{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T19:58:42Z","timestamp":1773345522120,"version":"3.50.1"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T00:00:00Z","timestamp":1664150400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T00:00:00Z","timestamp":1664150400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Deep learning\u2019s automatic feature extraction has proven to give superior performance in many sequence classification tasks. However, deep learning models generally require a massive amount of data to train, which in the case of Hemolytic Activity Prediction of Antimicrobial Peptides creates a challenge due to the small amount of available data.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>Three different datasets for hemolysis activity prediction of therapeutic and antimicrobial peptides are gathered and the AMPDeep pipeline is implemented for each. The result demonstrate that AMPDeep outperforms the previous works on all three datasets, including works that use physicochemical features to represent the peptides or those who solely rely on the sequence and use deep learning to learn representation for the peptides. Moreover, a combined dataset is introduced for hemolytic activity prediction to address the problem of sequence similarity in this domain. AMPDeep fine-tunes a large transformer based model on a small amount of peptides and successfully leverages the patterns learned from other protein and peptide databases to assist hemolysis activity prediction modeling.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>In this work transfer learning is leveraged to overcome the challenge of small data and a deep learning based model is successfully adopted for hemolysis activity classification of antimicrobial peptides. This model is first initialized as a protein language model which is pre-trained on masked amino acid prediction on many unlabeled protein sequences in a self-supervised manner. Having done so, the model is fine-tuned on an aggregated dataset of labeled peptides in a supervised manner to predict secretion. Through transfer learning, hyper-parameter optimization and selective fine-tuning, AMPDeep is able to achieve state-of-the-art performance on three hemolysis datasets using only the sequence of the peptides. This work assists the adoption of large sequence-based models for peptide classification and modeling tasks in a practical manner.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12859-022-04952-z","type":"journal-article","created":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T07:03:47Z","timestamp":1664175827000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":61,"title":["AMPDeep: hemolytic activity prediction of antimicrobial peptides using transfer learning"],"prefix":"10.1186","volume":"23","author":[{"given":"Milad","family":"Salem","sequence":"first","affiliation":[]},{"given":"Arash","family":"Keshavarzi Arshadi","sequence":"additional","affiliation":[]},{"given":"Jiann Shiun","family":"Yuan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,9,26]]},"reference":[{"issue":"11","key":"4952_CR1","doi-asserted-by":"publisher","first-page":"0187925","DOI":"10.1371\/journal.pone.0187925","volume":"12","author":"A Rayan","year":"2017","unstructured":"Rayan A, Raiyn J, Falah M. Nature is the best source of anticancer drugs: indexing natural products for their anticancer bioactivity. PloS One. 2017;12(11):0187925.","journal-title":"PloS One"},{"issue":"1","key":"4952_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12929-017-0328-x","volume":"24","author":"S Marqus","year":"2017","unstructured":"Marqus S, Pirogova E, Piva TJ. Evaluation of the use of therapeutic peptides for cancer treatment. J Biomed Sci. 2017;24(1):1\u201315.","journal-title":"J Biomed Sci"},{"issue":"28","key":"4952_CR3","doi-asserted-by":"publisher","first-page":"46635","DOI":"10.18632\/oncotarget.16743","volume":"8","author":"B Deslouches","year":"2017","unstructured":"Deslouches B, Di YP. Antimicrobial peptides with selective antitumor mechanisms: prospect for anticancer applications. Oncotarget. 