CIMLA: Interpretable AI for inference of differential causal networks
This work addresses the need for interpretable AI methods to infer differential causal networks in bioinformatics, particularly for analyzing gene regulatory changes between biological conditions, though it appears incremental as it builds on existing feature attribution models.
The paper tackled the problem of discovering causal relationships from high-dimensional data in bioinformatics by developing CIMLA, a tool for identifying condition-dependent changes in causal networks, and demonstrated its robustness and accuracy through benchmarking on simulated data and application to Alzheimer's disease data.
The discovery of causal relationships from high-dimensional data is a major open problem in bioinformatics. Machine learning and feature attribution models have shown great promise in this context but lack causal interpretation. Here, we show that a popular feature attribution model estimates a causal quantity reflecting the influence of one variable on another, under certain assumptions. We leverage this insight to implement a new tool, CIMLA, for discovering condition-dependent changes in causal relationships. We then use CIMLA to identify differences in gene regulatory networks between biological conditions, a problem that has received great attention in recent years. Using extensive benchmarking on simulated data sets, we show that CIMLA is more robust to confounding variables and is more accurate than leading methods. Finally, we employ CIMLA to analyze a previously published single-cell RNA-seq data set collected from subjects with and without Alzheimer's disease (AD), discovering several potential regulators of AD.