharmacophore elucidation with deep geometric reinforcement learning (standalone).
  • GENiPPI: Interface-aware molecular generative framework for protein-protein interaction modulators (standalone).
  • SwiftDock: Machine learning for scoring - active learning (standalone).
  • SurfDock: surface-informed diffusion generative model for reliable and accurate protein–ligand complex prediction (standalone, 2024).
  • vScreenML2: Improved Machine Learning Classification for Reducing False Positives in Structure-Based Virtual Screening (standalone, 2024).
  • VirtuDockDL: Deep learning pipeline for accelerating virtual screening in drug discovery (standalone, 2024).
  • DSDPFlex: Flexible-Receptor Docking with GPU Acceleration (standalone, 2024).
  • Rag2Mol: Retrieval Augmented Structure-based Drug Design (standalone).
  • QuickBind: A Light-Weight And Interpretable Molecular Docking Model (standalone, 2024).
  • FragGen: towards 3D geometry reliable fragment-based molecular generation (standalone, 2024).
  • ChatMol-Copilot: An Agent for Molecular Modeling and Computation Powered by LLMs (standalone).
  • KGDiff: towards explainable target-aware molecule generation with knowledge guidance (standalone).
  • Hot2Mol: Target-specific design of drug-like PPI inhibitors via hot-spot-guided generative deep learning
  • TamGen: drug design with target-aware molecule generation through a chemical language model (standalone).
  • PoseCheck: Benchmarking Generated Poses (standalone).
  • E-FTMap: Expanding FTMap for Fragment-Based Identification of Pharmacophore Regions in Ligand Binding Sites (online, 2024).
  • PCMol: AlphaFold Meets De Novo Drug Design: Leveraging Structural Protein Information in Multitarget Molecular Generative Models (standalone, 2024).
  • OpenDock: A pytorch-based open-source framework for protein-ligand docking and modelling (standalone, 2024).
  • SpaceHASTEN: A structure-based virtual screening tool for non-enumerated virtual chemical libraries (standalone, 2024).
  • uHTVS_toolkit: Python scripts to combine Glide HTVS and AutoDockGPU docking with Deep-Docking (standalone, 2024).
  • Vina-GPU 2.1: towards further optimizing docking speed and precision of AutoDock Vina and its derivatives (standalone, 2024).
  • traversing_chem_space: Traversing Chemical Space with Active Deep Learning (standalone, 2024).
  • FRAGSITE2: A structure and fragment-based approach for virtual ligand screening (online, 2024).
  • IEV2Mol: Molecular Generative Model Considering Protein−Ligand Interaction Energy Vectors (standalone, 2024).
  • pocket-cfdm: Augmenting a training dataset of the generative diffusion model for molecular docking with artificial binding pockets (standalone, 2024).
  • Milbinding: Predicting the binding of small molecules to proteins through invariant representation of the molecular structure (standalone, 2024).
  • OpenVS: An artificial intelligence accelerated virtual screening platform for drug discovery (standalone, 2024).
  • one collection for OpenVS: a drug-like centroid library (about 12-13 million compounds from ZINC) for OpenVS (dataset, 2024).
  • EnOpt: Ensemble Optimizer, a machine-learning tool to improve the accuracy and interpretability of ensemble virtual screening (standalone, 2024).
  • GraphBP: Generating 3D Molecules for Target Protein Binding (standalone, 2024).
  • SmartCADD: An AI-Integrated Drug Designing Platform
 (standalone, 2024).
  • 3D-MCTS: Flexible Data-Free Framework for Structure-Based De Novo Drug Design with Reinforcement Learning (standalone).
  • FLAG: Molecule Generation For Target Protein Binding With Structural Motifs (standalone, 2024).
  • MolGPT: Molecular Generation Using a Transformer-Decoder Model (standalone).
  • CBGBench: Complex Binding Graph Benchmark is a benchmark for generative target-aware molecule design (standalone).
  • DiffBP: Generative Diffusion of 3D Molecules for Target Protein Binding (standalone).
  • PocketFlow: an autoregressive flow model incorporated with chemical knowledge for generating drug-like molecules inside protein pockets (standalone, 2024).
  • TargetGAN: Deep generative model for drug design from protein target sequence (standalone, 2023).
  • DockingGA: enhancing targeted molecule generation using transformer neural network and genetic algorithm with docking simulation (standalone, 2024).
  • SPRank: A Knowledge-Based Scoring Function for RNA-Ligand Pose Prediction and Virtual Screening (standalone, 2024).
  • Umol: structure prediction of protein-ligand complexes from sequence information (standalone, 2024).
  • DrugCLIP: contrastive Protein-Molecule Representation Learning for Virtual Screening (standalone, 2024).
  • PoseBusters: AI-based docking methods fail to generate physically valid poses or generalise to novel sequences (standalone, 2024).
  • DockM8: an All-in-One Open-Source Platform for Consensus Virtual Screening in Drug Design (standalone, 2024).
  • DrugHIVE: structure-Based Drug Design with a Deep Hierarchical Generative Model (standalone, 2024).
  • BAT2: flexible, automated and low cost absolute binding free energy calculations (standalone, 2024).
  • FABind+: Enhancing Molecular Docking through Improved Pocket Prediction and Pose Generation (standalone).
  • FeatureDock: Protein-Ligand Docking Guided by Physicochemical Feature-Based Local Environment Learning using Transformer (standalone, 2024).
  • MolSnapper: Conditioning Diffusion for Structure Based Drug Design (standalone, 2024).
  • TacoGFN: Target Conditioned GFlowNet for Structure-based Drug Design (standalone, 2024).
  • MFE: Surface-based Multimodal Protein-Ligand Binding Affinity Prediction (standalone, 2024).
  • CENsible: Interpretable Insights into Small-Molecule Binding with Context Explanation Networks (standalone, 2024).
  • MolModa: accessible and secure molecular docking in a web browser (docking with Vina) (online, 2024).
  • FragGrow: Structure-Based Drug Design by Fragment Growing within Constraints (hit2lead) (online, 2024).
  • LigCys3D: Ligandable Cysteines in Three-Dimensional Structures (database) (online, 2024).
  • DeepCys: Machine Learning Models to Interrogate Proteome-Wide Covalent Ligandabilities Directed at Cysteines (online, 2024).
  • PMDM: A dual diffusion model enables 3D molecule generation and lead optimization based on target pockets (standalone, 2024).
  • ClassyPose: A Machine-Learning Classification Model for Ligand Pose Selection Applied to Virtual Screening in Drug Discovery (standalone, 2024).
  • RAD: Retrieval Augmented Docking (standalone, 2024).
  • Dragonfly: Prospective de novo drug design with deep interactome learning (standalone, 2024).
  • Lingo3DMol: Generation of 3D Molecules in Pockets via Language Model (diffusion) (online, 2024).
  • TargetDiff: 3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction (standalone, 2024).
  • MolProphet: A One-Stop, General Purpose, and AI-Based Platform for the Early Stages of Drug Discovery (needs registration) (online, 2024).
  • DiffSBDD: Structure-based Drug Design with Equivariant Diffusion Models (standalone, 2024).
  • DynamicBind: predicting ligand-specific protein-ligand complex structure with a deep equivariant generative model (standalone, published 2024).
  • PocketGen: Generating Full-Atom Ligand-Binding Protein Pockets (standalone).
  • PocketCFDM: Augmenting a training dataset of the generative diffusion model for molecular docking with artificial binding pockets (standalone).
  • Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets (standalone).
  • Lingo3dmol: Generation of a pocket-based 3d molecule using a language model (standalone).
  • DiffusionProteinLigand: End-to-end protein–ligand complex structure generation with diffusion-based generative models (standalone).
  • ResGen: pocket-aware 3D molecular generation model based on parallel multiscale modelling (standalone).
  • PROTACable: Integrative Computational Pipeline of 3-D Modeling and Deep Learning To Automate the De Novo Design of PROTACs (standalone, published 2024).
  • DiffDec: Structure-Aware Scaffold Decoration with an End-to-End Diffusion Model (generative chemistry) (standalone, published 2024).
  • VSpipe-GUI: an Interactive Graphical User Interface for Virtual Screening and Hit Selection (examples with fragment docking...) (standalone, published 2024).
  • ESSENCE-Dock: A Consensus-Based Approach to Enhance Virtual Screening Enrichment in Drug Discovery (standalone, published 2024).
  • ChemSpaceAL: an Efficient Active Learning Methodology Applied to Protein-Specific Molecular Generation (generative chemistry) (standalone, 2024).
  • CarsiDock: a deep learning paradigm for accurate protein–ligand docking and screening based on large-scale pre-training (standalone, 2024).
  • KarmaDock: a deep learning paradigm for ultra-large library docking with fast speed and high accuracy (standalone).
  • Uni-Dock: GPU-Accelerated Docking Enables Ultralarge Virtual Screening (standalone).
  • RxDock: a fast, versatile, and open-source program for docking ligands to proteins and nucleic acids (standalone).
  • Scipion-Chem: An Open Platform for Virtual Drug Screening (standalone).
  • Fast: Improved Protein-Ligand Binding Affinity Prediction with Structure-Based Deep Fusion Inference (standalone).
  • EasyDock: Customizable and scalable docking tool (standalone).
  • Autoparty: Machine Learning-Guided Visual Inspection of Molecular Docking Results (standalone).
  • PharmacoNet: Accelerating Large-Scale Virtual Screening by Deep Pharmacophore Modeling (ultra-large) (standalone).
  • CGraphDTA: Fusion-Based Deep Learning Architecture for Detecting Drug-Target Binding Affinity Using Target and Drug Sequence and Structure (Sept 2023) (standalone).
  • ML-PLIC: a web platform for characterizing protein–ligand interactions and developing machine learning-based scoring functions (online).
  • StackCPA: A stacking model for compound-protein binding affinity prediction based on pocket multi-scale features (scoring - 2023) (standalone).
  • PyRMD2Dock: Streamlining Large Chemical Library Docking with Artificial Intelligence: the PyRMD2Dock (and PyRMD) (ultralarge screening - 2023) (standalone).
  • ChemFlow_py: a flexible toolkit for docking and rescoring (standalone - 2023).
  • warpDOCK: Large-Scale Virtual Drug Discovery Using Cloud Infrastructure (ultralarge screening) (standalone).
  • PLANTAIN: Diffusion-inspired Pose Score Minimization for Fast and Accurate Molecular Docking (standalone).
  • MDLR: MD-ligand-receptor is a bioinformatics pipeline written in Python for analyzing non-covalent ligand-receptor interactions in 3D structures starting from a molecular dynamic trajectory (standalone).
  • DOCK Blaster 2.0: Automated Optimization of Docking Models using Retrospective Docking (dockopt - pydock3) (standalone).
  • SCORCH: Improving structure-based virtual screening with machine learning classifiers, data augmentation, and uncertainty estimation (standalone).
  • Moldock: python scripts to automate molecular docking (standalone).
  • TB-IECS: accurate machine learning-based scoring function for virtual screening (standalone).
  • pyCaverDock: Python Implementation of the Popular Tool for Analysis of Ligand Transport with Advanced Caching and Batch Calculation Support (standalone).
  • Uni-GBSA: open-source and web-based automatic workflow to perform MM/GB(PB)SA calculations for virtual screening (online).
  • Uni-GBSA: open-source and web-based automatic workflow to perform MM/GB(PB)SA calculations for virtual screening (standalone).
  • ACFIS 2.0: an improved web-server for fragment-based drug discovery via a dynamic screening strategy (online).
  • ConveyorLC: A Parallel Virtual Screening Pipeline for Docking and MM/GSBA (standalone).
  • nCoVDock2: a docking server to predict the binding modes between COVID-19 targets and its potential ligands (online).
  • Conformalpredictor: Rapid Traversal of Ultralarge Chemical Space using Machine Learning Guided Docking Screens (standalone).
  • SGPT: Optimization of binding affinities in chemical space with transformer and deep reinforcement learning (standalone).
  • MoFlow: an invertible flow model for generating molecular graphs (generative chemistry) (standalone).
  • VGAE-MCTS: A New Molecular Generative Model Combining the Variational Graph Auto-Encoder and Monte Carlo Tree Search (generative chemistry combining deep learning and reinforcement learning based on a molecular graph representation) (standalone).
  • PIGNet: a physics-informed deep learning model toward generalized drug-target interaction predictions (standalone).
  • Dockey: a modern integrated tool for large-scale molecular docking and virtual screening (Vina and several others) (online).
  • CAPLA: improved prediction of protein–ligand binding affinity by a deep learning approach based on a cross-attention mechanism (standalone).
  • EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction (standalone).
  • DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking (standalone).
