Haohuai He, Zhenchao Tang, Guanxing Chen, Fan Xu, Yao Hu, Yinglan Feng, Jibin Wu, Yu-An Huang, Zhi-An Huang, Kay Chen Tan
{"title":"scKAN:通过Kolmogorov-Arnold网络进行细胞类型特异性基因发现和药物再利用的可解释单细胞分析","authors":"Haohuai He, Zhenchao Tang, Guanxing Chen, Fan Xu, Yao Hu, Yinglan Feng, Jibin Wu, Yu-An Huang, Zhi-An Huang, Kay Chen Tan","doi":"10.1186/s13059-025-03779-0","DOIUrl":null,"url":null,"abstract":"Analysis of single-cell RNA sequencing (scRNA-seq) data has revolutionized our understanding of cellular heterogeneity, yet current approaches face challenges in efficiency, interpretability, and connecting molecular insights to therapeutic applications. Despite advances in deep learning methods, identifying cell-type-specific functional gene sets remains difficult. In this study, we present scKAN, an interpretable framework for scRNA-seq analysis with two primary goals: accurate cell-type annotation and the discovery of cell-type-specific marker genes and gene sets. The key innovation is using the learnable activation curves of the Kolmogorov-Arnold network to model gene-to-cell relationships. This approach provides a more direct way to visualize and interpret these specific interactions compared to the aggregated weighting schemes typical of attention mechanisms. This architecture achieves superior performance in cell-type annotation, with a 6.63% improvement in macro F1 score over state-of-the-art methods. Additionally, it enables the systematic identification of functionally coherent cell-type-specific gene sets. We demonstrate the framework’s translational potential through a case study on pancreatic ductal adenocarcinoma, where gene signatures identified by scKAN led to a potential drug repurposing candidate, whose binding stability was supported by molecular dynamics simulations. Our work establishes scKAN as an efficient and interpretable framework that effectively bridges single-cell analysis with drug discovery. By combining lightweight architecture with the ability to uncover nuanced biological patterns, our approach offers an interpretable method for translating large-scale single-cell data into actionable therapeutic strategies. This approach provides a robust foundation for accelerating the identification of cell-type-specific targets in complex diseases.","PeriodicalId":12611,"journal":{"name":"Genome Biology","volume":"40 1","pages":""},"PeriodicalIF":10.1000,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"scKAN: interpretable single-cell analysis for cell-type-specific gene discovery and drug repurposing via Kolmogorov-Arnold networks\",\"authors\":\"Haohuai He, Zhenchao Tang, Guanxing Chen, Fan Xu, Yao Hu, Yinglan Feng, Jibin Wu, Yu-An Huang, Zhi-An Huang, Kay Chen Tan\",\"doi\":\"10.1186/s13059-025-03779-0\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Analysis of single-cell RNA sequencing (scRNA-seq) data has revolutionized our understanding of cellular heterogeneity, yet current approaches face challenges in efficiency, interpretability, and connecting molecular insights to therapeutic applications. Despite advances in deep learning methods, identifying cell-type-specific functional gene sets remains difficult. In this study, we present scKAN, an interpretable framework for scRNA-seq analysis with two primary goals: accurate cell-type annotation and the discovery of cell-type-specific marker genes and gene sets. The key innovation is using the learnable activation curves of the Kolmogorov-Arnold network to model gene-to-cell relationships. This approach provides a more direct way to visualize and interpret these specific interactions compared to the aggregated weighting schemes typical of attention mechanisms. This architecture achieves superior performance in cell-type annotation, with a 6.63% improvement in macro F1 score over state-of-the-art methods. Additionally, it enables the systematic identification of functionally coherent cell-type-specific gene sets. We demonstrate the framework’s translational potential through a case study on pancreatic ductal adenocarcinoma, where gene signatures identified by scKAN led to a potential drug repurposing candidate, whose binding stability was supported by molecular dynamics simulations. Our work establishes scKAN as an efficient and interpretable framework that effectively bridges single-cell analysis with drug discovery. By combining lightweight architecture with the ability to uncover nuanced biological patterns, our approach offers an interpretable method for translating large-scale single-cell data into actionable therapeutic strategies. This approach provides a robust foundation for accelerating the identification of cell-type-specific targets in complex diseases.\",\"PeriodicalId\":12611,\"journal\":{\"name\":\"Genome Biology\",\"volume\":\"40 1\",\"pages\":\"\"},\"PeriodicalIF\":10.1000,\"publicationDate\":\"2025-09-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Genome Biology\",\"FirstCategoryId\":\"99\",\"ListUrlMain\":\"https://doi.org/10.1186/s13059-025-03779-0\",\"RegionNum\":1,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"BIOTECHNOLOGY & APPLIED MICROBIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Genome Biology","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1186/s13059-025-03779-0","RegionNum":1,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BIOTECHNOLOGY & APPLIED MICROBIOLOGY","Score":null,"Total":0}
scKAN: interpretable single-cell analysis for cell-type-specific gene discovery and drug repurposing via Kolmogorov-Arnold networks
Analysis of single-cell RNA sequencing (scRNA-seq) data has revolutionized our understanding of cellular heterogeneity, yet current approaches face challenges in efficiency, interpretability, and connecting molecular insights to therapeutic applications. Despite advances in deep learning methods, identifying cell-type-specific functional gene sets remains difficult. In this study, we present scKAN, an interpretable framework for scRNA-seq analysis with two primary goals: accurate cell-type annotation and the discovery of cell-type-specific marker genes and gene sets. The key innovation is using the learnable activation curves of the Kolmogorov-Arnold network to model gene-to-cell relationships. This approach provides a more direct way to visualize and interpret these specific interactions compared to the aggregated weighting schemes typical of attention mechanisms. This architecture achieves superior performance in cell-type annotation, with a 6.63% improvement in macro F1 score over state-of-the-art methods. Additionally, it enables the systematic identification of functionally coherent cell-type-specific gene sets. We demonstrate the framework’s translational potential through a case study on pancreatic ductal adenocarcinoma, where gene signatures identified by scKAN led to a potential drug repurposing candidate, whose binding stability was supported by molecular dynamics simulations. Our work establishes scKAN as an efficient and interpretable framework that effectively bridges single-cell analysis with drug discovery. By combining lightweight architecture with the ability to uncover nuanced biological patterns, our approach offers an interpretable method for translating large-scale single-cell data into actionable therapeutic strategies. This approach provides a robust foundation for accelerating the identification of cell-type-specific targets in complex diseases.
Genome BiologyBiochemistry, Genetics and Molecular Biology-Genetics
CiteScore
21.00
自引率
3.30%
发文量
241
审稿时长
2 months
期刊介绍:
Genome Biology stands as a premier platform for exceptional research across all domains of biology and biomedicine, explored through a genomic and post-genomic lens.
With an impressive impact factor of 12.3 (2022),* the journal secures its position as the 3rd-ranked research journal in the Genetics and Heredity category and the 2nd-ranked research journal in the Biotechnology and Applied Microbiology category by Thomson Reuters. Notably, Genome Biology holds the distinction of being the highest-ranked open-access journal in this category.
Our dedicated team of highly trained in-house Editors collaborates closely with our esteemed Editorial Board of international experts, ensuring the journal remains on the forefront of scientific advances and community standards. Regular engagement with researchers at conferences and institute visits underscores our commitment to staying abreast of the latest developments in the field.