2017;8(28):46635.","journal-title":"Oncotarget"},{"issue":"1","key":"4952_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-73644-6","volume":"10","author":"F Plisson","year":"2020","unstructured":"Plisson F, Ram\u00edrez-S\u00e1nchez O, Mart\u00ednez-Hern\u00e1ndez C. Machine learning-guided discovery and design of non-hemolytic peptides. Sci Rep. 2020;10(1):1\u201319.","journal-title":"Sci Rep"},{"issue":"11","key":"4952_CR5","doi-asserted-by":"publisher","first-page":"3350","DOI":"10.1093\/bioinformatics\/btaa160","volume":"36","author":"MM Hasan","year":"2020","unstructured":"Hasan MM, Schaduangrat N, Basith S, Lee G, Shoombuatong W, Manavalan B. Hlppred-fuse: improved and robust prediction of hemolytic peptide and its activity by fusing multiple feature representation. Bioinformatics. 2020;36(11):3350\u20136.","journal-title":"Bioinformatics"},{"key":"4952_CR6","doi-asserted-by":"publisher","first-page":"54","DOI":"10.3389\/fphar.2020.00054","volume":"11","author":"V Kumar","year":"2020","unstructured":"Kumar V, Kumar R, Agrawal P, Patiyal S, Raghava GP. A method for predicting hemolytic potency of chemically modified peptides from its structure. Front Pharm. 2020;11:54.","journal-title":"Front Pharm"},{"issue":"1","key":"4952_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-67701-3","volume":"10","author":"PB Timmons","year":"2020","unstructured":"Timmons PB, Hewage CM. Happenn is a novel tool for hemolytic activity prediction for therapeutic peptides which employs neural networks. Sci Rep. 2020;10(1):1\u201318.","journal-title":"Sci Rep"},{"issue":"1","key":"4952_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-021-04468-y","volume":"22","author":"H Khabbaz","year":"2021","unstructured":"Khabbaz H, Karimi-Jafari MH, Saboury AA, BabaAli B. Prediction of antimicrobial peptides toxicity based on their physico-chemical properties using machine learning techniques. BMC Bioinform. 2021;22(1):1\u201311.","journal-title":"BMC Bioinform"},{"issue":"8","key":"4952_CR9","doi-asserted-by":"publisher","first-page":"2168","DOI":"10.1109\/TBME.2011.2113395","volume":"58","author":"T Mar","year":"2011","unstructured":"Mar T, Zaunseder S, Mart\u00ednez JP, Llamedo M, Poll R. Optimization of ecg classification by means of feature selection. IEEE Trans Biomed Eng. 2011;58(8):2168\u201377. https:\/\/doi.org\/10.1109\/TBME.2011.2113395.","journal-title":"IEEE Trans Biomed Eng"},{"key":"4952_CR10","doi-asserted-by":"publisher","unstructured":"Dollar P, Tu Z, Tao H, BelongieS. Feature mining for image classification. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition; 2007, pp. 1\u20138. https:\/\/doi.org\/10.1109\/CVPR.2007.383046","DOI":"10.1109\/CVPR.2007.383046"},{"key":"4952_CR11","doi-asserted-by":"crossref","unstructured":"Wang, G.: Improved methods for classification, prediction, and design of antimicrobial peptides. In: Computational Peptidology, Springer ; 2015, , pp. 43\u201366.","DOI":"10.1007\/978-1-4939-2285-7_3"},{"issue":"26","key":"4952_CR12","doi-asserted-by":"publisher","first-page":"9221","DOI":"10.1039\/D1SC01713F","volume":"12","author":"A Capecchi","year":"2021","unstructured":"Capecchi A, Cai X, Personne H, K\u00f6hler T, van Delden C, Reymond J-L. Machine learning designs non-hemolytic antimicrobial peptides. Chem Sci. 2021;12(26):9221\u201332.","journal-title":"Chem Sci"},{"key":"4952_CR13","doi-asserted-by":"publisher","unstructured":"Peters ME, Neumann M, Iyyer M, Gardner M, Clark C, Lee K, Zettlemoyer L. Deep contextualized word representations; 2018. arXiv (2018). https:\/\/doi.org\/10.48550\/ARXIV.1802.05365. arXiv:1802.05365","DOI":"10.48550\/ARXIV.1802.05365"},{"key":"4952_CR14","unstructured":"Taho F. Antimicrobial peptide host toxicity prediction with transfer learning for proteins. In: PhD thesis, University of British Columbia; 2020."