  • TANKBind: Trigonometry-Aware Neural NetworKs for Drug-Protein Binding Structure Prediction (standalone).
  • SCARdock: A Web Server and Manually Curated Resource for Discovering Covalent Ligands (online).
  • SCARdock: A Web Server and Manually Curated Resource for Discovering Covalent Ligands (online).
  • SFSXplorer: Computational tool to explore the scoring function space (standalone).
  • Vina-GPU 2.0: Accelerating AutoDock Vina and Its Derivatives with Graphics Processing Units (standalone).
  • DrugGEN: Target Centric De Novo Design of Drug Candidate Molecules with Graph Generative Deep Adversarial Networks (standalone).
  • MetalProGNet: a structure-based deep graph model for metalloprotein-ligand interaction predictions (standalone).
  • HASTEN: Machine Learning Boosted Docking, An Open-source Tool To Accelerate Structure-based Virtual Screening Campaigns (active learning) (standalone).
  • MolPAL: Molecular Pool-based Active Learning (Efficient Exploration of Virtual Chemical Libraries through Active Learning) (standalone).
  • ChemFlow: From 2D Chemical Libraries to Protein–Ligand Binding Free Energies (standalone).
  • LiGANN: a structure-based de novo drug design tool based on generative neural-networks (generative chemistry) (online).
  • AlphaDrug: protein target specific de novo molecular generation (generative chemistry) (standalone).
  • COMA: efficient structure-constrained molecular generation using contractive and margin losses (standalone).
  • OptiMol: Optimization of Binding Affinities in Chemical Space for Drug Discovery (standalone).
  • liGAN: Generating 3D molecules conditional on receptor binding sites with deep generative models (generative chemistry) (standalone).
  • DENVIS: Scalable and High-Throughput Virtual Screening Using Graph Neural Networks with Atomic and Surface Protein Pocket Features (standalone).
  • HCovDock: an efficient docking method for modeling covalent protein-ligand interactions (online).
  • Apo2ph4: Workflow for the Generation of Receptor-based Pharmacophore Models for Virtual Screening (online).
  • CSAlign and CSAlign-Dock: Structure alignment of ligands considering full flexibility and application to protein-ligand docking (online).
  • CovBinderInPDB: A Structure-Based Covalent Binder Database (online).
  • ReMODE: a deep learning-based web server for target-specific drug design (online).
  • caverweb: Fully automated virtual screening pipeline of FDA-approved drugs using Caver Web (online).
  • VSTH: a user-friendly web server for structure-based virtual screening on Tianhe-2 (6 docking tools) (online).
  • Pocket2Drug: an encoder-decoder deep neural network that predicts binding drugs given protein binding sites (standalone).
  • PacDOCK: Positional Distance-Based and Interaction-Based Analysis of Docking Results (online).
  • DrugRep: an automatic virtual screening server (structure-based or ligand-based) for drug repurposing (online).
  • MO-MEMES: A method for accelerating virtual screening using multi-objective Bayesian optimization (online).
  • StoneWise: pocket-based 3D molecule generative model fueled by experimental electron density (standalone).
  • EDock-ML: A web server for using ensemble docking with machine learning to aid drug discovery (online).
  • LUNA: Prioritizing Virtual Screening with Interpretable Interaction Fingerprints (standalone).
  • Sfcnn: A scoring function model based on 3D convolutional neural network for protein-ligand binding affinity prediction (standalone).
  • PLAS-5k: Dataset of Protein-Ligand Affinities from Molecular Dynamics for Machine Learning Applications (5000 protein-ligand complexes) (dataset).
  • FitDock: protein–ligand docking by template fitting (Linux or Windows, need registration) (standalone).
  • restretto: Effective Protein–Ligand Docking Strategy via Fragment Reuse and a Proof-of-Concept Implementation (standalone).
  • WADDAICA: A webserver for aiding protein drug design by artificial intelligence and classical algorithm (online).
  • DockingPie: a Consensus Docking (Smina, AutoDock Vina, ADFR, and RxDock) Plugin for PyMOL (standaline).
  • MolHyb: Structure-Based Drug Design by Molecular Hybridization (online).
  • KinaFrag: Exploring the kinase-inhibitor fragment interaction space facilitates the discovery of kinase inhibitor overcoming resistance by mutations (online).
  • DeepDockingGUI: Deep docking (DD) is a deep learning-based tool developed to accelerate docking-based virtual screening (standalone).
  • DeepDocking: Data for Deep docking (about 1B compounds from Zinc).
  • CB-Dock2: improved protein-ligand blind docking by integrating cavity detection, docking and homologous template fitting (online).
  • fastDRH: a webserver to predict and analyze protein-ligand complexes based on molecular docking and MM/PB(GB)SA computation (online).
  • Vina-GPU: Accelerating AutoDock Vina with GPUs (standalone).
  • Drug-Sniffer: a virtual screening (VS) pipeline capable of screening billions of molecules using only thousands of CPU hours, using a novel combination of ligand-based (LBVS) and structure-based (SBVS) methods (ultra-large screening) (standalone).
  • ELIXIR-A: An Interactive Visualization Tool for Multi-Target Pharmacophore Refinement (online).
  • SyntaLinker: Automatic Fragment Linking with Deep Conditional Transformer Neural Networks (standalone).
  • PECAN: Pose Classification Using Three-Dimensional Atomic Structure-Based Neural Networks Applied to Ion Channel–Ligand Docking (standalone).
  • D3AI-CoV: a deep learning platform for predicting drug targets and for virtual screening against COVID-19 (online).
  • Fragmenstein: merge and link fragment hits in 3D (standalone).
  • PharmRF: A machine‐learning scoring function to identify the best protein‐ligand complexes for structure‐based pharmacophore screening with high enrichments (standalone).
  • OnionNet-2: tool constructed based on convolutional neural network (CNN) to predict the protein-ligand binding affinity (standalone).
  • ProBiS-Dock: A Hybrid Multitemplate Homology Flexible Docking Algorithm Enabled by Protein Binding Site Comparison (standalone).
  • ProBiS-Dock Database: A repository of 1,406,999 small-ligand binding sites (standalone).
  • FragPELE: a tool for in-silico hit-to-lead drug design, capable of growing a fragment from a bound core (Fragment-based drug discovery) (Pele platform is a python module to automatically launch PELE) (standalone).
  • Dockstring: A Python package for easy molecular docking (with Vina)… machine learning..(standalone).
  • BR-NiB: Brute Force Negative Image-Based Optimization. A docking rescoring method that relyes on shape/ electrostatic potential similarity between the docking poses of ligands and the cavity-based negative images (standalone).
  • ComBind: Integrated data-driven modeling and physics-based docking for improved binding pose prediction and binding affinity prediction (standalone).
  • DeepDock: A Geometric Deep Learning Approach to Predict Binding Conformations of Bioactive Molecules (standalone).
  • DD-GUI: a Graphical User Interface for Deep Learning-Accelerated Virtual Screening of Large Chemical Libraries (Deep Docking) (standalone).
  • MoleGuLAR: Molecule generation using Reinforcement Learning and Alternating Rewards (works with AutoDock GPU) (standalone).
  • Deep Docking: docking ultra-large collection (standalone).
  • Knime workflows: Fine tuning for success in structure-based virtual screening (standalone).
  • RNALigands: a database and web server for RNA - ligand interactions (online) (standalone on github SaisaiSun/RNALigands).
  • Virtual-Screen-Lab: Buried surface area calculator; DelG-to-Kd converter; IC50-to-pIC50 converter (standalone).
  • DockStream: Molecular AI, a Docking Wrapper to Enhance De Novo Molecular Design (standalone).
  • ProLIF: a library to encode molecular interactions as fingerprints (standalone).
  • Jupyter_Dock: Molecular Docking integrated in Jupyter Notebooks (standalone).
  • dockECR: Open consensus docking and ranking protocol for virtual screening of small molecules (standalone).
  • MP-Vina: fast Vina docking (standalone).
  • Geauxdock GPU: An ultra-fast automated docking program (standalone).
  • AutoDock GPU: fast AutoDock (standalone).
  • MolPAL: Molecular Pool-based Active Learning - fast screening (standalone).
  • SeamDock: An Interactive and Collaborative Online Docking Resource to Assist Small Compound Molecular Docking (AutoDock, Vina, Smina, Qvina) (online).
  • DeepFrag: An Open-Source Browser App for Deep-Learning Lead Optimization (online and standalone).
  • ProfKin: A comprehensive web server for structure-based kinase profiling (online).
  • AncPhore: A versatile tool for anchor pharmacophore steered drug discovery (Linux and Windows) (standalone).
  • AutoDock Vina 1.2.0: New Docking Methods, Expanded Force Field, and Python Bindings (new scoring function, simultaneous docking of multiple ligands, and a batch mode for docking a large number of ligands) (standalone and online).
  • AutoDock-Vina: to download (standalone).
  • LigTMap: ligand and structure-based target identification and activity prediction for small molecular compounds (online and standalone github.com/ShirleyWISiu/LigTMap).
  • VAD-MM/GBSA: webserver (VDGB) for protein-ligand binding free energy prediction by the variable atomic dielectric MM/GBSA method (online).
  • VirtualFlow Ants: Ultra-Large Virtual Screenings with Artificial Intelligence Driven Docking Algorithm Based on Ant Colony Optimization (standalone).
  • ePharmaLib: A Versatile Library of e-Pharmacophores to Address Small-Molecule (Poly-)Pharmacology. A library of 15,148 e-pharmacophores modeled from solved structures of pharmaceutically relevant protein-ligand complexes of the screening Protein Data Bank (sc-PDB). ePharmaLib can be used for target fishing of phenotypic hits, side effect predictions, drug repurposing, and scaffold hopping (online).
  • Cross-docking benchmark: for automated pose and ranking prediction of ligand binding (cross-docking data set containing 4,399 protein-ligand complexes across 95 protein targets) (online).
  • LIT-PCBA: Benchmarking Data Sets from PubChem BioAssay Data: Current Scenario and Room for Improvement (online).
  • VAD-MM/GBSA: A Variable Atomic Dielectric MM/GBSA Model for Improved Accuracy in Protein-Ligand Binding Free Energy Calculations (possibly better than MM/GBSA in AMBER software) (online).
  • FoldAffinity: binding affinities from nDSF experiments (Differential scanning fluorimetry (DSF) using the inherent fluorescence of proteins (nDSF) is a technique to evaluate thermal protein stability in different conditions (e.g. buffer, pH). In many cases, ligand binding increases thermal stability of a protein and often this can be detected as a clear shift in nDSF experiments. The tool evaluates binding affinity quantification based on thermal shifts (online).
  • SSnet: Secondary Structure based End-to-End Learning model for Protein-Ligand Interaction Prediction (standalone).
  • FAST: Improved Protein-Ligand Binding Affinity Prediction with Structure-Based Deep Fusion Inference (FAST: Fusion models for Atomic and molecular STructures) (standalone).
  • EDock-ML: A Web Server for Using Ensemble Docking (account for receptor flexibility) with Machine Learning (to assist scoring) to Aid Drug Discovery. At present for kinases but users to train their own models if they have already performed docking on a large number of actives and decoys by AutoDock Vina (online).
  • ASFP: Artificial Intelligence based Scoring Function Platform, a web server for the development of customized scoring functions (online).
  • MSLDOCK: Multi-Swarm Optimization for Flexible Ligand Docking and Virtual Screening (standalone).
  • GNINA 1.0: Molecular Docking with Deep Learning (standalone).
  • AnnapuRNA: A scoring function for predicting RNA-small molecule binding poses (standalone).
  • MDock: automated molecular docking software which can simultaneously docking ligands against multiple protein structures/conformations by using the ensemble docking algorithm (standalone).
  • IFPscore: Proteo-chemometrics interaction fingerprints of protein-ligand complexes predict binding affinity (standalone).
  • InstaDock: A single-click graphical user interface for molecular docking-based virtual high-throughput screening (with QuickVina-W) (standalone for Windows).
  • Pose&Rank: a free service for scoring protein-ligand complexes, using two atomic distance-dependent statistical scoring functions: PoseScore and RankScore (online).
  • DRDOCK: performs online automatic virtual drug screening of 2016 FDA-approved drugs on a user-submitted target protein. Combines molecular docking and molecular dynamic simulations to prioritize strong binders from less likely binders (used for COVID-19) (online).
  • RASPD+: Fast Protein-Ligand Binding Free Energy Prediction Using Simplified Physicochemical Features (standalone).
  • SpaceLight: search method for similarity-driven virtual screening in large combinatorial fragment spaces using topological fingerprints (large databases) (standalone).
  • LigGrep: a tool for filtering docked poses to improve virtual-screening hit rates (standalone).
