{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T06:05:07Z","timestamp":1790661907954,"version":"4.1.0"},"reference-count":34,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100018693","name":"HORIZON EUROPE Framework Programme","doi-asserted-by":"publisher","award":["101095432"],"award-info":[{"award-number":["101095432"]}],"id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Bioinform."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Single-cell RNA sequencing (scRNA-seq) enables gene expression profiling at the resolution of individual cells, revealing cellular heterogeneity that is obscured in bulk RNA-seq. While this offers a powerful lens to study disease-specific changes, leveraging scRNA-seq data for patient phenotype classification remains challenging due to limited sample numbers, cell count variability, high dimensionality, and dependence on cell-type annotations. Existing tools attempt to address these issues using probabilistic models or attention mechanisms, but face limitations in scalability, interpretability, or representational power.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this work, we introduce DeepCelllify, a novel deep learning-based framework that harnesses convolutional neural networks (CNNs) to classify patients using their individual cell expression profiles. Our approach converts tabular gene expression data into image-like representations, enabling CNNs to learn spatial feature relationships between genes. Each cell is treated as an independent input labeled by its originating patient\u2019s condition (e.g., disease or control), allowing us to sidestep the limitations posed by small patient cohorts and heterogeneous cell counts. The DeepCelllify pipeline includes a transformation module for data preprocessing and a classification module, culminating in CNN models trained through cross-validation to differentiate between disease states based on single-cell inputs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our method demonstrates competitive performance compared to state-of-the-art approaches, with added benefits in scalability, interpretability, and practical applicability. DeepCelllify further addresses critical bottlenecks in scRNA-seq-based phenotype prediction, including overfitting from low patient counts, challenges in feature matrix construction, and dimensionality issues. Additionally, our method provides interpretability by assigning weights to individual cells, helping to down-weight misclassified or noisy cells.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>This work introduces deep learning framework for patient phenotype prediction from scRNA-seq data, with potential applications in precision medicine and biomarker discovery.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fbinf.2026.1919127","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T05:48:25Z","timestamp":1790660905000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Patient classification using single-cell RNA-sequencing data with deep learning convolutional neural networks"],"prefix":"10.3389","volume":"6","author":[{"given":"Anastasis","family":"Oulas","sequence":"first","affiliation":[{"name":"Bioinformatics Department, The Cyprus Institute of Neurology and Genetics","place":["Nicosia, Cyprus"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nestoras","family":"Karathanasis","sequence":"additional","affiliation":[{"name":"Bioinformatics Department, The Cyprus Institute of Neurology and Genetics","place":["Nicosia, Cyprus"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Theodosios","family":"Lampadarios","sequence":"additional","affiliation":[{"name":"Bioinformatics Department, The Cyprus Institute of Neurology and Genetics","place":["Nicosia, Cyprus"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raphael","family":"Antartis","sequence":"additional","affiliation":[{"name":"Bioinformatics Department, The Cyprus Institute of Neurology and Genetics","place":["Nicosia, Cyprus"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"George M.","family":"Spyrou","sequence":"additional","affiliation":[{"name":"Bioinformatics Department, The Cyprus Institute of Neurology and Genetics","place":["Nicosia, Cyprus"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,29]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1109\/MCI.2010.938364","article-title":"Deep Machine Learning - A New Frontier in Artificial Intelligence Research [Research Frontier]","volume":"5","author":"Arel","year":"2010","journal-title":"IEEE Comput. Intell. Mag."},{"key":"B2","doi-asserted-by":"publisher","first-page":"4391","DOI":"10.1038\/s41467-020-18197-y","article-title":"Representation of features as images with neighborhood dependencies for compatibility with convolutional neural networks","volume":"11","author":"Bazgir","year":"2020","journal-title":"Nat. Commun."