TxPert: Leveraging Biochemical Relationships for Out-of-Distribution Transcriptomic Perturbation Prediction

TL;DR

TxPert is a novel method that uses biochemical knowledge graphs to improve prediction of cellular responses to genetic perturbations, especially in out-of-distribution scenarios involving unseen conditions.

Contribution

The paper introduces TxPert, a new approach leveraging biological knowledge graphs for better out-of-distribution transcriptomic perturbation prediction.

Findings

TxPert achieves state-of-the-art OOD prediction performance.

Knowledge graphs significantly enhance model generalization.

Expanded benchmarking improves evaluation standards.

Abstract

Accurately predicting cellular responses to genetic perturbations is essential for understanding disease mechanisms and designing effective therapies. Yet exhaustively exploring the space of possible perturbations (e.g., multi-gene perturbations or across tissues and cell types) is prohibitively expensive, motivating methods that can generalize to unseen conditions. In this work, we explore how knowledge graphs of gene-gene relationships can improve out-of-distribution (OOD) prediction across three challenging settings: unseen single perturbations; unseen double perturbations; and unseen cell lines. In particular, we present: (i) TxPert, a new state-of-the-art method that leverages multiple biological knowledge networks to predict transcriptional responses under OOD scenarios; (ii) an in-depth analysis demonstrating the impact of graphs, model architecture, and data on performance; and (iii) an expanded benchmarking framework that strengthens evaluation standards for perturbation modeling.