  • FWAVina: A novel optimization algorithm for protein-ligand docking based on the fireworks algorithm (standalone).
  • DelG-to-Kd converter, IC50-to-pIC50 converter: DelG-to-Kd converter, IC50-to-pIC50 converter, logBB calculator, Sanger sequencer, buried surface area calculator (standalone, python scripts).
  • APBScore: Development of a New Scoring Function for Virtual Screening (standalone).
  • DockCoV2: a drug database against SARS-CoV-2 (COVID-19) (online).
  • MolAICal: tools for 3D drug design of protein targets by artificial intelligence and classical algorithm (de novo design in protein pockets, fragment-based...) (standalone).
  • vsFilt: A Tool to Improve Virtual Screening by Structural Filtration of Docking Poses (detect various types of interactions that are known to be involved in the molecular recognition, including hydrogen and halogen bonds, ionic interactions, hydrophobic contacts, pi-stacking, and cation-pi interactions) (online).
  • VirtualFlow: open-source drug discovery platform enables ultra-large (billion) virtual screens (e.g., with Vina). Guidelines to set up a platform can be seen in the article (standalone).
  • PyPLIF HIPPOS: A Molecular Interaction Fingerprinting Tool for Docking Results of AutoDock Vina and PLANTS (standalone).
  • Enlighten2: Protocols and tools to run (automated) atomistic simulations (molecular dynamics) of enzyme-ligand systems (Python, PyMOL plugin, standalone).
  • GWOVina: A grey wolf optimization approach to rigid and flexible receptor docking (standalone).
  • EDock: high-quality blind docking (full-surface) (based on replica-exchange Monte Carlo simulations) built on low resolution protein structure prediction (online).
  • AutoGrow4: an open-source genetic algorithm for de novo drug design and lead optimization (needs RDKit etc) (standalone).
  • MDock: automated molecular docking software to simultaneously dock ligands against multiple protein structures or conformations by using the ensemble docking algorithm (standalone).
  • DPADFrag: A Database Built for the Exploration of Bioactive Fragment Space for Drug Discovery (online).
  • KinomeRun: An Interactive Utility for Kinome Target Screening and Interaction Fingerprint Analysis Towards Holistic Visualization on Kinome Tree - dock in several kinases (standalone).
  • KinomeRun: A tool for kinome target screening (inverse docking, profiling). KinomeRun can be used to screen the ligands of interest docked against multiple kinase structures in parallel around the kinase binding site and also to filter out the targets with unique interaction patterns (standalone).
  • LigTBM: Automated server for template-based small-molecule docking (ClusPro) (online).
  • LigBuilder V3: A Multi-Target de novo Drug Design Approach (standalone).
  • ECONTACT: Energetic Contributions of Amino Acid Residues and Its Cross-Talk to Delineate Ligand Binding Mechanism (standalone).
  • D3Targets-2019-nCoV: a webserver for predicting drug targets and for multi-target and multi-site based virtual screening against COVID-19 (online).
  • COVID-19 Docking Server: An interactive server for docking small molecules, peptides and antibodies against potential targets of COVID-19 (online).
  • Learning from the ligand: using ligand-based features to improve binding affinity prediction (standalone).
  • MolAr: Molecular Architect: A User-Friendly Workflow for Virtual Screening (with AutoDock Vina, DOCK 6, or a consensus of the two) (standalone).
  • ProtoCaller: Robust Automation of Binding Free Energy Calculations.It is a Python library distributed through Anaconda which automates relative protein-ligand binding free energies in GROMACS (standalone).
  • MedusaDock 2.0: Efficient and Accurate Protein-Ligand Docking With Constraints (online).
  • D-COID: Tool to generate highly-compelling decoy complexes that are individually matched to available active complexes (datasets - standalone).
  • Raccoon: a graphical interface for processing ligand libraries in different formats (PDB, multi-structure MOL2and PDBQT), multiple receptor conformations (e.g. relaxed complex experiments) and flexible residues, to generate all the files required to run an AutoDock virtual screening (standalone).
  • vScreenML: A general-purpose classifier for virtual screening (for identifying active complexes) (many depencies) (standalone).
  • EleKit 2: allows to measure the similarity of electrostatic potentials between a docked small molecule and a known ligand protein for the same receptor. EleKit is intended to facilitate the design of PPI inhibitors (standalone).
  • LigRMSD: automatic structure matching and RMSD calculations among identical and similar compounds in protein-ligand docking (online).
  • LARMD: integration of bioinformatic resources to profile ligand-driven protein dynamics. Normal mode analysis is also provided. Ligand binding, unbinding… (online).
  • disco: Cross Docking Benchmark server (online).
  • CaverDock web: Fast Screening of Inhibitor Binding/Unbinding (pocket definition and docking in buried tunnels) (online).
  • CaverDock: Fast Screening of Inhibitor Binding/Unbinding (pocket definition and docking in buried tunnels) (standalone linux).
  • Pharmmaker: Pharmacophore modeling model using outputs of druggability simulations. Uses multiple target conformations dependent on the binding poses of probes where they interact during druggability simulations (standalone and online).
  • DockRMSD: an open-source tool for atom mapping and RMSD calculation of symmetric molecules (after docking) through graph isomorphism (online and standalone linux).
  • FlexAID: structure-based virtual screening (standalone).
  • DeLinker: Deep Generative Models for 3D Compound Design. Takes two fragments or partial structures and designs a molecule incorporating both. The generation process is proteincontext dependent, utilising the relative dis-tance and orientation between the partial structures (standalone).
  • DockNmine: a Web Portal to Assemble and Analyse Virtual and Experimental Interaction Data, precision medicine (online).
  • DENOPTIM: Software for Computational de Novo Design of Organic and Inorganic Molecules (standalone).
  • AutoDock Bias: improving binding mode prediction and virtual screening using known protein–ligand interactions (standalone).
  • LEDOCK: structure-based docking (standalone).
  • Sanjeevini: structure-based virtual screening (online).
  • DDT: Drug Discovery Tool, a fast and intuitive graphics user interface for Docking (autodock) and Molecular Dynamics analysis (standalone).
  • DLIGAND2: an improved knowledge-based energy function for protein-ligand interactions using the distance-scaled, finite, ideal-gas reference state (rescoring, works better on some targets that are present in the dataset...) (standalone Linux).
  • Sfcnn: a novel scoring function based on 3D convolutional neural network for accurate and stable protein-ligand affinity prediction (2022) (standalone).
  • iPBSA: Improving virtual screening results with MM/GBSA and MM/PBSA rescoring (standalone).
  • NNScore: scoring function for characterizing the potency of receptor-ligand complexes based on neural networks (nnscore2 but see also nnscore1) (standalone).
  • MolScore: An automated scoring function to facilitate and standardize evaluation of goal-directed generative models for de novo molecular design (standalone).
  • Learning from Docked Ligands: Ligand-Based Features Rescue Structure-Based Scoring Functions When Trained On Docked Poses (can help ultra-large docking) (standalone).
  • RTMScore: Boosting Protein–Ligand Binding Pose Prediction and Virtual Screening Based on Residue–Atom Distance Likelihood Potential and Graph Transformer (standalone).
  • SCORCH: Improving structure-based virtual screening with machine learning classifiers, data augmentation, and uncertainty estimation (standalone).
  • DeepBindBC: A practical deep learning method for identifying native-like protein-ligand complexes in virtual screening (standalone).
  • D2: Deep Docking - a deep learning platform for augmentation of structure based drug discovery - Accelerate Virtual Screening by 50X for ultra-large collection (standalone).
  • Lean-Docking: Exploiting Ligands Predicted Docking Scores to Accelerate Molecular Docking (ultra-large docking) (standalone).
  • DeepBSP: a Machine Learning Method for Accurate Prediction of Protein-Ligand Docking Structures (scoring) (standalone).
  • OctSurf: Efficient hierarchical voxel-based molecular surface representation for protein-ligand affinity prediction (scoring) (standalone).
  • SCORCH: (Scoring COnsensus for RMSD-based Classification of Hits) is a fast scoring function based on a consensus of machine learning models (standalone).
  • XLPFE: a Simple and Effective Machine Learning Scoring Function for Protein-ligand Scoring and Ranking (standalone).
  • task-specific_scoring_functions: some examples (standalone).
  • RF-Score-VS: Random Forest-based scoring function for Virtual Screening (standalone).
  • DyScore: A Boosting Scoring Method with Dynamic Properties for Identifying True Binders and Non-binders in Structure-based Drug Discovery (standalone).
  • GB-Score: Minimally Designed Machine Learning Scoring Function Based on Distance-weighted Interatomic Contact Features (standalone).
  • DeltaVina: A scoring function for rescoring protein-ligand binding affinity (standalone).
  • ET-score: Improving Protein-ligand Binding Affinity Prediction Based on Distance-weighted Interatomic Contact Features Using Extremely Randomized Trees Algorithm (standalone).
  • delta_LinF9_XGB: Delta Machine Learning to Improve Scoring-Ranking-Screening Performances of Protein-Ligand Scoring Functions (standalone).
  • Lin_F9: A Linear Empirical Scoring Function for Protein-Ligand Docking (standalone).
  • FFENCODER-PL: Pair Wise Energy Descriptors for Protein-Ligand Pose Selection (standalone).
  • Pafnucy: Development and evaluation of a deep learning model for protein–ligand binding affinity prediction (standalone).
  • DSX: DSX (DrugScore) knowledge-based scoring function (online).
  • Convex-PL: knowledge-based potential for protein-ligand interactions (standalone).
  • X-score: Scoring function for virtual screening, X-tool (standalone).
  • Vinardo: scoring function implemented in Smina (standalone).
  • OnionNet-SFCT: rescoring docking poses with Onionnet-SFCT (standalone).
  • AA-Score: a New Scoring Function Based on Amino Acid-Specific Interaction for Molecular Docking (standalone).
  • Lin_F9: A Linear Empirical Scoring Function for Protein–Ligand Docking (linux, 2021) (standalone).
  • Cyscore: An empirical scoring function for accurate protein-ligand binding affinty prediction (linux command line) (standalone).
  • iRAISE: inverse screening benchmarking data sets.
  • PL-PatchSurfer2: A virtual screening program based on local surface matching (standalone).
  • DeepDTA: Deep drug-target binding affinity prediction (standalone).
  • MLSF: Classical scoring functions for docking are unable to exploit large volumes of structural and interaction data. Random Forest (RF)-based Scoring Functions could help. Code and data for reproducing the results of machine-learning vs classical scoring functions on a similarity-based benchmark (standalone).
  • SIEVE-Score: An Improved Method of Structure-based Virtual Screening via Interaction-energy-based Learning (standalone).
  • AutoDock Bias: improving binding mode prediction and virtual screening using known protein-ligand interactions (standalone).
  • PSOVina 2: Chaos-embedded particle swarm optimization approach for protein-ligand docking and virtual screening (standalone).
  • nAPOLI: a graph-based strategy to detect and visualize conserved protein-ligand interactions in large-scale (online).
  • CASF-2016 virtual screening benchmark: The complete CASF-2016 benchmark will be released on the PDBbind-CN web server. Comparative Assessment of Scoring Functions (docking - scoring dataset online).
  • FINDSITEcomb2.0: A New Approach for Virtual Ligand Screening of Proteins and Virtual Target Screening of Biomolecules (online).
  • WnS: Systematic exploration of multiple drug binding sites, Wrap 'n' Shake (WnS) (combine AutoDock 4.2.3 and GROMACS).
  • SAMSON: ligand unbinding pathways (standalone).
  • farPPI: a webserver for accurate prediction of protein-ligand binding structures for small-molecule PPI inhibitors by MM/PB(GB)SA methods, Fast Amber Rescoring (online).
  • ezCADD: a Rapid 2D/3D Visualization Enabled Web Modeling Environment for Democratizing Computer-Aided Drug Design (small molecule docking, protein docking, 2D/3D interaction viz, de novo lead optimization, pocket search and polypharmacology) online.
  • PLEC: Protein-Ligand Extended Connectivity fingerprint and its application for binding affinity predictions (standalone).
  • PRODIGY-LIG web server: Large-scale prediction of binding affinity in protein-small ligand complexes (online).
  • ProteinPrepare: Make your protein ready for molecular dynamics simulations by titrating and protonating the protein at a desired pH and by optimizing the H-bond network (online).
  • POAP: A GNU parallel based multithreaded pipeline of open babel and AutoDock suite for boosted high throughput virtual screening (The ligand preparation module is a unique feature in POAP) (standalone).
  • VSpipe: Integrated Resource for Virtual Screening and Hit Selection (AutoDock, standalone).
  • FITTED: virtual screening, scoring for metalloenzymes... (FORECASTER Suite, standalone).
