Dual-graph deconvolution of enzyme fitness: an interpretable framework to identify and explain catalytic modulators
- 1Harvard Medical School
Abstract
Models trained on protein sequences can predict mutational effects, but their outputs represent a convolution of different phenotypes. Isolating stability-independent activity effects is essential for rational enzyme design, allosteric drug design and functional annotation, yet existing pLM-based deconvolution methods lack interpretability. Here, we introduce a hybrid framework that pairs stability predictors with probabilistic graphical models of coevolution. Benchmarked on all enzymes with available multidimensional deep mutational scanning data, our framework isolates stability-independent activity effects with a fidelity that matches analogous pLM-based approaches. Crucially, we reveal biophysically plausible communication pathways that align with previous knowledge and that we validate with experimental data across a diverse set of targets. This hybrid approach merges statistical and geometric deep learning into a zero-shot, explainable tool for targeted engineering and mechanistic discovery.
Related
- miRAssist: a context-aware, evidence integration framework for interpretable miRNA-target prioritization
- hicream: A flexible framework to identify significantly different regions in Hi-C data
- Img2EEG: A Scalable and Interpretable Encoding Framework for Simulating Human EEG Responses to Visual Inputs
- RiboWin: A computational framework to identify non-canonical open reading frames
- PhenoMe: An interactive AI framework for interpretable, microscopy-driven phenotyping
BibTeX
@misc{busto2026dualgraph,
title = {{Dual-graph deconvolution of enzyme fitness: an interpretable framework to identify and explain catalytic modulators}},
author = {S. Garcia Busto and E. Eschbach and T. A. Hopf and C. Sander and S. Bacallado and D. S. Marks},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.15.759402},
url = {https://www.biorxiv.org/content/10.64898/2026.10.15.759402v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Dual-graph deconvolution of enzyme fitness: an interpretable framework to identify and explain catalytic modulators
AU - S. Garcia Busto
AU - E. Eschbach
AU - T. A. Hopf
AU - C. Sander
AU - S. Bacallado
AU - D. S. Marks
PY - 2026
DA - 2026/10/15
PB - bioRxiv
DO - 10.64898/2026.10.15.759402
UR - https://www.biorxiv.org/content/10.64898/2026.10.15.759402v1
AB - Models trained on protein sequences can predict mutational effects, but their outputs represent a convolution of different phenotypes. Isolating stability-independent activity effects is essential for rational enzyme design, allosteric drug design and functional annotation, yet existing pLM-based deconvolution methods lack interpretability. Here, we introduce a hybrid framework that pairs stability predictors with probabilistic graphical models of coevolution. Benchmarked on all enzymes with available multidimensional deep mutational scanning data, our framework isolates stability-independent activity effects with a fidelity that matches analogous pLM-based approaches. Crucially, we reveal biophysically plausible communication pathways that align with previous knowledge and that we validate with experimental data across a diverse set of targets. This hybrid approach merges statistical and geometric deep learning into a zero-shot, explainable tool for targeted engineering and mechanistic discovery.
ER -