{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T18:35:33Z","timestamp":1791484533758,"version":"4.3.4"},"reference-count":48,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T00:00:00Z","timestamp":1762732800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"The \u201cKorea National Institute of Health\u201d (KNIH) research project","award":["project No. 2024-ER-0801-01"],"award-info":[{"award-number":["project No. 2024-ER-0801-01"]}]},{"name":"The Bio&Medical Technology Development Program of the National Research Foundation (NRF) funded by the Korean government","award":["No. RS-2025-18732993"],"award-info":[{"award-number":["No. RS-2025-18732993"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>\n                    Cytokines play a crucial role in immune system regulation, mediating responses from pathogen defense to tissue-damaging inflammation. Excessive cytokine production is implicated in severe conditions such as cancer progression, hemophagocytic lymphohistiocytosis, and severe cases of Coronavirus disease-2019 (COVID-19). Studies have shown that cytokine expression profiles serve as biomarkers for disease severity and mortality prediction, with machine learning (ML) methods increasingly employed for predictive analysis. To improve patient outcome predictions, treatment adaptation, and survival rates, longitudinal analysis of cytokine profiles is essential. Time-series cytokine profiling has been linked to tumor response, overall survival in various cancers, and acute encephalopathy. Similarly, COVID-19 severity and patient outcomes correlate with cytokine expression dynamics over time. However, challenges remain due to the limited availability of time-series cytokine data, restricting broader experimental applications and robust predictive modeling. Recent advancements indicate that cytokine expression can be computationally inferred using gene expression data and transcription factor interactions. Inferring cytokine levels from existing gene expression datasets could enhance early disease detection and treatment response predictions while reducing profiling costs. This work proposes TSCytoPred, a deep learning-based model trained on time-series gene expression data to infer cytokine expression trajectories. TSCytoPred identifies genes relevant for predicting target cytokines through interaction relationships and high correlation. These identified genes are subsequently utilized in a neural network incorporating an interpolation block to estimate cytokine expression trajectories between observed time points. Performance evaluations using a COVID-19 dataset demonstrate that TSCytoPred significantly outperforms baseline regression methods, achieving the highest coefficient of determinataion (R\n                    <jats:sup>2<\/jats:sup>\n                    ) and the lowest mean absolute error (MAE). Furthermore, cytokine data inferred by TSCytoPred enhances COVID-19 patient severity risk predictions, demonstrating the model\u2019s clinical utility. TSCytoPred can be effectively applied to datasets with limited time points and accommodates longitudinal datasets containing irregular temporal gaps, thereby enhancing disease outcome analysis such as in COVID-19 cases and expanding the applicability of multi-omics datasets in rare disease contexts with missing multi-omics samples. TSCytoPred is publicly available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/joungmin-choi\/TSCytoPred\">https:\/\/github.com\/joungmin-choi\/TSCytoPred<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.7717\/peerj.20270","type":"journal-article","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T08:21:46Z","timestamp":1762762906000},"page":"e20270","source":"Crossref","is-referenced-by-count":3,"title":["TSCytoPred: a deep learning framework for inferring cytokine expression trajectories from irregular longitudinal gene expression data to enhance multi-omics