{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T01:37:22Z","timestamp":1780364242894,"version":"3.54.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2019,8,9]],"date-time":"2019-08-09T00:00:00Z","timestamp":1565308800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,8,9]],"date-time":"2019-08-09T00:00:00Z","timestamp":1565308800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100000925","name":"Department of Health | National Health and Medical Research Council","doi-asserted-by":"publisher","award":["1121629"],"award-info":[{"award-number":["1121629"]}],"id":[{"id":"10.13039\/501100000925","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Department of Education and Training | Australian Research Council","doi-asserted-by":"publisher","award":["DP180102060"],"award-info":[{"award-number":["DP180102060"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["31670723"],"award-info":[{"award-number":["31670723"]}],"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":["81861138009"],"award-info":[{"award-number":["81861138009"]}],"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":["91746119"],"award-info":[{"award-number":["91746119"]}],"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":["31621092"],"award-info":[{"award-number":["31621092"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Mach Intell"],"DOI":"10.1038\/s42256-019-0075-7","type":"journal-article","created":{"date-parts":[[2019,8,9]],"date-time":"2019-08-09T16:03:51Z","timestamp":1565366631000},"page":"347-355","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":38,"title":["Improved fragment sampling for ab initio protein structure prediction using deep neural networks"],"prefix":"10.1038","volume":"1","author":[{"given":"Tong","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanhua","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenze","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenzhi","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9958-5699","authenticated-orcid":false,"given":"Yaoqi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5532-1640","authenticated-orcid":false,"given":"Haipeng","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,8,9]]},"reference":[{"key":"75_CR1","doi-asserted-by":"publisher","first-page":"1868","DOI":"10.1126\/science.1113801","volume":"309","author":"P Bradley","year":"2005","unstructured":"Bradley, P., Misura, K. M. S. & Baker, D. Toward high-resolution de novo structure prediction for small proteins. Science 309, 1868\u20131871 (2005).","journal-title":"Science"},{"key":"75_CR2","doi-asserted-by":"publisher","first-page":"1042","DOI":"10.1126\/science.1219021","volume":"338","author":"KA Dill","year":"2012","unstructured":"Dill, K. A. & MacCallum, J. L. The protein-folding problem 50 years on. Science 338, 1042\u20131046 (2012).","journal-title":"Science"},{"key":"75_CR3","unstructured":"Rigden, D. J. From Protein Structure To Function With Bioinformatics Ch. 1. (Springer, 2017)."},{"key":"75_CR4","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1126\/science.aal4512","volume":"355","author":"J Soding","year":"2017","unstructured":"Soding, J. Big-data approaches to protein structure prediction. Science 355, 248\u2013249 (2017).","journal-title":"Science"},{"key":"75_CR5","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.jmb.2009.07.063","volume":"393","author":"DE Kim","year":"2009","unstructured":"Kim, D. E., Blum, B., Bradley, P. & Baker, D. Sampling bottlenecks in de novo protein structure prediction. J. Mol. Biol. 393, 249\u2013260 (2009).","journal-title":"J. Mol. Biol."},{"key":"75_CR6","doi-asserted-by":"publisher","first-page":"1194","DOI":"10.2174\/092986612803217015","volume":"19","author":"A Jothi","year":"2012","unstructured":"Jothi, A. Principles, challenges and advances in ab initio protein structure prediction. Protein Peptide Lett. 19, 1194\u20131204 (2012).","journal-title":"Protein Peptide Lett"},{"key":"75_CR7","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1093\/bioinformatics\/btw668","volume":"33","author":"T Wang","year":"2017","unstructured":"Wang, T., Yang, Y., Zhou, Y. & Gong, H. LRFragLib: an effective algorithm to identify fragments for de novo protein structure prediction. Bioinformatics 33, 677\u2013684 (2017).","journal-title":"Bioinformatics"},{"key":"75_CR8","doi-asserted-by":"publisher","first-page":"e1000083","DOI":"10.1371\/journal.pcbi.1000083","volume":"4","author":"L Baeten","year":"2008","unstructured":"Baeten, L. et al. Reconstruction of protein backbones from the BriX collection of canonical protein fragments. PLoS Comput. Biol. 4, e1000083 (2008).","journal-title":"PLoS Comput. Biol."