Interpretable Causal Representation Learning for Biological Data in the Pathway Space

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: de la Fuente, Jesus, Lehmann, Robert, Ruiz-Arenas, Carlos, Voges, Jan, Marin-Goñi, Irene, Martinez-de-Morentin, Xabier, Gomez-Cabrero, David, Ochoa, Idoia, Tegner, Jesper, Lagani, Vincenzo, Hernaez, Mikel
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916794010173440
author de la Fuente, Jesus
Lehmann, Robert
Ruiz-Arenas, Carlos
Voges, Jan
Marin-Goñi, Irene
Martinez-de-Morentin, Xabier
Gomez-Cabrero, David
Ochoa, Idoia
Tegner, Jesper
Lagani, Vincenzo
Hernaez, Mikel
author_facet de la Fuente, Jesus
Lehmann, Robert
Ruiz-Arenas, Carlos
Voges, Jan
Marin-Goñi, Irene
Martinez-de-Morentin, Xabier
Gomez-Cabrero, David
Ochoa, Idoia
Tegner, Jesper
Lagani, Vincenzo
Hernaez, Mikel
contents Predicting the impact of genomic and drug perturbations in cellular function is crucial for understanding gene functions and drug effects, ultimately leading to improved therapies. To this end, Causal Representation Learning (CRL) constitutes one of the most promising approaches, as it aims to identify the latent factors that causally govern biological systems, thus facilitating the prediction of the effect of unseen perturbations. Yet, current CRL methods fail in reconciling their principled latent representations with known biological processes, leading to models that are not interpretable. To address this major issue, we present SENA-discrepancy-VAE, a model based on the recently proposed CRL method discrepancy-VAE, that produces representations where each latent factor can be interpreted as the (linear) combination of the activity of a (learned) set of biological processes. To this extent, we present an encoder, SENA-δ, that efficiently compute and map biological processes' activity levels to the latent causal factors. We show that SENA-discrepancy-VAE achieves predictive performances on unseen combinations of interventions that are comparable with its original, non-interpretable counterpart, while inferring causal latent factors that are biologically meaningful.
format Preprint
id arxiv_https___arxiv_org_abs_2506_12439
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Interpretable Causal Representation Learning for Biological Data in the Pathway Space
de la Fuente, Jesus
Lehmann, Robert
Ruiz-Arenas, Carlos
Voges, Jan
Marin-Goñi, Irene
Martinez-de-Morentin, Xabier
Gomez-Cabrero, David
Ochoa, Idoia
Tegner, Jesper
Lagani, Vincenzo
Hernaez, Mikel
Machine Learning
Quantitative Methods
Predicting the impact of genomic and drug perturbations in cellular function is crucial for understanding gene functions and drug effects, ultimately leading to improved therapies. To this end, Causal Representation Learning (CRL) constitutes one of the most promising approaches, as it aims to identify the latent factors that causally govern biological systems, thus facilitating the prediction of the effect of unseen perturbations. Yet, current CRL methods fail in reconciling their principled latent representations with known biological processes, leading to models that are not interpretable. To address this major issue, we present SENA-discrepancy-VAE, a model based on the recently proposed CRL method discrepancy-VAE, that produces representations where each latent factor can be interpreted as the (linear) combination of the activity of a (learned) set of biological processes. To this extent, we present an encoder, SENA-δ, that efficiently compute and map biological processes' activity levels to the latent causal factors. We show that SENA-discrepancy-VAE achieves predictive performances on unseen combinations of interventions that are comparable with its original, non-interpretable counterpart, while inferring causal latent factors that are biologically meaningful.
title Interpretable Causal Representation Learning for Biological Data in the Pathway Space
topic Machine Learning
Quantitative Methods
url https://arxiv.org/abs/2506.12439