Format

Send to

Choose Destination
Genes (Basel). 2019 Jan 28;10(2). pii: E87. doi: 10.3390/genes10020087.

Machine Learning and Integrative Analysis of Biomedical Big Data.

Mirza B1,2, Wang W3,4,5,6, Wang J7,8, Choi H9,10,11, Chung NC12,13, Ping P14,15,16,17,18.

Author information

1
NIH BD2K Center of Excellence for Biomedical Computing, University of California Los Angeles, Los Angeles, CA 90095, USA. bmirza@mednet.ucla.edu.
2
Department of Physiology, University of California Los Angeles, Los Angeles, CA 90095, USA. bmirza@mednet.ucla.edu.
3
NIH BD2K Center of Excellence for Biomedical Computing, University of California Los Angeles, Los Angeles, CA 90095, USA. weiwang@cs.ucla.edu.
4
Department of Computer Science, University of California Los Angeles, Los Angeles, CA 90095, USA. weiwang@cs.ucla.edu.
5
Scalable Analytics Institute (ScAi), University of California Los Angeles, Los Angeles, CA 90095, USA. weiwang@cs.ucla.edu.
6
Department of Bioinformatics, University of California Los Angeles, Los Angeles, CA 90095, USA. weiwang@cs.ucla.edu.
7
NIH BD2K Center of Excellence for Biomedical Computing, University of California Los Angeles, Los Angeles, CA 90095, USA. jw744@g.ucla.edu.
8
Department of Physiology, University of California Los Angeles, Los Angeles, CA 90095, USA. jw744@g.ucla.edu.
9
NIH BD2K Center of Excellence for Biomedical Computing, University of California Los Angeles, Los Angeles, CA 90095, USA. cjh9595@g.ucla.edu.
10
Department of Physiology, University of California Los Angeles, Los Angeles, CA 90095, USA. cjh9595@g.ucla.edu.
11
Department of Bioinformatics, University of California Los Angeles, Los Angeles, CA 90095, USA. cjh9595@g.ucla.edu.
12
NIH BD2K Center of Excellence for Biomedical Computing, University of California Los Angeles, Los Angeles, CA 90095, USA. nchchung@gmail.com.
13
Institute of Informatics, Faculty of Mathematics, Informatics and Mechanics, University of Warsaw, Banacha 2, 02-097 Warsaw, Poland. nchchung@gmail.com.
14
NIH BD2K Center of Excellence for Biomedical Computing, University of California Los Angeles, Los Angeles, CA 90095, USA. pping38@g.ucla.edu.
15
Department of Physiology, University of California Los Angeles, Los Angeles, CA 90095, USA. pping38@g.ucla.edu.
16
Scalable Analytics Institute (ScAi), University of California Los Angeles, Los Angeles, CA 90095, USA. pping38@g.ucla.edu.
17
Department of Bioinformatics, University of California Los Angeles, Los Angeles, CA 90095, USA. pping38@g.ucla.edu.
18
Department of Medicine (Cardiology), University of California Los Angeles, Los Angeles, CA 90095, USA. pping38@g.ucla.edu.

Abstract

Recent developments in high-throughput technologies have accelerated the accumulation of massive amounts of omics data from multiple sources: genome, epigenome, transcriptome, proteome, metabolome, etc. Traditionally, data from each source (e.g., genome) is analyzed in isolation using statistical and machine learning (ML) methods. Integrative analysis of multi-omics and clinical data is key to new biomedical discoveries and advancements in precision medicine. However, data integration poses new computational challenges as well as exacerbates the ones associated with single-omics studies. Specialized computational approaches are required to effectively and efficiently perform integrative analysis of biomedical data acquired from diverse modalities. In this review, we discuss state-of-the-art ML-based approaches for tackling five specific computational challenges associated with integrative analysis: curse of dimensionality, data heterogeneity, missing data, class imbalance and scalability issues.

KEYWORDS:

class imbalance; curse of dimensionality; data integration; heterogeneous data; machine learning; missing data; multi-omics; scalability

Supplemental Content

Full text links

Icon for Multidisciplinary Digital Publishing Institute (MDPI) Icon for PubMed Central
Loading ...
Support Center