Protein Structure Prediction Python Packages

alphafold3-pytorch

Implementation of Alphafold 3 from Google Deepmind in Pytorch

prospr

Prospr is a universal toolbox for protein structure prediction within the HP-model. The Python package is based on a C++ core, which gives Prospr its high performance. The C++ core is made available as a separate zip file to facilitate high-performance computing applications. The package comes with many prediction algorithms and datasets to use.

protpy

Calculating a range of protein descriptors using their physicochemical, biological and structural properties 🔬.

uniprot-mcp-server

Auditable UniProt MCP server with per-response SHA-256 provenance, release pinning, verification, and offline replay.

bionemo-ir

Easy, fast, and memory-efficient structure prediction inference

boltz-community

Community-maintained Boltz fork with bug fixes, broader compatibility, and CI.

biosaic

KMer level tokenizer for DNA & Proteins sequences

novomcp

The open computational chemistry engine for drug discovery and materials science; MCP + REST + Workbench + Next.js dashboard, wrapping RDKit, GROMACS, AutoDock, OpenFold, Chai, Boltz, Gnina.

boltzyml

Preprocessing file generator (v1) and hosted Boltz-2 API builder/submitter (v2.0): binary, ternary, or N-body protein-ligand-DNA-RNA binding prediction.

foldrunner

All-vs-all protein structure-prediction panels with one alignment per sequence, for AlphaFold 3, Boltz-2, Protenix, Chai-1, ColabFold, AlphaFold2-Multimer, AlphaFold Server and SeedFold

igfold-pytorch

Unofficial re-implementation of IgFold, a fast antibody structure prediction method, in PyTorch.

dmpfold

Fast and accurate protein structure prediction

deepab-pytorch

An unofficial re-implementation of DeepAb, an interpretable deep learning model for antibody structure prediction.