{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T11:09:02Z","timestamp":1768648142138,"version":"3.49.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,4,12]],"date-time":"2021-04-12T00:00:00Z","timestamp":1618185600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2021,4,12]],"date-time":"2021-04-12T00:00:00Z","timestamp":1618185600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["21675180"],"award-info":[{"award-number":["21675180"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["21675035"],"award-info":[{"award-number":["21675035"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["21775169"],"award-info":[{"award-number":["21775169"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Scientific Technology Project of Guangdong Province","award":["2017B020221001"],"award-info":[{"award-number":["2017B020221001"]}]},{"name":"the Scientific Technology Project of Guangdong Province","award":["2016B010108007"],"award-info":[{"award-number":["2016B010108007"]}]},{"name":"the Scientific Technology Project of Guangzhou City","award":["201604020145"],"award-info":[{"award-number":["201604020145"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>The interactions of proteins are determined by their sequences and affect the regulation of the cell cycle, signal transduction and metabolism, which is of extraordinary significance to modern proteomics research. Despite advances in experimental technology, it is still expensive, laborious, and time-consuming to determine protein\u2013protein interactions (PPIs), and there is a strong demand for effective bioinformatics approaches to identify potential PPIs. Considering the large amount of PPI data, a high-performance processor can be utilized to enhance the capability of the deep learning method and directly predict protein sequences.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We propose the Sequence-Statistics-Content protein sequence encoding format (SSC) based on information extraction from the original sequence for further performance improvement of the convolutional neural network. The original protein sequences are encoded in the three-channel format by introducing statistical information (the second channel) and bigram encoding information (the third channel), which can increase the unique sequence features to enhance the performance of the deep learning model. On predicting protein\u2013protein interaction tasks, the results using the 2D convolutional neural network (2D CNN) with the SSC encoding method are better than those of the 1D CNN with one hot encoding. The independent validation of new interactions from the HIPPIE database (version 2.1 published on July 18, 2017) and the validation of directly predicted results by applying a molecular docking tool indicate the effectiveness of the proposed protein encoding improvement in the CNN model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The proposed protein sequence encoding method is efficient at improving the capability of the CNN model on protein sequence-related tasks and may also be effective at enhancing the capability of other machine learning or deep learning methods. Prediction accuracy and molecular docking validation showed considerable improvement compared to the existing hot encoding method, indicating that the SSC encoding method may be useful for analyzing protein sequence-related tasks. The source code of the proposed methods is freely available for academic research at<jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/wangy496\/SSC-format\/\">https:\/\/github.com\/wangy496\/SSC-format\/<\/jats:ext-link>.<\/jats:p><\/jats:sec>","DOI":"10.1186\/s12859-021-04111-w","type":"journal-article","created":{"date-parts":[[2021,4,12]],"date-time":"2021-04-12T13:03:16Z","timestamp":1618232596000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Performance improvement for a 2D convolutional neural network by using SSC encoding on protein\u2013protein interaction tasks"],"prefix":"10.1186","volume":"22","author":[{"given":"Yang","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanchao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanfei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingjun","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qixing","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zong","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9481-9687","authenticated-orcid":false,"given":"Xiaoyong","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,4,12]]},"reference":[{"issue":"1","key":"4111_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-016-1414-x","volume":"18","author":"T Sun","year":"2017","unstructured":"Sun T, Zhou B, Lai L, et al. Sequence-based prediction of protein protein interaction using a deep-learning algorithm. BMC Bioinformatics. 