A Knowledge-Based Discovery Approach Couples Artificial Neural Networks With Weight Engineering to Uncover Immune-Related Processes Underpinning Clinical Traits of Breast Cancer

Immune-related processes are important in underpinning the properties of clinical traits such as prognosis and drug response in cancer. The possibility to extract knowledge learned by artificial neural networks (ANNs) from omics data to explain cancer clinical traits is a very attractive subject for...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in immunology Vol. 13; p. 920669
Main Authors: Zhang, Cheng, Correia, Cristina, Weiskittel, Taylor M., Tan, Shyang Hong, Meng-Lin, Kevin, Yu, Grace T., Yao, Jingwen, Yeo, Kok Siong, Zhu, Shizhen, Ung, Choong Yong, Li, Hu
Format: Journal Article
Language:English
Published: Switzerland Frontiers Media S.A 14.07.2022
Subjects:
artificial intelligence
Breast Neoplasms - genetics
Breast Neoplasms - therapy
clinical traits
Female
gene–gene associations
Humans
Immunology
Knowledge Discovery
Learning
neural networks
Neural Networks, Computer
Neurons - physiology
Tumor Microenvironment
weight engineering
weight engineering
artificial intelligence
clinical traits
gene–gene associations
neural networks
ISSN:1664-3224, 1664-3224
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Immune-related processes are important in underpinning the properties of clinical traits such as prognosis and drug response in cancer. The possibility to extract knowledge learned by artificial neural networks (ANNs) from omics data to explain cancer clinical traits is a very attractive subject for novel discovery. Recent studies using a version of ANNs called autoencoders revealed their capability to store biologically meaningful information indicating that autoencoders can be utilized as knowledge discovery platforms aside from their initial assigned use for dimensionality reduction. Here, we devise an innovative weight engineering approach and ANN platform called artificial neural network encoder (ANNE) using an autoencoder and apply it to a breast cancer dataset to extract knowledge learned by the autoencoder model that explains clinical traits. Intriguingly, the extracted biological knowledge in the form of gene–gene associations from ANNE shows immune-related components such as chemokines, carbonic anhydrase, and iron metabolism that modulate immune-related processes and the tumor microenvironment play important roles in underpinning breast cancer clinical traits. Our work shows that biological “knowledge” learned by an ANN model is indeed encoded as weights throughout its neuronal connections, and it is possible to extract learned knowledge via a novel weight engineering approach to uncover important biological insights.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Edited by: Qiang Wu, Macau University of Science and Technology, Macao SAR, China
Reviewed by: Xiao Wang, Arizona State University, United States; Lang Wu, University of Hawaii at Manoa, United States
These authors have contributed equally to this work
This article was submitted to Systems Immunology, a section of the journal Frontiers in Immunology
ISSN:1664-3224
1664-3224
DOI:10.3389/fimmu.2022.920669