},{"key":"B3","doi-asserted-by":"publisher","first-page":"7040","DOI":"10.1038\/s41467-022-33944-z","article-title":"Single cell characterization of myeloma and its precursor conditions reveals transcriptional signatures of early tumorigenesis","volume":"13","author":"Boiarsky","year":"2022","journal-title":"Nat. Commun."},{"key":"B4","doi-asserted-by":"publisher","first-page":"1530","DOI":"10.3389\/fonc.2019.01530","article-title":"Spliced XBP1 levels determine sensitivity of multiple myeloma cells to proteasome inhibitor bortezomib independent of the unfolded protein response mediator GRP78","volume":"9","author":"Borjan","year":"2020","journal-title":"Front. Oncol."},{"key":"B5","doi-asserted-by":"publisher","first-page":"1032","DOI":"10.1016\/j.ccell.2023.05.007","article-title":"Single cell clonotypic and transcriptional evolution of multiple myeloma precursor disease","volume":"41","author":"Dang","year":"2023","journal-title":"Cancer Cell"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1182\/hem.V16.4.9651","article-title":"XBP1s: getting to the roots of multiple myeloma","volume":"16","author":"Dong","year":"2019","journal-title":"Hematologist"},{"key":"B7","doi-asserted-by":"publisher","first-page":"729","DOI":"10.3324\/haematol.2010.030577","article-title":"Polymorphisms of nuclear factor- B family genes are associated with development of multiple myeloma and treatment outcome in patients receiving bortezomib-based regimens","volume":"96","author":"Du","year":"2011","journal-title":"Haematologica"},{"key":"B8","doi-asserted-by":"publisher","first-page":"3693","DOI":"10.1016\/j.celrep.2018.12.016","article-title":"Non-overlapping control of transcriptome by Promoter- and super-enhancer-associated dependencies in multiple myeloma","volume":"25","author":"Fulciniti","year":"2018","journal-title":"Cell Rep."},{"key":"B9","doi-asserted-by":"publisher","first-page":"3573","DOI":"10.1016\/j.cell.2021.04.048","article-title":"Integrated analysis of multimodal single-cell data","volume":"184","author":"Hao","year":"2021","journal-title":"Cell"},{"key":"B10","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1142\/9789811250477_0031","article-title":"CloudPred: predicting patient phenotypes from single-cell RNA-seq","volume":"27","author":"He","year":"2022","journal-title":"Pac. Symp. Biocomput."},{"key":"B11","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1007\/s10618-019-00619-1","article-title":"Deep learning for time series classification: a review","volume":"33","author":"Ismail Fawaz","year":"2019","journal-title":"Data Min. Knowl. Discov."},{"key":"B12","doi-asserted-by":"publisher","first-page":"361","DOI":"10.20452\/pamw.15896","article-title":"Endoplasmic reticulum stress and proteasome inhibitors in multiple myeloma: room for improvement","volume":"131","author":"Kubicki","year":"2021","journal-title":"Pol. Arch. Intern. Med."},{"key":"B13","doi-asserted-by":"publisher","first-page":"17046","DOI":"10.1038\/nrdp.2017.46","article-title":"Multiple myeloma","volume":"3","author":"Kumar","year":"2017","journal-title":"Nat. Rev. Dis. Prim."},{"key":"B14","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"B15","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1186\/s12964-021-00781-4","article-title":"Pathophysiological role of calcium channels and transporters in the multiple myeloma","volume":"19","author":"Li","year":"2021","journal-title":"Cell Commun. Signal."},{"key":"B16","doi-asserted-by":"publisher","first-page":"btae067","DOI":"10.1093\/bioinformatics\/btae067","article-title":"Phenotype prediction from single-cell RNA-seq data using attention-based neural networks","volume":"40","author":"Mao","year":"2024","journal-title":"Bioinformatics"},{"key":"B17","doi-asserted-by":"publisher","first-page":"632564","DOI":"10.3389\/fimmu.2021.632564","article-title":"Co-evolution of immune response in multiple myeloma: implications for immune prevention","volume":"12","author":"McCachren","year":"2021","journal-title":"Front. Immunol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"e1007","DOI":"10.1002\/cti2.1007","article-title":"Endoplasmic reticulum stress in the development of multiple myeloma and drug resistance","volume":"7","author":"Nikesitch","year":"2018","journal-title":"Clin. Transl. Immunol."},{"key":"B19","doi-asserted-by":"publisher","first-page":"3069","DOI":"10.1182\/blood-2014-09-568899","article-title":"Smoldering multiple myeloma","volume":"125","author":"Rajkumar","year":"2015","journal-title":"Blood"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.20517\/2394-4722.2019.05","article-title":"Metabolic alterations and the potential for targeting metabolic pathways in the treatment of multiple myeloma","volume":"2019","author":"Rizzieri","year":"2019","journal-title":"J. Cancer Metastasis Treat."