Biology Tools
Software libraries for drug discovery and computational biology.
Deep Learning for Life Sciences
| Tool | Description | Link |
|---|---|---|
| DeepChem | Comprehensive ML library for drug discovery | deepchem.io |
| DGL-LifeSci | GNN library for life science applications | github |
| Chemprop | Message passing neural networks | github |
| TorchDrug | GNN-based drug discovery library | torchdrug.ai |
| DeepPurpose | Deep learning for drug-target interaction | github |
Protein Structure Prediction
| Tool | Description | Link |
|---|---|---|
| AlphaFold3 | Advanced modeling with ligands, nucleotides, PTMs | github |
| AlphaFold2 | Protein structure prediction | alphafold.ebi.ac.uk |
| ESM/ESMFold | Protein language models & fast structure prediction | github |
| ColabFold | Community notebooks for AF2, ESMFold, RoseTTAFold | github |
| OpenFold | PyTorch reimplementation of AlphaFold2 | github |
| RoseTTAFold | Three-track neural network for structure | github |
| OmegaFold | Single-sequence structure prediction | github |
| Boltz-1 | Unified prediction for proteins, RNA, DNA, ligands | github |
| Chai-1 | Proteins, small molecules, DNA, RNA with restraints | github |
Protein Design
| Tool | Description | Link |
|---|---|---|
| ProteinMPNN | Message passing for inverse folding | github |
| RFDiffusion | Diffusion model for backbone generation | github |
| ColabDesign | Notebooks for AfDesign, TrDesign, ProteinMPNN | github |
| ESM-IF1 | Inverse folding with ESM | github |
| EvoDiff | Discrete diffusion for sequences | github |
| ProtGPT2 | GPT-2 based sequence generation | huggingface |
| BindCraft | Binder design | github |
| LM-Design / ByProt | Language model design | github |
| ProteinSolver | Graph neural network for constraint-based design | github |
| ECNet | Fine-tunable fitness/function prediction | github |
Protein Language Models
| Model | Description | Link |
|---|---|---|
| ESM-2 | Protein embeddings (8M-15B params) | github |
| ProtTrans | Transformer embeddings for proteins | github |
| AMPLIFY | ESM2 reimplementation with open training | github |
| PoET | Variant effect prediction and generation | github |
| EvoProtGrad | MCMC-based directed evolution | github |
Multimer & Complex Prediction
| Tool | Description | Link |
|---|---|---|
| AlphaFold2-Multimer | Protein complex prediction | github |
| AlphaPulldown | Protein-protein interaction screening | github |
| AF2Complex | Complex assembly | github |
| PeSTo | Interface residue prediction | github |
Visualization & Analysis
| Tool | Description | Link |
|---|---|---|
| PyMOL | Molecular visualization | pymol.org |
| ChimeraX | Molecular visualization for structural biology | rbvi.ucsf.edu |
| BioPython | Python tools for biological computation | biopython.org |
| ProDy | Protein dynamics analysis | prody.csb.pitt.edu |
Single-Cell Analysis
| Tool | Description | Link |
|---|---|---|
| Scanpy | Single-cell analysis in Python | scanpy.readthedocs.io |
| Seurat | Single-cell analysis in R | satijalab.org/seurat |
| Squidpy | Spatial transcriptomics analysis | squidpy.readthedocs.io |
| scGPT | Transformer model for single-cell | github |
| scFoundation | Single-cell foundation model | github |
| scPRINT | Cell imputation model | github |
| Open Problems | Community benchmarking platform for single-cell methods — tasks, metrics, and leaderboards | openproblems.bio |
Drug Discovery Platforms
| Tool | Description | Link |
|---|---|---|
| RDKit | Core cheminformatics toolkit | rdkit.org |
| Open Drug Discovery Toolkit | ADMET prediction | github |
| TDC | Therapeutics Data Commons | tdcommons.ai |
Drug-Target Interaction
| Tool | Description | Link |
|---|---|---|
| NeoDTI | Drug-target interaction prediction | github |
| TransformerCPI | Transformer for compound-protein interaction | github |
| drGAT | Attention-based drug response predictor | github |
Biological Language Models
| Model | Description | Link |
|---|---|---|
| ESM-2 | Protein embedding models | github |
| ChemBERTa-2 | Chemical SMILES embeddings | github |
| BioGPT | Biomedical text generation | github |
| GeneGPT | Biomedical information system | github |
| GenePT | Single-cell foundation model | github |
Network & Pathway Analysis
| Tool | Description | Link |
|---|---|---|
| STRING | Protein-protein interaction networks | string-db.org |
| Cytoscape | Network visualization and analysis | cytoscape.org |
| PathwayCommons | Biological pathway data | pathwaycommons.org |
Awesome Lists
| List | Focus |
|---|---|
| awesome-protein-design | Protein design papers |
| awesome-protein-design-software | Protein design tools |
| awesome-AI-based-protein-design | AI protein design |
| awesome-computational-biology | Computational biology resources |
| awesome-small-molecule-ml | Drug discovery ML |
| awesome-drug-discovery | Drug discovery tools |
Getting Started
conda create -n bio python=3.10
conda activate bio
# Core tools
pip install deepchem rdkit
# For protein work
pip install biopython fair-esm
# For single-cell
pip install scanpy squidpy