{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T08:49:57Z","timestamp":1771231797072,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1012339","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2024,8,21]],"date-time":"2024-08-21T00:00:00Z","timestamp":1724198400000}}],"reference-count":56,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T00:00:00Z","timestamp":1723075200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172076"],"award-info":[{"award-number":["62172076"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62250028"],"award-info":[{"award-number":["62250028"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2038"],"award-info":[{"award-number":["U22A2038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LY23F020003"],"award-info":[{"award-number":["LY23F020003"]}]},{"name":"Municipal Government of Quzhou","award":["2023D038"],"award-info":[{"award-number":["2023D038"]}]},{"name":"Project from KeyLaboratory of Computational Science and Application of Hainan Province","award":["JSKX202201"],"award-info":[{"award-number":["JSKX202201"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Single-cell RNA sequencing (scRNA-seq) has emerged as a powerful tool in genomics research, enabling the analysis of gene expression at the individual cell level. However, scRNA-seq data often suffer from a high rate of dropouts, where certain genes fail to be detected in specific cells due to technical limitations. This missing data can introduce biases and hinder downstream analysis. To overcome this challenge, the development of effective imputation methods has become crucial in the field of scRNA-seq data analysis. Here, we propose an imputation method based on robust and non-negative matrix factorization (scRNMF). Instead of other matrix factorization algorithms, scRNMF integrates two loss functions:<jats:italic>L<\/jats:italic><jats:sub>2<\/jats:sub>loss and C-loss. The<jats:italic>L<\/jats:italic><jats:sub>2<\/jats:sub>loss function is highly sensitive to outliers, which can introduce substantial errors. We utilize the C-loss function when dealing with zero values in the raw data. The primary advantage of the C-loss function is that it imposes a smaller punishment for larger errors, which results in more robust factorization when handling outliers. Various datasets of different sizes and zero rates are used to evaluate the performance of scRNMF against other state-of-the-art methods. Our method demonstrates its power and stability as a tool for imputation of scRNA-seq data.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1012339","type":"journal-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:54:54Z","timestamp":1723139694000},"page":"e1012339","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":10,"title":["scRNMF: An imputation method for single-cell RNA-seq data by robust and non-negative matrix factorization"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8616-1677","authenticated-orcid":true,"given":"Yuqing","family":"Qian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6406-1142","authenticated-orcid":true,"given":"Quan","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengyuan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8346-0798","authenticated-orcid":true,"given":"Fei","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yijie","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2024,8,8]]},"reference":[{"issue":"1","key":"pcbi.1012339.ref001","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1038\/s41467-018-03405-7","article-title":"An accurate and robust imputation method scImpute for single-cell RNA-seq data","volume":"9","author":"WV Li","year":"2018","journal-title":"Nature communications"},{"issue":"7","key":"pcbi.1012339.ref002","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1038\/s41592-018-0033-z","article-title":"SAVER: gene expression recovery for single-cell RNA sequencing","volume":"15","author":"M Huang","year":"2018","journal-title":"Nature methods"},{"issue":"9","key":"pcbi.1012339.ref003","doi-asserted-by":"crossref","first-page":"875","DOI":"10.1038\/s41592-019-0537-1","article-title":"Data