  • Parameterize: Parameterize small organic molecules to obtain optimized parameters for AMBER and CHARMM force-fields (online).
  • QuickVina-W (QVina): fast and can do full surface screening (and related) (standalone).
  • QuickVina-W (QVina 2): tutorial (standalone).
  • Kdeep: Predict the binding affinity of a set of ligands docked in a protein using a state-of-the-art neural network-based predictor (deep learning) (online).
  • Surflex: Structure and ligand based (standalone).
  • Dockovalent: covalent docking (online).
  • AnchorQuery: structure-based design of PPI inhibitors (online).
  • DockThor: Free Web Server for Protein-ligand Docking, the V2 version has been shown efficient to dock peptides (online).
  • DrugDiscovery@TACC: Virtual Drug Discovery Portal (online).
  • e-LEA3D: virtual screening with PLANTS, de novo drug design, fragment (online).
  • iDock: structure-based virtual screening powered by fast and flexible ligand docking, tool inspired by AutoDock Vina, with RF score (standalone).
  • MOMA - LigPath: Starting from the model of a protein-ligand complex, MoMA-LigPath computes the ligand exit path from the active site to the protein surface using robotics-inspired algorithms (online).
  • DOCK Blaster: screening with DOCK (online).
  • AutoDock Vina: standalone.
  • Smina: Vina-like with scoring tools (standalone).
  • PyRx: virtual screening with Autodock tools (standalone).
  • Panther: A novel tool to predict small molecule binding into proteins (online).
  • DOCK: The Official UCSF DOCK Web-site (standalone for DOCK).
  • 3D-e-Chem-VM: Virtual Machine (VM) encompassing tools, databases & workflows, including new resources developed for ligand binding site comparisons and GPCR research (standalone).
  • Galaxy7TM: Given a GPCR structure and a ligand structure, optimized complex structures are generated by docking and refinement (online).
  • MTiOpenScreen: virtual screening, blind docking with Autodock or Vina (used for COVID-19, the Drugs-lib is used, the reference is Lagarde et al., PMID: 30190791) (online).
  • SPOT-ligand: Virtual Ligand Screening based on Binding Homology from Protein 3D Structure (online).
  • SPOT-ligand 2: (screening based on Binding Homology) (standalone).
  • iStar iDock: a software-as-a-service platform for general-purpose web applications (standalone and online tools).
  • Rocker: ROC curve visualization (online).
  • Screening Explorer: ROC curve visualization and related, evaluate screening results (online).
  • IonCom: Metal Ion-Binding site prediction. Metal ions (Zn2+, Cu2+, Fe2+, Fe3+, Ca2+, Mg2+, Mn2+, Na+, K+) and four acid radical ions (CO32-, NO2-, SO42-, PO43-) (online).
  • MIB: Metal Ion-Binding site prediction and docking server (12 different metal ions) online.
  • rDock: Versatile and Open Source Program for Docking Ligands to Proteins and Nucleic Acids (standalone).
  • Dynamic Undocking (DUck): tutorial for Dynamic Undocking (online).
  • MMsDockBench: DockBench - MMsDockBench is an integrate informatics platform to automatically perform and compare RMDS-based molecular docking performances (benchmark) of different docking/scoring methods (standalone).
  • DockingApp: user-friendly graphical application for carrying out molecular docking and virtual screening tasks, meant to enable non-experienced users to easily perform such activities and browse the docking results via a three-dimensional visualization (with Autodock Vina, standalone).
  • Octopus: virtual screening (VS). It can perform fast and friendly docking simulation. Differently from others VS platforms, Octopus can perform docking simulations of unlimited number of compounds into a set of molecular targets (standalone).
  • D3R: drug design data resource (also for ligand-based, benchmark).
  • Spark-VS: Structure-Based Virtual Screening (SBVS) pipelines in Spark (standalone).
  • AMMOS2: tool to refine protein-ligand-water complexes (online).
  • Spresso: Ultrafast Pre-screening Method Based on Compound Decomposition, fragment docking (standalone).
  • WaterDock-2.0: dock water molecules with Vina (PyMol, standalone)).
  • WaterDock-2.0: dock water molecules (standalone).
  • DEKOIS: datasets for benchmark.
  • DUDE: datasets for benchmark.
  • TocoDecoy: A New Approach to Design Unbiased Datasets for Training and Benchmarking Machine-Learning Scoring Functions (standalone).
  • TocoDecoy: A New Approach to Design Unbiased Datasets for Training and Benchmarking Machine-Learning Scoring Functions (dataset).
  • DUDE-Z: the next generation of DUDE (dataset).
  • BoBER: bioisosteric and scaffold hopping replacements, hit2lead, implements an interface to a database of bioisosteric and scaffold hopping replacements (online).
  • Magic Rings: Navigation in the Ring Chemical Space Guided by the Bioactive Rings (online).
  • rdScaffoldNetwork: RDKIT The Scaffold Network Implementation in RDKit (standalone).
  • FragRep: A Web Server for Structure-Based Drug Design by Fragment Replacement (bioisosteric replacement) (online).
  • MolOpt: A web server for drug design using bioisosteric transformation (online).
  • GalaxyDock2 and BP2 Score: hybrid scoring function, protein-ligand docking program that allows flexibility of pre-selected side-chains of ligand using Conformational Space Annealing (binary available, MAc Linux, standalone).

Ligand-based virtual screening, de novo design, generative chemistry, AI-based

  • SynFrag: Synthetic Accessibility Predictor Based on Fragment Assembly Generation in Drug Discovery (standalone 2026)
  • CF-MF: Collision-free morgan fingerprints: a principled approach to enhance machine learning performance and interpretability in chemistry (standalone 2026)
  • BAPULM: Binding Affinity Prediction using Language Models (standalone 2024)
  • Mol2mol: Exhaustive local chemical space exploration using a transformer model (standalone 2025)
  • NovoMolGen: Rethinking Molecular Language Model Pretraining (standalone 2025)
  • MEHC-Curation: A Python Framework for High-Quality Molecular Dataset Curation (standalone 2026)
  • TwistDAN: Twisted Domain Adversarial Network for Synthetic Accessibility Assessment (online 2026)
  • PROTAC-Splitter: A Machine Learning Framework for Automated Identification of PROTAC Substructures (standalone 2026)
  • CovaGen: A Deep Generative Approach to de novo Covalent Drug Design with Enhanced Drug-likeness and Safety (standalone 2026)
  • EVOSYNTH: Enabling multi-target drug discovery through latent evolutionary optimization and synthesis-aware prioritization (standalone 2026)
  • DataWarrior-Agent: Natural Language Control of Computational Chemistry Software « DataWarrior » Through Macro Orchestration (standalone 2026)
  • MolVE: Platform for Visualizing and Evaluating AI-Designed Molecules to Aid in Prioritization (eady-to-use code, containerized with Docker) (standalone 2026)
  • AgentD: LLM Agent for Modular Task Execution in Drug Discovery (standalone 2026)
  • DrugAgent: Multi-Agent Large Language Model-Based Reasoning for Drug-Target Interaction Prediction (standalone 2025)
  • CoSynLLM: an LLM-assisted predictive framework for predicting drug combination synergy (standalone 2026)
  • ChemGLaM: Chemical Genomics Language Model toward Reliable and Explainable Compound-Protein Interaction Exploration (DTI) (standalone 2026)
  • ohe: One-Hot News: Drug Synergy Models Shortcut Molecular Features (standalone 2026)
  • PLXFPred: Interpretable cross-attention networks with hierarchical fusion of multi-modal features for predicting protein-ligand interactions and affinities (standalone 2026)
  • Ouroboros: Learned Conformational Space and Pharmacophore Into Molecular Foundational Model (standalone 2026)
  • CoNCISE: Learning a CoNCISE language for small-molecule binding (a method that accelerates drug-target interaction (DTI) prediction by 2-3 orders of magnitude) (standalone 2026)
  • protac_deep_qsp: Proteolysis-targeting Chimera efficacy prediction using a deep-learning–QSP model (standalone 2026)
  • federated-learning: Empowering Federated Learning for Robust Compound-Protein Interaction Prediction across Heterogeneous Cross-Pharma Domains (standalone 2026)
  • StructureFree-DTA: Structure-free drug–target affinity prediction using protein and molecule language models (online 2025-2026)
  • StructureFree-DTA: Structure-free drug–target affinity prediction using protein and molecule language models (standalone 2025-2026)
  • RetroScore: graph edit distance-guided retrosynthesis for accessibility scoring with route metrics (online 2025)
  • RetroScore: graph edit distance-guided retrosynthesis for accessibility scoring with route metrics (standalone 2025)
  • DeepSEQreen: accelerates early stage drug discovery by integrating a variety of cutting-edge sequence-based deep learning models for drug-target interaction prediction (online 2025)
  • VNFlow: integration of variational autoencoders and normalizing flows for novel molecular design (standalone 2025)
  • pharmacophore-toolkit: A Simple Pharmacophore-Toolkit (standalone 2025)
  • gneprop: A high-throughput phenotypic screen combined with an ultra-large-scale deep learning-based virtual screening reveals novel scaffolds of antibacterial compounds (standalone, 2025)
  • BitBIRCH-Lean: fast small molecules clustering (standalone 2025)
  • ToolUniverse: Democratizing AI scientists using ToolUniverse (standalone 2025)
  • SGcCA: Deciphering Drug-Target Interaction Based on End-to-End Model with Spatial and Channel Reconstruction Convolution and Cross-Efficient-Additive Attention (standalone 2025)
  • ZeroGEN: Leveraging Language Models for Zero-Shot Ligand Design from Protein Sequences (standalone 2025)
  • VeGA: A Versatile Generative Architecture for Bioactive Molecules across Multiple Therapeutic Targets (generative chemistry) (standalone 2025)
  • MolDecor: Transformer based molecule decorator for Lead Optimization (hit2lead) (standalone 2025)
  • Subgrapher: visual fingerprinting of chemical structures (standalone 2025)
  • MolPrice: assessing synthetic accessibility of molecules based on market value (standalone 2025)
  • PyaiVS: unifies AI workflows to accelerate ligand discovery (standalone 2025)
  • MOLPILE: large-scale, diverse dataset for molecular representation learning (222M compounds) (standalone 2025)
  • MolCL-SP: multimodal molecular property prediction framework
  • ChemBounce: A computational framework for scaffold hopping in drug discovery
  • KGGraph: Knowledge-Guided Graph Self-Supervised Learning to Enhance Molecular Property Predictions
  • GP-MoLFormer: A foundation model for molecular generation
  • Alphappimi: A comprehensive deep learning framework for predicting PPI-modulator interactions (standalone 2025)
  • ChemDFM: Developing ChemDFM as a large language foundation model for chemistry (standalone 2025)
  • MolPrompt: Improving multi-modal molecular pre-training with knowledge prompts (standalone 2025)
  • ChemLML: Chemical Language Model Linker: Blending Text and Molecules with Modular Adapters (standalone 2025)
  • AnGe: Analog Generator with AnGe v2025.07 (online 2025).
  • AccFG: Functional Group Extraction and Molecular Structure Comparison (standalone 2025).
  • ChemLM: Domain adaptable language modeling of chemical compounds (standalone 2025).
  • ProtLigand: Beyond the Leaderboard: Leveraging Predictive Modeling for Protein-Ligand Insights and Discovery (standalone 2025).
  • EviDTI: Evidential deep learning-based drug-target interaction prediction (standalone, 2025).
  • DMFF-DTA: Dual modality feature fused neural network integrating binding site information for drug target affinity prediction (standalone, 2025).
  • DeepDTAGen: A multitask deep learning framework for drug-target affinity prediction and target-aware drugs generation (standalone, 2025).
  • DyeLeS: a web platform for predicting and classifying fluorescence properties of bioactive molecules (Theranostics thus diagnostics and therapeutics) (online, 2025).
  • DyeLeS: a web platform for predicting and classifying fluorescence properties of bioactive molecules (Theranostics thus diagnostics and therapeutics) (standalone).
  • DeepPSA: A Geometric Deep Learning Model for PROTAC Synthetic Accessibility Prediction (standalone).
  • HSR: Hypershape recognition (standalone).
  • FastTargetPred: a program enabling the fast prediction of putative protein targets for input chemical databases - drug repositioning, phenotypic screening... drug target interactions... (standalone, 2020)
  • SyntheMol: Generative AI for Drug Discovery (molecules that are easy to synthesize) (standalone).
  • MHNfs: Prompting In-Context Bioactivity Predictions for Low-Data Drug Discovery (hit discovery, hit2lead) (standalone, online).
  • DrugDiff: Small molecule diffusion model with flexible guidance towards molecular properties (standalone).
