{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,4]],"date-time":"2026-10-04T03:24:02Z","timestamp":1791084242277,"version":"4.1.0"},"reference-count":56,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T00:00:00Z","timestamp":1643846400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["22173065"],"award-info":[{"award-number":["22173065"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJMS"],"abstract":"<jats:p>As one of the most important post-translational modifications (PTMs), phosphorylation refers to the binding of a phosphate group with amino acid residues like Ser (S), Thr (T) and Tyr (Y) thus resulting in diverse functions at the molecular level. Abnormal phosphorylation has been proved to be closely related with human diseases. To our knowledge, no research has been reported describing specific disease-associated phosphorylation sites prediction which is of great significance for comprehensive understanding of disease mechanism. In this work, focusing on three types of leukemia, we aim to develop a reliable leukemia-related phosphorylation site prediction models by combing deep convolutional neural network (CNN) with transfer-learning. CNN could automatically discover complex representations of phosphorylation patterns from the raw sequences, and hence it provides a powerful tool for improvement of leukemia-related phosphorylation site prediction. With the largest dataset of myelogenous leukemia, the optimal models for S\/T\/Y phosphorylation sites give the AUC values of 0.8784, 0.8328 and 0.7716 respectively. When transferred learning on the small size datasets, the models for T-cell and lymphoid leukemia also give the promising performance by common sharing the optimal parameters. Compared with other five machine-learning methods, our CNN models reveal the superior performance. Finally, the leukemia-related pathogenesis analysis and distribution analysis on phosphorylated proteins along with K-means clustering analysis and position-specific conversation profiles on the phosphorylation site all indicate the strong practical feasibility of our easy-to-use CNN models.<\/jats:p>","DOI":"10.3390\/ijms23031741","type":"journal-article","created":{"date-parts":[[2022,2,4]],"date-time":"2022-02-04T11:35:17Z","timestamp":1643974517000},"page":"1741","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["A Transfer-Learning-Based Deep Convolutional Neural Network for Predicting Leukemia-Related Phosphorylation Sites from Protein Primary Sequences"],"prefix":"10.3390","volume":"23","author":[{"given":"Jian","family":"He","sequence":"first","affiliation":[{"name":"College of Chemistry, Sichuan University, Chengdu 610064, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanling","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Chemistry, Sichuan University, Chengdu 610064, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5519-4258","authenticated-orcid":false,"given":"Xuemei","family":"Pu","sequence":"additional","affiliation":[{"name":"College of Chemistry, Sichuan University, Chengdu 610064, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Menglong","family":"Li","sequence":"additional","affiliation":[{"name":"College of Chemistry, Sichuan University, Chengdu 610064, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanzhi","family":"Guo","sequence":"additional","affiliation":[{"name":"College of Chemistry, Sichuan University, Chengdu 610064, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,2,3]]},"reference":[{"key":"ref_1","first-page":"433","article-title":"Posttranslational Modification of Proteins","volume":"5","author":"Green","year":"2010","journal-title":"Compr. Nat. Prod. II"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/S0092-8674(00)81688-8","article-title":"Signaling\u20142000 and Beyond","volume":"100","author":"Hunter","year":"2000","journal-title":"Cell"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1750","DOI":"10.1016\/j.cell.2016.11.034","article-title":"CDK Substrate Phosphorylation and Ordering the Cell Cycle","volume":"167","author":"Swaffer","year":"2016","journal-title":"Cell"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1393","DOI":"10.1016\/j.cell.2020.02.037","article-title":"Phosphorylation-Mediated IFN-\u03b3R2 Membrane Translocation Is Required to Activate Macrophage Innate Response","volume":"184","author":"Xu","year":"2018","journal-title":"Cell"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"404","DOI":"10.1002\/prot.21563","article-title":"Prediction of kinase-specific phosphorylation sites with sequence features by a log-odds ratio approach","volume":"70","author":"Li","year":"2010","journal-title":"Proteins Struct. Funct. Bioinform."