2017;18(1):1\u20138.","journal-title":"BMC Bioinformatics"},{"issue":"24","key":"4111_CR2","doi-asserted-by":"publisher","first-page":"3909","DOI":"10.1093\/bioinformatics\/btx496","volume":"33","author":"D Wang","year":"2017","unstructured":"Wang D, Zeng S, Xu C, Qiu W, Liang Y, Joshi T, Xu D. MusiteDeep: a deep-learning framework for general and kinase-specific phosphorylation site prediction. Bioinformatics. 2017;33(24):3909\u201316.","journal-title":"Bioinformatics"},{"issue":"13","key":"4111_CR3","doi-asserted-by":"publisher","first-page":"2216","DOI":"10.1093\/bioinformatics\/bty953","volume":"35","author":"A Elbasir","year":"2018","unstructured":"Elbasir A, Moovarkumudalvan B, Kunji K, Kolatkar PR, Mall R, Bensmail H. DeepCrystal: a deep learning framework for sequence-based protein crystallization prediction. Bioinformatics. 2018;35(13):2216\u201325.","journal-title":"Bioinformatics"},{"issue":"1","key":"4111_CR4","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1186\/s12859-018-2112-7","volume":"19","author":"L Huang","year":"2018","unstructured":"Huang L, Liao L, Wu CH. Completing sparse and disconnected protein-protein network by deep learning. BMC Bioinformatics. 2018;19(1):103.","journal-title":"BMC Bioinformatics"},{"issue":"13","key":"4111_CR5","doi-asserted-by":"publisher","first-page":"i254","DOI":"10.1093\/bioinformatics\/bty275","volume":"34","author":"S Seokjun","year":"2018","unstructured":"Seokjun S, Minsik O, Youngjune P, Sun K. DeepFam: deep learning based alignment-free method for protein family modeling and prediction. Bioinformatics. 2018;34(13):i254\u201362.","journal-title":"Bioinformatics"},{"issue":"15","key":"4111_CR6","doi-asserted-by":"publisher","first-page":"2605","DOI":"10.1093\/bioinformatics\/bty166","volume":"34","author":"S Khurana","year":"2018","unstructured":"Khurana S, Rawi R, Kunji K, Chuang GY, Bensmail H, Mall R. DeepSol: a deep learning framework for sequence-based protein solubility prediction. Bioinformatics. 2018;34(15):2605\u201313.","journal-title":"Bioinformatics"},{"issue":"4","key":"4111_CR7","doi-asserted-by":"crossref","first-page":"1114","DOI":"10.1093\/bioinformatics\/btz699","volume":"36","author":"M Zeng","year":"2020","unstructured":"Zeng M, Zhang F, Wu FX, et al. Protein\u2013protein interaction site prediction through combining local and global features with deep neural networks. Bioinformatics. 2020;36(4):1114\u201320.","journal-title":"Bioinformatics"},{"issue":"17","key":"4111_CR8","doi-asserted-by":"publisher","first-page":"i802","DOI":"10.1093\/bioinformatics\/bty573","volume":"34","author":"H Somaye","year":"2018","unstructured":"Somaye H, Behnam N, Khan AA, Jinbo X, et al. Predicting protein\u2013protein interactions through sequence-based deep learning. Bioinformatics. 2018;34(17):i802\u201310.","journal-title":"Bioinformatics"},{"issue":"10","key":"4111_CR9","doi-asserted-by":"publisher","first-page":"1690","DOI":"10.1093\/bioinformatics\/btx818","volume":"34","author":"C Savojardo","year":"2017","unstructured":"Savojardo C, Martelli PL, Fariselli P, Casadio R. DeepSig:deep learning improves signal peptide detection in proteins. Bioinformatics. 2017;34(10):1690\u20136.","journal-title":"Bioinformatics"},{"issue":"2","key":"4111_CR10","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1504\/IJDMB.2016.076534","volume":"15","author":"Z Zhao","year":"2016","unstructured":"Zhao Z, Yang Z, Lin H, et al. A protein-protein interaction extraction approach based on deep neural network. Int J Data Min Bioinform. 2016;15(2):145\u201364.","journal-title":"Int J Data Min Bioinform"},{"key":"4111_CR11","doi-asserted-by":"crossref","unstructured":"Jain A, Phanishayee A, Mars J, Tang LJ. Gist: Efficient data encoding for deep neural network training. In: 2018 ACM\/IEEE 45th annual international symposium on computer architecture (ISCA), IEEE.2018; pp 776\u2013789.","DOI":"10.1109\/ISCA.2018.00070"},{"issue":"17","key":"4111_CR12","doi-asserted-by":"publisher","first-page":"1886","DOI":"10.1109\/LPT.2016.2574800","volume":"28","author":"FN Khan","year":"2016","unstructured":"Khan FN, Zhong K, Al-Arashi WH. Modulation format identification in coherent receivers using deep machine learning. IEEE Photonics Technol Lett. 2016;28(17):1886\u20139.","journal-title":"IEEE Photonics Technol Lett"},{"issue":"1","key":"4111_CR13","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1186\/1471-2105-10-419","volume":"10","author":"Y Park","year":"2009","unstructured":"Park Y. Critical assessment of sequence-based protein-protein interaction prediction methods that do not require homologous protein sequences. BMC Bioinf. 