A model-based factorization method for scRNA data unveils bifurcating transcriptional modules underlying cell fate determination
Manifold-learning is particularly useful to resolve the complex cellular state space from single-cell RNA sequences. While current manifold-learning methods provide insights into cell fate by inferring graph-based trajectory at cell level, challenges remain to retrieve interpretable biology underlyi...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
eLife Sciences Publications Ltd
2025-02-01
|
| Series: | eLife |
| Subjects: | |
| Online Access: | https://elifesciences.org/articles/97424 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832096584251211776 |
|---|---|
| author | Jun Ren Ying Zhou Yudi Hu Jing Yang Hongkun Fang Xuejing Lyu Jintao Guo Xiaodong Shi Qiyuan Li |
| author_facet | Jun Ren Ying Zhou Yudi Hu Jing Yang Hongkun Fang Xuejing Lyu Jintao Guo Xiaodong Shi Qiyuan Li |
| author_sort | Jun Ren |
| collection | DOAJ |
| description | Manifold-learning is particularly useful to resolve the complex cellular state space from single-cell RNA sequences. While current manifold-learning methods provide insights into cell fate by inferring graph-based trajectory at cell level, challenges remain to retrieve interpretable biology underlying the diverse cellular states. Here, we described MGPfactXMBD, a model-based manifold-learning framework and capable to factorize complex development trajectories into independent bifurcation processes of gene sets, and thus enables trajectory inference based on relevant features. MGPfactXMBD offers a more nuanced understanding of the biological processes underlying cellular trajectories with potential determinants. When bench-tested across 239 datasets, MGPfactXMBD showed advantages in major quantity-control metrics, such as branch division accuracy and trajectory topology, outperforming most established methods. In real datasets, MGPfactXMBD recovered the critical pathways and cell types in microglia development with experimentally valid regulons and markers. Furthermore, MGPfactXMBD discovered evolutionary trajectories of tumor-associated CD8+ T cells and yielded new subtypes of CD8+ T cells with gene expression signatures significantly predictive of the responses to immune checkpoint inhibitor in independent cohorts. In summary, MGPfactXMBD offers a manifold-learning framework in scRNA-seq data which enables feature selection for specific biological processes and contributing to advance our understanding of biological determination of cell fate. |
| format | Article |
| id | doaj-art-567a71df15534d96a5135eff847e0da3 |
| institution | Kabale University |
| issn | 2050-084X |
| language | English |
| publishDate | 2025-02-01 |
| publisher | eLife Sciences Publications Ltd |
| record_format | Article |
| series | eLife |
| spelling | doaj-art-567a71df15534d96a5135eff847e0da32025-02-05T13:53:30ZengeLife Sciences Publications LtdeLife2050-084X2025-02-011310.7554/eLife.97424A model-based factorization method for scRNA data unveils bifurcating transcriptional modules underlying cell fate determinationJun Ren0https://orcid.org/0000-0002-9027-2303Ying Zhou1Yudi Hu2Jing Yang3Hongkun Fang4Xuejing Lyu5Jintao Guo6Xiaodong Shi7Qiyuan Li8https://orcid.org/0000-0002-8934-8948National Institute for Data Science in Health and Medicine, School of Medicine, Xiamen University, Xiamen, China; Department of Hematology, The First Affiliated Hospital of Xiamen University and Institute of Hematology, School of Medicine, Xiamen University, Xiamen, China; School of Informatics, Xiamen University, Xiamen, Xiamen, ChinaNational Institute for Data Science in Health and Medicine, School of Medicine, Xiamen University, Xiamen, China; Department of Hematology, The First Affiliated Hospital of Xiamen University and Institute of Hematology, School of Medicine, Xiamen University, Xiamen, ChinaNational Institute for Data Science in Health and Medicine, School of Medicine, Xiamen University, Xiamen, ChinaNational Institute for Data Science in Health and Medicine, School of Medicine, Xiamen University, Xiamen, ChinaDepartment of Scientific Research Management, Weifang People’s Hospital, Shandong Second Medical University, Weifang, ChinaNational Institute for Data Science in Health and Medicine, School of Medicine, Xiamen University, Xiamen, ChinaDepartment of Scientific Research Management, Weifang People’s Hospital, Shandong Second Medical University, Weifang, ChinaSchool of Informatics, Xiamen University, Xiamen, Xiamen, ChinaNational Institute for Data Science in Health and Medicine, School of Medicine, Xiamen University, Xiamen, China; Department of Hematology, The First Affiliated Hospital of Xiamen University and Institute of Hematology, School of Medicine, Xiamen University, Xiamen, ChinaManifold-learning is particularly useful to resolve the complex cellular state space from single-cell RNA sequences. While current manifold-learning methods provide insights into cell fate by inferring graph-based trajectory at cell level, challenges remain to retrieve