A benchmark study of deep learning-based multi-omics data fusion methods for cancer.

Publisher: BioMed Central Ltd Country of Publication: England NLM ID: 100960660 Publication Model: Electronic Cited Medium: Internet ISSN: 1474-760X (Electronic) Linking ISSN: 14747596 NLM ISO Abbreviation: Genome Biol Subsets: MEDLINE

Publication: London, UK : BioMed Central Ltd
Original Publication: London : Genome Biology Ltd., c2000-

Deep Learning* ; Neoplasms*/genetics; Algorithms ; Benchmarking ; Cluster Analysis ; Humans

Background: A fused method using a combination of multi-omics data enables a comprehensive study of complex biological processes and highlights the interrelationship of relevant biomolecules and their functions. Driven by high-throughput sequencing technologies, several promising deep learning methods have been proposed for fusing multi-omics data generated from a large number of samples.
Results: In this study, 16 representative deep learning methods are comprehensively evaluated on simulated, single-cell, and cancer multi-omics datasets. For each of the datasets, two tasks are designed: classification and clustering. The classification performance is evaluated by using three benchmarking metrics including accuracy, F1 macro, and F1 weighted. Meanwhile, the clustering performance is evaluated by using four benchmarking metrics including the Jaccard index (JI), C-index, silhouette score, and Davies Bouldin score. For the cancer multi-omics datasets, the methods' strength in capturing the association of multi-omics dimensionality reduction results with survival and clinical annotations is further evaluated. The benchmarking results indicate that moGAT achieves the best classification performance. Meanwhile, efmmdVAE, efVAE, and lfmmdVAE show the most promising performance across all complementary contexts in clustering tasks.
Conclusions: Our benchmarking results not only provide a reference for biomedical researchers to choose appropriate deep learning-based multi-omics data fusion methods, but also suggest the future directions for the development of more effective multi-omics data fusion methods. The deep learning frameworks are available at https://github.com/zhenglinyi/DL-mo .
(© 2022. The Author(s).)