  • Dedenser: A Python Package for Clustering and Downsampling Chemical Libraries (standalone).
  • hitl-al-gomg: Human-in-the-loop Active Learning for Goal-Oriented Molecule Generation (standalone).
  • PharmacoNet: deep learning-guided pharmacophore modeling for ultra-large-scale virtual screening (standalone, 2024).
  • AAscore: Analog Accessibility Score (AAscore) for Rational Compound Selection (standalone, 2024).
  • Deepmol: an automated machine and deep learning framework for computational chemistry (standalone, 2024).
  • DrugLAMP: Accurate and Transferable Drug-Target Interaction Prediction (standalone, 2024).
  • QSPRpred: a Flexible Open-Source Quantitative Structure-Property Relationship Modelling Tool (standalone, 2024).
  • VideoMol: A molecular video-derived foundation model for scientific drug discovery (standalone, 2024).
  • ImageMol: Accurate prediction of molecular properties and drug targets using a self-supervised image representation learning framework (standalone).
  • ROBERT: Bridging the Gap Between Machine Learning and Chemistry (standalone, 2024).
  • CACTUS: Chemistry (virtual) Agent Connecting Tool Usage to Science (can be 3D also) (standalone, 2024).
  • Alzyfinder: Tools for ligand-based virtual screening and network pharmacology (standalone).
  • 3DSTarPred: Server for Target Prediction of Bioactive Small Molecules Based on 3D Shape Similarity (online, 2024).
  • Molli: A General-Purpose Python Toolkit for Combinatorial Small Molecule Library Generation,Manipulation, and Feature Extraction (standalone, 2024).
  • DataValuationPlatform: Machine Learning-Driven Data Valuation for Optimizing High-Throughput Screening Pipelines (standalone, 2024).
  • Poeclm: Navigating Ultra-Large Virtual Chemical Spaces with Product-of-Experts Chemical Language Models (standalone, 2024).
  • SCINS: An Open-Source Implementation of the Scaffold Identification and Naming System (SCINS) and Example Applications (standalone, 2024).
  • SynFormer: generative framework for synthesizable molecular design, molecular optimization, bottom-Up synthesis planning (standalone, 2024).
  • BIND: Protein language models are performant in structure-free virtual screening (standalone, 2024).
  • MolPROP: Molecular Property prediction with multimodal language and graph fusion (standalone).
  • SSM-DTA: Breaking the barriers of data scarcity in drug–target affinity prediction (standalone).
  • KinomePro-DL: predict the kinome selectivity profiles and kinome-wide polypharmacology effects of small molecules (online, 2024).
  • Mothra: Multiobjective de novo Molecular Generation Using Monte Carlo Tree Search (standalone, 2024).
  • MolPipeline: A python package for processingmolecules with RDKit in scikit-learn (standalone, 2024).
  • DrugSynthMC: An Atom-Based Generation of Drug-like Molecules with Monte Carlo Search (standalone, 2024).
  • MoFlow: an invertible flow model for generating molecular graphs (standalone).
  • SyntheMol: Generative AI for Drug Discovery (molecules that are easy to synthesize) (standalone).
  • Molecular-Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction (standalone).
  • AiZynthFinder: tool for retrosynthetic planning (standalone, 2020).
  • Komet: Drug−Target Interactions Prediction at Scale: The Komet Algorithm with the LCIdb Dataset (standalone, 2024).
  • ChatMol: Interactive Molecular Discovery with Natural Language (standalone, 2024).
  • DTI-LM: Language Model Powered Drug-target interaction prediction (standalone, 2024).
  • ChemCrow: Augmenting large language models with chemistry tools (standalone, 2024).
  • augmented_memory: Sample-Efficient Generative Molecular Design with Reinforcement Learning (standalone, 2024).
  • BuildAMol: molecular building suite designed to facilitate the generation and alteration of atomic models for large, macrocycles, small chemical structures, short peptides (standalone, 2024).
  • transformerCPI2.0: Sequence-based drug design as a concept in computational drug design (standalone, 2024).
  • STRGNN: Deep learning of multimodal networks with topological regularization for drug repositioning (standalone, 2024).
  • MolCompassViewer: a tool that provides a pretrained parametric t-SNE model for chemical space visualization and the visual validation of QSAR/QSPR models (standalone, 2024).
  • bitBIRCH: Efficient clustering of large molecular libraries (standalone, 2024).
  • iSIM: Instant similarity (standalone, 2024).
  • O-LAP: Building shape-focused pharmacophore models for effective docking screening (O-LAP, overlap-toolkit) (standalone, 2024).
  • Roshambo: Open-Source Molecular Alignment and 3D Similarity Scoring (standalone, 2024).
  • RLSynC: Offline–Online Reinforcement Learning for Synthon Completion (Retrosynthesis) (standalone, 2024).
  • RLSynC: A multimodal transformer network for protein-small molecule interactions enhances predictions of drug-target affinities and enzyme substrates (standalone, 2024).
  • ClickGen: Directed exploration of synthesizable chemical space via modular reactions and reinforcement learning (standalone, 2024).
  • bionavi: Hybrid Retrosynthesis Planning for Chemicals (online, 2024).
  • bionavi: Hybrid Retrosynthesis Planning for Chemicals (standalone, 2024).
  • BR-SAScore : synthetic accessibility with building block and reaction-aware SAScore (standalone, 2024).
  • CACTI: in silico chemical analysis for chemogenomics (standalone, 2024).
  • DeLA-DrugSelf: Empowering multi-objective de novo design through SELFIES molecular representation (hit2lead) (online, 2024).
  • Mol-CycleGAN: a generative model for molecular optimization (hit2lead) (standalone).
  • GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation (hit2lead) (standalone).
  • TorchDrug: PyTorch-based machine learning toolbox for small molecules and also for proteins (TorchProtein) (hit2lead) (standalone).
  • Gargoyles: An Open Source Graph-Based Molecular Optimization Method Based on Deep Reinforcement Learning (hit2lead) (standalone, 2024).
  • FPSim2: Simple package for fast molecular similarity searches (standalone).
  • FS-CAP: Few-Shot Compound Activity Prediction (hit2lead) (standalone, 2024).
  • DrugFlow: An AI-Driven One-Stop Platform for Innovative Drug Discovery (online, 2024).
  • SMILES-RNN: code for a SMILES-based recurrent neural network used for de novo molecule generation with several reinforcement learning algorithms (standalone).
  • AceGen: A TorchRL-based toolkit for reinforcement learning in generative chemistry (standalone).
  • SAFE: Sequential Attachment-based Fragment Embedding is a novel molecular line notation that represents molecules as an unordered sequence of fragment blocks to improve molecule design using generative models (standalone).
  • PromptSMILES: prompting for scaffold decoration and fragment linking in chemical language models (seems to miss the CLM to reproduce the article) (standalone, 2024).
  • Datamol: RDKit-powered Python library optimized for molecular machine learning workflows (standalone).
  • Molfeat: makes it easy to evaluate and implement a wide range of featurizers (datamol) (standalone).
  • MDF-DTA: A Multi-Dimensional Fusion Approach for Drug-Target Binding Affinity Prediction (standalone, 2024).
  • OLB-AC: Towards Optimizing Ligand Bioactivities Through Deep Graph Learning and Activity Cliffs (hit2lead) (standalone, 2024).
  • QSARtuna: QSAR using Optimization for Hyperparameter Tuning (standalone, 2024).
  • KinomeMETA: platform for kinome-wide polypharmacology profiling with meta-learning (online, 2024).
  • Generative Design: Generative design of compounds with desired potency from target protein sequences using a multimodal biochemical language model (standalone, 2024).
  • Holistic-screening: Consensus holistic virtual screening for drug discovery (standalone, 2024).
  • HBCVTr: an end-to-end transformer with a deep neural network hybrid model for anti-HBV and HCV activity predictor from SMILES (standalone, 2024).
  • FaissMolLib: a very fast tool for ligand-based virtual screening (standalone, 2024).
  • DrugMGR: a deep bioactive molecule binding method to identify compounds targeting proteins (standalone, 2024).
  • PPII-AEAT: Prediction of protein-protein interaction inhibitors based on autoencoders with adversarial training (generative chemistry) (standalone, 2024).
  • REINVENT 4.0: Modern AI–driven generative molecule design (generative chemistry) (standalone, 2024).
  • CNSMolGen: a bidirectional recurrent neural networks based generative model for de novo central nervous system drug design (generative chemistry) (standalone, 2024).
  • drugAI: De Novo Drug Design Using Transformer-Based Machine Translation and Reinforcement Learning of an Adaptive Monte Carlo Tree Search, published in 2024 (generative chemistry) (standalone).
  • DompeKeys: a set of novel substructure-based descriptors for efficient chemical space mapping, development and structural interpretation of machine learning models, and indexing of large databases, published in 2024 (standalone).
  • iSIM: Instant Similarity (standalone).
  • SYBA: SYnthetic BAyesian classifier (SYBA) is a Python package for the classification of organic compounds as easy-to-synthesize (ES) or hard-to-synthesize (ES) (standalone).
  • GenerativeChemTool-RNN: Generative deep learning enables the discovery of a potent and selective RIPK1 inhibitor (generative chemistry) (standalone).
  • AutoMolDesigner: An AI-based Open-source Software for Automated Design of Small-molecule Antibiotics (generative chemistry) (standalone).
  • Tree-Invent: A novel molecular generative model constrained with topological tree (generative chemistry) (standalone).
  • Ligand Expo: provides chemical and structural information about small molecules within the structure entries of the Protein Data Bank (formerly Ligand Depot) (online).
  • DeepSA: A deep-learning driven predictor of compound synthesis accessibility (standalone).
  • GCVec: GcForest-based compound-protein interaction prediction model and its application in discovering small-molecule drugs targeting CD47 (hit2lead, standalone).
  • SELFIES: Self-Referencing Embedded Strings -A 100% robust molecular string representation (standalone).
  • Bloom filters: efficiently check if a proposed molecule is present in ultra-large compound collections (standalone).
  • RAscore: Retrosynthetic accessibility score - rapid machine learned synthesizability classification from AI driven retrosynthetic planning (help generative chemistry) (standalone).
  • LigMate: A Multifeature Integration Algorithm for Ligand-Similarity-Based Virtual Screening (standalone).
  • GENiPPI: An interface-based molecular generative framework for protein-protein interaction inhibitors (PPIs) (generative chemistry) (online).
  • stoned-selfies: Beyond Generative Models: Superfast Traversal, Optimization, Novelty, Exploration and Discovery (STONED) Algorithm for Molecules using SELFIES (standalone).
  • CODD-Pred: A Web Server for Efficient Target Identification and Bioactivity Prediction of Small Molecules (online).
  • ScaffoldGVAE: scaffold generation and hopping of drug molecules via a variational autoencoder based on multi-view graph neural networks (generative chemistry) (standalone).
  • GMTransformer: Probabilistic generative transformer language models for generative design of molecules (generative chemistry) (standalone).
  • Molpert: A molecule perturbation software library and its application to study the effects of molecular design constraints (standalone).
  • MolSHAP: Interpreting Quantitative Structure–Activity Relationships Using Shapley Values of R-Groups (Hit2Lead - 2023) (standalone).
  • DrugEx: Deep Learning Models and Tools for Exploration of Drug-Like Chemical Space (2023) (generative chemistry) (standalone).
  • A-HIOT: automated hit identification and optimization tool (Hit2Lead) (standalone).
  • LOGICS: Learning optimal generative distribution for designing de novo chemical structures (2023) (generative chemistry) (standalone).
  • DFRscore: Scoring Synthesizability of Candidates for Virtual Screening (generative chemistry) (standalone).
  • DeLA-Drug: A Deep Learning Algorithm for Automated Design of Druglike Analogues (generative chemistry) (standalone).
  • DenovoProfiling: A webserver for de novo generated molecule library profiling (generative chemistry) (online).
  • GENERA: A Combined Genetic/Deep-Learning Algorithm for Multiobjective Target-Oriented De Novo Design (generative chemistry) (can take 3D docking scores as features) (standalone).
  • CREM: generate chemical structures using a fragment-based approach (standalone).
  • SMILES-corrector: UnCorrupt SMILES: a novel approach to de novo design (generative chemistry) (standalone).
  • MF-PCBA: Multifidelity High-Throughput Screening Benchmarks for Drug Discovery and Machine Learning (standalone).
  • TransformerCPI: improving compound-protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments (this is not LB-VS per se) (standalone).
  • SELPPI: Using a stacked ensemble learning framework to predict modulators of PPIs (standalone).
  • MBROLE3: Functional enrichment analysis of chemical compounds (online).
  • Connectivity Map: L1000 Platform and the First 1,000,000 Profiles (online).