analyses"],"prefix":"10.7717","volume":"13","author":[{"given":"Joung Min","family":"Choi","sequence":"first","affiliation":[{"name":"Department of Computer Science, Virginia Polytechnic Institute and State University (Virginia Tech),  Blacksburg, VA, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heejoon","family":"Chae","sequence":"additional","affiliation":[{"name":"Division of Computer Science, Sookmyung Women\u2019s University, Seoul, Republic of South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"10.7717\/peerj.20270\/ref-1","doi-asserted-by":"publisher","first-page":"20793","DOI":"10.1038\/s41598-021-00190-0","article-title":"Cytokine signature and COVID-19 prediction models in the two waves of pandemics","volume":"11","author":"Cabaro","year":"2021","journal-title":"Scientific Reports"},{"issue":"18","key":"10.7717\/peerj.20270\/ref-2","doi-asserted-by":"publisher","first-page":"9321","DOI":"10.1093\/nar\/gky787","article-title":"Global landscape of mouse and human cytokine transcriptional regulation","volume":"46","author":"Carrasco\u00a0Pro","year":"2018","journal-title":"Nucleic Acids Research"},{"issue":"11","key":"10.7717\/peerj.20270\/ref-3","doi-asserted-by":"publisher","first-page":"2260","DOI":"10.1002\/jmv.26078","article-title":"COVID-19: consider IL-6 receptor antagonist for the therapy of cytokine storm syndrome in SARS-CoV-2 infected patients","volume":"92","author":"Chakraborty","year":"2020","journal-title":"Journal of Medical Virology"},{"key":"10.7717\/peerj.20270\/ref-4","first-page":"6989","article-title":"Nhits: neural hierarchical interpolation for time series forecasting","author":"Challu","year":"2023"},{"issue":"5","key":"10.7717\/peerj.20270\/ref-5","doi-asserted-by":"publisher","first-page":"btad286","DOI":"10.1093\/bioinformatics\/btad286","article-title":"DeepMicroGen: a generative adversarial network-based method for longitudinal microbiome data imputation","volume":"39","author":"Choi","year":"2023","journal-title":"Bioinformatics"},{"issue":"10","key":"10.7717\/peerj.20270\/ref-6","doi-asserted-by":"publisher","first-page":"1636","DOI":"10.1038\/s41591-020-1051-9","article-title":"An inflammatory cytokine signature predicts COVID-19 severity and survival","volume":"26","author":"Del\u00a0Valle","year":"2020","journal-title":"Nature Medicine"},{"issue":"19","key":"10.7717\/peerj.20270\/ref-7","doi-asserted-by":"publisher","first-page":"10578","DOI":"10.3390\/ijms251910578","article-title":"Prospective variation of cytokine trends during COVID-19: a progressive approach from disease onset until outcome","volume":"25","author":"Deus","year":"2024","journal-title":"International Journal of Molecular Sciences"},{"key":"10.7717\/peerj.20270\/ref-8","doi-asserted-by":"publisher","first-page":"24712","DOI":"10.1038\/s41598-024-75924-x","article-title":"Disease progression associated cytokines in COVID-19 patients with deteriorating and recovering health conditions","volume":"14","author":"Han","year":"2024","journal-title":"Scientific Reports"},{"issue":"6","key":"10.7717\/peerj.20270\/ref-9","doi-asserted-by":"publisher","first-page":"7833","DOI":"10.1109\/JSEN.2019.2923982","article-title":"A review of deep learning models for time series prediction","volume":"21","author":"Han","year":"2019","journal-title":"IEEE Sensors Journal"},{"issue":"7825","key":"10.7717\/peerj.20270\/ref-10","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"Harris","year":"2020","journal-title":"Nature"},{"key":"10.7717\/peerj.20270\/ref-11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1177\/1847979018808673","article-title":"Forecasting of demand using ARIMA model","volume":"10","author":"Fattah","year":"2018","journal-title":"International Journal of Engineering Business Management"},{"issue":"10","key":"10.7717\/peerj.20270\/ref-12","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1038\/s41592-021-01274-5","article-title":"Systematic investigation of cytokine signaling activity at the