denoising with transfer learning in single-cell transcriptomics","volume":"16","author":"J Wang","year":"2019","journal-title":"Nature methods"},{"issue":"3","key":"pcbi.1012339.ref004","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1016\/j.cell.2018.05.061","article-title":"Recovering gene interactions from single-cell data using data diffusion","volume":"174","author":"D Van Dijk","year":"2018","journal-title":"Cell"},{"issue":"10","key":"pcbi.1012339.ref005","doi-asserted-by":"crossref","first-page":"3131","DOI":"10.1093\/bioinformatics\/btaa108","article-title":"scTSSR: gene expression recovery for single-cell RNA sequencing using two-side sparse self-representation","volume":"36","author":"K Jin","year":"2020","journal-title":"Bioinformatics"},{"issue":"2","key":"pcbi.1012339.ref006","doi-asserted-by":"crossref","first-page":"1445","DOI":"10.1109\/TCBB.2022.3170587","article-title":"scTSSR2: imputing dropout events for single-cell RNA sequencing using fast two-side self-representation","volume":"20","author":"B Li","year":"2022","journal-title":"IEEE\/ACM Transactions on Computational Biology and Bioinformatics"},{"issue":"12","key":"pcbi.1012339.ref007","doi-asserted-by":"crossref","first-page":"3222","DOI":"10.1093\/bioinformatics\/btac300","article-title":"Imputing dropouts for single-cell RNA sequencing based on multi-objective optimization","volume":"38","author":"K Jin","year":"2022","journal-title":"Bioinformatics"},{"issue":"12","key":"pcbi.1012339.ref008","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1038\/s41592-018-0229-2","article-title":"Deep generative modeling for single-cell transcriptomics","volume":"15","author":"R Lopez","year":"2018","journal-title":"Nature methods"},{"issue":"1","key":"pcbi.1012339.ref009","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13059-019-1837-6","article-title":"DeepImpute: an accurate, fast, and scalable deep neural network method to impute single-cell RNA-seq data","volume":"20","author":"C Arisdakessian","year":"2019","journal-title":"Genome biology"},{"issue":"21","key":"pcbi.1012339.ref010","doi-asserted-by":"crossref","first-page":"12100","DOI":"10.1093\/nar\/gkx870","article-title":"Deep learning of the splicing (epi) genetic code reveals a novel candidate mechanism linking histone modifications to ESC fate decision","volume":"45","author":"Y Xu","year":"2017","journal-title":"Nucleic acids research"},{"issue":"1","key":"pcbi.1012339.ref011","doi-asserted-by":"crossref","first-page":"16329","DOI":"10.1038\/s41598-018-34688-x","article-title":"AutoImpute: Autoencoder based imputation of single-cell RNA-seq data","volume":"8","author":"D Talwar","year":"2018","journal-title":"Scientific reports"},{"issue":"1","key":"pcbi.1012339.ref012","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1038\/s41467-018-07931-2","article-title":"Single-cell RNA-seq denoising using a deep count autoencoder","volume":"10","author":"G Eraslan","year":"2019","journal-title":"Nature communications"},{"issue":"1","key":"pcbi.1012339.ref013","doi-asserted-by":"crossref","first-page":"1901","DOI":"10.1038\/s41467-022-29576-y","article-title":"A universal deep neural network for in-depth cleaning of single-cell RNA-Seq data","volume":"13","author":"H Li","year":"2022","journal-title":"Nature Communications"},{"issue":"1","key":"pcbi.1012339.ref014","doi-asserted-by":"crossref","first-page":"1882","DOI":"10.1038\/s41467-021-22197-x","article-title":"scGNN is a novel graph neural network framework for single-cell RNA-Seq analyses","volume":"12","author":"J Wang","year":"2021","journal-title":"Nature communications"},{"issue":"15","key":"pcbi.1012339.ref015","doi-asserted-by":"crossref","first-page":"e85","DOI":"10.1093\/nar\/gkaa506","article-title":"scIGANs: single-cell RNA-seq imputation using generative adversarial networks","volume":"48","author":"Y Xu","year":"2020","journal-title":"Nucleic acids research"},{"issue":"3","key":"pcbi.1012339.ref016","doi-asserted-by":"crossref","first-page":"btad098","DOI":"10.1093\/bioinformatics\/btad098","article-title":"scGCL: an imputation method for