Deep Learning with Evolutionary and Genomic Profiles for Identifying Cancer Subtypes

Files

No files are attached to this item.

View at the publisher (DOI) ›

Date

2018-01-01

Journal Title

PROCEEDINGS 2018 IEEE 18TH INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOENGINEERING (BIBE)

Volume, issue and pages

pp. 147–150

ISSN

2471-7819

Language

English

Abstract

Cancer subtype identification is an unmet need in precision diagnosis. Recently, evolutionary conservation has been indicated containing understandable signatures for functional significance in cancers. However, the importance of evolutionary conservation in distinguishing cancer subtypes remains unclear. Here, we identified the evolutionarily conserved genes (i.e., core gene) and observed that they are mainly involved in the pathways relevant to cell growth and metabolisms. By using these core genes, we integrated their evolutionary and genomic profiles with deep learning to develop a feature-based strategy (FES) and an image-based strategy (IMS). In comparison with FES using the random set and the strategy using the PAM50 classifier, core gene set-based FES has higher accuracy for identifying breast cancer subtypes. Moreover, the IMS with data augmentation yields better performance than the other strategies. Comprehensive analysis of eight TCGA cancer data demonstrates that our evolutionary conservation-based models provide a valid and helpful approach to identify cancer subtypes and the core gene set offers distinguishable clues of cancer subtypes.

Collections

Conferences Paper
Full item page Statistics

Cite this item

Lin, C.-Y., Li, R., Akutsu, T., Ruan, P., See, S., & Yang, J.-M. (2018). Deep Learning with Evolutionary and Genomic Profiles for Identifying Cancer Subtypes. PROCEEDINGS 2018 IEEE 18TH INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOENGINEERING (BIBE), 147–150. https://doi.org/10.1109/BIBE.2018.00035

BibTeX RIS

Citation generated in APA 7th edition style; please check it before use.

Share

Permanent link: https://ir.lib.nycu.edu.tw/handle/11536/150963