tissue and single-cell levels","volume":"18","author":"Jiang","year":"2021","journal-title":"Nature Methods"},{"issue":"9","key":"10.7717\/peerj.20270\/ref-13","doi-asserted-by":"publisher","first-page":"465","DOI":"10.5483\/BMBRep.2022.55.9.077","article-title":"Establishment of the large-scale longitudinal multi-omics dataset in COVID-19 patients: data profile and biospecimen","volume":"55","author":"Jo","year":"2022","journal-title":"BMB Reports"},{"key":"10.7717\/peerj.20270\/ref-14","first-page":"1","article-title":"Cardiovascular disease prediction using LSTM algorithm based on cytokines","author":"Kavitha","year":"2023"},{"issue":"8","key":"10.7717\/peerj.20270\/ref-15","doi-asserted-by":"publisher","first-page":"255","DOI":"10.3390\/fi15080255","article-title":"A review of ARIMA vs. machine learning approaches for time series forecasting in data driven networks","volume":"15","author":"Kontopoulou","year":"2023","journal-title":"Future Internet"},{"key":"10.7717\/peerj.20270\/ref-16","doi-asserted-by":"publisher","first-page":"5481","DOI":"10.1038\/s41598-023-31542-7","article-title":"Explanatory predictive model for COVID-19 severity risk employing machine learning, shapley addition, and LIME","volume":"13","author":"Laatifi","year":"2023","journal-title":"Scientific Reports"},{"issue":"10","key":"10.7717\/peerj.20270\/ref-17","doi-asserted-by":"publisher","first-page":"796","DOI":"10.3390\/w9100796","article-title":"Interpolation in time series: an introductive overview of existing methods, their performance criteria and uncertainty assessment","volume":"9","author":"Lepot","year":"2017","journal-title":"Water"},{"key":"10.7717\/peerj.20270\/ref-18","first-page":"2024","article-title":"A machine learning framework for cancer prognostics: integrating temporal and immune gene dynamics via ARIMA-CNN","author":"Lin","year":"2024","journal-title":"MedRxiv"},{"key":"10.7717\/peerj.20270\/ref-19","article-title":"A critical review of recurrent neural networks for sequence learning","author":"Lipton","year":"2015"},{"key":"10.7717\/peerj.20270\/ref-20","doi-asserted-by":"publisher","first-page":"747","DOI":"10.54097\/9zf6kd91","article-title":"Navigating the financial landscape: the power and limitations of the ARIMA model","volume":"88","author":"Liu","year":"2024","journal-title":"Highlights in Science, Engineering and Technology"},{"issue":"1","key":"10.7717\/peerj.20270\/ref-21","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1080\/07853890.2022.2042590","article-title":"One-on-one comparison between qCSI and NEWS scores for mortality risk assessment in patients with COVID-19","volume":"54","author":"Mart\u00edn-Rodr\u00edguez","year":"2022","journal-title":"Annals of Medicine"},{"key":"10.7717\/peerj.20270\/ref-22","doi-asserted-by":"publisher","first-page":"56","DOI":"10.25080\/Majora-92bf1922-00a","article-title":"Data structures for statistical computing in Python","author":"McKinney","year":"2010"},{"issue":"9","key":"10.7717\/peerj.20270\/ref-23","doi-asserted-by":"publisher","first-page":"517","DOI":"10.3390\/info15090517","article-title":"Recurrent neural networks: a comprehensive review of architectures, variants, and applications","volume":"15","author":"Mienye","year":"2024","journal-title":"Information"},{"issue":"11","key":"10.7717\/peerj.20270\/ref-24","doi-asserted-by":"publisher","first-page":"442","DOI":"10.3390\/info12110442","article-title":"Analysis of gradient vanishing of RNNs and performance comparison","volume":"12","author":"Noh","year":"2021","journal-title":"Information"},{"issue":"3","key":"10.7717\/peerj.20270\/ref-25","doi-asserted-by":"publisher","first-page":"387","DOI":"10.3390\/healthcare11030387","article-title":"Cytokine levels and severity of illness scoring systems to predict mortality in COVID-19 infection","volume":"11","author":"Onuk","year":"2023","journal-title":"Healthcare"},{"issue":"14","key":"10.7717\/peerj.20270\/ref-26","doi-asserted-by":"publisher","first-page":"3069","DOI":"10.3390\/math11143069","article-title":"An