scapGNN: A graph neural network-based framework for active pathway and gene module inference from single-cell multi-omics data.
Although advances in single-cell technologies have enabled the characterization of multiple omics profiles in individual cells, extracting functional and mechanistic insights from such information remains a major challenge. Here, we present scapGNN, a graph neural network (GNN)-based framework that...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2023-11-01
|
| Series: | PLoS Biology |
| Online Access: | https://journals.plos.org/plosbiology/article/file?id=10.1371/journal.pbio.3002369&type=printable |
| _version_ | 1797394719449284608 |
|---|---|
| author | Xudong Han Bing Wang Chenghao Situ Yaling Qi Hui Zhu Yan Li Xuejiang Guo |
| author_facet | Xudong Han Bing Wang Chenghao Situ Yaling Qi Hui Zhu Yan Li Xuejiang Guo |
| author_sort | Xudong Han |
| collection | DOAJ |
| description | Although advances in single-cell technologies have enabled the characterization of multiple omics profiles in individual cells, extracting functional and mechanistic insights from such information remains a major challenge. Here, we present scapGNN, a graph neural network (GNN)-based framework that creatively transforms sparse single-cell profile data into the stable gene-cell association network for inferring single-cell pathway activity scores and identifying cell phenotype-associated gene modules from single-cell multi-omics data. Systematic benchmarking demonstrated that scapGNN was more accurate, robust, and scalable than state-of-the-art methods in various downstream single-cell analyses such as cell denoising, batch effect removal, cell clustering, cell trajectory inference, and pathway or gene module identification. scapGNN was developed as a systematic R package that can be flexibly extended and enhanced for existing analysis processes. It provides a new analytical platform for studying single cells at the pathway and network levels. |
| first_indexed | 2024-03-09T00:23:49Z |
| format | Article |
| id | doaj.art-ee7d066c5cb2492a8344dbf8d96544f8 |
| institution | Directory Open Access Journal |
| issn | 1544-9173 1545-7885 |
| language | English |
| last_indexed | 2024-03-09T00:23:49Z |
| publishDate | 2023-11-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS Biology |
| spelling | doaj.art-ee7d066c5cb2492a8344dbf8d96544f82023-12-12T05:31:07ZengPublic Library of Science (PLoS)PLoS Biology1544-91731545-78852023-11-012111e300236910.1371/journal.pbio.3002369scapGNN: A graph neural network-based framework for active pathway and gene module inference from single-cell multi-omics data.Xudong HanBing WangChenghao SituYaling QiHui ZhuYan LiXuejiang GuoAlthough advances in single-cell technologies have enabled the characterization of multiple omics profiles in individual cells, extracting functional and mechanistic insights from such information remains a major challenge. Here, we present scapGNN, a graph neural network (GNN)-based framework that creatively transforms sparse single-cell profile data into the stable gene-cell association network for inferring single-cell pathway activity scores and identifying cell phenotype-associated gene modules from single-cell multi-omics data. Systematic benchmarking demonstrated that scapGNN was more accurate, robust, and scalable than state-of-the-art methods in various downstream single-cell analyses such as cell denoising, batch effect removal, cell clustering, cell trajectory inference, and pathway or gene module identification. scapGNN was developed as a systematic R package that can be flexibly extended and enhanced for existing analysis processes. It provides a new analytical platform for studying single cells at the pathway and network levels.https://journals.plos.org/plosbiology/article/file?id=10.1371/journal.pbio.3002369&type=printable |
| spellingShingle | Xudong Han Bing Wang Chenghao Situ Yaling Qi Hui Zhu Yan Li Xuejiang Guo scapGNN: A graph neural network-based framework for active pathway and gene module inference from single-cell multi-omics data. PLoS Biology |
| title | scapGNN: A graph neural network-based framework for active pathway and gene module inference from single-cell multi-omics data. |
| title_full | scapGNN: A graph neural network-based framework for active pathway and gene module inference from single-cell multi-omics data. |
| title_fullStr | scapGNN: A graph neural network-based framework for active pathway and gene module inference from single-cell multi-omics data. |
| title_full_unstemmed | scapGNN: A graph neural network-based framework for active pathway and gene module inference from single-cell multi-omics data. |
| title_short | scapGNN: A graph neural network-based framework for active pathway and gene module inference from single-cell multi-omics data. |
| title_sort | scapgnn a graph neural network based framework for active pathway and gene module inference from single cell multi omics data |
| url | https://journals.plos.org/plosbiology/article/file?id=10.1371/journal.pbio.3002369&type=printable |
| work_keys_str_mv | AT xudonghan scapgnnagraphneuralnetworkbasedframeworkforactivepathwayandgenemoduleinferencefromsinglecellmultiomicsdata AT bingwang scapgnnagraphneuralnetworkbasedframeworkforactivepathwayandgenemoduleinferencefromsinglecellmultiomicsdata AT chenghaositu scapgnnagraphneuralnetworkbasedframeworkforactivepathwayandgenemoduleinferencefromsinglecellmultiomicsdata AT yalingqi scapgnnagraphneuralnetworkbasedframeworkforactivepathwayandgenemoduleinferencefromsinglecellmultiomicsdata AT huizhu scapgnnagraphneuralnetworkbasedframeworkforactivepathwayandgenemoduleinferencefromsinglecellmultiomicsdata AT yanli scapgnnagraphneuralnetworkbasedframeworkforactivepathwayandgenemoduleinferencefromsinglecellmultiomicsdata AT xuejiangguo scapgnnagraphneuralnetworkbasedframeworkforactivepathwayandgenemoduleinferencefromsinglecellmultiomicsdata |