The DynaSig-ML Python package: automated learning of biomolecular dynamics-function relationships

TL;DR

The DynaSig-ML Python package enables efficient, user-friendly exploration of biomolecular dynamics-function relationships using elastic network models and machine learning, demonstrated by predicting enzyme fitness from mutational data.

Contribution

It introduces a new Python package that integrates elastic network models with machine learning to analyze biomolecular dynamics and predict functional outcomes.

Findings

Successfully predicts enzyme fitness from mutational data

Uses sequence-sensitive coarse-grained NMA model (ENCoM)

Provides an accessible, parallelizable pipeline for large datasets

Abstract

Summary: The DynaSig-ML (Dynamical Signatures - Machine Learning) Python package allows the efficient, user-friendly exploration of 3D dynamics-function relationships in biomolecules, using datasets of experimental measures from large numbers of sequence variants. The DynaSig-ML package is built around the Elastic Network Contact Model (ENCoM), the first and only sequence-sensitive coarse-grained NMA model, which is used to generate the input Dynamical Signatures. Starting from in silico mutated structures, the whole pipeline can be run with just a few lines of Python and modest computational resources. The compute-intensive steps can also easily be parallelized in the case of either large biomolecules or vast amounts of sequence variants. As an example application, we use the DynaSig-ML package to predict the evolutionary fitness of the bacterial enzyme VIM-2 lactamase from deep mutational scan data. Availability and implementation: DynaSig-ML is open source software available at https: //github.com/gregorpatof/dynasigml package Contact: rafael.najmanovich@umontreal.ca