Machine learning for multi-omics data integration in cancer
The University of Sydney · Children's Medical Research Institute · +2 more institutions
Abstract
Multi-omics data analysis is an important aspect of cancer molecular biology studies and has led to ground-breaking discoveries. Many efforts have been made to develop machine learning methods that automatically integrate omics data. Here, we review machine learning tools categorized as either general-purpose or task-specific, covering both supervised and unsupervised learning for integrative analysis of multi-omics data. We benchmark the performance of five machine learning approaches using data from the Cancer Cell Line Encyclopedia, reporting accuracy on cancer type classification and mean absolute error on drug response prediction, and evaluating runtime efficiency. This review provides recommendations to…
Citation impact
- FWCI
- 22.95
- Percentile
- 100%
- References
- 150
Authors
4- ZCZhaoxiang Cai
The University of Sydney, Children's Medical Research Institute
- RCRebecca C. Poulos
The University of Sydney, Children's Medical Research Institute
- JLJia Liu
Camden and Campbelltown Hospitals, The University of Sydney, Children's Medical Research Institute, Western Sydney University
- QZQing ZhongCorresponding
The University of Sydney, Children's Medical Research Institute
Topics & keywords
- Machine learning
- Artificial intelligence
- Computer science
- Omics
- Benchmark (surveying)
- Data integration
- Bioinformatics
- Data mining
- Good health and well-being
Funding
- AAstraZeneca
- CMChildren’s Medical Research Institute
- ACAustralian Cancer Research Foundation
- NBNational Breast Cancer FoundationAward: IIRS-18-164
- IPIan Potter Foundation
- CICancer Institute NSW
- UOUniversity of Sydney
- NMNSW Ministry of HealthAward: CMP-01
- H2Horizon 2020 Framework ProgrammeAwards: 826121, H2020-SC1-DTH-2018-1
- NHNational Health and Medical Research CouncilAwards: GNT1138536, GNT1170739
- CCCancer Council NSWAward: IG 18-01
- NCNational Cancer Institute