  • FunARTS: Identification of fungal bioactive compounds (online).
  • EDmodel: Investigation of chemical structure recognition by encoder–decoder models in learning progress (standalone).
  • QSAR-activity-cliff: Systematically Exploring QSAR Models for Activity-Cliff Prediction (standalone).
  • TAME-VS: Target-driven machine learning-enabled virtual screening platform for early-stage hit identification (standalone).
  • ACP4: 3D-Sensitive Encoding of Pharmacophore Features (compare ligand in 3D or ligand-binding sites (holo structures) can compare pockets) (standalone).
  • CBFP: Computational Bioactivity Fingerprint Similarities To Navigate the Discovery of Novel Scaffolds - scaffold hopping. R code (standalone).
  • PyRMD: A New Fully Automated AI-Powered Ligand-Based Virtual Screening Tool (standalone).
  • MolFilterGAN: a progressively augmented generative adversarial network for triaging AI-designed molecules (standalone).
  • Sc2Mol: a scaffold-based two-step molecule generator with variational autoencoder and transformer (generative chemistry) (standalone).
  • MultipleComparisons: allows to calculate and process extended (e.g., n-ary) similarity indices (standalone).
  • iPPIGAN: De novo molecular design with deep molecular generative models for PPI inhibitors (ligand-based) (generative chemistry) (standalone).
  • LigDream: Shape-Based Compound Generation (ligand-based) (generative chemistry) (standalone).
  • ASAP: Critical assessment of synthetic accessibility scores in computer-assisted synthesis planning (AiZynthFinder) (generative chemistry validation) (standalone).
  • COPFEA: COrrelated Pharmacophore FEatures Analysis - Identifies correlative pharmacophore features of small molecules from the trajectories of molecular dynamic simulations (standalone).
  • MacFrag: segmenting large-scale molecules to obtain diverse fragments with high qualities (compound fragmentation) (standalone).
  • MORTAR: a rich client application for in silico molecule fragmentation (standalone app).
  • DrugRep: an automatic virtual screening server (structure-based or ligand-based) for drug repurposing (online).
  • cpi_cpp: A deep learning method for predicting molecular properties and compound-protein interactions (standalone).
  • iRaPCA and SOMoC: New Approaches for the Clustering of Small Molecules (standalone, online - paper suppl).
  • Ring Replacement Recommender: Ring modifications for improving biological activity (related to bioisosteric replacement) (data).
  • Usrcat_sim: Creation of targeted compound libraries based on 3D shape recognition (standalone).
  • mmpdb: An Open-Source Matched Molecular Pair Platform for Large Multiproperty Data Sets (bioisosteric and related) (standalone).
  • Molecular-AI: Molecular Optimization by Capturing Chemist's Intuition Using Deep Neural Networks (standalone).
  • MB-Isoster: to build molecules based on bioisosterism principles (standalone).
  • AFSE: towards improving model generalization of deep graph learning of ligand bioactivities targeting GPCR proteins (online).
  • AIMSim: a tool for visualizing molecular diversity using structural fingerprints (standalone).
  • REINVENT 2.0: an AI tool for de novo compound generation under constraints (autoencoders) (standalone).
  • ReinventCommunity: notebook tutorials for REINVENT 3.2 (standalone).
  • LiSiCA: Ligand Similarity using Clique Algorithm is a ligand-based virtual screening software that searches for 2D and 3D similarities between a reference compound and a database of target compounds which should be represented in a Mol2 format. The similarities are expressed using the Tanimoto coefficients and the target compounds are ranked accordingly (standalone).
  • DrugEx v2: de novo design of drug molecules by Pareto-based multi-objective reinforcement learning in polypharmacology (DrugEx v2 (Drug Explorer V2)) (standalone).
  • Empire: Scaffold-Retained Structure Generator to Exhaustively Create Molecules in an Arbitrary Chemical Space (standalone).
  • SCScore: The model assigns a synthetic complexity (S Accessibility) score between 1 and 5 to a molecule. The score is based on the premise that published reactions, overall, should exhibit an increase in synthetic complexity. The model has been trained on 12M reactions from Reaxys (standalone).
  • AILDE: Protocol for hit-to-lead optimization of compounds by auto in silico ligand directing evolution approach (standalone).
  • SECSE: Systemic Evolutionary Chemical Space Explorer (standalone).
  • SOM_Screen: Ligand Based Virtual Screening Using Self-organizing Maps (standalone).
  • VSFlow: python scripts for ligand-based virtual screening (2D and 3D) (standalone).
  • MERMAID: an open source automated hit-to-lead (hit2lead) method based on deep reinforcement learning. This method generates partial SMILES and inserts it into the original SMILES using Monte Carlo Tree Search and a Recurrent Neural Network (standalone).
  • Pria-ams-enamine: AI-powered ligand-based virtual screening on PriA-SSB with the AMS and Enamine REAL libraries (ultra-large) (standalone).
  • Open3DALIGN: unsupervised molecular alignment (standalone).
  • pdCSM-PPI: Using Graph-Based Signatures to Identify Protein-Protein Interaction Inhibitors (PPI) (online).
  • FASMIFRA: Molecular generation by Fast Assembly of (Deep)SMILES fragments (standalone).
  • DeepHop: Deep scaffold hopping with multimodal transformer neural networks (standalone).
  • DeepFMPO v3D: On the value of using 3D-shape and electrostatic similarities in deep generative methods (Multi-parameter optimization) (online).
  • RealVS: Toward Enhancing the Precision of Top Hits in Ligand-Based Virtual Screening of Drug Leads from Large Compound Databases (this site computes also fingerprints and different descriptors including RDKIT) (online) (online).
  • PrepFlow: A Toolkit for Chemical Library Preparation and Management for Virtual Screening (standalone).
  • LibINVENT: Reaction-based Generative Scaffold Decoration for in Silico Library Design (standalone).
  • MAP4: a new molecular fingerprint suitable for drugs, biomolecules, and the metabolome and can be adopted as a universal fingerprint to describe and search chemical space (standalone) implemented online for example here (http://map-search.gdb.tools/).
  • QSAR-Co-X: an open source toolkit for multitarget QSAR modelling (standalone).
  • PyRMD: A New Fully Automated AI-Powered Ligand-Based Virtual Screening Tool (random matrix theory) (standalone).
  • LigAdvisor: a versatile and user-friendly web-platformfor drug design (online).
  • Covid19_pred: Stratified-bagging models for the prediction of SARS-CoV-2 Inhibitors (Covid-19) (standalone).
  • NCATS Predictor: QSAR data sets and models related to the NCATS projects (standalone and online).
  • Enamine REAL database: search (similarity) for analogs in the Enamine REAL database (over 1.95 billion molecules which comply with rule of 5 and Veber criteria: MW≤500, SlogP≤5, HBA≤10, HBD≤5, rotatable bonds≤10, and TPSA≤140) (ultra-large screening) (online).
  • CoVID19screen: Predicting Potential SARS-COV-2 Drugs-In Depth Drug Database Screening Using Deep Neural Network Framework SSnet, Classical Virtual Screening and Docking (standalone).
  • ChemGenerator: a web server for generating potential ligands for specific targets based on user input ligands, virtual compounds (online).
  • REINVENT 2.0: an AI Tool for De Novo Drug Design (standalone).
  • sensaas: Shape-based Alignment by Registration of Colored Point-based Surfaces (standalone).
  • Cloud 3D-QSAR: a web tool for the development of quantitative structure-activity relationship models in drug discovery (online).
  • REDIAL-2020: A Suite of Machine Learning Models to Estimate Anti-SARS-CoV-2 Activities (Covid-19) (online).
  • DECIMER: towards deep learning for chemical image recognition (image to smiles) (standalone).
  • MolNexTR: image to smile (standalone).
  • D3Similarity: A Ligand-Based Approach for Predicting Drug Targets and for Virtual Screening of Active Compounds Against COVID-19 (online).
  • Cell2Chem: Mining Explored and Unexplored Biosynthetic Chemical Spaces (online).
  • RANKERS: Ranking Molecules with Vanishing Kernels and a Single Parameter: Active Applicability Domain Included (standalone).
  • Spaya: uses Artificial Intelligence to discover and prioritize synthetic routes (beta version March 2020) (online).
  • Ccbmlib: A Python Package for Modeling Tanimoto Similarity Value Distributions (standalone).
  • FragPELE: Dynamic ligand growing within a binding site. A novel tool for hit-to-lead Drug Design (standalone).
  • Craig plot 2.0: an interactive navigation in the substituent bioisosteric space (online).
  • Mol-CycleGAN: a generative model for molecular optimization (generates optimized compounds with high structural similarity to the original ones) (standalone).
  • PubChem3D: search PubChem in 3D (online).
  • LatentGAN: A de novo molecular generation method using latent vector based generative adversarial network (standalone).
  • ChEMBL-Likeness Score and Database GDBChEMBL: virtual compounds (online).
  • Chemprop (V2 end of 2025): Machine Learning /AI for Molecular Property Prediction (at present for Antibiotics) (standalone).
  • Chemprop: Machine Learning /AI for Molecular Property Prediction (at present for Antibiotics) (online).
  • Alvascience: alvaMolecule (visualise, analyse, curate and standardize molecular dataset), alvaDesc (computes about 5000 molecular descriptors and molecular fingerprints), alvaModel (creates QSAR/QSPR models) that are deployed via alvaRunner.
  • TMAP: A new data visualization method, TMAP, capable of representing data sets of up to millions of data points and arbitrary high dimensionality as a two-dimensional tree. Visualizations based on TMAP are better suited than t-SNE or UMAP for the exploration and interpretation of large data sets due to their tree-like nature. The Python source code for TMAP is available on GitHub (https://github.com/reymond-group/tmap).
  • Kinase inhibitor models: Machine Learning Models for Accurate Prediction of Kinase Inhibitors with Different Binding Modes. Datasets and models (standalone).
  • GPUSVMSCREEN: Ligand based virtual screening using SVM on GPU (standalone).
  • PPIMpred: high-throughput 2D screening (machine learning) of small molecules for targeting specific protein–protein interactions, namely Mdm2/P53, Bcl2/Bak and c-Myc/Max (online).
  • KekuleScope: Prediction of cancer cell line sensitivity and compound potency using convolutional neural networks trained on compound images (standalone).
  • LSC: Large-scale comparison of machine learning methods for drug target prediction on ChEMBL (code and datasets, deeplearning... standalone).
  • HTS_shrink: Fully automatic Distance-Based Boolean Applicability Domain (DBBAD) algorithm for category QSAR (standalone).
  • 3d-qsar.com: a web portal that brings 3-D QSAR to all electronic devices-the Py-CoMFA web application as tool to build models from pre-aligned datasets (standalone and online).
  • open3dqsar: A New Workflow for QSAR Model Development from Small Data Sets: Integration of Data Curation, Exhaustive Double Cross-Validation and A Set of Optimal Model Selection Techniques. Many other tools (standalone).
  • GDBMedChem: Medicinal Chemistry Aware Database GDBMedChem (10 million virtual cmpds) (online).
  • BRUSELAS: HPC generic and customizable software architecture for 3D ligand-based virtual screening of large molecular databases (shape similarity searching and pharmacophore screening) (online).
  • smallmoleculesuite: Cheminformatics Tools for Analyzing and Designing Optimized Small-Molecule Collections and Libraries (eg, liganded genome, kinases…) (R shiny online).
  • Faerun Viz of NLP and NLC: MXFP (macromolecule extended atom‐pair fingerprint), a 217‐D fingerprint tailored to analyze large molecules in terms of molecular shape and pharmacophores. Visualize non‐Lipinski PubChem (NLP) and ChEMBL (NLC) interactively using Faerun (online).
  • FINDSITEcomb2.0: A New Approach for Virtual Ligand Screening of Proteins and Virtual Target Screening of Biomolecules (online).
  • SIME: synthetic insight-based macrolide enumerator to generate the V1B library of 1 billion macrolides (standalone).
  • V1B: 1 billion virtual library - macrolides - macrocyles (standalone).
  • ChemoTyper: tool that allows for searching and highlighting chemical chemotypes (chemical substructures or subgraphs) in datasets of molecules. Can be used to search for structural alerts (standalone).
  • MolOpt: A web server for drug design using bioisosteric transformation (online).
  • Scaffold Keys: Bioisosteric Search using Scaffold Keys (online).
  • MB-Isoster: A software for bioisosterism simulation (optimize lead compounds in drug research, 2D and 3D) standalone, 2018.
  • ChemMaps.com: Exploring chemical spaces.
  • Sachem: a chemical cartridge for high-performance substructure search (standalone).
  • Diversity Genie: analyze cmpds - collection diversity (standalone).
