{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T20:38:46Z","timestamp":1789763926810,"version":"4.0.1"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T00:00:00Z","timestamp":1686182400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T00:00:00Z","timestamp":1686182400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","award":["161015\/2021-2"],"award-info":[{"award-number":["161015\/2021-2"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","award":["304380\/2018-0"],"award-info":[{"award-number":["304380\/2018-0"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","award":["309330\/2018-1"],"award-info":[{"award-number":["309330\/2018-1"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"crossref","award":["2015\/11937-9"],"award-info":[{"award-number":["2015\/11937-9"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"crossref","award":["2017\/12646-3"],"award-info":[{"award-number":["2017\/12646-3"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"crossref","award":["3342017\/16246-0"],"award-info":[{"award-number":["3342017\/16246-0"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"crossref","award":["2019\/20875-8"],"award-info":[{"award-number":["2019\/20875-8"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002322","name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","doi-asserted-by":"crossref","award":["0001"],"award-info":[{"award-number":["0001"]}],"id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Although the development of sequencing technologies has provided a large number of protein sequences, the analysis of functions that each one plays is still difficult due to the efforts of laboratorial methods, making necessary the usage of computational methods to decrease this gap. As the main source of information available about proteins is their sequences, approaches that can use this information, such as classification based on the patterns of the amino acids and the inference based on sequence similarity using alignment tools, are able to predict a large collection of proteins. The methods available in the literature that use this type of feature can achieve good results, however, they present restrictions of protein length as input to their models. In this work, we present a new method, called TEMPROT, based on the fine-tuning and extraction of embeddings from an available architecture pre-trained on protein sequences. We also describe TEMPROT+, an ensemble between TEMPROT and BLASTp, a local alignment tool that analyzes sequence similarity, which improves the results of our former approach.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The evaluation of our proposed classifiers with the literature approaches has been conducted on our dataset, which was derived from CAFA3 challenge database. Both TEMPROT and TEMPROT+ achieved competitive results on\n                      <jats:inline-formula>\n                        <jats:alternatives>\n                          <jats:tex-math>$$F_{\\max }$$<\/jats:tex-math>\n                          <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                            <mml:msub>\n                              <mml:mi>F<\/mml:mi>\n                              <mml:mo>max<\/mml:mo>\n                            <\/mml:msub>\n                          <\/mml:math>\n                        <\/jats:alternatives>\n                      <\/jats:inline-formula>\n                      ,\n                      <jats:inline-formula>\n                        <jats:alternatives>\n                          <jats:tex-math>$$S_{\\min }$$<\/jats:tex-math>\n                          <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                            <mml:msub>\n                              <mml:mi>S<\/mml:mi>\n                              <mml:mo>min<\/mml:mo>\n                            <\/mml:msub>\n                          <\/mml:math>\n                        <\/jats:alternatives>\n                      <\/jats:inline-formula>\n                      , AuPRC and IAuPRC metrics on Biological Process (BP), Cellular Component (CC) and Molecular Function (MF) ontologies compared to state-of-the-art models, with the main results equal to 0.581, 0.692 and 0.662 of\n                      <jats:inline-formula>\n                        <jats:alternatives>\n                          <jats:tex-math>$$F_{\\max }$$<\/jats:tex-math>\n                          <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                            <mml:msub>\n                              <mml:mi>F<\/mml:mi>\n                              <mml:mo>max<\/mml:mo>\n                            <\/mml:msub>\n                          <\/mml:math>\n                        <\/jats:alternatives>\n                      <\/jats:inline-formula>\n                      on BP, CC and MF, respectively.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The comparison with the literature showed that our model presented competitive results compared the state-of-the-art approaches considering the amino acid sequence pattern recognition and homology analysis. Our model also presented improvements related to the input size that the model can use to train compared to the literature methods.