DeepVelo: deep learning extends RNA velocity to multi-lineage systems with cell-specific kinetics
Abstract Existing RNA velocity estimation methods strongly rely on predefined dynamics and cell-agnostic constant transcriptional kinetic rates, assumptions often violated in complex and heterogeneous single-cell RNA sequencing (scRNA-seq) data. Using a graph convolution network, DeepVelo overcomes...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-01-01
|
| Series: | Genome Biology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13059-023-03148-9 |
| _version_ | 1827377262755840000 |
|---|---|
| author | Haotian Cui Hassaan Maan Maria C. Vladoiu Jiao Zhang Michael D. Taylor Bo Wang |
| author_facet | Haotian Cui Hassaan Maan Maria C. Vladoiu Jiao Zhang Michael D. Taylor Bo Wang |
| author_sort | Haotian Cui |
| collection | DOAJ |
| description | Abstract Existing RNA velocity estimation methods strongly rely on predefined dynamics and cell-agnostic constant transcriptional kinetic rates, assumptions often violated in complex and heterogeneous single-cell RNA sequencing (scRNA-seq) data. Using a graph convolution network, DeepVelo overcomes these limitations by generalizing RNA velocity to cell populations containing time-dependent kinetics and multiple lineages. DeepVelo infers time-varying cellular rates of transcription, splicing, and degradation, recovers each cell’s stage in the differentiation process, and detects functionally relevant driver genes regulating these processes. Application to various developmental and pathogenic processes demonstrates DeepVelo’s capacity to study complex differentiation and lineage decision events in heterogeneous scRNA-seq data. |
| first_indexed | 2024-03-08T12:37:30Z |
| format | Article |
| id | doaj.art-6cf53315e61f4c3ea3e7ec45154ee2dc |
| institution | Directory Open Access Journal |
| issn | 1474-760X |
| language | English |
| last_indexed | 2024-03-08T12:37:30Z |
| publishDate | 2024-01-01 |
| publisher | BMC |
| record_format | Article |
| series | Genome Biology |
| spelling | doaj.art-6cf53315e61f4c3ea3e7ec45154ee2dc2024-01-21T12:23:36ZengBMCGenome Biology1474-760X2024-01-0125113110.1186/s13059-023-03148-9DeepVelo: deep learning extends RNA velocity to multi-lineage systems with cell-specific kineticsHaotian Cui0Hassaan Maan1Maria C. Vladoiu2Jiao Zhang3Michael D. Taylor4Bo Wang5Peter Munk Cardiac Center, University Health NetworkPeter Munk Cardiac Center, University Health NetworkDepartment of Pathology and Molecular Medicine, McMaster UniversityThe Arthur and Sonia Labatt Brain Tumor Research Centre, The Hospital for Sick ChildrenThe Arthur and Sonia Labatt Brain Tumor Research Centre, The Hospital for Sick ChildrenPeter Munk Cardiac Center, University Health NetworkAbstract Existing RNA velocity estimation methods strongly rely on predefined dynamics and cell-agnostic constant transcriptional kinetic rates, assumptions often violated in complex and heterogeneous single-cell RNA sequencing (scRNA-seq) data. Using a graph convolution network, DeepVelo overcomes these limitations by generalizing RNA velocity to cell populations containing time-dependent kinetics and multiple lineages. DeepVelo infers time-varying cellular rates of transcription, splicing, and degradation, recovers each cell’s stage in the differentiation process, and detects functionally relevant driver genes regulating these processes. Application to various developmental and pathogenic processes demonstrates DeepVelo’s capacity to study complex differentiation and lineage decision events in heterogeneous scRNA-seq data.https://doi.org/10.1186/s13059-023-03148-9RNA velocitySingle-cell RNA sequencingDeep LearningDevelopmentCancer |
| spellingShingle | Haotian Cui Hassaan Maan Maria C. Vladoiu Jiao Zhang Michael D. Taylor Bo Wang DeepVelo: deep learning extends RNA velocity to multi-lineage systems with cell-specific kinetics Genome Biology RNA velocity Single-cell RNA sequencing Deep Learning Development Cancer |
| title | DeepVelo: deep learning extends RNA velocity to multi-lineage systems with cell-specific kinetics |
| title_full | DeepVelo: deep learning extends RNA velocity to multi-lineage systems with cell-specific kinetics |
| title_fullStr | DeepVelo: deep learning extends RNA velocity to multi-lineage systems with cell-specific kinetics |
| title_full_unstemmed | DeepVelo: deep learning extends RNA velocity to multi-lineage systems with cell-specific kinetics |
| title_short | DeepVelo: deep learning extends RNA velocity to multi-lineage systems with cell-specific kinetics |
| title_sort | deepvelo deep learning extends rna velocity to multi lineage systems with cell specific kinetics |
| topic | RNA velocity Single-cell RNA sequencing Deep Learning Development Cancer |
| url | https://doi.org/10.1186/s13059-023-03148-9 |
| work_keys_str_mv | AT haotiancui deepvelodeeplearningextendsrnavelocitytomultilineagesystemswithcellspecifickinetics AT hassaanmaan deepvelodeeplearningextendsrnavelocitytomultilineagesystemswithcellspecifickinetics AT mariacvladoiu deepvelodeeplearningextendsrnavelocitytomultilineagesystemswithcellspecifickinetics AT jiaozhang deepvelodeeplearningextendsrnavelocitytomultilineagesystemswithcellspecifickinetics AT michaeldtaylor deepvelodeeplearningextendsrnavelocitytomultilineagesystemswithcellspecifickinetics AT bowang deepvelodeeplearningextendsrnavelocitytomultilineagesystemswithcellspecifickinetics |