Interpretable Causal Representation Learning for Biological Data in the Pathway Space
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| 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 |