Bio Tools

RDKit

Molecule properties, standardization and substructure search, and explicit bond edits from atom-mapped reactions.

OpenDDE

Structure prediction for proteins, DNA/RNA, ligands, and ions. Supports co-folding.

Boltz-2

All-atom biomolecular structure and binding-affinity prediction.

Chai-1

Molecular structure prediction, including proteins. Similar to AlphaFold3.

Protenix-v2

Structure prediction for proteins, DNA/RNA, ligands, and ions. Supports co-folding.

ESMFold 2

Fast all-atom structure prediction for biomolecular complexes.

ESMC

Protein language-model embeddings, amino-acid probabilities, and substitution scores.

IgBLAST

Annotate antibody and T cell receptor sequences against germline V, D and J genes.

ProteinMPNN

Protein sequence prediction, to conform with backbone coordinates. Does not take external molecules into account. A useful step after RFDiffusion in a protein design pipeline, and before validation with structure prediction.

LigandMPNN

Protein sequence prediction, to conform with backbone coordinates. Takes external molecules into account; to some degree a superset of ProteinMPNN, but is a different model. A useful step after RFDiffusion in a protein design pipeline, and before validation with structure prediction.

ProteinMPNN-ddG

Estimate changes in protein stability upon point mutation

RFdiffusion3

Generates protein backbone coordinates around proteins, small molecules, nucleic acids, and metals. Given geometric and other constraints, specifies backbone geometry. A useful first step in a protein design pipeline. Very well documented!

ThermoMPNN

A graph neural network (GNN) trained using transfer learning to predict changes in stability for protein point mutants

CatPred

Predict kcat, Km or Ki for an enzyme and its substrate, with an uncertainty estimate.

Deep-Learning models for predicting the structures of immune proteins.

Predict the structure of a cyclic peptide or a cyclic-peptide complex.

Designs proteins and peptides that bind to a wide range of biomolecular targets.

Design de novo protein or peptide binders against a target structure.

Humanize antibody sequences or estimate their humanness.

Structure-based antibody design using inverse folding

Design antibody sequences from a backbone structure.

Design antibody or nanobody binders against a target structure.

Efficient generation of epitope-targeted de novo antibodies

A protein design framework for antibody binder design

Design antibody CDRs against a target antigen by inverse folding.

Predict Tier-1 ADME summary properties (lipophilicity, permeability, and solubility) for a batch of small molecules by SMILES.

Fast protein design through all-atom SE(3)-equivariance

Predict 30 spatial developability descriptors for an antibody from sequence alone.

Score how likely a peptide-MHC class I pair is to provoke a CD8 T-cell response.

Score how likely a peptide-MHC class II pair is to provoke a CD4 T-cell response.

Predict whether a protein will be soluble and usable when expressed in E. coli.

Predict the melting temperature of a protein from its sequence.

Predict an enzyme turnover number from its sequence and a substrate structure.

Number an antibody or TCR sequence and report its regions and liabilities.

Generate an ensemble of protein-ligand poses and side-chain conformations. Given a protein pocket and ligand, estimates how the ligand and sidechains will arrange themselves.