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12859-023-05375-0","type":"journal-article","created":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T04:01:43Z","timestamp":1686196903000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["TEMPROT: protein function annotation using transformers embeddings and homology search"],"prefix":"10.1186","volume":"24","author":[{"given":"Gabriel B.","family":"Oliveira","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helio","family":"Pedrini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zanoni","family":"Dias","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,6,8]]},"reference":[{"issue":"21","key":"5375_CR1","doi-asserted-by":"publisher","first-page":"11449","DOI":"10.3390\/ijms222111449","volume":"22","author":"GB Oliveira","year":"2021","unstructured":"Oliveira GB, Pedrini H, Dias Z. Ensemble of template-free and template-based classifiers for protein secondary structure prediction. Int J Mol Sci. 2021;22(21):11449.","journal-title":"Int J Mol Sci"},{"issue":"18","key":"5375_CR2","doi-asserted-by":"publisher","first-page":"2825","DOI":"10.1093\/bioinformatics\/btab198","volume":"37","author":"Y Cao","year":"2021","unstructured":"Cao Y, Shen Y. TALE: transformer-based protein function annotation with joint sequence-label embedding. Bioinformatics. 2021;37(18):2825\u201333.","journal-title":"Bioinformatics"},{"issue":"896295","key":"5375_CR3","first-page":"1","volume":"2","author":"Y Kagaya","year":"2022","unstructured":"Kagaya Y, et al. ContactPFP: protein function prediction using predicted contact information. Front Bioinform. 2022;2(896295):1\u201317.","journal-title":"Front Bioinform"},{"issue":"1","key":"5375_CR4","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1038\/75556","volume":"25","author":"M Ashburner","year":"2000","unstructured":"Ashburner M, et al. Gene ontology: tool for the unification of biology. Nat Genet. 2000;25(1):25\u20139.","journal-title":"Nat Genet"},{"issue":"4","key":"5375_CR5","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1093\/bioinformatics\/btx624","volume":"34","author":"M Kulmanov","year":"2018","unstructured":"Kulmanov M, et al. DeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifier. Bioinformatics. 2018;34(4):660\u20138.","journal-title":"Bioinformatics"},{"issue":"2","key":"5375_CR6","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1093\/bioinformatics\/btz595","volume":"36","author":"M Kulmanov","year":"2019","unstructured":"Kulmanov M, Hoehndorf R. DeepGOPlus: improved protein function prediction from sequence. Bioinformatics. 2019;36(2):422\u20139.","journal-title":"Bioinformatics"},{"issue":"12","key":"5375_CR7","doi-asserted-by":"publisher","first-page":"1010793","DOI":"10.1371\/journal.pcbi.1010793","volume":"18","author":"Y-H Zhu","year":"2022","unstructured":"Zhu Y-H, et al. Integrating unsupervised language model with triplet neural networks for protein gene ontology prediction. PLoS Comput Biol. 2022;18(12):1010793.","journal-title":"PLoS Comput Biol"},{"issue":"13","key":"5375_CR8","doi-asserted-by":"publisher","first-page":"3799","DOI":"10.1093\/nar\/gkg555","volume":"31","author":"G Zehetner","year":"2003","unstructured":"Zehetner G. OntoBlast function: from sequence similarities directly to potential functional annotations by ontology terms. Nucleic Acids Res. 2003;31(13):3799\u2013803.","journal-title":"Nucleic Acids Res"},{"key":"5375_CR9","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.ymeth.2015.08.009","volume":"93","author":"Q Gong","year":"2016","unstructured":"Gong Q, et al. GoFDR: a sequence alignment based method for predicting protein functions. Methods. 2016;93:3\u201314.","journal-title":"Methods"},{"issue":"17","key":"5375_CR10","doi-asserted-by":"publisher","first-page":"3389","DOI":"10.1093\/nar\/25.17.3389","volume":"25","author":"SF Altschul","year":"1997","unstructured":"Altschul SF, et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. Nucleic Acids Res. 1997;25(17):3389\u2013402.","journal-title":"Nucleic Acids Res"},{"issue":"4","key":"5375_CR11","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1038\/s41592-021-01101-x","volume":"18","author":"B Buchfink","year":"2021","unstructured":"Buchfink B, et al. Sensitive protein alignments at tree-of-life scale using DIAMOND. Nat Methods. 2021;18(4):366\u20138.","journal-title":"Nat Methods"},{"issue":"1","key":"5375_CR12","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1093\/bib\/bbab502","volume":"23","author":"B Lai","year":"2022","unstructured":"Lai B, Xu J. Accurate protein function prediction via graph attention networks with predicted structure information. Brief Bioinform. 2022;23(1):502.","journal-title":"Brief Bioinform"},{"issue":"15","key":"5375_CR13","doi-asserted-by":"publisher","first-page":"2256","DOI":"10.1016\/j.jmb.2018.03.004","volume":"430","author":"C Zhang","year":"2018","unstructured":"Zhang C, et al. MetaGO: predicting gene ontology of non-homologous proteins through low-resolution protein structure prediction and protein\u2013protein network mapping. J Mol Biol. 2018;430(15):2256\u201365.","journal-title":"J Mol Biol"},{"issue":"12","key":"5375_CR14","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1093\/bioinformatics\/btv260","volume":"31","author":"S Wang","year":"2015","unstructured":"Wang S, et al. Exploiting ontology graph for predicting sparsely annotated gene function. Bioinformatics. 