{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T01:31:00Z","timestamp":1779413460181,"version":"3.53.1"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T00:00:00Z","timestamp":1775865600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T00:00:00Z","timestamp":1779408000000},"content-version":"vor","delay-in-days":41,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"the National Natural Science Foundation of China Mathematics Tianyuan Fund Project","award":["12326377"],"award-info":[{"award-number":["12326377"]}]},{"DOI":"10.13039\/100007847","name":"Natural Science Foundation of Jilin Province","doi-asserted-by":"publisher","award":["YDZJ202301ZYTS401"],"award-info":[{"award-number":["YDZJ202301ZYTS401"]}],"id":[{"id":"10.13039\/100007847","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BioData Mining"],"DOI":"10.1186\/s13040-026-00534-4","type":"journal-article","created":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T02:57:10Z","timestamp":1775876230000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SeqHIVE: a Python package to convert the biological sequences to informative vectors for sequence property predictions"],"prefix":"10.1186","volume":"19","author":[{"given":"Xin","family":"Feng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sudan","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxin","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cuinan","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kewei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"You","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengfeng","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,11]]},"reference":[{"issue":"13","key":"534_CR1","doi-asserted-by":"publisher","first-page":"3337","DOI":"10.1093\/bioinformatics\/btac345","volume":"38","author":"B Yang","year":"2022","unstructured":"Yang B, Yang Y, Su X. Deep structure integrative representation of multi-omics data for cancer subtyping[J]. Bioinformatics. 2022;38(13):3337\u201342.","journal-title":"Bioinformatics"},{"key":"534_CR2","doi-asserted-by":"crossref","unstructured":"Andrews TD, Jeelall Y, Talaulikar D, et al. DeepSNVMiner: a sequence analysis tool to detect emergent, rare mutations in subsets of cell populations[J]. PeerJ. 20164: e2074.","DOI":"10.7717\/peerj.2074"},{"issue":"4","key":"534_CR3","doi-asserted-by":"publisher","first-page":"bbac215","DOI":"10.1093\/bib\/bbac215","volume":"23","author":"X Peng","year":"2022","unstructured":"Peng X, Wang X, Guo Y, et al. RBP-TSTL is a two-stage transfer learning framework for genome-scale prediction of RNA-binding proteins[J]. Brief Bioinform. 2022;23(4):bbac215.","journal-title":"Brief Bioinform"},{"issue":"7","key":"534_CR4","doi-asserted-by":"publisher","first-page":"2654","DOI":"10.1021\/acs.jcim.3c01726","volume":"64","author":"X Feng","year":"2024","unstructured":"Feng X, Ma Z, Yu C, et al. MRNDR: multihead attention-based recommendation network for drug repurposing[J]. J Chem Inf Model. 2024;64(7):2654\u201369.","journal-title":"J Chem Inf Model"},{"issue":"10","key":"534_CR5","doi-asserted-by":"publisher","first-page":"2712","DOI":"10.1093\/bioinformatics\/btac200","volume":"38","author":"K Yan","year":"2022","unstructured":"Yan K, Lv H, Guo Y, et al. TPpred-ATMV: therapeutic peptide prediction by adaptive multi-view tensor learning model[J]. Bioinformatics. 2022;38(10):2712\u20138.","journal-title":"Bioinformatics"},{"issue":"5","key":"534_CR6","doi-asserted-by":"publisher","first-page":"bbac173","DOI":"10.1093\/bib\/bbac173","volume":"23","author":"Y Zhang","year":"2022","unstructured":"Zhang Y, Zhu G, Li K, et al. HLAB: learning the BiLSTM features from the ProtBert-encoded proteins for the class I HLA-peptide binding prediction[J]. Brief Bioinform. 