Modeling Protein Sequence Evolution as an Ornstein-Uhlenbeck Process in a Latent Space
- 1Politecnico di Torino
Abstract
High-throughput directed evolution produces longitudinal sequence libraries that are ideal for probing local fitness neighborhoods but often underpowered for global inference tasks such as contact prediction. We present an unsupervised inference model that integrates directed-evolution sequencing time series with natural homologs. We project sequences into a low-dimensional latent space learned from the natural multiple sequence alignment and model the experimental process as an Ornstein-Uhlenbeck dynamics in that space. Maximum-likelihood estimation of the latent drift and noise parameters determines a stationary Gaussian distribution, which induces an effective Potts model in sequence space. The inferred couplings improve structural contact prediction by combining global evolutionary constraints from nature with local, experiment-specific signals. Experiments on PSE1 {beta}-lactamase and dihydrofolate reductase demonstrate the ability to identify correct complementary contacts not recovered by methods using either natural or experimental data alone, with gains concentrated in intermediate- and long-range contacts.
Related
- DNA Sequence-Programmed Protein Coronas Determine Intracellular Fate and Proteostatic Stress of Carbon Nanotubes
- PathFold: Predicting the Entire Protein Folding Pathway from Protein Sequence Alone
- Repurposing PeTriBERT for Protein Protein Interaction Prediction with Sequence Structure Fusion
- EMAP-SSN: An Embedding- and Multiple-Alignment-Integrated Sequence Similarity Network Platform for Interactive Exploration of Protein Sequence Space
- Sequence-structured fitness landscapes predict influenza evolution
BibTeX
@misc{leonardis2026modeling,
title = {{Modeling Protein Sequence Evolution as an Ornstein-Uhlenbeck Process in a Latent Space}},
author = {M. De Leonardis and A. Pagnani},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.16.751972},
url = {https://www.biorxiv.org/content/10.64898/2026.09.16.751972v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Modeling Protein Sequence Evolution as an Ornstein-Uhlenbeck Process in a Latent Space
AU - M. De Leonardis
AU - A. Pagnani
PY - 2026
DA - 2026/09/16
PB - bioRxiv
DO - 10.64898/2026.09.16.751972
UR - https://www.biorxiv.org/content/10.64898/2026.09.16.751972v1
AB - High-throughput directed evolution produces longitudinal sequence libraries that are ideal for probing local fitness neighborhoods but often underpowered for global inference tasks such as contact prediction. We present an unsupervised inference model that integrates directed-evolution sequencing time series with natural homologs. We project sequences into a low-dimensional latent space learned from the natural multiple sequence alignment and model the experimental process as an Ornstein-Uhlenbeck dynamics in that space. Maximum-likelihood estimation of the latent drift and noise parameters determines a stationary Gaussian distribution, which induces an effective Potts model in sequence space. The inferred couplings improve structural contact prediction by combining global evolutionary constraints from nature with local, experiment-specific signals. Experiments on PSE1 {beta}-lactamase and dihydrofolate reductase demonstrate the ability to identify correct complementary contacts not recovered by methods using either natural or experimental data alone, with gains concentrated in intermediate- and long-range contacts.
ER -