fasthydromap 0.1.1

Predict per-residue Fdewet using SASA + MPNN

FastHydroMap

FastHydroMap predicts per-residue dewetting free energies (Fdewet) from protein structures and trajectories.

Quick Start

Start from a fresh Python environment. FastHydroMap currently supports Python 3.11, 3.12, and 3.13.

pip install fasthydromap
fasthydromap install-torch
fasthydromap predict your_structure.pdb -o outputs/your_structure_fdewet

fasthydromap install-torch defaults to the CPU build, which is usually the right choice for current FastHydroMap workloads because SASA preprocessing dominates runtime.

Advanced installation options, Docker usage, GPU Torch variants, and release/developer workflows are documented in docs/INSTALL.md and docs/PYPI_RELEASE.md.

Inputs

FastHydroMap supports:

• Single protein structures in PDB format
• Protein trajectories in DCD or XTC format together with a matching topology PDB

Typical usage:

# Single structure
fasthydromap predict examples/1A1U.pdb -o outputs/1A1U_fdewet

# Trajectory
fasthydromap predict-trajectory examples/proteinG.pdb examples/proteinG_short.dcd -o outputs/proteinG_fdewet

Outputs

For a single structure, FastHydroMap writes:

• *.csv: one row per residue with Fdewet; with --parts, intrinsic and context columns are included
• *.pdb: a copy of the input structure with predicted Fdewet written to B-factors

For a trajectory, FastHydroMap writes wide CSV files containing one row per frame and one column per residue. Use --parts to also write intrinsic, context, and per-frame summary CSVs.

Model Scope

FastHydroMap was trained on structured single-chain proteins and the 20 canonical amino-acid chemistries. Predictions for PTMs and other non-canonical chemistries should be treated cautiously.

Test your installation

fasthydromap predict examples/1A1U.pdb -o outputs/1A1U_fdewet
# Trajectory run (DCD or XTC)
fasthydromap predict-trajectory examples/proteinG.pdb examples/proteinG_short.dcd

Acknowledgements

Shell Lab and Shea Group