2022;23(5):bbac173.","journal-title":"Brief Bioinform"},{"issue":"6","key":"534_CR7","doi-asserted-by":"publisher","first-page":"592","DOI":"10.1038\/s41587-019-0140-0","volume":"37","author":"\u017d Avsec","year":"2019","unstructured":"Avsec \u017d, Kreuzhuber R, Israeli J, et al. The Kipoi repository accelerates community exchange and reuse of predictive models for genomics[J]. Nat Biotechnol. 2019;37(6):592\u2013600.","journal-title":"Nat Biotechnol"},{"issue":"14","key":"534_CR8","doi-asserted-by":"publisher","first-page":"2499","DOI":"10.1093\/bioinformatics\/bty140","volume":"34","author":"Z Chen","year":"2018","unstructured":"Chen Z, Zhao P, Li F, et al. iFeature: a python package and web server for features extraction and selection from protein and peptide sequences[J]. Bioinformatics. 2018;34(14):2499\u2013502.","journal-title":"Bioinformatics"},{"issue":"3","key":"534_CR9","doi-asserted-by":"publisher","first-page":"1047","DOI":"10.1093\/bib\/bbz041","volume":"21","author":"Z Chen","year":"2020","unstructured":"Chen Z, Zhao P, Li F, et al. iLearn: an integrated platform and meta-learner for feature engineering, machine-learning analysis and modeling of DNA, RNA and protein sequence data[J]. Brief Bioinform. 2020;21(3):1047\u201357.","journal-title":"Brief Bioinform"},{"issue":"1","key":"534_CR10","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1186\/s12915-023-01804-x","volume":"22","author":"M Niu","year":"2024","unstructured":"Niu M, Wang C, Chen Y, et al. CircRNA identification and feature interpretability analysis[J]. BMC Biol. 2024;22(1):44.","journal-title":"BMC Biol"},{"key":"534_CR11","doi-asserted-by":"publisher","first-page":"3522","DOI":"10.1016\/j.csbj.2022.06.045","volume":"20","author":"L Meng","year":"2022","unstructured":"Meng L, Chan WS, Huang L, et al. Mini-review: recent advances in post-translational modification site prediction based on deep learning[J]. Comput Struct Biotechnol J. 2022;20:3522\u201332.","journal-title":"Comput Struct Biotechnol J"},{"issue":"9","key":"534_CR12","doi-asserted-by":"publisher","first-page":"btad524","DOI":"10.1093\/bioinformatics\/btad524","volume":"39","author":"J Ma","year":"2023","unstructured":"Ma J, Li C, Zhang Y, et al. MULGA, a unified multi-view graph autoencoder-based approach for identifying drug\u2013protein interaction and drug repositioning[J]. Bioinformatics. 2023;39(9):btad524.","journal-title":"Bioinformatics"},{"issue":"1","key":"534_CR13","doi-asserted-by":"publisher","first-page":"bbab434","DOI":"10.1093\/bib\/bbab434","volume":"23","author":"RP Bonidia","year":"2022","unstructured":"Bonidia RP, Domingues DS, Sanches DS, et al. MathFeature: feature extraction package for DNA, RNA and protein sequences based on mathematical descriptors[J]. Brief Bioinform. 2022;23(1):bbab434.","journal-title":"Brief Bioinform"},{"issue":"suppl2","key":"534_CR14","doi-asserted-by":"publisher","first-page":"W32","DOI":"10.1093\/nar\/gkl305","volume":"34","author":"ZR Li","year":"2006","unstructured":"Li ZR, Lin HH, Han LY, et al. PROFEAT: a web server for computing structural and physicochemical features of proteins and peptides from amino acid sequence[J]. Nucleic Acids Res. 2006;34(suppl2):W32\u20137.","journal-title":"Nucleic Acids Res"},{"issue":"2","key":"534_CR15","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1016\/j.ab.2007.10.012","volume":"373","author":"HB Shen","year":"2008","unstructured":"Shen HB, Chou KC. PseAAC: a flexible web server for generating various kinds of protein pseudo amino acid composition[J]. Anal Biochem. 