},{"key":"4952_CR15","doi-asserted-by":"publisher","unstructured":"Elnaggar A, Heinzinger M, Dallago C, Rehawi G, Wang Y, Jones L, Gibbs T, Feher T, Angerer C, Steinegger M, Bhowmik D, Rost B. Prottrans: Towards cracking the language of life\u2019s code through self-supervised learning. bioRxiv ; 2021. https:\/\/doi.org\/10.1101\/2020.07.12.199554. https:\/\/www.biorxiv.org\/content\/early\/2021\/05\/04\/2020.07.12.199554.full.pdf","DOI":"10.1101\/2020.07.12.199554"},{"key":"4952_CR16","unstructured":"Consortium T.U. Uniprot: the universal protein knowledgebase in 2021. Nucleic acids research. 2021;49(D1):480\u20139."},{"key":"4952_CR17","unstructured":"Petsko GA, Ringe D. Protein Structure and Function. New Science Press (2004)"},{"issue":"3","key":"4952_CR18","doi-asserted-by":"publisher","first-page":"275","DOI":"10.4155\/fmc-2016-0188","volume":"9","author":"TS Win","year":"2017","unstructured":"Win TS, Malik AA, Prachayasittikul V, Wikberg SJE, Nantasenamat C, Shoombuatong W. Hemopred: a web server for predicting the hemolytic activity of peptides. Future Med Chem. 2017;9(3):275\u201391.","journal-title":"Future Med Chem."},{"issue":"1","key":"4952_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/srep22843","volume":"6","author":"K Chaudhary","year":"2016","unstructured":"Chaudhary K, Kumar R, Singh S, Tuknait A, Gautam A, Mathur D, Anand P, Varshney GC, Raghava GP. A web server and mobile app for computing hemolytic potency of peptides. Sci Rep. 2016;6(1):1\u201313.","journal-title":"Sci Rep"},{"key":"4952_CR20","unstructured":"Lu K, Grover A, Abbeel P, Mordatch I. Pretrained transformers as universal computation engines. CoRR abs\/2103.05247; 2021. arXiv:2103.05247"},{"key":"4952_CR21","doi-asserted-by":"publisher","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv ; 2018. https:\/\/doi.org\/10.48550\/ARXIV.1810.04805. arXiv:1810.04805","DOI":"10.48550\/ARXIV.1810.04805"},{"key":"4952_CR22","doi-asserted-by":"crossref","unstructured":"Wang Z, Dai Z, Poczos B, Carbonell J. Characterizing and avoiding negative transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2019","DOI":"10.1109\/CVPR.2019.01155"},{"issue":"D1","key":"4952_CR23","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1093\/nar\/gkt1008","volume":"42","author":"A Gautam","year":"2014","unstructured":"Gautam A, Chaudhary K, Singh S, Joshi A, Anand P, Tuknait A, Mathur D, Varshney GC, Raghava GP. Hemolytik: a database of experimentally determined hemolytic and non-hemolytic peptides. Nucleic Acids Res. 2014;42(D1):444\u20139.","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"4952_CR24","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1111\/1574-6968.12489","volume":"357","author":"G Gogoladze","year":"2014","unstructured":"Gogoladze G, Grigolava M, Vishnepolsky B, Chubinidze M, Duroux P, Lefranc M-P, Pirtskhalava M. Dbaasp: database of antimicrobial activity and structure of peptides. FEMS Microbiol Lett. 2014;357(1):63\u20138.","journal-title":"FEMS Microbiol Lett"},{"issue":"21","key":"4952_CR25","doi-asserted-by":"publisher","first-page":"4272","DOI":"10.1093\/bioinformatics\/btz246","volume":"35","author":"L Wei","year":"2019","unstructured":"Wei L, Zhou C, Su R, Zou Q. Pepred-suite: improved and robust prediction of therapeutic peptides using adaptive feature representation learning. Bioinformatics. 2019;35(21):4272\u201380.","journal-title":"Bioinformatics"},{"key":"4952_CR26","unstructured":"huggingface: Rostlab Prot Bert Bfd. https:\/\/huggingface.co\/Rostlab Accessed 2022-04-25"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-022-04952-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-022-04952-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-022-04952-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T07:03:52Z","timestamp":1664175832000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-022-04952-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,26]]},"references-count":26,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["4952"],"URL":"https:\/\/doi.org\/10.1186\/s12859-022-04952-z","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,26]]},"assertion":[{"value":"2 May 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 September 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 September 2022","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":"389"}}