interpretable biology underlying the diverse cellular states. Here, we described MGPfactXMBD, a model-based manifold-learning framework and capable to factorize complex development trajectories into independent bifurcation processes of gene sets, and thus enables trajectory inference based on relevant features. MGPfactXMBD offers a more nuanced understanding of the biological processes underlying cellular trajectories with potential determinants. When bench-tested across 239 datasets, MGPfactXMBD showed advantages in major quantity-control metrics, such as branch division accuracy and trajectory topology, outperforming most established methods. In real datasets, MGPfactXMBD recovered the critical pathways and cell types in microglia development with experimentally valid regulons and markers. Furthermore, MGPfactXMBD discovered evolutionary trajectories of tumor-associated CD8+ T cells and yielded new subtypes of CD8+ T cells with gene expression signatures significantly predictive of the responses to immune checkpoint inhibitor in independent cohorts. In summary, MGPfactXMBD offers a manifold-learning framework in scRNA-seq data which enables feature selection for specific biological processes and contributing to advance our understanding of biological determination of cell fate.https://elifesciences.org/articles/97424scRNA-seqfactorizationmanifold-learningbifurcation processmixtures of Gaussian processes |
| spellingShingle | Jun Ren Ying Zhou Yudi Hu Jing Yang Hongkun Fang Xuejing Lyu Jintao Guo Xiaodong Shi Qiyuan Li A model-based factorization method for scRNA data unveils bifurcating transcriptional modules underlying cell fate determination eLife scRNA-seq factorization manifold-learning bifurcation process mixtures of Gaussian processes |
| title | A model-based factorization method for scRNA data unveils bifurcating transcriptional modules underlying cell fate determination |
| title_full | A model-based factorization method for scRNA data unveils bifurcating transcriptional modules underlying cell fate determination |
| title_fullStr | A model-based factorization method for scRNA data unveils bifurcating transcriptional modules underlying cell fate determination |
| title_full_unstemmed | A model-based factorization method for scRNA data unveils bifurcating transcriptional modules underlying cell fate determination |
| title_short | A model-based factorization method for scRNA data unveils bifurcating transcriptional modules underlying cell fate determination |
| title_sort | model based factorization method for scrna data unveils bifurcating transcriptional modules underlying cell fate determination |
| topic | scRNA-seq factorization manifold-learning bifurcation process mixtures of Gaussian processes |
| url | https://elifesciences.org/articles/97424 |
| work_keys_str_mv | AT junren amodelbasedfactorizationmethodforscrnadataunveilsbifurcatingtranscriptionalmodulesunderlyingcellfatedetermination AT yingzhou amodelbasedfactorizationmethodforscrnadataunveilsbifurcatingtranscriptionalmodulesunderlyingcellfatedetermination AT yudihu amodelbasedfactorizationmethodforscrnadataunveilsbifurcatingtranscriptionalmodulesunderlyingcellfatedetermination AT jingyang amodelbasedfactorizationmethodforscrnadataunveilsbifurcatingtranscriptionalmodulesunderlyingcellfatedetermination AT hongkunfang amodelbasedfactorizationmethodforscrnadataunveilsbifurcatingtranscriptionalmodulesunderlyingcellfatedetermination AT xuejinglyu amodelbasedfactorizationmethodforscrnadataunveilsbifurcatingtranscriptionalmodulesunderlyingcellfatedetermination AT jintaoguo amodelbasedfactorizationmethodforscrnadataunveilsbifurcatingtranscriptionalmodulesunderlyingcellfatedetermination AT xiaodongshi amodelbasedfactorizationmethodforscrnadataunveilsbifurcatingtranscriptionalmodulesunderlyingcellfatedetermination AT qiyuanli amodelbasedfactorizationmethodforscrnadataunveilsbifurcatingtranscriptionalmodulesunderlyingcellfatedetermination AT junren modelbasedfactorizationmethodforscrnadataunveilsbifurcatingtranscriptionalmodulesunderlyingcellfatedetermination AT yingzhou modelbasedfactorizationmethodforscrnadataunveilsbifurcatingtranscriptionalmodulesunderlyingcellfatedetermination AT yudihu modelbasedfactorizationmethodforscrnadataunveilsbifurcatingtranscriptionalmodulesunderlyingcellfatedetermination AT jingyang modelbasedfactorizationmethodforscrnadataunveilsbifurcatingtranscriptionalmodulesunderlyingcellfatedetermination AT hongkunfang modelbasedfactorizationmethodforscrnadataunveilsbifurcatingtranscriptionalmodulesunderlyingcellfatedetermination AT xuejinglyu modelbasedfactorizationmethodforscrnadataunveilsbifurcatingtranscriptionalmodulesunderlyingcellfatedetermination AT jintaoguo modelbasedfactorizationmethodforscrnadataunveilsbifurcatingtranscriptionalmodulesunderlyingcellfatedetermination AT xiaodongshi modelbasedfactorizationmethodforscrnadataunveilsbifurcatingtranscriptionalmodulesunderlyingcellfatedetermination AT qiyuanli modelbasedfactorizationmethodforscrnadataunveilsbifurcatingtranscriptionalmodulesunderlyingcellfatedetermination |