GPO-VAE: modeling explainable gene perturbation responses utilizing GRN-aligned parameter optimization

TL;DR

This paper introduces GPO-VAE, a new model that improves the explainability of gene perturbation predictions by aligning them with gene regulatory networks.

Contribution

The novel contribution is integrating GRN-aligned parameter optimization into VAEs to enhance model explainability and prediction accuracy.

Findings

GPO-VAE achieves state-of-the-art performance in predicting transcriptional responses to genetic perturbations.

The model generates biologically meaningful gene regulatory networks that align with experimentally validated pathways.

Abstract

Predicting cellular responses to genetic perturbations is essential for understanding biological systems and developing targeted therapeutic strategies. While variational autoencoders (VAEs) have shown promise in modeling perturbation responses, their limited explainability poses a significant challenge, as the learned features often lack clear biological meaning. Nevertheless, model explainability is one of the most important aspects in the realm of biological AI. One of the most effective ways to achieve explainability is incorporating the concept of gene regulatory networks (GRNs) in designing deep learning models such as VAEs. GRNs elicit the underlying causal relationships between genes and are capable of explaining the transcriptional responses caused by genetic perturbation treatments.

We propose GPO-VAE, an explainable VAE enhanced by GRN-aligned Parameter Optimization that explicitly models gene regulatory networks in the latent space. Our key approach is to optimize the learnable parameters related to latent perturbation effects toward GRN-aligned explainability. Experimental results on perturbation prediction show our model achieves state-of-the-art performance in predicting transcriptional responses across multiple benchmark datasets. Furthermore, additional results on evaluating the GRN inference task reveal our model’s ability to generate meaningful GRNs compared to other methods. According to qualitative analysis, GPO-VAE possesses the ability to construct biologically explainable GRNs that align with experimentally validated regulatory pathways.

GPO-VAE is available at https://github.com/dmis-lab/GPO-VAE.

Figures