Discover Resources

Catalysis-oriented atomistic modeling workflows in fairchem, using pretrained UMA models and ASE calculators for surface relaxation, energy prediction and molecular dynamics.

Materials Discovery

SPICE provides quantum-mechanical energies, forces and other molecular properties for training machine learning potentials, with an emphasis on drug-like molecules and protein interactions.

Quantum Chemistry · Scientific Data

ANI-1 provides calculated off-equilibrium molecular conformations, with Python readers for accessing HDF5 files containing coordinates and energies for organic molecules.

Quantum Chemistry

GEOM provides 37 million energy- and statistical-weight-annotated molecular conformations for over 450,000 molecules, with MessagePack data, RDKit objects, and loading and analysis tutorials.

Molecular Generation · Computational Chemistry

Matbench Discovery benchmarks machine-learning models for crystal stability and atomistic simulation tasks, using an interactive leaderboard to compare accuracy, robustness, and computational cost.

Materials Discovery

Matbench provides 13 curated materials-science machine learning tasks for benchmarking property-prediction methods, with benchmark data, leaderboards and a pip-installable package.

Materials Discovery

Open Reaction Database provides structured reaction datasets as Parquet files containing Protobuf records, with mirrored downloads and ord_schema workflows for streaming access and text or JSON conversion.

Reaction Prediction · Scientific Data

Therapeutics Data Commons provides therapeutic machine learning datasets, Python loaders, data splits, evaluation metrics and benchmarks for prediction and molecule-generation research.

Molecular Property Prediction · Drug Discovery

MOSES combines a ZINC-derived molecular dataset, generation baselines and evaluation metrics to benchmark the validity, diversity and novelty of generated molecules.

Molecular Generation

GuacaMol is a Python benchmarking package for de novo molecular design, with distribution-learning and goal-directed evaluations plus standardized ChEMBL-derived datasets.

Molecular Generation

REINVENT is a Python molecular-design toolkit that uses generative models, reinforcement learning and transfer learning for configurable small-molecule generation and optimization.

Molecular Generation · Drug Discovery

RetroXpert is a two-stage retrosynthesis research implementation that predicts product bond disconnections, then generates reactants from synthons using an OpenNMT-based model.

Retrosynthesis

LocalRetro is a research implementation for retrosynthesis prediction using local reaction templates, with workflows for template extraction, model training, testing and decoding predicted reactants.

Retrosynthesis

RxnMapper uses attention from an unsupervised ALBERT model to assign atom mappings to valid reaction SMILES, returning mapped reactions and confidence scores through a Python interface.

Cheminformatics · Reaction Prediction

DECIMER converts chemical structure images into predicted SMILES using EfficientNet-V2 and a transformer, with a Python prediction interface and a separately described hand-drawn model.

Chemical Structure Recognition

MolScribe is an image-to-graph model for converting molecular diagrams into chemical structures, with SMILES and molfile output plus optional atom, bond and confidence information.

Chemical Structure Recognition

TANKBind is a research model for predicting protein–ligand binding structures and affinity, with repository notebooks for prediction, dataset preparation, self-docking evaluation and virtual screening.

Drug Discovery

EquiBind is an SE(3)-equivariant model for predicting receptor binding locations and ligand poses directly from protein–ligand structures, with workflows for inference and training.

Drug Discovery

DiffDock predicts protein–small-molecule binding poses using a diffusion-based model, with single-complex and batch inference, sequence-based protein inputs, and pose confidence scores.

Drug Discovery

Official research code for E(3)-equivariant diffusion models that generate 3D molecules, with QM9 and GEOM-Drugs training workflows, sample analysis, and property-conditioned generation.

Molecular Generation