{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T11:25:21Z","timestamp":1763810721370},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,1,4]],"date-time":"2022-01-04T00:00:00Z","timestamp":1641254400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,1,4]],"date-time":"2022-01-04T00:00:00Z","timestamp":1641254400000},"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"],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>Protein backbone angle prediction has achieved significant accuracy improvement with the development of deep learning methods. Usually the same deep learning model is used in making prediction for all residues regardless of the categories of secondary structures they belong to. In this paper, we propose to train separate deep learning models for each category of secondary structures. Machine learning methods strive to achieve generality over the training examples and consequently loose accuracy. In this work, we explicitly exploit classification knowledge to restrict generalisation within the specific class of training examples. This is to compensate the loss of generalisation by exploiting specialisation knowledge in an informed way.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The new method named SAP4SS obtains mean absolute error (MAE) values of 15.59, 18.87, 6.03, and 21.71 respectively for four types of backbone angles<jats:inline-formula><jats:alternatives><jats:tex-math>$$\\phi$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\"><mml:mi>\u03d5<\/mml:mi><\/mml:math><\/jats:alternatives><\/jats:inline-formula>,<jats:inline-formula><jats:alternatives><jats:tex-math>$$\\psi$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\"><mml:mi>\u03c8<\/mml:mi><\/mml:math><\/jats:alternatives><\/jats:inline-formula>,<jats:inline-formula><jats:alternatives><jats:tex-math>$$\\theta$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\"><mml:mi>\u03b8<\/mml:mi><\/mml:math><\/jats:alternatives><\/jats:inline-formula>, and<jats:inline-formula><jats:alternatives><jats:tex-math>$$\\tau$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\"><mml:mi>\u03c4<\/mml:mi><\/mml:math><\/jats:alternatives><\/jats:inline-formula>. Consequently, SAP4SS significantly outperforms existing state-of-the-art methods SAP, OPUS-TASS, and SPOT-1D: the differences in MAE for all four types of angles are from 1.5 to 4.1% compared to the best known results.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability<\/jats:title><jats:p>SAP4SS along with its data is available from<jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/gitlab.com\/mahnewton\/sap4ss\">https:\/\/gitlab.com\/mahnewton\/sap4ss<\/jats:ext-link>.<\/jats:p><\/jats:sec>","DOI":"10.1186\/s12859-021-04525-6","type":"journal-article","created":{"date-parts":[[2022,1,4]],"date-time":"2022-01-04T17:26:46Z","timestamp":1641317206000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Secondary structure specific simpler prediction models for protein backbone angles"],"prefix":"10.1186","volume":"23","author":[{"given":"M. A. Hakim","family":"Newton","sequence":"first","affiliation":[]},{"given":"Fereshteh","family":"Mataeimoghadam","sequence":"additional","affiliation":[]},{"given":"Rianon","family":"Zaman","sequence":"additional","affiliation":[]},{"given":"Abdul","family":"Sattar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,4]]},"reference":[{"issue":"2","key":"4525_CR1","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1073\/pnas.58.2.420","volume":"58","author":"KD Gibson","year":"1967","unstructured":"Gibson KD, Scheraga HA. Minimization of polypeptide energy. I. Preliminary structures of bovine pancreatic ribonuclease s-peptide. Proc Natl Acad Sci USA. 1967;58(2):420.","journal-title":"Proc Natl Acad Sci USA"},{"issue":"1","key":"4525_CR2","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s00214-010-0799-2","volume":"128","author":"Y Zhou","year":"2011","unstructured":"Zhou Y, Duan Y, Yang Y, Faraggi E, Lei H. Trends in template\/fragment-free protein structure prediction. Theoret Chem Acc. 2011;128(1):3\u201316.","journal-title":"Theoret Chem Acc"},{"issue":"6","key":"4525_CR3","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1098\/rsif.2005.0083","volume":"3","author":"V Cutello","year":"2005","unstructured":"Cutello V, Narzisi G, Nicosia G. A multi-objective evolutionary approach to the protein structure prediction problem. J R Soc Interface. 