scRNA-seq data based on graph contrastive learning","volume":"39","author":"Z Xiong","year":"2023","journal-title":"Bioinformatics"},{"key":"pcbi.1012339.ref017","doi-asserted-by":"crossref","first-page":"9","DOI":"10.3389\/fgene.2019.00009","article-title":"McImpute: matrix completion based imputation for single cell RNA-seq data","volume":"10","author":"A Mongia","year":"2019","journal-title":"Frontiers in genetics"},{"issue":"1","key":"pcbi.1012339.ref018","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1038\/s41467-021-27729-z","article-title":"Zero-preserving imputation of single-cell RNA-seq data","volume":"13","author":"GC Linderman","year":"2022","journal-title":"Nature communications"},{"issue":"2","key":"pcbi.1012339.ref019","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1101\/gr.251603.119","article-title":"netNMF-sc: leveraging gene\u2013gene interactions for imputation and dimensionality reduction in single-cell expression analysis","volume":"30","author":"R Elyanow","year":"2020","journal-title":"Genome research"},{"issue":"10","key":"pcbi.1012339.ref020","doi-asserted-by":"crossref","first-page":"3139","DOI":"10.1093\/bioinformatics\/btaa109","article-title":"CMF-Impute: an accurate imputation tool for single-cell RNA-seq data","volume":"36","author":"J Xu","year":"2020","journal-title":"Bioinformatics"},{"issue":"1","key":"pcbi.1012339.ref021","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1093\/jmcb\/mjaa052","article-title":"Imputing single-cell RNA-seq data by considering cell heterogeneity and prior expression of dropouts","volume":"13","author":"L Zhang","year":"2021","journal-title":"Journal of molecular cell biology"},{"issue":"11","key":"pcbi.1012339.ref022","doi-asserted-by":"crossref","first-page":"1139","DOI":"10.1038\/s41592-019-0576-7","article-title":"Exploring single-cell data with deep multitasking neural networks","volume":"16","author":"M Amodio","year":"2019","journal-title":"Nature methods"},{"issue":"9","key":"pcbi.1012339.ref023","doi-asserted-by":"crossref","first-page":"4877","DOI":"10.1093\/nar\/gkac317","article-title":"scIMC: a platform for benchmarking comparison and visualization analysis of scRNA-seq data imputation methods","volume":"50","author":"C Dai","year":"2022","journal-title":"Nucleic Acids Research"},{"issue":"5","key":"pcbi.1012339.ref024","doi-asserted-by":"crossref","first-page":"bbac389","DOI":"10.1093\/bib\/bbac389","article-title":"Boosting single-cell gene regulatory network reconstruction via bulk-cell transcriptomic data","volume":"23","author":"H Shu","year":"2022","journal-title":"Briefings in Bioinformatics"},{"key":"pcbi.1012339.ref025","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1007\/978-1-4939-7717-8_19","article-title":"Applications of single-cell sequencing for multiomics","author":"Y Xu","year":"2018","journal-title":"Computational Systems Biology: Methods and Protocols"},{"issue":"1","key":"pcbi.1012339.ref026","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13059-019-1681-8","article-title":"SCRABBLE: single-cell RNA-seq imputation constrained by bulk RNA-seq data","volume":"20","author":"T Peng","year":"2019","journal-title":"Genome biology"},{"issue":"4","key":"pcbi.1012339.ref027","doi-asserted-by":"crossref","first-page":"bbac223","DOI":"10.1093\/bib\/bbac223","article-title":"DURIAN: an integrative deconvolution and imputation method for robust signaling analysis of single-cell transcriptomics data","volume":"23","author":"M Karikomi","year":"2022","journal-title":"Briefings in bioinformatics"},{"issue":"1","key":"pcbi.1012339.ref028","doi-asserted-by":"crossref","first-page":"bbac580","DOI":"10.1093\/bib\/bbac580","article-title":"Bubble: a fast single-cell RNA-seq imputation using an autoencoder constrained by bulk RNA-seq data","volume":"24","author":"S Chen","year":"2023","journal-title":"Briefings in bioinformatics"},{"issue":"1","key":"pcbi.1012339.ref029","doi-asserted-by":"crossref","first-page":"780","DOI":"10.1038\/s41467-022-28431-4","article-title":"UINMF performs mosaic integration of single-cell multi-omic datasets using nonnegative matrix