Related Experiment Video
Updated: Oct 31, 2025
03:08
Using Human Differentially Expressed Gene Lists to Perform Downstream Pathway Enrichment Analysis and Target Prioritization
Published on: October 3, 2025
575
ACSNI: An unsupervised machine-learning tool for prediction of tissue-specific pathway components using gene
Chinedu Anthony Anene1, Faraz Khan1, Findlay Bewicke-Copley1
1Centre for Cancer Genomics and Computational Biology, Barts Cancer Institute, Queen Mary University of London, London EC1M 6BQ, UK.
Patterns (New York, N.Y.)
|June 28, 2021
Summary
A new algorithm, ACSNI, uses deep learning to uncover unknown components of biological pathways from gene expression data. This tool aids in discovering molecular mechanisms and prioritizing genes for future research.
Area of Science:
- Molecular Biology
- Systems Biology
- Bioinformatics
Background:
- Identifying tissue- and disease-specific biological pathways is crucial but challenging due to unknown components.
- Incomplete pathway characterization hinders a full understanding of biological processes.
Purpose of the Study:
- To develop an algorithm (ACSNI) that decomposes gene expression profiles (GEPs) into pathway activities.
- To identify unknown components within biological signaling pathways.
- To provide a tool for molecular mechanism discovery and gene prioritization.
Main Methods:
- Developed ACSNI, an algorithm integrating prior biological knowledge with deep neural networks.
- Applied ACSNI to public GEP data to analyze pathway activities.
- Validated findings using genetic perturbation and transcription factor binding datasets.
Main Results:
- ACSNI effectively decomposed GEPs into multi-variable pathway activities.
- The algorithm identified plausible components for mTOR, ATF2, and HOTAIRM1 signaling pathways.
- Predicted pathway components were consistent with regulatory information from external datasets.
Conclusions:
- ACSNI offers a fast and user-friendly method for identifying signaling pathway components.
- The algorithm facilitates molecular mechanism discovery and aids in prioritizing genes for targeted experiments.
- ACSNI advances the characterization of biological pathways and supports future research directions.
