BioPipelines Tool Reference¶

Complete tool reference, organized into the same categories as the project README.

For a single flat list of every public-API tool (with category and source-file mapping), see tool_index.md.

Structure Generation¶

Generate novel protein structures and pockets.

• BoltzGen — Protein/peptide/nanobody binder design
• PocketGen — Ligand-tailored pocket co-design
• RFdiffusion — Backbone generation
• RFdiffusion3 — Third-generation design
• RFdiffusionAllAtom — All-atom with ligands

Sequence Design¶

Design and manipulate sequences.

• DNAEncoder — Codon optimization
• Frame2Seq — Fast inverse folding
• Fuse — Fusion proteins with linkers
• LigandMPNN — Ligand-aware sequence design
• Mutagenesis — Systematic substitutions
• MutationComposer — Combinatorial mutants
• ProteinMPNN — Sequence design for backbones
• RBSDesigner — Ribosome binding site design
• StitchSequences — Sequence combinations

Structure Prediction & Docking¶

Predict protein and complex structures, and dock ligands.

• AlphaFold — AlphaFold2 prediction
• Boltz2 — Biomolecular complex prediction
• DiffDock — Blind diffusion docking
• DynamicBind — Flexible-backbone docking
• ESMFold — Single-sequence prediction (no MSA)
• Gnina — Docking with CNN scoring
• NeuralPLexer — Protein–ligand complex prediction
• PLACER — Ligand-pose ensemble in a bound pocket

Analysis¶

Analyze structures, interactions, stability, and fitness.

• ADMETAI — ADMET endpoint predictions
• AF2BIND — AF2-based binding-residue prediction
• Aggrescan3D — Structure-based aggregation propensity
• Angle — Bond, torsional, and vector angles
• APBS — Electrostatic surface potential
• BioEmu — Equilibrium ensemble sampling
• CABSflex — Fast flexibility simulation
• ConformationalChange — Structural changes
• Consensus — Per-group aggregation of a resi-csv stream
• Contacts — Contact analysis
• Distance — Distance measurements
• DistanceSelector — Proximity-based selection
• DSSP — Secondary-structure assignment
• EnsembleAnalysis — Per-residue RMSF from any ensemble
• FPocket — Alpha-sphere pocket detection
• GEMS — Protein–ligand affinity (GNN)
• OpenMM — Energy minimization
• P2Rank — Ligand binding-site prediction
• PLIP — Interaction profiling
• PLM_Sol — Sequence-based solubility prediction
• PoseBusters — Pose validation
• PoseChange — Ligand pose comparison
• Prodigy — Protein–protein affinity
• ProLIF — Interaction fingerprints
• Reduce — Add explicit hydrogens
• RTMScore — Pose ranking
• SASA — Solvent-accessible surface area
• ThermoMPNN — Fold-stability change (ddG) from structure
• VespaG — Zero-shot fitness from sequence
• XTB — Quantum interaction energy

Cheminformatics¶

Convert molecules and compute chemical descriptors.

• OpenBabel — Format conversion, 3-D coordinates, protonation
• RDKit — Molecular descriptors

Sequence Statistics¶

Mutation analysis and frequency optimization.

• BayesianAdjuster — Correlation-based frequency adjustment
• MutationProfiler — Mutation patterns
• SequenceMetricCorrelation — Mutation–metric correlations

MSAs¶

Generate and convert multiple-sequence alignments.

• MMseqs2 — MSA generation
• MMseqs2Server — Local MSA server management
• MSA — MSA format conversion (CSV/A3M)

Data Management¶

Filter, transform, and route tables and streams.

• ExtractMetrics — Metric extraction for Prism
• Panda — Unified table transformations
• Pool — Gather parallel-run outputs
• ReMap — Rename IDs across streams and tables
• Selection — Selection string manipulation

Inputs & I/O¶

Bring data into a pipeline and take results out.

• CompoundLibrary — Create compound collections
• Ligand — Fetch small molecules
• Load / LoadMultiple — Reload previous outputs
• PDB — Fetch protein structures
• Plot — Plots
• PyMOL — Session creation and rendering
• RCSB — Search RCSB PDB and download
• Sequence — Create sequences from strings
• Table — Load an existing CSV/Excel table
• UniProt — Fetch sequences and annotations