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2927","DOI":"10.1093\/bioinformatics\/btr525","article-title":"Computational prediction of eukaryotic phosphorylation sites","volume":"27","author":"Trost","year":"2011","journal-title":"Bioinformatics"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"8240","DOI":"10.1038\/s41598-018-26392-7","article-title":"PhosContext2vec: A distributed representation of residue-level sequence contexts and its application to general and kinase-specific phosphorylation site prediction","volume":"8","author":"Ying","year":"2018","journal-title":"Sci. Rep."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e3281590","DOI":"10.1155\/2016\/3281590","article-title":"RF-Phos: A Novel General Phosphorylation Site Prediction Tool Based on Random Forest","volume":"2016","author":"Ismail","year":"2016","journal-title":"BioMed Res. Int."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.gpb.2020.01.001","article-title":"GPS 5.0: An Update on the Prediction of Kinase-specific Phosphorylation Sites in Proteins","volume":"18","author":"Wang","year":"2020","journal-title":"Genom. Proteom. Bioinform."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3909","DOI":"10.1093\/bioinformatics\/btx496","article-title":"MusiteDeep: A deep-learning framework for general and kinase-specific phosphorylation site prediction","volume":"33","author":"Wang","year":"2017","journal-title":"Bioinformatics"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2766","DOI":"10.1093\/bioinformatics\/bty1051","article-title":"DeepPhos: Prediction of protein phosphorylation sites with deep learning","volume":"35","author":"Luo","year":"2019","journal-title":"Bioinformatics"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"113955","DOI":"10.1016\/j.ab.2020.113955","article-title":"DeepPPSite: A deep learning-based model for analysis and prediction of phosphorylation sites using efficient sequence information","volume":"612","author":"Sa","year":"2021","journal-title":"Anal. Biochem."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1038\/s41597-020-0506-7","article-title":"dbPSP 2.0, an updated database of protein phosphorylation sites in prokaryotes","volume":"7","author":"Shi","year":"2020","journal-title":"Sci. Data"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1339","DOI":"10.1038\/nbt1208-1339","article-title":"PhosphoPep--a database of protein phosphorylation sites in model organisms","volume":"26","author":"Bodenmiller","year":"2008","journal-title":"Nat. Biotechnol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1093\/nar\/gkq1104","article-title":"Phospho.ELM: A database of phosphorylation sites--update 2011","volume":"39","author":"Dinkel","year":"2010","journal-title":"Nucleic Acids Res."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1038\/ncb0502-e127","article-title":"The origins of protein phosphorylation","volume":"4","author":"Cohen","year":"2002","journal-title":"Nat. Cell Biol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1093\/nar\/gky1052","article-title":"qPhos: A database of protein phosphorylation dynamics in humans","volume":"47","author":"Yu","year":"2019","journal-title":"Nucleic Acids Res."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1016\/j.gpb.2018.06.004","article-title":"PTMD: A Database of Human Disease-associated Post-translational Modifications","volume":"16","author":"Xu","year":"2018","journal-title":"Genom. Proteom. Bioinform."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1093\/nar\/gku1267","article-title":"PhosphoSitePlus, 2014: Mutations, PTMs and recalibrations","volume":"43","author":"Hornbeck","year":"2015","journal-title":"Nucleic Acids Res."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1605","DOI":"10.1007\/s11357-021-00383-5","article-title":"Regulation of TDP-43 phosphorylation in aging and disease","volume":"43","author":"Randall","year":"2021","journal-title":"GeroScience"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zhang, T., Chen, D.M., and Lee, T.H. (2020). Phosphorylation Signaling in APP Processing in Alzheimer\u2019s Disease. Int. J. Mol. Sci., 21.","DOI":"10.3390\/ijms21010209"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Brustovetsky, N. (2021). Involvement of CRMP2 in Regulation of Mitochondrial Morphology and Motility in Hunti Kim ngton\u2019s Disease. Cells, 10.","DOI":"10.3390\/cells10113172"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"851","DOI":"10.1016\/j.str.2016.03.020","article-title":"Death-associated protein kinase activity is regulated by coupled calcium\/calmodulin binding to two distinct sites","volume":"24","author":"Simon","year":"2016","journal-title":"Structure"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"9051","DOI":"10.1096\/fj.202000500R","article-title":"Genotype-phenotype analysis of LMNA-related diseases predicts phenotype-selective alterations in lamin phosphorylation","volume":"34","author":"Lin","year":"2020","journal-title":"FASEB J."