biostudies-literatureLu WFundamental Research Funds for the Central UniversitiesNational Key R&D Program of ChinaNational Key R&D Program of ChinaOpening Research Fund from Shanghai Key Laboratory of Stomatology, Shanghai Ninth People’s Hospital, College of Stomatology, Shanghai Jiao Tong University School of MedicineZhejiang Provincial Natural Science Foundation of ChinaNational Natural Science Foundation of ChinaOpening Research Fund from Shanghai Key Laboratory of Stomatology, Shanghai Ninth People's Hospital, College of Stomatology, Shanghai Jiao Tong University School of Medicinebbae373https://www.ebi.ac.uk/biostudies/studies/S-EPMC11285185biostudies-literatureUnknown25(5)Histone modifications, known as histone marks, are pivotal in regulating gene expression within cells. The vast array of potential combinations of histone marks presents a considerable challenge in decoding the regulatory mechanisms solely through biological experimental approaches. To overcome this challenge, we have developed a method called CatLearning. It utilizes a modified convolutional neural network architecture with a specialized adaptation Residual Network to quantitatively interpret histone marks and predict gene expression. This architecture integrates long-range histone information up to 500Kb and learns chromatin interaction features without 3D information. By using only one histone mark, CatLearning achieves a high level of accuracy. Furthermore, CatLearning predicts gene exBriefings in bioinformaticsCatLearning: highly accurate gene expression prediction from histone mark.PMC112851852022YFA1302800LZ24C0600012019QN8100532361133547, 32370613, 32222017, and 818741532022SKLS-KFKT002Liu YShuai QLu WLin SFang DZhang RTang YCheng YLiang BfalseCatLearning: highly accurate gene expression prediction from histone mark.Histone modifications, known as histone marks, are pivotal in regulating gene expression within cells. The vast array of potential combinations of histone marks presents a considerable challenge in decoding the regulatory mechanisms solely through biological experimental approaches. To overcome this challenge, we have developed a method called CatLearning. It utilizes a modified convolutional neural network architecture with a specialized adaptation Residual Network to quantitatively interpret histone marks and predict gene expression. This architecture integrates long-range histone information up to 500Kb and learns chromatin interaction features without 3D information. By using only one histone mark, CatLearning achieves a high level of accuracy. Furthermore, CatLearning predicts gene ex2024-01-01T00:00:00Z2024 Jul2026-06-01T06:55:38.002Z2026-04-08T10:20:10.713ZS-EPMC112851853907383110.1093/bib/bbae373