{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Yuan L"],"funding":["the Ability Improvement Project of Science and Technology SMES in Shandong Province","the Youth Innovation Team of Colleges and Universities in Shandong Province","Natural Science Foundation of Shandong Province","National Natural Science Foundation of China","Young Taishan Scholars Program"],"pagination":["350"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11974017"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["26(1)"],"pubmed_abstract":["<h4>Background</h4>Clustering scRNA-seq data plays a vital role in scRNA-seq data analysis and downstream analyses. Many computational methods have been proposed and achieved remarkable results. However, there are several limitations of these methods. First, they do not fully exploit cellular features. Second, they are developed based on gene expression information and lack of flexibility in integrating intercellular relationships. Finally, the performance of these methods is affected by dropout event.<h4>Results</h4>We propose a novel deep learning (DL) model based on attention autoencoder and zero-inflated (ZI) layer, namely scAMZI, to cluster scRNA-seq data. scAMZI is mainly composed of SimAM (a Simple, parameter-free Attention Module), autoencoder, ZINB (Zero-Inflated Negative Binomial"],"journal":["BMC genomics"],"pubmed_title":["scAMZI: attention-based deep autoencoder with zero-inflated layer for clustering scRNA-seq data."],"pmcid":["PMC11974017"],"funding_grant_id":["ZR2021MH104","2023KJ329","62472239","2023TSGC0279","ZR2024MF011","tsqn201909178"],"pubmed_authors":["Ye L","Meng B","Yuan L","Xu Z"],"additional_accession":[]},"is_claimable":false,"name":"scAMZI: attention-based deep autoencoder with zero-inflated layer for clustering scRNA-seq data.","description":"<h4>Background</h4>Clustering scRNA-seq data plays a vital role in scRNA-seq data analysis and downstream analyses. Many computational methods have been proposed and achieved remarkable results. However, there are several limitations of these methods. First, they do not fully exploit cellular features. Second, they are developed based on gene expression information and lack of flexibility in integrating intercellular relationships. Finally, the performance of these methods is affected by dropout event.<h4>Results</h4>We propose a novel deep learning (DL) model based on attention autoencoder and zero-inflated (ZI) layer, namely scAMZI, to cluster scRNA-seq data. scAMZI is mainly composed of SimAM (a Simple, parameter-free Attention Module), autoencoder, ZINB (Zero-Inflated Negative Binomial","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Apr","modification":"2026-05-29T15:20:31.69Z","creation":"2025-06-26T03:05:43.115Z"},"accession":"S-EPMC11974017","cross_references":{"pubmed":["40197174"],"doi":["10.1186/s12864-025-11511-2"]}}