},{"key":"B21","doi-asserted-by":"publisher","first-page":"5873","DOI":"10.1182\/bloodadvances.2022007217","article-title":"Characterizing the role of the immune microenvironment in multiple myeloma progression at a single-cell level","volume":"6","author":"Schinke","year":"2022","journal-title":"Blood Adv."},{"key":"B22","doi-asserted-by":"crossref","first-page":"618","DOI":"10.1109\/ICCV.2017.74","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","volume-title":"2017 IEEE International Conference on Computer Vision (ICCV)","author":"Selvaraju","year":"2017"},{"key":"B23","doi-asserted-by":"publisher","first-page":"11399","DOI":"10.1038\/s41598-019-47765-6","article-title":"DeepInsight: a methodology to transform a non-image data to an image for convolution neural network architecture","volume":"9","author":"Sharma","year":"2019","journal-title":"Sci. Rep."},{"key":"B24","doi-asserted-by":"publisher","first-page":"829","DOI":"10.31557\/APJCP.2024.25.3.829","article-title":"Impact of genetic polymorphisms in NF-\u0138B2 and TRAF3 genes on response to Bortezomib-Based therapy in multiple myeloma patients","volume":"25","author":"Sood","year":"2024","journal-title":"Asian pac. J. Cancer Prev."},{"key":"B25","doi-asserted-by":"publisher","first-page":"904","DOI":"10.1038\/s41591-021-01329-2","article-title":"Single-cell multi-omics analysis of the immune response in COVID-19","volume":"27","author":"Stephenson","year":"2021","journal-title":"Nat. Med."},{"key":"B26","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1186\/s12859-025-06309-8","article-title":"scMFF: a machine learning framework with multiple feature fusion strategies for cell type identification","volume":"26","author":"Sun","year":"2025","journal-title":"BMC Bioinforma."},{"key":"B27","doi-asserted-by":"publisher","first-page":"1682","DOI":"10.3390\/cancers15061682","article-title":"Metabolic alterations in multiple myeloma: from oncogenesis to proteasome inhibitor resistance","volume":"15","author":"Weir","year":"2023","journal-title":"Cancers (Basel)"},{"key":"B28","doi-asserted-by":"publisher","first-page":"e90","DOI":"10.1002\/cpz1.90","article-title":"Gene set knowledge discovery with Enrichr","volume":"1","author":"Xie","year":"2021","journal-title":"Curr. Protoc."},{"key":"B29","doi-asserted-by":"publisher","first-page":"3883","DOI":"10.1007\/s00018-021-03756-3","article-title":"Crosstalk between endoplasmic reticulum stress and oxidative stress: a dynamic duo in multiple myeloma","volume":"78","author":"Xiong","year":"2021","journal-title":"Cell. Mol. Life Sci."},{"key":"B30","doi-asserted-by":"publisher","first-page":"btad493","DOI":"10.1093\/bioinformatics\/btad493","article-title":"ProtoCell4P: an explainable prototype-based neural network for patient classification using single-cell RNA-seq","volume":"39","author":"Xiong","year":"2023","journal-title":"Bioinformatics"},{"key":"B31","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s43018-020-0053-3","article-title":"Single-cell RNA sequencing reveals compromised immune microenvironment in precursor stages of multiple myeloma","volume":"1","author":"Zavidij","year":"2020","journal-title":"Nat. Cancer"},{"key":"B32","volume-title":"scPheno: A Deep Generative Model to Integrate scRNA-seq with Disease Phenotypes and its Application on Prediction of COVID-19 Pneumonia and Severe Assessment","author":"Zeng","year":"2022"},{"key":"B33","doi-asserted-by":"publisher","first-page":"111213","DOI":"10.18632\/oncotarget.22740","article-title":"Alteration of mitochondrial biogenesis promotes disease progression in multiple myeloma","volume":"8","author":"Zhan","year":"2017","journal-title":"Oncotarget"},{"key":"B34","doi-asserted-by":"publisher","first-page":"11325","DOI":"10.1038\/s41598-021-90923-y","article-title":"Converting tabular data into images for deep learning with convolutional neural networks","volume":"11","author":"Zhu","year":"2021","journal-title":"Sci. Rep."}],"container-title":["Frontiers in Bioinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2026.1919127\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T05:48:27Z","timestamp":1790660907000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2026.1919127\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,29]]},"references-count":34,"alternative-id":["10.3389\/fbinf.2026.1919127"],"URL":"https:\/\/doi.org\/10.3389\/fbinf.2026.1919127","relation":{},"ISSN":["2673-7647"],"issn-type":[{"value":"2673-7647","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,29]]},"article-number":"1919127"}}