2008;373(2):386\u20138.","journal-title":"Anal Biochem"},{"issue":"7","key":"534_CR16","doi-asserted-by":"publisher","first-page":"960","DOI":"10.1093\/bioinformatics\/btt072","volume":"29","author":"DS Cao","year":"2013","unstructured":"Cao DS, Xu QS, Liang YZ. propy: a tool to generate various modes of Chou\u2019s PseAAC[J]. Bioinformatics. 2013;29(7):960\u20132.","journal-title":"Bioinformatics"},{"issue":"1","key":"534_CR17","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1093\/bioinformatics\/btu602","volume":"31","author":"W Chen","year":"2015","unstructured":"Chen W, Zhang X, Brooker J, et al. PseKNC-General: a cross-platform package for generating various modes of pseudo nucleotide compositions[J]. Bioinformatics. 2015;31(1):119\u201320.","journal-title":"Bioinformatics"},{"issue":"2","key":"534_CR18","doi-asserted-by":"publisher","first-page":"386","DOI":"10.5740\/jaoacint.18-0388","volume":"102","author":"A Bayley","year":"2019","unstructured":"Bayley A. A summary of current DNA methods for herb and spice identification[J]. J AOAC Int. 2019;102(2):386\u20139.","journal-title":"J AOAC Int"},{"issue":"11","key":"534_CR19","doi-asserted-by":"publisher","first-page":"1857","DOI":"10.1093\/bioinformatics\/btv042","volume":"31","author":"N Xiao","year":"2015","unstructured":"Xiao N, Cao DS, Zhu MF, et al. protr\/ProtrWeb: R package and web server for generating various numerical representation schemes of protein sequences[J]. Bioinformatics. 2015;31(11):1857\u20139.","journal-title":"Bioinformatics"},{"issue":"21","key":"534_CR20","doi-asserted-by":"publisher","first-page":"3429","DOI":"10.1093\/bioinformatics\/btv345","volume":"31","author":"D Ofer","year":"2015","unstructured":"Ofer D, Linial M, ProFET. Feature engineering captures high-level protein functions[J]. Bioinformatics. 2015;31(21):3429\u201336.","journal-title":"Bioinformatics"},{"issue":"W1","key":"534_CR21","doi-asserted-by":"publisher","first-page":"W65","DOI":"10.1093\/nar\/gkv458","volume":"43","author":"B Liu","year":"2015","unstructured":"Liu B, Liu F, Wang X, et al. Pse-in-One: a web server for generating various modes of pseudo components of DNA, RNA, and protein sequences[J]. Nucleic Acids Res. 2015;43(W1):W65\u201371.","journal-title":"Nucleic Acids Res"},{"issue":"8","key":"534_CR22","doi-asserted-by":"publisher","first-page":"1307","DOI":"10.1093\/bioinformatics\/btu820","volume":"31","author":"B Liu","year":"2015","unstructured":"Liu B, Liu F, Fang L, et al. repDNA: a Python package to generate various modes of feature vectors for DNA sequences by incorporating user-defined physicochemical properties and sequence-order effects[J]. Bioinformatics. 2015;31(8):1307\u20139.","journal-title":"Bioinformatics"},{"issue":"2","key":"534_CR23","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1093\/bioinformatics\/btu624","volume":"31","author":"DS Cao","year":"2015","unstructured":"Cao DS, Xiao N, Xu QS, et al. Rcpi: R\/Bioconductor package to generate various descriptors of proteins, compounds and their interactions[J]. Bioinformatics. 2015;31(2):279\u201381.","journal-title":"Bioinformatics"},{"issue":"1","key":"534_CR24","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1007\/s00438-015-1078-7","volume":"291","author":"F Bin Liu","year":"2016","unstructured":"Bin Liu F, Liu L, Fang X, Wang, Kuo-Chen Chou. reprna: a web server for generating various feature vectors of rna sequences. Mol Genet Genomics. 2016;291(1):473\u201381.","journal-title":"Mol Genet Genomics"},{"issue":"4","key":"534_CR25","doi-asserted-by":"publisher","first-page":"1280","DOI":"10.1093\/bib\/bbx165","volume":"20","author":"B Liu","year":"2019","unstructured":"Liu B. BioSeq-Analysis: a platform for DNA, RNA and protein sequence analysis based on machine learning approaches[J]. Brief Bioinform. 