overview of forecast analysis with ARIMA models during the COVID-19 pandemic: methodology and case study in Brazil","volume":"11","author":"Ospina","year":"2023","journal-title":"Mathematics"},{"issue":"33","key":"10.7717\/peerj.20270\/ref-27","doi-asserted-by":"publisher","first-page":"29355","DOI":"10.1074\/jbc.R200003200","article-title":"Cytokine and cytokine receptor pleiotropy and redundancy","volume":"277","author":"Ozaki","year":"2002","journal-title":"Journal of Biological Chemistry"},{"key":"10.7717\/peerj.20270\/ref-28","first-page":"8026","article-title":"Pytorch: an imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.7717\/peerj.20270\/ref-29","first-page":"2825","article-title":"Scikit-learn: machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"10.7717\/peerj.20270\/ref-30","doi-asserted-by":"publisher","first-page":"lqae019","DOI":"10.1093\/nargab\/lqae019","article-title":"Unraveling the complex relationship between mRNA and protein abundances: a machine learning-based approach for imputing protein levels from RNA-seq data","volume":"6","author":"Prabahar","year":"2024","journal-title":"NAR Genomics and Bioinformatics"},{"issue":"2","key":"10.7717\/peerj.20270\/ref-31","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.3892\/ol.2019.11209","article-title":"Time-series clustering of cytokine expression after transarterial chemoembolization in patients with hepatocellular carcinoma","volume":"19","author":"Qi","year":"2020","journal-title":"Oncology Letters"},{"issue":"4","key":"10.7717\/peerj.20270\/ref-32","doi-asserted-by":"publisher","first-page":"e28751","DOI":"10.1002\/jmv.28751","article-title":"The roles of critical pro-inflammatory cytokines in the drive of cytokine storm during SARS-CoV-2 infection","volume":"95","author":"Qudus","year":"2023","journal-title":"Journal of Medical Virology"},{"issue":"1","key":"10.7717\/peerj.20270\/ref-33","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.dsx.2020.12.025","article-title":"Long COVID-19: challenges in the diagnosis and proposed diagnostic criteria","volume":"15","author":"Raveendran","year":"2020","journal-title":"Diabetes & Metabolic Syndrome"},{"issue":"6","key":"10.7717\/peerj.20270\/ref-34","doi-asserted-by":"publisher","first-page":"1023","DOI":"10.1038\/s41416-023-02527-0","article-title":"Time-series blood cytokine profiles correlate with treatment responses in triple-negative breast cancer patients","volume":"130","author":"Saldajeno","year":"2024","journal-title":"British Journal of Cancer"},{"key":"10.7717\/peerj.20270\/ref-35","doi-asserted-by":"publisher","first-page":"946730","DOI":"10.3389\/fimmu.2022.946730","article-title":"Time evolution of cytokine profiles associated with mortality in COVID-19 hospitalized patients","volume":"13","author":"Sanchez-de Prada","year":"2022","journal-title":"Frontiers in Immunology"},{"issue":"21","key":"10.7717\/peerj.20270\/ref-36","doi-asserted-by":"publisher","first-page":"12055","DOI":"10.1093\/nar\/gkaa1055","article-title":"Comprehensive mapping of the human cytokine gene regulatory network","volume":"48","author":"Santoso","year":"2020","journal-title":"Nucleic Acids Research"},{"issue":"W1","key":"10.7717\/peerj.20270\/ref-37","doi-asserted-by":"publisher","first-page":"W216","DOI":"10.1093\/nar\/gkac194","article-title":"DAVID: a web server for functional enrichment analysis and functional annotation of gene lists (2021 update)","volume":"50","author":"Sherman","year":"2022","journal-title":"Nucleic Acids Research"},{"key":"10.7717\/peerj.20270\/ref-38","doi-asserted-by":"publisher","first-page":"1365481","DOI":"10.3389\/fcvm.2024.1365481","article-title":"Advanced detection of coronary artery disease via deep learning analysis of plasma cytokine data","volume":"11","author":"Shoaib","year":"2024","journal-title":"Frontiers in Cardiovascular