Learning Early Treatment Strategy from Snapshots for mRNA-Protein Regulatory Networks

Xun Shen, Mehrshad Sadria, LI TAIWEI, Hampei Sasahara, Akifumi Wachi, Jun-ichi Imura

Keywords: Snapshot data, gene regulatory networks, biology, statistical learning, treatment design

TL;DR: We estimate gene regulatory dynamics from snapshot data and design energy-efficient interventions to re-stabilize the system before disease onset.

Abstract:

Early disease detection with snapshot data has been effectively addressed by the Dynamical Network Biomarkers (DNBs) theory.
After early disease detection, it is crucial to consider early medical treatment to prevent it.
This paper presents a novel framework for identifying mRNA-protein regulatory systems from snapshot data and designing interventions.
We first estimate the state covariance of mRNA-protein expression using multi-episode snapshot samples.
Then, we identify the underlying continuous-time dynamics by solving a Lyapunov-based regression problem.
We provide finite-sample guarantees on the estimation accuracy of the system matrix and its dominant eigenvectors, which are essential for downstream treatment design.
Building on these estimates, we formulate an optimal re-stabilization strategy that minimizes input energy with desired spectral shifts.
To ensure practical feasibility, we further propose a diagonal re-stabilization scheme that identifies key regulatory nodes using a first-order eigenvalue sensitivity analysis.
Numerical examples on synthetic mRNA-protein network demonstrate that our method accurately identifies regulatory node under high-dimensional, low-sample conditions and significantly outperforms existing baselines.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 8740