},{"key":"ref_25","first-page":"155","article-title":"Prediction of human disease-specific phosphorylation sites with combined feature selection approach and support vector machine","volume":"9","author":"Xu","year":"2015","journal-title":"IEEE Int. Conf. Bioinform. Biomed."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1073\/pnas.0134224100","article-title":"Structural basis and prediction of substrate specificity in protein serine\/threonine kinases","volume":"100","author":"Ri","year":"2003","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_27","unstructured":"Stewart, B.W., and Wild, C.P. (2014). World Cancer Report 2014, IARC Publications."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1645","DOI":"10.1111\/febs.15102","article-title":"Identification of chlorprothixene as a potential drug that induces apoptosis and autophagic cell death in acute myeloid leukemia cells","volume":"287","author":"Du","year":"2020","journal-title":"FEBS J."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1007\/s12539-018-0285-4","article-title":"Region-Specific Methylation Profiling in Acute Myeloid Leukemia","volume":"10","author":"Cecotka","year":"2018","journal-title":"Interdiscip. Sci. Comput. Life Sci."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1186\/s12967-019-1944-x","article-title":"CEBPE expression is an independent prognostic factor for acute myeloid leukemia","volume":"17","author":"Li","year":"2020","journal-title":"J. Transl. Med."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1007\/s12539-017-0216-9","article-title":"Comprehensive Analysis of MILE Gene Expression Data Set Advances Discovery of Leukaemia Type and Subtype Biomarkers","volume":"9","author":"Labaj","year":"2017","journal-title":"Interdiscip. Sci."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2231","DOI":"10.1002\/prot.25388","article-title":"Prediction of phosphorylation sites based on Krawtchouk image moments","volume":"85","author":"Wang","year":"2017","journal-title":"Proteins"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"723","DOI":"10.1016\/j.chom.2015.11.002","article-title":"Meta-and Orthogonal Integration of Influenza \u201cOMICs\u201d Data Defines a Role for UBR4 in Virus Budding","volume":"18","author":"Shashank","year":"2015","journal-title":"Cell Host Microbe"},{"key":"ref_34","first-page":"391","article-title":"The effects of thymoquinone and Doxorubicin on leukemia and cardiomyocyte cell lines","volume":"50","author":"Brown","year":"2014","journal-title":"Biomed Sci. Instrum."},{"key":"ref_35","first-page":"699","article-title":"Subcellular localization of caspase-3 activation correlates with changes in apoptotic morphology in MOLT-4 leukemia cells exposed to X-ray irradiation","volume":"27","author":"Feng","year":"2005","journal-title":"Int. J. Oncol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1875","DOI":"10.1093\/bioinformatics\/btm270","article-title":"Predicting functionally important residues from sequence conservation","volume":"23","author":"Capra","year":"2007","journal-title":"Bioinformatics"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Li, T.T., Du, P.F., and Xu, N.F. (2010). Identifying Human Kinase-Specific Protein Phosphorylation Sites by Integrating Heterogeneous Information from Various Sources. PLoS ONE, 5.","DOI":"10.1371\/journal.pone.0015411"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.bbapap.2013.04.008","article-title":"A Sequence-based Computational Approach to Predicting PDZ Domain-Peptide Interactions","volume":"1844","author":"Nakariyakul","year":"2014","journal-title":"Biochim. Biophys. Acta"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1536","DOI":"10.1093\/bioinformatics\/btl151","article-title":"Two Sample Logo: A graphical representation of the differences between two sets of sequence alignments","volume":"22","author":"Vacic","year":"2006","journal-title":"Bioinformatics"},{"key":"ref_40","first-page":"71","article-title":"Review of Imbalanced Data Learning for Protein Methylation Prediction","volume":"Volume 1","author":"Pan","year":"2013","journal-title":"Algorithmic and Artificial Intelligence Methods for Protein Bioinformatics"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"e69","DOI":"10.1093\/nar\/gky215","article-title":"DeFine: Deep convolutional neural networks accurately quantify intensities of transcription factor-DNA binding and facilitate evaluation of functional non-coding variants","volume":"11","author":"Wang","year":"2018","journal-title":"Nucleic Acids Res."