ACSNI: An unsupervised machine-learning tool for prediction of tissue-specific pathway components using gene expression profiles

Chinedu Anthony Anene; Faraz Khan; Findlay Bewicke-Copley; Eleni Maniati; Jun Wang

doi:10.1016/j.patter.2021.100270

ACSNI: An unsupervised machine-learning tool for prediction of tissue-specific pathway components using gene expression profiles

Patterns (N Y). 2021 Jun 11;2(6):100270. doi: 10.1016/j.patter.2021.100270.

Authors

Chinedu Anthony Anene¹, Faraz Khan¹, Findlay Bewicke-Copley¹, Eleni Maniati¹, Jun Wang¹

Affiliation

¹ Centre for Cancer Genomics and Computational Biology, Barts Cancer Institute, Queen Mary University of London, London EC1M 6BQ, UK.

Abstract

Determining the tissue- and disease-specific circuit of biological pathways remains a fundamental goal of molecular biology. Many components of these biological pathways still remain unknown, hindering the full and accurate characterization of biological processes of interest. Here we describe ACSNI, an algorithm that combines prior knowledge of biological processes with a deep neural network to effectively decompose gene expression profiles (GEPs) into multi-variable pathway activities and identify unknown pathway components. Experiments on public GEP data show that ACSNI predicts cogent components of mTOR, ATF2, and HOTAIRM1 signaling that recapitulate regulatory information from genetic perturbation and transcription factor binding datasets. Our framework provides a fast and easy-to-use method to identify components of signaling pathways as a tool for molecular mechanism discovery and to prioritize genes for designing future targeted experiments (https://github.com/caanene1/ACSNI).

Keywords: autoencoder; cell signaling; dimension reduction; gene expression; gene-regulatory networks; machine learning; neural network; pathways; systems biology.