factorization","volume":"13","author":"AR Kriebel","year":"2022","journal-title":"Nature communications"},{"key":"pcbi.1012339.ref030","doi-asserted-by":"crossref","unstructured":"Kong D, Ding C, Huang H. Robust nonnegative matrix factorization using l21-norm. In: Proceedings of the 20th ACM international conference on Information and knowledge management; 2011. p. 673\u2013682.","DOI":"10.1145\/2063576.2063676"},{"key":"pcbi.1012339.ref031","doi-asserted-by":"crossref","unstructured":"Du L, Li X, Shen YD. Robust nonnegative matrix factorization via half-quadratic minimization. In: 2012 IEEE 12th International Conference on Data Mining. IEEE; 2012. p. 201\u2013210.","DOI":"10.1109\/ICDM.2012.39"},{"key":"pcbi.1012339.ref032","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1109\/TSP.2019.2952057","article-title":"Robust matrix completion via maximum correntropy criterion and half-quadratic optimization","volume":"68","author":"Y He","year":"2019","journal-title":"IEEE Transactions on Signal Processing"},{"key":"pcbi.1012339.ref033","first-page":"1","article-title":"A systematic evaluation of single-cell RNA-sequencing imputation methods","volume":"21","author":"W Hou","year":"2020","journal-title":"Genome biology"},{"issue":"1","key":"pcbi.1012339.ref034","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1186\/s12859-023-05417-7","article-title":"Evaluating imputation methods for single-cell RNA-seq data","volume":"24","author":"Y Cheng","year":"2023","journal-title":"BMC bioinformatics"},{"key":"pcbi.1012339.ref035","article-title":"A novel triple matrix factorization method for detecting drug-side effect association based on kernel target alignment","volume":"2020","author":"X Guo","year":"2020","journal-title":"BioMed Research International"},{"issue":"5","key":"pcbi.1012339.ref036","doi-asserted-by":"crossref","first-page":"bbaa409","DOI":"10.1093\/bib\/bbaa409","article-title":"Exploring associations of non-coding RNAs in human diseases via three-matrix factorization with hypergraph-regular terms on center kernel alignment","volume":"22","author":"H Wang","year":"2021","journal-title":"Briefings in Bioinformatics"},{"issue":"2","key":"pcbi.1012339.ref037","doi-asserted-by":"crossref","first-page":"bbab582","DOI":"10.1093\/bib\/bbab582","article-title":"Identification of drug\u2013target interactions via multiple kernel-based triple collaborative matrix factorization","volume":"23","author":"Y Ding","year":"2022","journal-title":"Briefings in Bioinformatics"},{"key":"pcbi.1012339.ref038","doi-asserted-by":"crossref","unstructured":"Wang Y, Zhai Y, Ding Y, Zou Q. SBSM-Pro: Support Bio-sequence Machine for Proteins. arXiv preprint arXiv:230810275. 2023.","DOI":"10.1007\/s11432-024-4171-9"},{"key":"pcbi.1012339.ref039","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511804441","volume-title":"Convex optimization","author":"SP Boyd","year":"2004"},{"issue":"6","key":"pcbi.1012339.ref040","doi-asserted-by":"crossref","first-page":"1623","DOI":"10.1109\/TIP.2007.896622","article-title":"The equivalence of half-quadratic minimization and the gradient linearization iteration","volume":"16","author":"M Nikolova","year":"2007","journal-title":"IEEE Transactions on Image Processing"},{"key":"pcbi.1012339.ref041","unstructured":"Lee D, Seung HS. Algorithms for non-negative matrix factorization. Advances in neural information processing systems. 2000;13."},{"issue":"1","key":"pcbi.1012339.ref042","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1186\/s13059-017-1305-0","article-title":"Splatter: simulation of single-cell RNA sequencing data","volume":"18","author":"L Zappia","year":"2017","journal-title":"Genome biology"},{"issue":"9","key":"pcbi.1012339.ref043","doi-asserted-by":"crossref","first-page":"2812","DOI":"10.1039\/C3AY41907J","article-title":"Principal component analysis","volume":"6","author":"R Bro","year":"2014","journal-title":"Analytical methods"},{"issue":"1","key":"pcbi.1012339.ref044","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1038\/nbt.4314","article-title":"Dimensionality reduction for visualizing single-cell data using