  • SwissSimilarity: virtual screening using different approaches (online).
  • WDL-RF: weighted deep learning and random forest pipeline for bioactivity prediction of GPCR-associated ligand molecules (online).
  • LS-align: an atom-level, flexible ligand structural alignment algorithm for high-throughput virtual screening (standalone).
  • Automated framework for QSAR: An automated framework for QSAR model building in Knime (standalone).
  • Ezqsar: An R Package for Developing QSAR Models Directly From Structures (standalone).
  • ChemSAR: an online pipelining platform for molecular SAR modeling - machine learning (online).
  • ChemDes: an integrated web-based platform for molecular descriptor and fingerprint computation (online).
  • RRegrs: an R package for computer-aided model selection with multiple regression models (standalone).
  • QSARINS: build QSAR models - machine learning (standalone).
  • camb: Chemically Aware Model Builder, an R package for property and bioactivity modelling of small molecules (standalone).
  • Cluster: The open source clustering software Cluster 3.0 (standalone).
  • Molecular Autoencoder: converts discrete representations of molecules to and from a vector representation, deep learning (standalone).
  • Recursive Neural Networks: Inner- and Outer Recursive Neural Networks for Chemoinformatics... (deep learning) (standalone).
  • Variational autoencoder (VAE): framework and code for constructing a variational autoencoder (VAE) for use with molecular SMILES... (deep learning) (standalone).
  • Mol2vec: an unsupervised machine learning approach to learn vector representations of molecular substructures, deep learning (standalone).
  • Rchemcpp: online structural analoging (structural analogs are compounds having a similar chemical structure to a given query compound) in ChEMBL, Drugbank and the Connectivity Map (online).
  • Consent: ligand-based virtual screening with consensus queries) (standalone.
  • Pharmit: pharmacophore mainly pocket-based (online).
  • pepMMsMIMIC: given a peptide three-dimensional structure, is able to automate a multiconformers three-dimensional similarity search among 17 million of conformers (online).
  • Combinatorial-chem-design: De novo generated combinatorial library design (generative chemistry) (standalone).
  • Consensus Diversity Plots: This tool will help you to compare and clasify data sets using diversity metrics (i.e. scaffold counts, fingerprints similarity, molecular properties), describe how diverse each data set is and determine which one is the most diverse (online).
  • Activity Landscape Plotter: SAR, activity cliff, hit2lead (online).
  • BoBER: bioisosteric and scaffold hopping replacements, hit2lead (online).
  • PUMA: Platform for Unified Molecular Analysis (online).
  • ChemMine: service for analyzing and clustering small molecules by structural similarities, physicochemical properties or custom data types (online).
  • PharmMapper: reversed pharmacophore matching (online).
  • ZINCPharmer: free pharmacophore search software for screening the purchasable subset of the ZINC database. ZINCPharmer can import LigandScout and MOE pharmacophore definitions, as well as identify pharmacophore features directly from structure (online).
  • SMARTS-plus: A Toolbox for Chemical Pattern Design (online).
  • LiSiCA PyMOL plugin: Ligand-based virtual screening interface between PyMOL and LiSiCA (standalone).
  • VIDEAN: Visual Analytics in Cheminformatics, User-Supervised Descriptor Selection for QSAR Methods (online).
  • wwLig-CSRre: a 3D ligand-based server for hit identification and optimization (online).
  • ChemmineR: Cheminformatics Toolkit for R (standalone).
  • Dimorphite-DL: an open-source program for enumerating the ionization (protonation) states of drug-like small molecules (standalone, requires RDKIT).
  • OpenBabel: file format and more (standalone).
  • Unicon: command-line tool to cope with common cheminformatics tasks (convert file format, file conversion between standard formats SDF, MOL2, SMILES, PDB, and PDBx/mmCIF via the generation of 2D structure coordinates and 3D structures to the enumeration of tautomeric forms, protonation states, and conformer ensembles (standalone).
  • Tautobase: An Open Tautomer Database DataWarrior file: (Tautobase.dwar) and SMIRKS transformations: (Tautobase_SMIRKS.txt) (standalone).
  • webDrugCS: Interactive 3D-Visualization of DrugBank chemical space in the web browser (online).
  • Xfp-Browsers: for pharmacophore similarity search online.
  • 3D-APfp-Browsers: for shape similarity search online.
  • MQN Mapplets: similarity search standalone.
  • Multi Fingerprint Browsers: online.
  • cApp: analyze collections, clustering... (standalone).
  • molBLOCKS: fragments, clusters..., (standalone).
  • MayaChemTools: similarity search, descriptors, AutoDock Vina, Meeko, and RDKit, etc (standalone).
  • KNIME: HitSEE..., workflow, etc (standalone).
  • FAF-Drugs4 and FAF-QED: prepare compound collections, filtering, etc (online).
  • DeepDL: Drug-likeness scoring based on unsupervised learning (kind of QED score via RNN) (standalone).
  • Ambitcli: no 3D but Java application for standardization (standalone).
  • Ambit-Tautomer: Ambit2 (standalone).
  • Molecule Validation and Standardization: MolVS (standalone).
  • chEMBL standardiser: prepare small molecules, curation (standalone).
  • PubChem Standardization Service: prepare small molecules, curation (online).
  • PaDEL: molecular descriptors for machine learning (standalone).
  • Mordred: a molecular descriptor calculator (standalone).
  • CVAE: Molecular generative model based on conditional variational autoencoder for de novo molecular design (standalone).
  • PyDPI: Freely Available Python Package for Chemoinformatics, Bioinformatics, and Chemogenomics Studies (descriptors proteins, ligands, computation of fingerprints...) (standalone).
  • OpenGrowth: de novo ligand design (standalone).

Repositioning, repurposing, polypharmacology, target fishing, drug combination

  • DBR-X: DrugMechDB relevant files of curated mechanism for DBR-X (data)
  • DBR-X: MIND knowledge graph for DBR-X (data)
  • DBR-X: A Case-Based Explainable Graph Neural Network Framework for Mechanistic Drug Repositioning (standalone 2026)
  • ProfhEX: Empowering Early Drug Discovery with Machine Learning-Based Target Profiling and Liability Prediction (online 2025)
  • Tahoe-x1: Scaling Perturbation-Trained Single-Cell Foundation Models to 3 Billion Parameters (the method could be applied for repositioning but can do much more) (standalone 2026)
  • DeepSEQreen: accelerates early stage drug discovery by integrating a variety of cutting-edge sequence-based deep learning models for drug-target interaction prediction (online 2025)
  • DeepDRK: a deep learning framework for drug repurposing through kernel-based multi-omics integration (standalone, 2024).
  • Chemogenomic-Model: In-Silico Target Prediction by Ensemble Chemogenomic Model based on Multi-Scale Information of Chemical Structures and Protein Sequences (standalone)
  • MOViDA: multiomics visible drug activity prediction with a biologically informed neural network model (DTI) (standalone)
  • DTINet: A Network Integration Approach for Drug-Target Interaction Prediction (standalone)
  • DACPGTN: An end-to-end model DACPGTN for predicting ATC code for a given drug (standalone)
  • CDCDB: Continuous-Drug Combination DataBase (online)
  • DrugRepo: a novel approach to repurposing drugs based on chemical and genomic features (online)
  • DrugRep: an automatic virtual screening server (structure-based or ligand-based) for drug repurposing (online)
  • EviCor: Interactive Web Platform for Exploration of Molecular Features and Response to Anti-cancer Drugs (online)
  • PLATO: Polypharmacology pLATform predictiOn (target fishing) (online)
  • PharmOmics: A species- and tissue-specific drug signature database and gene-network-based drug repositioning tool (online)
  • DrugShot: querying biomedical search terms to retrieve prioritized lists of small molecules (text mining) (appyters) (online)
  • DrugShot: querying biomedical search terms to retrieve prioritized lists of small molecules (text mining) (online)
  • SBGNview: towards data analysis, integration and visualization on all pathways (standalone)
  • PATHOME-Drug: a subpathway-based polypharmacology drug-repositioning method (online)
  • DRUIDom: Protein domain-based prediction of drug/compound-target interactions (DRUg Interacting Domain prediction, DTI) - (PubChem - Chembl datasets) (standalone)
  • Multiscale-interactome: Identification of disease treatment mechanisms through the multiscale interactome (standalone)
  • CSNAP3D: 3D chemical similarity using a network algorithms score - target fishing (online)
  • STarFish: combining multiple multi-target QSAR models for target fishing (model stacking) - target fishing (standalone)
  • DGB: Drug Gene Budger Assists investigators in order to prioritize small molecules that are predicted to maximally influence the expression of their target gene of interest. Users can enter a gene symbol along with the wish to upregulate or downregulate its expression. Data signatures are extracted from the LINCS L1000 dataset, the original Connectivity Map (CMap) dataset, and the Gene Expression Omnibus (GEO) (online)
  • CREEDS: Crowd Extracted Expression of Differential Signatures (online database)
  • DrugMatrix: Molecular toxicology reference database and informatics system. Large-scale gene expression data (online database)
  • CEBS: Chemical Effects in Biological Systems (online database)
  • VirtualFlow @ Covid19: Ultra-large structure-based virtual screening SARS-CoV-2 related targets (top 1 million compounds and repositioning) (COVID-19 datasets online)
  • LigAdvisor: a versatile and user-friendly web-platformfor drug design (online)
  • CROssBAR: Comprehensive Resource of Biomedical Relations with Deep Learning Applications and Knowledge Graph Representations (standalone and online)
  • ePharmaLib: A Versatile Library of e-Pharmacophores to Address Small-Molecule (Poly-)Pharmacology. A library of 15,148 e-pharmacophores modeled from solved structures of pharmaceutically relevant protein-ligand complexes of the screening Protein Data Bank (sc-PDB). ePharmaLib can be used for target fishing of phenotypic hits, side effect predictions, drug repurposing, and scaffold hopping (online)
  • PharmOmics: prediction of potential drugs targeting disease processes that were identified by Mergeomics (online)
  • Standardize Drug Names: script to standardize drug names (standalone)
  • LigTMap: ligand and structure-based target identification and activity prediction for small molecular compounds (standalone)
  • multi_DTI: Deep learning integration of molecular and interactome data for protein–compound interaction prediction (standalone)
  • PHENSIM: RapidIdentification of Druggable Targets and the Power of the PHENotype SIMulator for Effective Drug Repurposing in COVID-19 (standalone)
  • LigTMap: Ligand and Structure-Based Target Identification and Activity Prediction for Small Molecular Compounds (identify protein targets of chemical compounds among 17 classes of therapeutic proteins (and 6000+ proteins) (profiling) (online)
  • Epigenetic Target Profiler: A Web Server to Predict Epigenetic Targets of Small Molecules (online)
  • FRAGSITE: A Fragment-Based Approach for Virtual Ligand Screening. For virtual ligand screening: screening a protein against library of compounds. For virtual target screening: screening a compound against the Human proteome (online)
  • CCVPAP-SARS-COV-2: A Modelling Framework for Embedding-based Predictions for Compound-Viral Protein Activity (Covid-19) (standalone)
  • ReFRAME: collection of 12,000 compounds is a best-in-class drug repurposing library containing nearly all small molecules that have reached clinical development or undergone significant preclinical profiling (online)
  • Drugvirus.info: Broad-spectrum antiviral agents (BSAAs) and viruses they inhibit (Covid-19) (online)
  • DRDOCK: performs online automatic virtual drug screening of 2016 FDA-approved drugs on a user-submitted target protein. Combines molecular docking and molecular dynamic simulations to prioritize strong binders from less likely binders (online)
  • CORDITE: CORona Drug InTERactions database - COVID-19 (database online)
  • CoronaVIR: predicted and existing information on coronavirus severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) (COVID-19) (online)
  • H-RACS: a handy tool to rank anti-cancer synergistic drugs (online)
  • DockThor-VS Web Server: Virtual Screening focusing on SARS-CoV-2 Therapeutic Targets and their Non-Synonym Variants (Covid-19), drug Repurposing (online)
  • DockCoV2: a drug database against SARS-CoV-2 (COVID-19) (online)
  • PubChem COVID-19: COVID-19 (Coronavirus Disease 2019) data in PubChem (data)
  • ChEMBL_27 SARS-CoV-2 release: COVID-19 experimental screening (dataset)
  • SPVec: Codes and datasets for SPVec, A Word2vec-inspired feature representation method for Drug-Target Interaction Prediction (standalone)
  • COVID-19: COVID-19 Worldwide Preclinical Studies, Targeting COVID-19 Portal (dataset online)
  • Chemical Checker Covid-19: Bioactivity Profile Similarities to Expand the Repertoire of COVID-19 Drugs, suggested compounds and possible targets (dataset)
  • Stanford Coronavirus Antiviral Research Database: compounds and some possible targets COVID-19 Drugs (dataset)
  • MTiOpenScreen (repositioning): Online structure-based screening of purchasable approved drugs and natural compounds: retrospective examples of drug repositioning on cancer targets - (used for COVID-19, the Drugs-lib is used, the reference is Lagarde et al., PMID: 30190791) (online)
