MOCSS : Multi-omics data clustering and cancer subtyping via shared and specific representation learning
© 2023 The Author(s)..
Cancer is an extremely complex disease and each type of cancer usually has several different subtypes. Multi-omics data can provide more comprehensive biological information for identifying and discovering cancer subtypes. However, existing unsupervised cancer subtyping methods cannot effectively learn comprehensive shared and specific information of multi-omics data. Therefore, a novel method is proposed based on shared and specific representation learning. For each omics data, two autoencoders are applied to extract shared and specific information, respectively. To reduce redundancy and mutual interference, orthogonality constraint is introduced to separate shared and specific information. In addition, contrastive learning is applied to align the shared information and strengthen their consistency. Finally, the obtained shared and specific information for all samples are used for clustering tasks to achieve cancer subtyping. Experimental results demonstrate that the proposed method can effectively capture shared and specific information of multi-omics data and outperform other state-of-the-art methods on cancer subtyping.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:26 |
---|---|
Enthalten in: |
iScience - 26(2023), 8 vom: 18. Aug., Seite 107378 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Chen, Yuxin [VerfasserIn] |
---|
Links: |
---|
Themen: |
Biocomputational method |
---|
Anmerkungen: |
Date Revised 11.08.2023 published: Electronic-eCollection Citation Status PubMed-not-MEDLINE |
---|
doi: |
10.1016/j.isci.2023.107378 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM360594980 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM360594980 | ||
003 | DE-627 | ||
005 | 20231226083336.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.isci.2023.107378 |2 doi | |
028 | 5 | 2 | |a pubmed24n1201.xml |
035 | |a (DE-627)NLM360594980 | ||
035 | |a (NLM)37559907 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Chen, Yuxin |e verfasserin |4 aut | |
245 | 1 | 0 | |a MOCSS |b Multi-omics data clustering and cancer subtyping via shared and specific representation learning |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Revised 11.08.2023 | ||
500 | |a published: Electronic-eCollection | ||
500 | |a Citation Status PubMed-not-MEDLINE | ||
520 | |a © 2023 The Author(s). | ||
520 | |a Cancer is an extremely complex disease and each type of cancer usually has several different subtypes. Multi-omics data can provide more comprehensive biological information for identifying and discovering cancer subtypes. However, existing unsupervised cancer subtyping methods cannot effectively learn comprehensive shared and specific information of multi-omics data. Therefore, a novel method is proposed based on shared and specific representation learning. For each omics data, two autoencoders are applied to extract shared and specific information, respectively. To reduce redundancy and mutual interference, orthogonality constraint is introduced to separate shared and specific information. In addition, contrastive learning is applied to align the shared information and strengthen their consistency. Finally, the obtained shared and specific information for all samples are used for clustering tasks to achieve cancer subtyping. Experimental results demonstrate that the proposed method can effectively capture shared and specific information of multi-omics data and outperform other state-of-the-art methods on cancer subtyping | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Biocomputational method | |
650 | 4 | |a Cancer | |
650 | 4 | |a Cancer systems biology | |
650 | 4 | |a Omics | |
700 | 1 | |a Wen, Yuqi |e verfasserin |4 aut | |
700 | 1 | |a Xie, Chenyang |e verfasserin |4 aut | |
700 | 1 | |a Chen, Xinjian |e verfasserin |4 aut | |
700 | 1 | |a He, Song |e verfasserin |4 aut | |
700 | 1 | |a Bo, Xiaochen |e verfasserin |4 aut | |
700 | 1 | |a Zhang, Zhongnan |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t iScience |d 2018 |g 26(2023), 8 vom: 18. Aug., Seite 107378 |w (DE-627)NLM285332627 |x 2589-0042 |7 nnns |
773 | 1 | 8 | |g volume:26 |g year:2023 |g number:8 |g day:18 |g month:08 |g pages:107378 |
856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.isci.2023.107378 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 26 |j 2023 |e 8 |b 18 |c 08 |h 107378 |