Saved in:
Bibliographic Details
Main Authors: Wenkel, Frederik, Tu, Wilson, Masschelein, Cassandra, Shirzad, Hamed, Eastwood, Cian, Whitfield, Shawn T., Bendidi, Ihab, Russell, Craig, Hodgson, Liam, Mesbahi, Yassir El, Ding, Jiarui, Fay, Marta M., Earnshaw, Berton, Noutahi, Emmanuel, Denton, Alisandra K.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.14919
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913849776537600
author Wenkel, Frederik
Tu, Wilson
Masschelein, Cassandra
Shirzad, Hamed
Eastwood, Cian
Whitfield, Shawn T.
Bendidi, Ihab
Russell, Craig
Hodgson, Liam
Mesbahi, Yassir El
Ding, Jiarui
Fay, Marta M.
Earnshaw, Berton
Noutahi, Emmanuel
Denton, Alisandra K.
author_facet Wenkel, Frederik
Tu, Wilson
Masschelein, Cassandra
Shirzad, Hamed
Eastwood, Cian
Whitfield, Shawn T.
Bendidi, Ihab
Russell, Craig
Hodgson, Liam
Mesbahi, Yassir El
Ding, Jiarui
Fay, Marta M.
Earnshaw, Berton
Noutahi, Emmanuel
Denton, Alisandra K.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_14919
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TxPert: Leveraging Biochemical Relationships for Out-of-Distribution Transcriptomic Perturbation Prediction
Wenkel, Frederik
Tu, Wilson
Masschelein, Cassandra
Shirzad, Hamed
Eastwood, Cian
Whitfield, Shawn T.
Bendidi, Ihab
Russell, Craig
Hodgson, Liam
Mesbahi, Yassir El
Ding, Jiarui
Fay, Marta M.
Earnshaw, Berton
Noutahi, Emmanuel
Denton, Alisandra K.
Machine Learning
Quantitative Methods
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.
title TxPert: Leveraging Biochemical Relationships for Out-of-Distribution Transcriptomic Perturbation Prediction
topic Machine Learning
Quantitative Methods
url https://arxiv.org/abs/2505.14919