2009;10(1):419.","journal-title":"BMC Bioinf"},{"issue":"2","key":"4111_CR14","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1093\/bioinformatics\/bth483","volume":"21","author":"S Martin","year":"2005","unstructured":"Martin S, Roe D, Faulon J-L. Predicting protein-protein interactions using signature products. Bioinformatics. 2005;21(2):218\u201326.","journal-title":"Bioinformatics"},{"issue":"11","key":"4111_CR15","doi-asserted-by":"publisher","first-page":"4337","DOI":"10.1073\/pnas.0607879104","volume":"104","author":"J Shen","year":"2007","unstructured":"Shen J, Zhang J, Luo X, et al. Predicting protein\u2013protein interactions based only on sequences information. Proc Natl Acad Sci. 2007;104(11):4337\u201341.","journal-title":"Proc Natl Acad Sci"},{"issue":"9","key":"4111_CR16","doi-asserted-by":"publisher","first-page":"3025","DOI":"10.1093\/nar\/gkn159","volume":"36","author":"Y Guo","year":"2008","unstructured":"Guo Y, Yu L, Wen Z, Li M. Using support vector machine combined with auto covariance to predict protein-protein interactions from protein sequences. Nucleic Acids Res. 2008;36(9):3025\u201330.","journal-title":"Nucleic Acids Res"},{"issue":"3","key":"4111_CR17","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1504\/IJDMB.2018.097682","volume":"21","author":"S Ahmed","year":"2018","unstructured":"Ahmed S, Kabir M, Arif M, Ali Z, Ali F, Swati ZNK. Improving secretory proteins prediction in Mycobacterium tuberculosis using the unbiased dipeptide composition with support vector machine. J Data Min Bioinf. 2018;21(3):212\u201329.","journal-title":"J Data Min Bioinf"},{"key":"4111_CR18","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.ab.2018.04.021","volume":"550","author":"YD Khan","year":"2018","unstructured":"Khan YD, Rasool N, Hussain W, Khan SA, Chou KC. iPhosT-PseAAC: Identify phosphothreonine sites by incorporating sequence statistical moments into PseAAC. Anal Biochem. 2018;550:109\u201316.","journal-title":"Anal Biochem"},{"issue":"7553","key":"4111_CR19","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y Lecun","year":"2015","unstructured":"Lecun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436.","journal-title":"Nature"},{"issue":"7","key":"4111_CR20","doi-asserted-by":"publisher","first-page":"878","DOI":"10.15252\/msb.20156651","volume":"12","author":"C Angermueller","year":"2016","unstructured":"Angermueller C, P\u00e4rnamaa T, Parts L, Stegle O. Deep learning for computational biology. Mol Syst Biol. 2016;12(7):878.","journal-title":"Mol Syst Biol"},{"key":"4111_CR21","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016; pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"4111_CR22","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1186\/s12859-016-1191-6","volume":"17","author":"M Pellegrini","year":"2016","unstructured":"Pellegrini M, Baglioni M, Geraci F. Protein complex prediction for large protein\u2013protein interaction networks with the Core Peel method. BMC Bioinf. 2016;17:372\u201384.","journal-title":"BMC Bioinf"},{"issue":"9","key":"4111_CR23","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.1038\/nbt861","volume":"21","author":"SV Date","year":"2003","unstructured":"Date SV, Marcotte EM. Discovery of uncharacterized cellular systems by genome-wide analysis of functional linkages. Nat Biotechnol. 2003;21(9):1055\u201362.","journal-title":"Nat Biotechnol"},{"issue":"12","key":"4111_CR24","doi-asserted-by":"publisher","first-page":"1524","DOI":"10.1093\/bioinformatics\/btg187","volume":"19","author":"J Wu","year":"2003","unstructured":"Wu J, Kasif S, DeLisi C. Identification of functional links between genes using phylo-genetic profiles. Bioinformatics. 2003;19(12):1524\u201330.","journal-title":"Bioinformatics"},{"issue":"6","key":"4111_CR25","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1093\/bioinformatics\/btr720","volume":"28","author":"M Simonsen","year":"2012","unstructured":"Simonsen M, Stefan R, Maetschke M. Automatic selection of reference taxa for protein\u2013protein interaction prediction with phylogenetic profiling. Bioinformatics. 