Nat Rev Drug Discov. 2013 Jan;12(1):35-50. (PMID: 23274470)
PLoS Comput Biol. 2018 Oct 31;14(10):e1006520. (PMID: 30379847)
Nat Rev Drug Discov. 2003 Aug;2(8):668-76. (PMID: 12904817)
Am J Transl Res. 2020 Aug 15;12(8):4669-4682. (PMID: 32913540)
Bioinformatics. 2021 Aug 20;:. (PMID: 34415323)
Nat Mach Intell. 2019 Dec;1(12):568-577. (PMID: 32368721)
IEEE/ACM Trans Comput Biol Bioinform. 2022 Jul-Aug;19(4):2334-2344. (PMID: 34086576)
Brief Bioinform. 2019 Jul 19;20(4):1269-1279. (PMID: 29272335)
BMC Genomics. 2019 Dec 20;20(Suppl 11):944. (PMID: 31856727)
Nat Methods. 2019 Jul;16(7):607-610. (PMID: 31249421)
Nat Commun. 2021 Jun 8;12(1):3445. (PMID: 34103512)
Methods. 2019 Aug 15;166:66-73. (PMID: 30853547)
Biomedicines. 2021 Feb 10;9(2):. (PMID: 33578890)
Comput Struct Biotechnol J. 2020 Aug 11;18:2185-2199. (PMID: 32952934)
Nucleic Acids Res. 2020 Sep 4;48(15):e85. (PMID: 32588900)
Nat Rev Cancer. 2022 Feb;22(2):114-126. (PMID: 34663944)
Exp Mol Med. 2020 Sep;52(9):1428-1442. (PMID: 32929225)
Nat Rev Genet. 2017 Oct;18(10):613-623. (PMID: 28649135)
Cancers (Basel). 2021 Apr 22;13(9):. (PMID: 33921978)
AMIA Jt Summits Transl Sci Proc. 2018 May 18;2017:197-206. (PMID: 29888072)
Brief Bioinform. 2020 Mar 23;21(2):541-552. (PMID: 31220206)
Comput Struct Biotechnol J. 2020 Feb 15;18:427-438. (PMID: 32153729)
BMC Bioinformatics. 2021 Feb 27;22(1):97. (PMID: 33639858)
J Clin Endocrinol Metab. 2017 Mar 01;102(3):923-932. (PMID: 27967600)
Sci Rep. 2021 Mar 18;11(1):6265. (PMID: 33737557)
Nat Rev Drug Discov. 2020 Jan;19(1):23-38. (PMID: 31712683)
IEEE J Biomed Health Inform. 2021 Oct;25(10):4041-4051. (PMID: 33974548)
Eur J Radiol. 2020 Jul;128:109041. (PMID: 32408222)
Genes (Basel). 2020 Aug 04;11(8):. (PMID: 32759821)
IEEE Trans Neural Netw Learn Syst. 2018 Aug;29(8):3573-3587. (PMID: 28829320)
Cancer Cell. 2017 Jul 10;32(1):42-56.e6. (PMID: 28697342)
Bioinformatics. 2006 Oct 1;22(19):2405-12. (PMID: 16882653)
Nature. 2012 Oct 4;490(7418):61-70. (PMID: 23000897)
Methods Mol Biol. 2021;2194:223-238. (PMID: 32926369)
Genomics. 2020 Jul;112(4):2833-2841. (PMID: 32234433)
Nat Commun. 2021 Jun 24;12(1):3932. (PMID: 34168145)
Life Sci Alliance. 2019 Dec 2;2(6):. (PMID: 31792061)
BioData Min. 2020 Aug 24;13:10. (PMID: 32863885)
BMC Bioinformatics. 2020 Jul 21;21(1):323. (PMID: 32693790)
Nucleic Acids Res. 2018 Nov 16;46(20):10546-10562. (PMID: 30295871)
Bioinformatics. 2018 May 1;34(9):1538-1546. (PMID: 29253077)
Front Mol Biosci. 2020 Sep 08;7:562798. (PMID: 33102518)
BMC Med Inform Decis Mak. 2020 Sep 15;20(1):225. (PMID: 32933515)
Sci Rep. 2020 May 14;10(1):7948. (PMID: 32409715)
Nat Genet. 2020 Oct;52(10):1024-1035. (PMID: 32989324)
Front Endocrinol (Lausanne). 2016 Jan 20;6:195. (PMID: 26834703)
Brief Bioinform. 2021 Nov 5;22(6):. (PMID: 33963829)
Mol Cells. 2021 Jul 31;44(7):433-443. (PMID: 34238766)
Commun Biol. 2020 Sep 10;3(1):502. (PMID: 32913254)
Comput Methods Programs Biomed. 2016 May;128:69-74. (PMID: 27040832)
Nat Commun. 2021 Jan 5;12(1):124. (PMID: 33402734)
Brief Bioinform. 2021 Jul 20;22(4):. (PMID: 33200787)
Bioinformatics. 2019 Jul 15;35(14):i501-i509. (PMID: 31510700)
Front Genet. 2020 Sep 30;11:869. (PMID: 33133123)
Nat Rev Nephrol. 2021 Nov;17(11):710-724. (PMID: 34417589)
Front Genet. 2019 Mar 08;10:166. (PMID: 30906311)
Nat Commun. 2019 Jan 28;10(1):470. (PMID: 30692544)
Comput Biol Chem. 2020 May 12;87:107277. (PMID: 32512487)
Bioinformatics. 2020 Jul 1;36(Suppl_1):i445-i454. (PMID: 32657357)
IEEE/ACM Trans Comput Biol Bioinform. 2020 Sep-Oct;17(5):1605-1612. (PMID: 30969931)
Brief Bioinform. 2020 Dec 1;21(6):2011-2030. (PMID: 31792509)
BMC Cancer. 2022 Jan 20;22(1):86. (PMID: 35057766)

Date Created: 20220809 Date Completed: 20220811 Latest Revision: 20221027

20240104

PMC9361561

10.1186/s13059-022-02739-2

35945544