2005;3(6):139\u201351.","journal-title":"J R Soc Interface"},{"key":"4525_CR4","doi-asserted-by":"crossref","unstructured":"Guo J-t, Ellrott K, Xu Y. A historical perspective of template-based protein structure prediction. In: Protein structure prediction. Springer; 2008. pp. 3\u201342.","DOI":"10.1007\/978-1-59745-574-9_1"},{"issue":"28","key":"4525_CR5","doi-asserted-by":"publisher","first-page":"2040","DOI":"10.1002\/jcc.23718","volume":"35","author":"J Lyons","year":"2014","unstructured":"Lyons J, Dehzangi A, Heffernan R, Sharma A, Paliwal K, Sattar A, Zhou Y, Yang Y. Predicting backbone c\u03b1 angles and dihedrals from protein sequences by stacked sparse auto-encoder deep neural network. J Comput Chem. 2014;35(28):2040\u20136.","journal-title":"J Comput Chem"},{"issue":"18","key":"4525_CR6","doi-asserted-by":"publisher","first-page":"2842","DOI":"10.1093\/bioinformatics\/btx218","volume":"33","author":"R Heffernan","year":"2017","unstructured":"Heffernan R, Yang Y, Paliwal K, Zhou Y. Capturing non-local interactions by long short-term memory bidirectional recurrent neural networks for improving prediction of protein secondary structure, backbone angles, contact numbers and solvent accessibility. Bioinformatics. 2017;33(18):2842\u20139.","journal-title":"Bioinformatics"},{"issue":"14","key":"4525_CR7","doi-asserted-by":"publisher","first-page":"2403","DOI":"10.1093\/bioinformatics\/bty1006","volume":"35","author":"J Hanson","year":"2018","unstructured":"Hanson J, Paliwal K, Litfin T, Yang Y, Zhou Y. Improving prediction of protein secondary structure, backbone angles, solvent accessibility and contact numbers by using predicted contact maps and an ensemble of recurrent and residual convolutional neural networks. Bioinformatics. 2018;35(14):2403\u201310.","journal-title":"Bioinformatics"},{"issue":"20","key":"4525_CR8","doi-asserted-by":"publisher","first-page":"5021","DOI":"10.1093\/bioinformatics\/btaa629","volume":"36","author":"G Xu","year":"2020","unstructured":"Xu G, Wang Q, Ma J. OPUS-TASS: a protein backbone torsion angles and secondary structure predictor based on ensemble neural networks. Bioinformatics (Oxford, England). 2020;36(20):5021\u20136.","journal-title":"Bioinformatics (Oxford, England)"},{"key":"4525_CR9","doi-asserted-by":"publisher","first-page":"11476","DOI":"10.1038\/srep11476","volume":"5","author":"R Heffernan","year":"2015","unstructured":"Heffernan R, Paliwal K, Lyons J, Dehzangi A, Sharma A, Wang J, Sattar A, Yang Y, Zhou Y. Improving prediction of secondary structure, local backbone angles, and solvent accessible surface area of proteins by iterative deep learning. Sci Rep. 2015;5:11476.","journal-title":"Sci Rep"},{"issue":"17","key":"4525_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, Madden TL, Sch\u00e4ffer AA, Zhang J, Zhang Z, Miller W, Lipman DJ. 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"},{"key":"4525_CR11","unstructured":"Fang C. Applications of deep neural networks to protein structure prediction. PhD thesis. University of Missouri-Columbia; 2018."},{"issue":"10","key":"4525_CR12","doi-asserted-by":"publisher","first-page":"3400","DOI":"10.1371\/journal.pone.0003400","volume":"3","author":"S Wu","year":"2008","unstructured":"Wu S, Zhang Y. Anglor: a composite machine-learning algorithm for protein backbone torsion angle prediction. PLoS ONE. 2008;3(10):3400.","journal-title":"PLoS ONE"},{"issue":"9","key":"4525_CR13","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1007\/s008940100038","volume":"7","author":"J Meiler","year":"2001","unstructured":"Meiler J, M\u00fcller M, Zeidler A, Schm\u00e4schke F. Generation and evaluation of dimension-reduced amino acid parameter representations by artificial neural networks. Mol Model Annu. 2001;7(9):360\u20139.","journal-title":"Mol Model Annu"},{"issue":"6","key":"4525_CR14","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1002\/prot.25674","volume":"87","author":"MS Klausen","year":"2019","unstructured":"Klausen MS, Jespersen MC, Nielsen H, Jensen KK, Jurtz VI, Soenderby CK, Sommer MOA, Winther O, Nielsen M, Petersen B, et al. NetSurfP-2.0: improved prediction of protein structural features by integrated deep learning. Proteins Struct Funct Bioinf. 