A mechanism-informed deep neural network enables prioritization of regulators that drive cell state transitions
Abstract Cells are regulated at multiple levels, from regulations of individual genes to interactions across multiple genes. Some recent neural network models can connect molecular changes to cellular phenotypes, but their design lacks modeling of regulatory mechanisms, limiting the decoding of regu...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-025-56475-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861844744339456 |
|---|---|
| author | Xi Xi Jiaqi Li Jinmeng Jia Qiuchen Meng Chen Li Xiaowo Wang Lei Wei Xuegong Zhang |
| author_facet | Xi Xi Jiaqi Li Jinmeng Jia Qiuchen Meng Chen Li Xiaowo Wang Lei Wei Xuegong Zhang |
| author_sort | Xi Xi |
| collection | DOAJ |
| description | Abstract Cells are regulated at multiple levels, from regulations of individual genes to interactions across multiple genes. Some recent neural network models can connect molecular changes to cellular phenotypes, but their design lacks modeling of regulatory mechanisms, limiting the decoding of regulations behind key cellular events, such as cell state transitions. Here, we present regX, a deep neural network incorporating both gene-level regulation and gene-gene interaction mechanisms, which enables prioritizing potential driver regulators of cell state transitions and providing mechanistic interpretations. Applied to single-cell multi-omics data on type 2 diabetes and hair follicle development, regX reliably prioritizes key transcription factors and candidate cis-regulatory elements that drive cell state transitions. Some regulators reveal potential new therapeutic targets, drug repurposing possibilities, and putative causal single nucleotide polymorphisms. This method to analyze single-cell multi-omics data demonstrates how the interpretable design of neural networks can better decode biological systems. |
| format | Article |
| id | doaj-art-d2c2e579bf0e448c8e7603a13ce6669c |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-d2c2e579bf0e448c8e7603a13ce6669c2025-02-09T12:45:52ZengNature PortfolioNature Communications2041-17232025-02-0116111810.1038/s41467-025-56475-9A mechanism-informed deep neural network enables prioritization of regulators that drive cell state transitionsXi Xi0Jiaqi Li1Jinmeng Jia2Qiuchen Meng3Chen Li4Xiaowo Wang5Lei Wei6Xuegong Zhang7MOE Key Laboratory of Bioinformatics and Bioinformatics Division, BNRIST / Department of Automation, Tsinghua UniversityMOE Key Laboratory of Bioinformatics and Bioinformatics Division, BNRIST / Department of Automation, Tsinghua UniversityMOE Key Laboratory of Bioinformatics and Bioinformatics Division, BNRIST / Department of Automation, Tsinghua UniversityMOE Key Laboratory of Bioinformatics and Bioinformatics Division, BNRIST / Department of Automation, Tsinghua UniversityMOE Key Laboratory of Bioinformatics and Bioinformatics Division, BNRIST / Department of Automation, Tsinghua UniversityMOE Key Laboratory of Bioinformatics and Bioinformatics Division, BNRIST / Department of Automation, Tsinghua UniversityMOE Key Laboratory of Bioinformatics and Bioinformatics Division, BNRIST / Department of Automation, Tsinghua UniversityMOE Key Laboratory of Bioinformatics and Bioinformatics Division, BNRIST / Department of Automation, Tsinghua UniversityAbstract Cells are regulated at multiple levels, from regulations of individual genes to interactions across multiple genes. Some recent neural network models can connect molecular changes to cellular phenotypes, but their design lacks modeling of regulatory mechanisms, limiting the decoding of regulations behind key cellular events, such as cell state transitions. Here, we present regX, a deep neural network incorporating both gene-level regulation and gene-gene interaction mechanisms, which enables prioritizing potential driver regulators of cell state transitions and providing mechanistic interpretations. Applied to single-cell multi-omics data on type 2 diabetes and hair follicle development, regX reliably prioritizes key transcription factors and candidate cis-regulatory elements that drive cell state transitions. Some regulators reveal potential new therapeutic targets, drug repurposing possibilities, and putative causal single nucleotide polymorphisms. This method to analyze single-cell multi-omics data demonstrates how the interpretable design of neural networks can better decode biological systems.https://doi.org/10.1038/s41467-025-56475-9 |
| spellingShingle | Xi Xi Jiaqi Li Jinmeng Jia Qiuchen Meng Chen Li Xiaowo Wang Lei Wei Xuegong Zhang A mechanism-informed deep neural network enables prioritization of regulators that drive cell state transitions Nature Communications |
| title | A mechanism-informed deep neural network enables prioritization of regulators that drive cell state transitions |
| title_full | A mechanism-informed deep neural network enables prioritization of regulators that drive cell state transitions |
| title_fullStr | A mechanism-informed deep neural network enables prioritization of regulators that drive cell state transitions |
| title_full_unstemmed | A mechanism-informed deep neural network enables prioritization of regulators that drive cell state transitions |
| title_short | A mechanism-informed deep neural network enables prioritization of regulators that drive cell state transitions |
| title_sort | mechanism informed deep neural network enables prioritization of regulators that drive cell state transitions |
| url | https://doi.org/10.1038/s41467-025-56475-9 |
| work_keys_str_mv | AT xixi amechanisminformeddeepneuralnetworkenablesprioritizationofregulatorsthatdrivecellstatetransitions AT jiaqili amechanisminformeddeepneuralnetworkenablesprioritizationofregulatorsthatdrivecellstatetransitions AT jinmengjia amechanisminformeddeepneuralnetworkenablesprioritizationofregulatorsthatdrivecellstatetransitions AT qiuchenmeng amechanisminformeddeepneuralnetworkenablesprioritizationofregulatorsthatdrivecellstatetransitions AT chenli amechanisminformeddeepneuralnetworkenablesprioritizationofregulatorsthatdrivecellstatetransitions AT xiaowowang amechanisminformeddeepneuralnetworkenablesprioritizationofregulatorsthatdrivecellstatetransitions AT leiwei amechanisminformeddeepneuralnetworkenablesprioritizationofregulatorsthatdrivecellstatetransitions AT xuegongzhang amechanisminformeddeepneuralnetworkenablesprioritizationofregulatorsthatdrivecellstatetransitions AT xixi mechanisminformeddeepneuralnetworkenablesprioritizationofregulatorsthatdrivecellstatetransitions AT jiaqili mechanisminformeddeepneuralnetworkenablesprioritizationofregulatorsthatdrivecellstatetransitions AT jinmengjia mechanisminformeddeepneuralnetworkenablesprioritizationofregulatorsthatdrivecellstatetransitions AT qiuchenmeng mechanisminformeddeepneuralnetworkenablesprioritizationofregulatorsthatdrivecellstatetransitions AT chenli mechanisminformeddeepneuralnetworkenablesprioritizationofregulatorsthatdrivecellstatetransitions AT xiaowowang mechanisminformeddeepneuralnetworkenablesprioritizationofregulatorsthatdrivecellstatetransitions AT leiwei mechanisminformeddeepneuralnetworkenablesprioritizationofregulatorsthatdrivecellstatetransitions AT xuegongzhang mechanisminformeddeepneuralnetworkenablesprioritizationofregulatorsthatdrivecellstatetransitions |