Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
Repository Index
47,133 repositories indexed
1–24 of 24 · Most stars
State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology
Official repository for the Boltz biomolecular interaction models
Message Passing Neural Networks for Molecule Property Prediction
A Deep Learning Toolkit for DTI, Drug Property, PPI, DDI, Protein Function Prediction (Bioinformatics)
Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models
Python package for graph neural networks in chemistry and biology
A PyTorch and TorchDrug based deep learning library for drug pair scoring. (KDD 2022)
OpenChem: Deep Learning toolkit for Computational Chemistry and Drug Design Research
Molecular Processing Made Easy.
Universal cheminformatics toolkit, utilities and database search tools
Deep Reinforcement Learning for de-novo Drug Design
A curated list of resources for machine learning for small-molecule drug discovery
ChemML is a machine learning and informatics program suite for the chemical and materials sciences.
LLM for Drug Editing, ICLR 2024
Code for "Predicting Cellular Responses to Novel Drug Perturbations at a Single-Cell Resolution", NeurIPS 2022.
TransformerCPI: Improving compound–protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments(BIOINFORMATICS 2020) https://doi.org/10.1093/bioinformatics/btaa524
Optimising chemical reactions using machine learning
We would like to maintain a list of resources which aim to solve molecular docking and other closely related tasks.
TypeDB Bio: Biomedical Knowledge Graph
Multi-stage Riemannian flow matching for physically valid molecular docking, with GNINA scoring, PoseBusters filtering, CLI inference, and benchmarks.
UV-first benchmark for protein-ligand docking with reproducible annotation, pocket similarity, and HPC workflows.
Generative models for transcriptomic-driven or protein-driven molecular design (PaccMann^RL).