2019;20(4):1280\u201394.","journal-title":"Brief Bioinform"},{"issue":"22","key":"534_CR26","doi-asserted-by":"publisher","first-page":"4797","DOI":"10.1093\/bioinformatics\/btz432","volume":"35","author":"R Nikam","year":"2019","unstructured":"Nikam R, Gromiha MM. Seq2Feature: a comprehensive web-based feature extraction tool for biological sequence data[J]. Bioinformatics. 2019;35(22):4797\u20139.","journal-title":"Bioinformatics"},{"key":"534_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-018-0270-2","volume":"10","author":"J Dong","year":"2018","unstructured":"Dong J, Yao ZJ, Zhang L, et al. PyBioMed: a python library for various molecular representations of chemicals, proteins and DNAs and their interactions[J]. J Cheminform. 2018;10:1\u201311.","journal-title":"J Cheminform"},{"issue":"19","key":"534_CR28","doi-asserted-by":"publisher","first-page":"3831","DOI":"10.1093\/bioinformatics\/btz165","volume":"35","author":"R Muhammod","year":"2019","unstructured":"Muhammod R, Ahmed S, Md Farid D, et al. PyFeat: a Python-based effective feature generation tool for DNA, RNA and protein sequences[J]. Bioinformatics. 2019;35(19):3831\u20133.","journal-title":"Bioinformatics"},{"key":"534_CR29","doi-asserted-by":"crossref","unstructured":"Bostrom K, Durrett G. Byte pair encoding is suboptimal for language model pretraining[J]. arXiv preprint arXiv:2004.03720. 2020.","DOI":"10.18653\/v1\/2020.findings-emnlp.414"},{"key":"534_CR30","doi-asserted-by":"crossref","unstructured":"Song X, Salcianu A, Song Y, et al. Fast wordpiece tokenization[J]. arXiv preprint arXiv:2012.15524. 2020.","DOI":"10.18653\/v1\/2021.emnlp-main.160"},{"issue":"1","key":"534_CR31","doi-asserted-by":"publisher","first-page":"2175112","DOI":"10.1080\/08839514.2023.2175112","volume":"37","author":"S Choo","year":"2023","unstructured":"Choo S, Kim W. A study on the evaluation of tokenizer performance in natural language processing[J]. Appl Artif Intell. 2023;37(1):2175112.","journal-title":"Appl Artif Intell"},{"issue":"3","key":"534_CR32","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1080\/01431169008955028","volume":"11","author":"F Becker","year":"1990","unstructured":"Becker F, Li ZL. Towards a local split window method over land surfaces[J]. Int J Remote Sens. 1990;11(3):369\u201393.","journal-title":"Int J Remote Sens"},{"key":"534_CR33","unstructured":"Wu Y. Google\u2019s neural machine translation system: Bridging the gap between human and machine translation[J]. arXiv preprint arXiv:1609.08144. 2016."},{"key":"534_CR34","doi-asserted-by":"crossref","unstructured":"Kudo T, Sentencepiece. A simple and language independent subword tokenizer and detokenizer for neural text processing[J]. arXiv preprint arXiv:1808.06226. 2018.","DOI":"10.18653\/v1\/D18-2012"},{"issue":"20","key":"534_CR35","doi-asserted-by":"publisher","first-page":"e127","DOI":"10.1093\/nar\/gkz740","volume":"47","author":"B Liu","year":"2019","unstructured":"Liu B, Gao X, Zhang H. BioSeq-Analysis2. 0: an updated platform for analyzing DNA, RNA and protein sequences at sequence level and residue level based on machine learning approaches[J]. Nucleic Acids Res. 2019;47(20):e127\u2013127.","journal-title":"Nucleic Acids Res"},{"issue":"suppl1","key":"534_CR36","doi-asserted-by":"publisher","first-page":"i338","DOI":"10.1093\/bioinformatics\/bti1047","volume":"21","author":"WS Noble","year":"2005","unstructured":"Noble WS, Kuehn S, Thurman R, et al. Predicting the in vivo signature of human gene regulatory sequences[J]. Bioinformatics. 