2012;28(6):851\u20137.","journal-title":"Bioinformatics"},{"key":"4111_CR26","unstructured":"Gregorio AL, Andrade-Navarro M A, Schaefer MH. HIPPIE v2. 0: enhancing meaningfulness and reliability of protein\u2013protein interaction networks. Nucleic Acids Res. 2016; gkw985."},{"issue":"1","key":"4111_CR27","first-page":"204","volume":"43","author":"UniProt Consortium","year":"2014","unstructured":"UniProt Consortium. UniProt:a hub for protein information. Nucleic Acids Res. 2014;43(1):204-D212.","journal-title":"Nucleic Acids Res"},{"key":"4111_CR28","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1007\/978-1-4939-7000-1_26","volume":"1607","author":"SK Burley","year":"2017","unstructured":"Burley SK, Berman HM, Kleywegt GJ, Markley JL, Nakamura H, Velankar S. Protein Data Bank (PDB): the single global macromolecular structure archive. Protein Crystallogr. 2017;1607:627\u201341.","journal-title":"Protein Crystallogr."},{"issue":"13","key":"4111_CR29","doi-asserted-by":"publisher","first-page":"1658","DOI":"10.1093\/bioinformatics\/btl158","volume":"22","author":"W Li","year":"2006","unstructured":"Li W, Godzik A. Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences. Bioinformatics. 2006;22(13):1658\u20139.","journal-title":"Bioinformatics"},{"key":"4111_CR30","doi-asserted-by":"crossref","unstructured":"Hassanzadeh HR, Wang MD. DeeperBind: Enhancing prediction of sequence specificities of DNA binding proteins. Bioinformatics and Biomedicine (BIBM). In: IEEE International Conference on IEEE. 2016; pp 178\u2013183","DOI":"10.1109\/BIBM.2016.7822515"},{"issue":"12","key":"4111_CR31","doi-asserted-by":"publisher","first-page":"i121","DOI":"10.1093\/bioinformatics\/btw255","volume":"32","author":"HY Zeng","year":"2016","unstructured":"Zeng HY, Edwards MD, Ge L, Gifford DK. Convolutional neural network architectures for predicting DNA\u2013protein binding. Bioinformatics. 2016;32(12):i121\u20137.","journal-title":"Bioinformatics"},{"issue":"1","key":"4111_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-11-505","volume":"11","author":"K Ning","year":"2010","unstructured":"Ning K, Ng HK, Srihari S. Examination of the relationship between essential genes in PPI network and hub proteins in reverse nearest neighbor topology. BMC Bioinf. 2010;11(1):1\u201314.","journal-title":"BMC Bioinf"},{"issue":"5","key":"4111_CR33","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1093\/bioinformatics\/btx659","volume":"34","author":"YJ Zhang","year":"2017","unstructured":"Zhang YJ, Zeng W, Lin HF, Wang J, Yang ZH, Michel D. Drug\u2013drug interaction extraction via hierarchical RNNs on sequence and shortest dependency paths. Bioinformatics. 2017;34(5):828\u201335.","journal-title":"Bioinformatics"},{"issue":"7","key":"4111_CR34","doi-asserted-by":"publisher","first-page":"1057","DOI":"10.1093\/bioinformatics\/btv695","volume":"32","author":"ZC Li","year":"2015","unstructured":"Li ZC, Huang MH, Zhong WQ, Liu ZQ, Xie Y, Dai Z. Identification of drug\u2013target interaction from interactome network with \u2018guilt-by-association\u2019 principle and topology features. Bioinformatics. 2015;32(7):1057\u201364.","journal-title":"Bioinformatics"},{"key":"4111_CR35","first-page":"1607","volume":"22","author":"GE Hinton","year":"2009","unstructured":"Hinton GE, Salakhutdinov R. Replicated softmax: an undirected topic model. Adv Neural Inf Process Syst. 2009;22:1607\u201314.","journal-title":"Adv Neural Inf Process Syst"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-021-04111-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-021-04111-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-021-04111-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,2]],"date-time":"2023-11-02T00:01:22Z","timestamp":1698883282000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-021-04111-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,12]]},"references-count":35,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["4111"],"URL":"https:\/\/doi.org\/10.1186\/s12859-021-04111-w","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,12]]},"assertion":[{"value":"22 August 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 March 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 April 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"184"}}