2019;87(6):520\u20137.","journal-title":"Proteins Struct Funct Bioinf"},{"issue":"2","key":"4525_CR15","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1038\/nmeth.1818","volume":"9","author":"M Remmert","year":"2012","unstructured":"Remmert M, Biegert A, Hauser A, S\u00f6ding J. HHblits: lightning-fast iterative protein sequence searching by hmm-hmm alignment. Nat Methods. 2012;9(2):173.","journal-title":"Nat Methods"},{"issue":"26","key":"4525_CR16","doi-asserted-by":"publisher","first-page":"2210","DOI":"10.1002\/jcc.25534","volume":"39","author":"R Heffernan","year":"2018","unstructured":"Heffernan R, Paliwal K, Lyons J, Singh J, Yang Y, Zhou Y. Single-sequence-based prediction of protein secondary structures and solvent accessibility by deep whole-sequence learning. J Comput Chem. 2018;39(26):2210\u20136.","journal-title":"J Comput Chem"},{"issue":"suppl\u20132","key":"4525_CR17","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1093\/nar\/gki402","volume":"33","author":"G Wang","year":"2005","unstructured":"Wang G, Dunbrack RL. PISCES: recent improvements to a PDB sequence culling server. Nucleic Acids Res. 2005;33(suppl\u20132):94\u20138.","journal-title":"Nucleic Acids Res"},{"issue":"23","key":"4525_CR18","doi-asserted-by":"crossref","first-page":"4039","DOI":"10.1093\/bioinformatics\/bty481","volume":"34","author":"J Hanson","year":"2018","unstructured":"Hanson J, Paliwal K, Litfin T, Yang Y, Zhou Y. Accurate prediction of protein contact maps by coupling residual two-dimensional bidirectional long short-term memory with convolutional neural networks. Bioinformatics. 2018;34(23):4039\u201345.","journal-title":"Bioinformatics"},{"issue":"3","key":"4525_CR19","doi-asserted-by":"publisher","first-page":"1020","DOI":"10.1109\/TCBB.2018.2814586","volume":"16","author":"C Fang","year":"2018","unstructured":"Fang C, Shang Y, Xu D. Prediction of protein backbone torsion angles using deep residual inception neural networks. IEEE\/ACM Trans Comput Biol Bioinf. 2018;16(3):1020\u20138.","journal-title":"IEEE\/ACM Trans Comput Biol Bioinf"},{"key":"4525_CR20","doi-asserted-by":"publisher","DOI":"10.1093\/database\/bat031","author":"J Haas","year":"2013","unstructured":"Haas J, Roth S, Arnold K, Kiefer F, Schmidt T, Bordoli L, Schwede T. The protein model portal-a comprehensive resource for protein structure and model information. Database. 2013. https:\/\/doi.org\/10.1093\/database\/bat031.","journal-title":"Database"},{"key":"4525_CR21","unstructured":"Lodish H, Berk A, Zipursky SL, Matsudaira P, Baltimore D, Darnell J. Hierarchical structure of proteins. In: Molecular cell biology, 4th ed. WH Freeman; 2000."},{"issue":"17","key":"4525_CR22","doi-asserted-by":"publisher","first-page":"3538","DOI":"10.3390\/app9173538","volume":"9","author":"H Hu","year":"2019","unstructured":"Hu H, Li Z, Elofsson A, Xie S. A Bi-LSTM based ensemble algorithm for prediction of protein secondary structure. Appl Sci. 2019;9(17):3538.","journal-title":"Appl Sci"},{"issue":"1","key":"4525_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-48786-x","volume":"9","author":"M Torrisi","year":"2019","unstructured":"Torrisi M, Kaleel M, Pollastri G. Deeper profiles and cascaded recurrent and convolutional neural networks for state-of-the-art protein secondary structure prediction. Sci Rep. 2019;9(1):1\u201312.","journal-title":"Sci Rep"},{"key":"4525_CR24","first-page":"289033","volume":"2018","author":"M Torrisi","year":"2018","unstructured":"Torrisi M, Kaleel M, Pollastri G. Porter 5: fast, state-of-the-art ab initio prediction of protein secondary structure in 3 and 8 classes. bioRxiv. 