2015;31(12):357\u201364.","journal-title":"Bioinformatics"},{"issue":"1","key":"5375_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-022-04565-6","volume":"23","author":"E Rojano","year":"2022","unstructured":"Rojano E, et al. Assigning protein function from domain-function associations using DomFun. BMC Bioinform. 2022;23(1):1\u201319.","journal-title":"BMC Bioinform"},{"issue":"W1","key":"5375_CR16","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1093\/nar\/gkv488","volume":"43","author":"S Das","year":"2015","unstructured":"Das S, et al. CATH FunFHMMer web server: protein functional annotations using functional family assignments. Nucleic Acids Res. 2015;43(W1):148\u201353.","journal-title":"Nucleic Acids Res"},{"key":"5375_CR17","doi-asserted-by":"crossref","unstructured":"Fodeh S, et\u00a0al. Exploiting PubMed for protein molecular function prediction via NMF based multi-label classification. In: IEEE international conference on data mining workshops (ICDMW), 2017. p. 446\u201351.","DOI":"10.1109\/ICDMW.2017.64"},{"issue":"14","key":"5375_CR18","doi-asserted-by":"publisher","first-page":"2465","DOI":"10.1093\/bioinformatics\/bty130","volume":"34","author":"R You","year":"2018","unstructured":"You R, et al. GOLabeler: improving sequence-based large-scale protein function prediction by learning to rank. Bioinformatics. 2018;34(14):2465\u201373.","journal-title":"Bioinformatics"},{"issue":"W1","key":"5375_CR19","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1093\/nar\/gkab398","volume":"49","author":"S Yao","year":"2021","unstructured":"Yao S, et al. NetGO 2.0: improving large-scale protein function prediction with massive sequence, text, domain, family and network information. Nucleic Acids Res. 2021;49(W1):469\u201375.","journal-title":"Nucleic Acids Res"},{"key":"5375_CR20","doi-asserted-by":"crossref","unstructured":"Elnaggar A, et al. ProtTrans: towards cracking the language of life\u2019s code through self-supervised deep learning and high performance computing. 2021. arXiv:2007.06225.","DOI":"10.1101\/2020.07.12.199554"},{"key":"5375_CR21","unstructured":"Vaswani A, et\u00a0al. Attention is all you need. In: Advances in neural information processing systems (NIPS), 2017. p. 5998\u20136008."},{"key":"5375_CR22","volume-title":"Atlas of protein sequence and structure","author":"MO Dayhoff","year":"1972","unstructured":"Dayhoff MO. Atlas of protein sequence and structure. Washington: National Biomedical Research Foundation; 1972."},{"issue":"1","key":"5375_CR23","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1186\/s13059-019-1835-8","volume":"20","author":"N Zhou","year":"2019","unstructured":"Zhou N, et al. The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens. Genome Biol. 2019;20(1):244.","journal-title":"Genome Biol"},{"key":"5375_CR24","unstructured":"Devlin J, et al. BERT: pre-training of deep bidirectional transformers for language understanding. 2018. arXiv:1810.04805."},{"issue":"7873","key":"5375_CR25","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","volume":"596","author":"J Jumper","year":"2021","unstructured":"Jumper J, et al. Highly accurate protein structure prediction with AlphaFold. Nature. 2021;596(7873):583\u20139.","journal-title":"Nature"},{"key":"5375_CR26","unstructured":"Wolf T, et al. Huggingface\u2019s transformers: state-of-the-art natural language processing. 2019. arXiv:1910.03771."},{"key":"5375_CR27","unstructured":"Abadi M, et al. TensorFlow: large-scale machine learning on heterogeneous systems. 2015. https:\/\/www.tensorflow.org."},{"key":"5375_CR28","unstructured":"Maiya AS. ktrain: a low-code library for augmented machine learning. 2020. arXiv:2004.10703."},{"key":"5375_CR29","unstructured":"Kingma DP, Ba J. Adam: a method for stochastic optimization. 2014. arXiv:1412.6980."},{"key":"5375_CR30","doi-asserted-by":"crossref","unstructured":"Wei J, Zou K. EDA: easy data augmentation techniques for boosting performance on text classification tasks. 2019. arXiv:1901.11196.","DOI":"10.18653\/v1\/D19-1670"},{"issue":"15","key":"5375_CR31","doi-asserted-by":"publisher","first-page":"2016239118","DOI":"10.1073\/pnas.2016239118","volume":"118","author":"A Rives","year":"2021","unstructured":"Rives A, et al. Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proc Natl Acad Sci. 2021;118(15):2016239118.","journal-title":"Proc Natl Acad Sci"},{"issue":"3","key":"5375_CR32","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1002\/prot.25832","volume":"88","author":"R Bonetta","year":"2020","unstructured":"Bonetta R, Valentino G. Machine learning techniques for protein function prediction. Proteins Struct Funct Bioinform. 2020;88(3):397\u2013413.","journal-title":"Proteins Struct Funct Bioinform"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-023-05375-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-023-05375-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-023-05375-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T04:02:00Z","timestamp":1686196920000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-023-05375-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,8]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["5375"],"URL":"https:\/\/doi.org\/10.1186\/s12859-023-05375-0","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,8]]},"assertion":[{"value":"20 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 June 2023","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":"242"}}