2005;21(suppl1):i338\u201343.","journal-title":"Bioinformatics"},{"issue":"10","key":"534_CR37","doi-asserted-by":"publisher","first-page":"e60","DOI":"10.1093\/nar\/gkab122","volume":"49","author":"Z Chen","year":"2021","unstructured":"Chen Z, Zhao P, Li C, et al. iLearnPlus: a comprehensive and automated machine-learning platform for nucleic acid and protein sequence analysis, prediction and visualization[J]. Nucleic Acids Res. 2021;49(10):e60\u201360.","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"534_CR38","doi-asserted-by":"publisher","first-page":"13859","DOI":"10.1038\/srep13859","volume":"5","author":"W Chen","year":"2015","unstructured":"Chen W, Tran H, Liang Z, et al. Identification and analysis of the N6-methyladenosine in the Saccharomyces cerevisiae transcriptome[J]. Sci Rep. 2015;5(1):13859.","journal-title":"Sci Rep"},{"key":"534_CR39","doi-asserted-by":"crossref","unstructured":"Chen Z, Zhou Y, Song J, et al. hCKSAAP_UbSite: improved prediction of human ubiquitination sites by exploiting amino acid pattern and properties[J]. Biochimica et Biophysica Acta (BBA)-Proteins and Proteomics. 2013;1834(8): 1461\u20137.","DOI":"10.1016\/j.bbapap.2013.04.006"},{"issue":"22","key":"534_CR40","doi-asserted-by":"publisher","first-page":"23262","DOI":"10.1074\/jbc.M401932200","volume":"279","author":"M Bhasin","year":"2004","unstructured":"Bhasin M, Raghava GPS. Classification of nuclear receptors based on amino acid composition and dipeptide composition[J]. J Biol Chem. 2004;279(22):23262\u20136.","journal-title":"J Biol Chem"},{"issue":"8","key":"534_CR41","doi-asserted-by":"publisher","first-page":"554","DOI":"10.1038\/s41477-018-0214-x","volume":"4","author":"C Zhou","year":"2018","unstructured":"Zhou C, Wang C, Liu H, et al. Identification and analysis of adenine N 6-methylation sites in the rice genome[J]. Nat plants. 2018;4(8):554\u201363.","journal-title":"Nat plants"},{"issue":"10","key":"534_CR42","doi-asserted-by":"publisher","first-page":"648","DOI":"10.1089\/omi.2015.0095","volume":"19","author":"V Saravanan","year":"2015","unstructured":"Saravanan V, Gautham N. Harnessing computational biology for exact linear B-cell epitope prediction: a novel amino acid composition-based feature descriptor[J]. OMICS. 2015;19(10):648\u201358.","journal-title":"OMICS"},{"issue":"1","key":"534_CR43","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1093\/bioinformatics\/btz506","volume":"36","author":"C Lou","year":"2020","unstructured":"Lou C, Zhao J, Shi R, et al. sefOri: selecting the best-engineered sequence features to predict DNA replication origins[J]. Bioinformatics. 2020;36(1):49\u201355.","journal-title":"Bioinformatics"},{"issue":"15","key":"534_CR44","doi-asserted-by":"publisher","first-page":"3785","DOI":"10.1093\/bioinformatics\/btac406","volume":"38","author":"M Ayati","year":"2022","unstructured":"Ayati M, Y\u0131lmaz S, Chance MR, et al. Functional characterization of co-phosphorylation networks[J]. Bioinformatics. 2022;38(15):3785\u201393.","journal-title":"Bioinformatics"},{"key":"534_CR45","doi-asserted-by":"publisher","first-page":"104405","DOI":"10.1016\/j.compbiomed.2021.104405","volume":"133","author":"S Gao","year":"2021","unstructured":"Gao S, Wang P, Feng Y, et al. RIFS2D: A two-dimensional version of a randomly restarted incremental feature selection algorithm with an application for detecting low-ranked biomarkers[J]. Comput Biol Med. 2021;133:104405.","journal-title":"Comput Biol Med"},{"issue":"4","key":"534_CR46","doi-asserted-by":"publisher","first-page":"1316","DOI":"10.1109\/TCBB.2017.2666141","volume":"16","author":"H Lin","year":"2017","unstructured":"Lin H, Liang ZY, Tang H, et al. Identifying sigma70 promoters with novel pseudo nucleotide composition[J]. IEEE\/ACM Trans Comput Biol Bioinf. 