2018;2018:289033.","journal-title":"bioRxiv"},{"issue":"3","key":"4525_CR25","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1002\/jcc.21968","volume":"33","author":"E Faraggi","year":"2012","unstructured":"Faraggi E, Zhang T, Yang Y, Kurgan L, Zhou Y. SPINE X: improving protein secondary structure prediction by multistep learning coupled with prediction of solvent accessible surface area and backbone torsion angles. J Comput Chem. 2012;33(3):259\u201367.","journal-title":"J Comput Chem"},{"issue":"8","key":"4525_CR26","doi-asserted-by":"publisher","first-page":"1955","DOI":"10.1110\/ps.051479505","volume":"14","author":"D Kihara","year":"2005","unstructured":"Kihara D. The effect of long-range interactions on the secondary structure formation of proteins. Protein Sci. 2005;14(8):1955\u201363.","journal-title":"Protein Sci"},{"issue":"2\u20133","key":"4525_CR27","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1006\/jsbi.2001.4336","volume":"134","author":"B Rost","year":"2001","unstructured":"Rost B. Protein secondary structure prediction continues to rise. J Struct Biol. 2001;134(2\u20133):204\u201318.","journal-title":"J Struct Biol"},{"issue":"18","key":"4525_CR28","doi-asserted-by":"publisher","first-page":"2592","DOI":"10.1093\/bioinformatics\/btu352","volume":"30","author":"CN Magnan","year":"2014","unstructured":"Magnan CN, Baldi P. SSpro\/ACCpro 5: almost perfect prediction of protein secondary structure and relative solvent accessibility using profiles, machine learning and structural similarity. Bioinformatics. 2014;30(18):2592\u20137.","journal-title":"Bioinformatics"},{"issue":"4","key":"4525_CR29","first-page":"73","volume":"19","author":"Y Gao","year":"2018","unstructured":"Gao Y, Wang S, Deng M, Xu J. Raptorx-angle: real-value prediction of protein backbone dihedral angles through a hybrid method of clustering and deep learning. BMC Bioinformatics. 2018;19(4):73\u201384.","journal-title":"BMC Bioinformatics"},{"issue":"1","key":"4525_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-76317-6","volume":"10","author":"F Mataeimoghadam","year":"2020","unstructured":"Mataeimoghadam F, Newton MH, Dehzangi A, Karim A, Jayaram B, Ranganathan S, Sattar A. Enhancing protein backbone angle prediction by using simpler models of deep neural networks. Sci Rep. 2020;10(1):1\u201312.","journal-title":"Sci Rep"},{"key":"4525_CR31","doi-asserted-by":"crossref","unstructured":"Vapnik V. The support vector method of function estimation. In: Nonlinear modeling. Springer; 1998. pp. 55\u201385.","DOI":"10.1007\/978-1-4615-5703-6_3"},{"key":"4525_CR32","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I. Attention is all you need. In: Advances in neural information processing systems; 2017. pp. 5998\u20136008."},{"issue":"20","key":"4525_CR33","doi-asserted-by":"publisher","first-page":"3113","DOI":"10.1016\/j.jmb.2017.08.013","volume":"429","author":"G Xu","year":"2017","unstructured":"Xu G, Ma T, Zang T, Sun W, Wang Q, Ma J. OPUS-DOSP: a distance-and orientation-dependent all-atom potential derived from side-chain packing. J Mol Biol. 2017;429(20):3113\u201320.","journal-title":"J Mol Biol"},{"issue":"1","key":"4525_CR34","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1002\/pro.3327","volume":"27","author":"G Xu","year":"2018","unstructured":"Xu G, Ma T, Zang T, Wang Q, Ma J. OPUS-CSF: ac-atom-based scoring function for ranking protein structural models. Protein Sci. 2018;27(1):286\u201392.","journal-title":"Protein Sci"},{"key":"4525_CR35","unstructured":"Lounici K, Pontil M, Tsybakov AB, Van De\u00a0Geer S. Taking advantage of sparsity in multi-task learning. 2009. arXiv preprint arXiv:0903.1468."},{"issue":"D1","key":"4525_CR36","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1093\/nar\/gkw1081","volume":"45","author":"M Mirdita","year":"2017","unstructured":"Mirdita M, von den Driesch L, Galiez C, Martin MJ, S\u00f6ding J, Steinegger M. Uniclust databases of clustered and deeply annotated protein sequences and alignments. Nucleic Acids Res. 2017;45(D1):170\u20136.","journal-title":"Nucleic Acids Res"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-021-04525-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-021-04525-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-021-04525-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T09:18:12Z","timestamp":1700039892000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-021-04525-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,4]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["4525"],"URL":"https:\/\/doi.org\/10.1186\/s12859-021-04525-6","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,4]]},"assertion":[{"value":"24 March 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 December 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 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 author(s) declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"6"}}