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1188","DOI":"10.1101\/gr.849004","article-title":"WebLogo: A Sequence Logo Generator","volume":"14","author":"Crooks","year":"2004","journal-title":"Genome Res."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"2740","DOI":"10.1093\/bioinformatics\/bty179","article-title":"Deep Learning Improves Antimicrobial Peptide Recognition","volume":"34","author":"Daniel","year":"2018","journal-title":"Bioinformatics"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"605782","DOI":"10.3389\/fmicb.2021.605782","article-title":"DeepT3_4: A Hybrid Deep Neural Network Model for the Distinction Between Bacterial Type III and IV Secreted Effectors","volume":"12","author":"Yu","year":"2021","journal-title":"Front. Microbiol."},{"key":"ref_45","first-page":"433","article-title":"15 years of PhosphoSitePlus: Integrating post-translationally modified sites, disease variants and isoforms","volume":"8","author":"Hornbeck","year":"2018","journal-title":"Nucleic Acids Res."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1464","DOI":"10.1111\/mmi.12069","article-title":"A translocator-specific export signal establishes the translocator-effector secretion hierarchy that is important for type iii secretion system function","volume":"86","author":"Tomalka","year":"2012","journal-title":"Mol. Microbiol."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"7227","DOI":"10.1128\/jb.178.24.7227-7233.1996","article-title":"Delineation and mutational analysis of the Yersinia pseudotuberculosis YopE domains which mediate translocation across bacterial and eukaryotic cellular membranes","volume":"178","author":"Schesser","year":"1996","journal-title":"J. Bacteriol."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1093\/nar\/gkg129","article-title":"The UCSC Genome Browser Database","volume":"1","author":"Karolchik","year":"2003","journal-title":"Nucleic Acids Res."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"3150","DOI":"10.1093\/bioinformatics\/bts565","article-title":"CD-HIT: Accelerated for clustering the next-generation sequencing data","volume":"28","author":"Fu","year":"2012","journal-title":"Bioinformatics"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"3685","DOI":"10.1093\/bioinformatics\/btx531","article-title":"An introduction to deep learning on biological sequence data: Examples and solutions","volume":"33","author":"Jurtz","year":"2017","journal-title":"Bioinformatics"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-Vector Networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1126\/science.1087361","article-title":"Bayesian Networks Approach for Predicting Protein-Protein Interactions from Genomic Data","volume":"302","author":"Jansen","year":"2003","journal-title":"Science"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"2038","DOI":"10.1016\/j.patcog.2006.12.019","article-title":"ML-KNN: A lazy learning approach to multi-label learning","volume":"40","author":"Zhang","year":"2007","journal-title":"Pattern Recognit."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Aledo, J.C., Cant\u00f3n, F., and Veredas, F.J. (2017). A machine learning approach for predicting methionine oxidation sites. BMC Bioinform., 18.","DOI":"10.1186\/s12859-017-1848-9"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"e127","DOI":"10.7717\/peerj-cs.127","article-title":"Accelerating the XGBoost algorithm using GPU computing","volume":"3","author":"Mitchell","year":"2017","journal-title":"PeerJ Comput. Sci."}],"container-title":["International Journal of Molecular Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1422-0067\/23\/3\/1741\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:13:35Z","timestamp":1760134415000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1422-0067\/23\/3\/1741"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,3]]},"references-count":56,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2022,2]]}},"alternative-id":["ijms23031741"],"URL":"https:\/\/doi.org\/10.3390\/ijms23031741","relation":{},"ISSN":["1422-0067"],"issn-type":[{"value":"1422-0067","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,3]]}}}