2017;16(4):1316\u201321.","journal-title":"IEEE\/ACM Trans Comput Biol Bioinf"},{"issue":"Suppl 3","key":"534_CR47","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1186\/s12859-020-03870-2","volume":"22","author":"J Meng","year":"2021","unstructured":"Meng J, Kang Q, Chang Z, et al. PlncRNA-HDeep: plant long noncoding RNA prediction using hybrid deep learning based on two encoding styles[J]. BMC Bioinformatics. 2021;22(Suppl 3):242.","journal-title":"BMC Bioinformatics"},{"issue":"22","key":"534_CR48","doi-asserted-by":"publisher","first-page":"3889","DOI":"10.1093\/bioinformatics\/bty418","volume":"34","author":"J Baek","year":"2018","unstructured":"Baek J, Lee B, Kwon S, et al. LncRNAnet: long non-coding RNA identification using deep learning[J]. Bioinformatics. 2018;34(22):3889\u201397.","journal-title":"Bioinformatics"},{"issue":"22","key":"534_CR49","doi-asserted-by":"publisher","first-page":"3825","DOI":"10.1093\/bioinformatics\/bty428","volume":"34","author":"C Yang","year":"2018","unstructured":"Yang C, Yang L, Zhou M, et al. LncADeep: an ab initio lncRNA identification and functional annotation tool based on deep learning[J]. Bioinformatics. 2018;34(22):3825\u201334.","journal-title":"Bioinformatics"},{"issue":"10","key":"534_CR50","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1007\/s10822-020-00323-z","volume":"34","author":"P Charoenkwan","year":"2020","unstructured":"Charoenkwan P, Nantasenamat C, Hasan MM, et al. Meta-iPVP: a sequence-based meta-predictor for improving the prediction of phage virion proteins using effective feature representation[J]. J Comput Aided Mol Des. 2020;34(10):1105\u201316.","journal-title":"J Comput Aided Mol Des"},{"issue":"8","key":"534_CR51","doi-asserted-by":"publisher","first-page":"2229","DOI":"10.1039\/C4MB00316K","volume":"10","author":"H Ding","year":"2014","unstructured":"Ding H, Feng PM, Chen W, et al. Identification of bacteriophage virion proteins by the ANOVA feature selection and analysis[J]. Mol Biosyst. 2014;10(8):2229\u201335.","journal-title":"Mol Biosyst"},{"key":"534_CR52","doi-asserted-by":"publisher","first-page":"476","DOI":"10.3389\/fmicb.2018.00476","volume":"9","author":"B Manavalan","year":"2018","unstructured":"Manavalan B, Shin TH, Lee G. PVP-SVM: sequence-based prediction of phage virion proteins using a support vector machine[J]. Front Microbiol. 2018;9:476.","journal-title":"Front Microbiol"},{"issue":"2","key":"534_CR53","doi-asserted-by":"publisher","first-page":"353","DOI":"10.3390\/cells9020353","volume":"9","author":"P Charoenkwan","year":"2020","unstructured":"Charoenkwan P, Kanthawong S, Schaduangrat N, et al. PVPred-SCM: improved prediction and analysis of phage virion proteins using a scoring card method[J]. Cells. 2020;9(2):353.","journal-title":"Cells"}],"container-title":["BioData Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13040-026-00534-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-026-00534-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-026-00534-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T01:03:00Z","timestamp":1779411780000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13040-026-00534-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,11]]},"references-count":53,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["534"],"URL":"https:\/\/doi.org\/10.1186\/s13040-026-00534-4","relation":{},"ISSN":["1756-0381"],"issn-type":[{"value":"1756-0381","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,11]]},"assertion":[{"value":"23 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"44"}}