  • FastTargetPred: a program enabling the fast prediction of putative protein targets for input chemical databases - drug repositioning, phenotypic screening... drug target interactions... (standalone, 2020)
  • ADRriskestimator: The Development of a Scoring and Ranking Strategy for a Patient-Tailored Adverse Drug Reaction Prediction in Polypharmacy (drug combination, toxicity) (online)
  • HDR: Drug repositioning based on a heterogeneous network of drugs and diseases (Cytoscape standalone app)
  • Chemical Checker on Covid19: Expanding the universe of drugs to fight SARS-CoV-2 (Covid19) (online)
  • MDock: automated molecular docking software to simultaneously dock ligands against multiple protein structures or conformations by using the ensemble docking algorithm (standalone)
  • cando.py: Open Source Software for Predictive Bioanalytics of Large Scale Drug-Protein-Disease Data (Conda Python package installer, standalone)
  • iBioProVis: Interactive Visualization and Analysis of Compound Bioactivity Space (drug repositioning - target fishing - online)
  • CTRP: the Cancer Therapeutic Response Portal measured sensitivity of 242 genetically characterized cancer cell lines to 354 small molecule probes and drugs (dataset)
  • CCLE: The Cancer Cell Line Encyclopedia (dataset)
  • CC: Chemical Checker provides processed, harmonized and integrated bioactivity data on about 800,000 small molecules (combined similarity search and biological activity named CC signatures). The tool helps for target identification and library characterization, discovery of compounds that reverse and mimic biological signatures of disease models and genetic perturbations (online)
  • GalaxySagittarius: Structure- And Similarity-Based Prediction of Protein Targets for Drug-Like Compounds (input 1 ligand) - Target Fishing (online)
  • PaccMann: A Web Service for Interpretable Anticancer Compound Sensitivity Prediction (drug repositioning - online)
  • QuartataWeb: Chemical-protein-pathway mapping for polypharmacology and chemogenomics. (Users can easily obtain information on experimentally verified (known) and computationally predicted (new) interactions between 5,494 drugs and 2,807 human proteins in DrugBank, and between 315,514 chemicals and 9,457 human proteins in the STITCH database). Query a series of chemicals, drug combinations, or multiple targets, to enable multi-drug, multi-target, multi-pathway analyses (online)
  • iATC-NRAKEL: An Efficient Multi-Label Classifier for Recognizing Anatomical Therapeutic Chemical Classes of Drugs (standalone)
  • ATC code prediction: Anatomical Therapeutic Chemical Classes of Drugs (standalone)
  • Polypharmacology: A Python implementation of Polypharmacology pipeline to generate a dataset of reference ligands, perform in silico target fishing on the dataset, identify similar compounds between two or more targets in the dataset etc. (standalone)
  • DrugClust: A machine learning approach for drugs side effects prediction (R, standalone)
  • Genomics of Drug Sensitivity in Cancer (GDSC): data set contains over 1000 cancer cell lines and 225 drugs (database online)
  • iATC-NRAKEL: an efficient multi-label classifier for recognizing anatomical therapeutic chemical classes of drugs (ATC) (standalone)
  • eModel-BDB: database of comparative structure models of drug-target interactions from the Binding Database (database online)
  • PharmacoGx: an R package for analysis of large pharmacogenomic datasets (gene signature) (standalone)
  • DIA-DB: prediction of diabetes drugs (ligand-based and inverse screening) (online)
  • DailyMed: provides trustworthy information about marketed drugs in the United States - Database (online)
  • LSC: Large-scale comparison of machine learning methods for drug target prediction on ChEMBL (code and datasets, deeplearning... standalone)
  • X2K: Web infers upstream regulatory networks from signatures of differentially expressed genes (standalone)
  • DeepCOP: deep learning-based approach to predict gene regulating effects of small molecules (standalone)
  • deepDR: A network-based deep learning approach to in silico drug repositioning (standalone)
  • DrugZ: DrugZ is an open-source Python software for the analysis of genome-scale drug modifier screens. The software accurately identifies genetic perturbations that enhance or suppress drug activity. Identifying chemogenetic interactions from CRISPR screens with drugZ (standalone)
  • EK-DRD: A Comprehensive Database for Drug Repositioning Inspired by Experimental Knowledge. EK-DRD contains experimentally validated drug repositioning annotation for 1861 FDA-approved and 102 withdrawn small molecule drugs. Annotation is done at four levels, using 30,944 target assay records, 3999 cell assay records, 585 organism assay records, and 8910 clinical trial records (online)
  • ReactomeFIViz: drug-target visualization in the context of pathways and networks (integrates drug-target interaction information with high quality manually curated pathways and a genome-wide human functional interaction network). Both the pathways and the functional interaction network are provided by Reactome (Reactome Cytoscape app standalone)
  • PPB2: Polypharmacology prediction (online)
  • PROTEINATOR: enables repurposing of leads based on secondary interactions. Direct Drugs are listed and Indirect Drugs (Compounds that bind to the 'first-neighbour' of the primary protein(s)) (online)
  • PatchSearch: a web server for off-target protein identification (input a protein complexed with a ligand and identifies within user-defined or predefined collections of protein structures, those having a binding site compatible with this ligand in terms of geometry and physicochemical properties) (online)
  • Drug ReposER: web server for predicting similar amino acid arrangements to known drug binding interfaces for potential drug repositioning (pocket comparison, ligand transposition) (online)
  • DEEPScreen: Virtual Screening Using Convolutional Neural Networks By Images of Compounds (standalone)
  • TIN-X: target importance and novelty explorer (prediction via text mining) (online)
  • ReDO_DB: the repurposing drugs in oncology database (online)
  • Target2: Predicting protein targets for drug-like compounds using transcriptomics (LINCS Data) (data set)
  • Drug Targetor: a web interface to investigate the human druggome for over 500 phenotypes
  • PathwayMap: Fast prediction of the interaction between a set of ligands (similarity) and major human biological and signaling pathways using state-of-the-art neural networks (online)
  • CONNECTOR: predicts propensity of putative drug-protein interactions based on similarity between the input drug structure, drug profile, and/or protein sequence and the experimental drug-protein interactions that are included in the internal database (online)
  • DIGREM: Drug-Induced Genomic Response models for identification of Effective Multi-drug combinations, an online tool kit that can effectively predict drug synergy (online)
  • Drug-Target Explorer: DTexplorer, Probing the chemical–biological relationship space (phenotypic screening, polypharmacology, prediction of molecular targets for novel molecules based on structural similarity (online)
  • SynergyFinder: a web application for analyzing drug combination dose-response matrix data (online)
  • SynergyFinder: an interactive tool for analyzing drug combination dose-response data (online)
  • SYNERGxDB: an integrative pharmacogenomic portal to identify synergistic drug combinations for precision oncology (online)
  • Combenefit: an interactive platform for the analysis and visualization of drug combinations (for windows) standalone
  • Similarity ensemble approach (SEA): the approach relates proteins based on the set-wise chemical similarity among their ligands (online)
  • Open Targets: visualisation of potential drug targets associated with disease (online)
  • DrugDiseaseNet: a novel computational approach for drug repurposing using systems biology (R package) (standalone)
  • eRepo-ORP: contains data generated for the repositioning of DrugBank drugs to Orphanet proteins (online data)
  • Chemotext: Publicly-Available Web Server for Mining Drug-Target-Disease Relationships in PubMed (polypharmacology, repositioning...) (online)
  • TargetNet: a web service for predicting potential drug-target interaction profiling via multi-target SAR models. When the user submits a molecule, the server will predict the activity of the user’s molecule across 623 human proteins by establishing the high quality QSAR model for each human protein (thus 623 QSAR models), thus generating a DTI profiling that can used as a feature vector for wide applications (online)
  • Probe Miner: Objective Assessment of Chemical Probes. This resource provides evaluation of > 1.8m small molecules against for >2,200 human targets (online, input target name)
  • DTINet: novel drug–target interactions from a constructed heterogeneous network (standalone)
  • ChemViz2: extends the capabilities of Cytoscape into the domain of cheminformatics (Cytoscape App, standalone, help to visualize data)
  • AVCpred: Antiviral compound prediction via QSAR (input SDF, online)
  • Mantra: computational tool for the analysis of the Mode of Action (MoA) of novel drugs and the identification of known and approved candidates for “drug repositioning”. It is based on network theory and non-parametric statistics on gene expression data (online)
  • SwissTargetPrediction: allows to predict the targets of a small molecule. Using a combination of 2D and 3D similarity measures, it compares the query molecule to a library of 280'000 compounds active on more than 2000 targets of 5 different organisms (online)
  • DGIdb 4: Drug gene interactions database. User-friendly browsing, searching, and filtering of information on drug-gene interactions and the druggable genome, mined from over thirty trusted sources (online)
  • KEGG Drug: comprehensive drug information resource for approved drugs in Japan, USA, and Europe (online)
  • DrugCentral: search by drug, target name and by pharmacologic action (online)
  • ChemCom: (Chemical Comparator) is a computer application which facilitates searching and comparing chemical libraries (standalone)
  • DINIES: Drug-target Interaction Network Inference Engine based on Supervised Analysis enables us to predict potential interactions between drug molecules and target proteins, based on drug data and omics-scale protein data (online)
  • BalestraWeb: efficient online evaluation of drug–target interactions (online)
  • ProBis: align protein binding site (online)
  • KEGG: Kyoto Encyclopedia of Genes and Genomes (database online)
  • GO: Gene Ontology Consortium (online)
  • UniProt: provide the scientific community with a comprehensive, high-quality and freely accessible resource of protein sequence and functional information (online)
  • GEO2R: compare two or more groups of Samples in order to identify genes that are differentially expressed across experimental conditions (online)
  • PDID: Protein-Drug Interaction Database in the structural human proteome (similar binding site, docking, inverse docking) (online)
  • e-LEA3D: docking (online)
  • MANORAA: Mapping Analogous Nuclei Onto Residue And Affinity for identifying protein–ligand fragment interaction, pathways and SNPs (online)
  • Phenolyzer: stands for Phenotype Based Gene Analyzer, a tool focusing on discovering genes based on user-specific disease/phenotype terms (online)
  • DRABAL: Novel Method for Mining Large High-throughput Screening Assays using Bayesian Active Learning (standalone)
  • webDrugCS: Interactive 3D-Visualization of DrugBank chemical space in the web browser (online)
  • MeSHDD (text mining) MeSH-based Drug-Drug Similarity and Repositioning (online)
  • MeSHHeading2vec: a new method for representing MeSH headings as vectors based on graph embedding algorithm (standalone)
  • PatchSearch (pocket-based) standalone
  • RepoDB (database for drug repositioning) online
  • SIMCOMP/SUBCOMP (target fishing), input mol file, online
  • CSNAP (target fishing), Large-scale Chemical Similarity Networks for Drug Target Profiling of Compounds Identified in Cell-based Chemical Screens (online)
  • Drug Repurposing Hub (online)
  • Off-label and polypharmacy side effect databases (online download) (Offsides)
  • Twosides databases (polypharmacy side effects for pairs of drug, online to download)
  • SIDER (ADR of marketed medicines), contains information on marketed medicines and their recorded adverse drug reactions (online)
  • LINCSCLOUD or CLUE.IO (perturbation-driven gene expression dataset, online)
  • PharmMapper (reversed pharmacophore matching, target fishing) online
  • Rephetio: Drug repurposing predictions (online)
  • Hetionet (integrative network of biomedicine) standalone
  • CoGe (comparative genomics) online
  • Enrichr (datasets of diseases, genes..) online, input BED or list of genes
  • Drugs.com (data about drugs and clinical trials) online
  • JAPIC (side effects) (online)
  • DrugKiNET (kinase inhibitors) online
  • PDSP Ki database
  • Drug Repurposing Wiki (online)
  • Breakthrough Therapies chart: is a list of all publicly announced breakthrough therapy designations since the program’s inception in 2012 (online)
  • SDTNBI: an integrated network and chemoinformatics tool for systematic prediction of drug-target interactions and drug repositioning (standalone)
  • DTome: Drug-Target Interactome (online)
  • chemogenomicAlg4DTIpred: Open-source chemogenomic data-driven algorithms for predicting drug-target interactions (in R) standalone
  • Selenzyme: a free online enzyme selection tool for metabolic pathway design (online)