Back

Knowledge-Driven Interpretable Neural Networks for Mechanistic Insight

Ke, Y.; Yu, T.

2025-09-08 bioinformatics
10.1101/2025.09.08.674894 bioRxiv
Show abstract

Analyzing omics data based on pathway knowledge is critical for understanding the molecular mechanism behind pathological changes, but current pathway analysis methods do not model the detailed mechanistic nature of biological interactions, limiting the understanding of pathway behavior to a relatively shallow level. To address this issue, we present a knowledge-driven machine learning framework that embeds features into pathway graphs and models reactions analytically, producing interpretable feature hierarchies and sub-networks where functional associations are estimated to model biological interactions. The approach is agnostic to feature selection, enabling the use of full omics datasets without discarding weak signals. Applications to breast cancer microRNA-gene regulation data and COVID-19 metabolomics data highlight immune and metabolic pathways relevant to disease progression. This framework bridges predictive modeling with mechanistic interpretation, offering a foundation for integrative pathway analysis.

Published in Genome Research · training set

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.