Medicine"},{"issue":"D1","key":"10.7717\/peerj.20270\/ref-39","doi-asserted-by":"publisher","first-page":"D638","DOI":"10.1093\/nar\/gkac1000","article-title":"The STRING database in 2023: protein\u2013protein association networks and functional enrichment analyses for any sequenced genome of interest","volume":"51","author":"Szklarczyk","year":"2023","journal-title":"Nucleic Acids Research"},{"key":"10.7717\/peerj.20270\/ref-40","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/s12883-022-03048-8","article-title":"Time course of serum cytokine level changes within 72 h after onset in children with acute encephalopathy and febrile seizures","volume":"23","author":"Tomioka","year":"2023","journal-title":"BMC Neurology"},{"issue":"11","key":"10.7717\/peerj.20270\/ref-41","doi-asserted-by":"publisher","first-page":"2563","DOI":"10.1016\/j.bbamcr.2014.05.014","article-title":"Cytokines and chemokines: at the crossroads of cell signalling and inflammatory disease","volume":"1843","author":"Turner","year":"2014","journal-title":"Biochimica Et Biophysica Acta (BBA)-Molecular Cell Research"},{"issue":"5","key":"10.7717\/peerj.20270\/ref-42","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1016\/j.ccell.2020.09.019","article-title":"Cytokine storms in cancer and COVID-19","volume":"38","author":"Turnquist","year":"2020","journal-title":"Cancer Cell"},{"issue":"6","key":"10.7717\/peerj.20270\/ref-43","doi-asserted-by":"publisher","first-page":"509","DOI":"10.7861\/clinmed.2022-0435","article-title":"Using NEWS2: an essential component of reliable clinical assessment","volume":"22","author":"Welch","year":"2022","journal-title":"Clinical Medicine"},{"key":"10.7717\/peerj.20270\/ref-44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s40521-021-00297-9","article-title":"Management of post-COVID-19 olfactory dysfunction","volume":"9","author":"Wu","year":"2022","journal-title":"Current Treatment Options in Allergy"},{"key":"10.7717\/peerj.20270\/ref-45","doi-asserted-by":"publisher","first-page":"8733","DOI":"10.1038\/s41598-025-93409-3","article-title":"Artificial intelligence-powered prediction of AIM-2 inflammasome sequences using transformers and graph attention networks in periodontal inflammation","volume":"15","author":"Yadalam","year":"2025","journal-title":"Scientific Reports"},{"issue":"24","key":"10.7717\/peerj.20270\/ref-46","doi-asserted-by":"publisher","first-page":"13860","DOI":"10.1002\/ece3.6976","article-title":"Relationships between immune gene expression and circulating cytokine levels in wild house mice","volume":"10","author":"Young","year":"2020","journal-title":"Ecology and Evolution"},{"key":"10.7717\/peerj.20270\/ref-47","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/j.eswa.2017.04.003","article-title":"An up-to-date comparison of state-of-the-art classification algorithms","volume":"82","author":"Zhang","year":"2017","journal-title":"Expert Systems with Applications"},{"issue":"5","key":"10.7717\/peerj.20270\/ref-48","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1007\/s12026-022-09285-w","article-title":"Cytokine storm and targeted therapy in hemophagocytic lymphohistiocytosis","volume":"70","author":"Zhang","year":"2022","journal-title":"Immunologic Research"}],"container-title":["PeerJ"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/20270.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/20270.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/20270.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/20270.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T08:21:50Z","timestamp":1762762910000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/20270"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":48,"alternative-id":["10.7717\/peerj.20270"],"URL":"https:\/\/doi.org\/10.7717\/peerj.20270","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2167-8359"],"issn-type":[{"value":"2167-8359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,10]]},"article-number":"e20270"}}