UMAP","volume":"37","author":"E Becht","year":"2019","journal-title":"Nature biotechnology"},{"issue":"1","key":"pcbi.1012339.ref045","first-page":"100","article-title":"Algorithm AS 136: A k-means clustering algorithm","volume":"28","author":"JA Hartigan","year":"1979","journal-title":"Journal of the royal statistical society series c (applied statistics)"},{"key":"pcbi.1012339.ref046","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/BF01908075","article-title":"Comparing partitions","volume":"2","author":"L Hubert","year":"1985","journal-title":"Journal of classification"},{"issue":"1","key":"pcbi.1012339.ref047","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1093\/bioinformatics\/btp616","article-title":"edgeR: a Bioconductor package for differential expression analysis of digital gene expression data","volume":"26","author":"MD Robinson","year":"2010","journal-title":"bioinformatics"},{"key":"pcbi.1012339.ref048","first-page":"1","article-title":"Single-cell RNA-seq reveals novel regulators of human embryonic stem cell differentiation to definitive endoderm","volume":"17","author":"LF Chu","year":"2016","journal-title":"Genome biology"},{"issue":"3","key":"pcbi.1012339.ref049","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1038\/nmeth.4150","article-title":"Single-cell mRNA quantification and differential analysis with Census","volume":"14","author":"X Qiu","year":"2017","journal-title":"Nature methods"},{"issue":"13","key":"pcbi.1012339.ref050","doi-asserted-by":"crossref","first-page":"e117","DOI":"10.1093\/nar\/gkw430","article-title":"TSCAN: Pseudo-time reconstruction and evaluation in single-cell RNA-seq analysis","volume":"44","author":"Z Ji","year":"2016","journal-title":"Nucleic acids research"},{"key":"pcbi.1012339.ref051","doi-asserted-by":"crossref","DOI":"10.12688\/f1000research.16613.1","article-title":"False signals induced by single-cell imputation","volume":"7","author":"TS Andrews","year":"2018","journal-title":"F1000Research"},{"issue":"8","key":"pcbi.1012339.ref052","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/MC.2009.263","article-title":"Matrix factorization techniques for recommender systems","volume":"42","author":"Y Koren","year":"2009","journal-title":"Computer"},{"key":"pcbi.1012339.ref053","first-page":"1","article-title":"SCANPY: large-scale single-cell gene expression data analysis","volume":"19","author":"FA Wolf","year":"2018","journal-title":"Genome biology"},{"key":"pcbi.1012339.ref054","doi-asserted-by":"crossref","first-page":"828479","DOI":"10.3389\/fgene.2022.828479","article-title":"Dimensionality reduction and louvain agglomerative hierarchical clustering for cluster-specified frequent biomarker discovery in single-cell sequencing data","volume":"13","author":"S Seth","year":"2022","journal-title":"Frontiers in Genetics"},{"key":"pcbi.1012339.ref055","unstructured":"Erichson NB, Voronin S, Brunton SL, Kutz JN. Randomized matrix decompositions using R. arXiv preprint arXiv:160802148. 2016;."},{"issue":"4","key":"pcbi.1012339.ref056","doi-asserted-by":"crossref","first-page":"1004","DOI":"10.1162\/REST_a_00043","article-title":"Determining the number of factors from empirical distribution of eigenvalues","volume":"92","author":"A Onatski","year":"2010","journal-title":"The Review of Economics and Statistics"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1012339","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2024,8,21]],"date-time":"2024-08-21T00:00:00Z","timestamp":1724198400000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012339","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T13:28:10Z","timestamp":1732627690000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012339"}},"subtitle":[],"editor":[{"given":"Qing","family":"Nie","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2024,8,8]]},"references-count":56,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2024,8,8]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1012339","relation":{"new_version":[{"id-type":"doi","id":"10.1371\/journal.pcbi.1012339","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,8]]}}}