Deep cross-omics cycle attention model for joint analysis of single-cell multi-omics data
© The Author(s) 2021. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissionsoup.com..
MOTIVATION: Joint profiling of single-cell transcriptomics and epigenomics data enables us to characterize cell states and transcriptomics regulatory programs related to cellular heterogeneity. However, the highly different features on sparsity, heterogeneity and dimensionality between multi-omics data have severely hindered its integrative analysis.
RESULTS: We proposed deep cross-omics cycle attention (DCCA) model, a computational tool for joint analysis of single-cell multi-omics data, by combining variational autoencoders (VAEs) and attention-transfer. Specifically, we show that DCCA can leverage one omics data to fine-tune the network trained for another omics data, given a dataset of parallel multi-omics data within the same cell. Studies on both simulated and real datasets from various platforms, DCCA demonstrates its superior capability: (i) dissecting cellular heterogeneity; (ii) denoising and aggregating data and (iii) constructing the link between multi-omics data, which is used to infer new transcriptional regulatory relations. In our applications, DCCA was demonstrated to have a superior power to generate missing stages or omics in a biologically meaningful manner, which provides a new way to analyze and also understand complicated biological processes.
AVAILABILITY AND IMPLEMENTATION: DCCA source code is available at https://github.com/cmzuo11/DCCA, and has been deposited in archived format at https://doi.org/10.5281/zenodo.4762065.
SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2021 |
|---|---|
| Erschienen: |
2021 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:37 |
|---|---|
| Enthalten in: |
Bioinformatics (Oxford, England) - 37(2021), 22 vom: 18. Nov., Seite 4091-4099 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Zuo, Chunman [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Completed 13.04.2023 Date Revised 16.04.2023 published: Print Citation Status MEDLINE |
|---|
| doi: |
10.1093/bioinformatics/btab403 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM325777977 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM325777977 | ||
| 003 | DE-627 | ||
| 005 | 20231225193146.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1093/bioinformatics/btab403 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1085.xml |
| 035 | |a (DE-627)NLM325777977 | ||
| 035 | |a (NLM)34028557 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Zuo, Chunman |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Deep cross-omics cycle attention model for joint analysis of single-cell multi-omics data |
| 264 | 1 | |c 2021 | |
| 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 Completed 13.04.2023 | ||
| 500 | |a Date Revised 16.04.2023 | ||
| 500 | |a published: Print | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a © The Author(s) 2021. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissionsoup.com. | ||
| 520 | |a MOTIVATION: Joint profiling of single-cell transcriptomics and epigenomics data enables us to characterize cell states and transcriptomics regulatory programs related to cellular heterogeneity. However, the highly different features on sparsity, heterogeneity and dimensionality between multi-omics data have severely hindered its integrative analysis | ||
| 520 | |a RESULTS: We proposed deep cross-omics cycle attention (DCCA) model, a computational tool for joint analysis of single-cell multi-omics data, by combining variational autoencoders (VAEs) and attention-transfer. Specifically, we show that DCCA can leverage one omics data to fine-tune the network trained for another omics data, given a dataset of parallel multi-omics data within the same cell. Studies on both simulated and real datasets from various platforms, DCCA demonstrates its superior capability: (i) dissecting cellular heterogeneity; (ii) denoising and aggregating data and (iii) constructing the link between multi-omics data, which is used to infer new transcriptional regulatory relations. In our applications, DCCA was demonstrated to have a superior power to generate missing stages or omics in a biologically meaningful manner, which provides a new way to analyze and also understand complicated biological processes | ||
| 520 | |a AVAILABILITY AND IMPLEMENTATION: DCCA source code is available at https://github.com/cmzuo11/DCCA, and has been deposited in archived format at https://doi.org/10.5281/zenodo.4762065 | ||
| 520 | |a SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Research Support, Non-U.S. Gov't | |
| 700 | 1 | |a Dai, Hao |e verfasserin |4 aut | |
| 700 | 1 | |a Chen, Luonan |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Bioinformatics (Oxford, England) |d 1998 |g 37(2021), 22 vom: 18. Nov., Seite 4091-4099 |w (DE-627)NLM094620342 |x 1367-4811 |7 nnns |
| 773 | 1 | 8 | |g volume:37 |g year:2021 |g number:22 |g day:18 |g month:11 |g pages:4091-4099 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1093/bioinformatics/btab403 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 37 |j 2021 |e 22 |b 18 |c 11 |h 4091-4099 | ||