},{"key":"75_CR9","doi-asserted-by":"crossref","unstructured":"Xu, J. Distance-based protein folding powered by deep learning. Preprint at https:\/\/arxiv.org\/abs\/1811.03481 (2018).","DOI":"10.1101\/465955"},{"key":"75_CR10","unstructured":"Evans, R. et al. De novo structure prediction with deep-learning based scoring. In Thirteenth Critical Assessment of Techniques for Protein Structure Prediction Abstracts (Iberostar Paraiso, 2018)."},{"key":"75_CR11","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 34, 4039\u20134045 (2018).","journal-title":"Bioinformatics"},{"key":"75_CR12","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1006\/jmbi.1997.0959","volume":"268","author":"KT Simons","year":"1997","unstructured":"Simons, K. T., Kooperberg, C., Huang, E. & Baker, D. Assembly of protein tertiary structures from fragments with similar local sequences using simulated annealing and Bayesian scoring functions. J. Mol. Biol. 268, 209\u2013225 (1997).","journal-title":"J. Mol. Biol."},{"key":"75_CR13","doi-asserted-by":"publisher","first-page":"1715","DOI":"10.1002\/prot.24105","volume":"80","author":"D Xu","year":"2012","unstructured":"Xu, D. & Zhang, Y. Ab initio protein structure assembly using continuous structure fragments and optimized knowledge-based force field. Proteins 80, 1715\u20131735 (2012).","journal-title":"Proteins"},{"key":"75_CR14","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1038\/nmeth.3213","volume":"12","author":"J Yang","year":"2015","unstructured":"Yang, J. et al. The I-TASSER Suite: protein structure and function prediction. Nat. Methods 12, 7\u20138 (2015).","journal-title":"Nat. Methods"},{"key":"75_CR15","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/S0076-6879(04)83004-0","volume":"383","author":"CA Rohl","year":"2004","unstructured":"Rohl, C. A., Strauss, C. E., Misura, K. M. & Baker, D. Protein structure prediction using Rosetta. Methods Enzymol. 383, 66\u201393 (2004).","journal-title":"Methods Enzymol."},{"key":"75_CR16","doi-asserted-by":"publisher","first-page":"W526","DOI":"10.1093\/nar\/gkh468","volume":"32","author":"DE Kim","year":"2004","unstructured":"Kim, D. E., Chivian, D. & Baker, D. Protein structure prediction and analysis using the Robetta server. Nucleic Acids Res. 32, W526\u2013W531 (2004).","journal-title":"Nucleic Acids Res."},{"key":"75_CR17","doi-asserted-by":"publisher","first-page":"e23294","DOI":"10.1371\/journal.pone.0023294","volume":"6","author":"D Gront","year":"2011","unstructured":"Gront, D., Kulp, D. W., Vernon, R. M., Strauss, C. E. & Baker, D. Generalized fragment picking in Rosetta: design, protocols and applications. PloS ONE 6, e23294 (2011).","journal-title":"PloS ONE"},{"key":"75_CR18","doi-asserted-by":"publisher","first-page":"3110","DOI":"10.1093\/bioinformatics\/btr541","volume":"27","author":"I Kalev","year":"2011","unstructured":"Kalev, I. & Habeck, M. HHfrag: HMM-based fragment detection using HHpred. Bioinformatics 27, 3110\u20133116 (2011).","journal-title":"Bioinformatics"},{"key":"75_CR19","doi-asserted-by":"publisher","first-page":"e0170131","DOI":"10.1371\/journal.pone.0170131","volume":"12","author":"R Trevizani","year":"2017","unstructured":"Trevizani, R., Custodio, F. L., Dos Santos, K. B. & Dardenne, L. E. Critical features of fragment libraries for protein structure prediction. PloS ONE 12, e0170131 (2017).","journal-title":"PloS ONE"},{"key":"75_CR20","doi-asserted-by":"publisher","first-page":"2059","DOI":"10.1093\/bioinformatics\/btw067","volume":"32","author":"D Bhattacharya","year":"2016","unstructured":"Bhattacharya, D., Adhikari, B., Li, J. & Cheng, J. FRAGSION: ultra-fast protein fragment library generation by IOHMM sampling. Bioinformatics 32, 2059\u20132061 (2016).","journal-title":"Bioinformatics"},{"key":"75_CR21","doi-asserted-by":"publisher","first-page":"2219","DOI":"10.1093\/bioinformatics\/bty084","volume":"34","author":"SHP de Oliveira","year":"2018","unstructured":"de Oliveira, S. H. P. & Deane, C. M. Combining co-evolution and secondary structure prediction to improve fragment library generation. Bioinformatics 34, 2219\u20132227 (2018).","journal-title":"Bioinformatics"},{"key":"75_CR22","doi-asserted-by":"publisher","first-page":"e1005324","DOI":"10.1371\/journal.pcbi.1005324","volume":"13","author":"S Wang","year":"2017","unstructured":"Wang, S., Sun, S., Li, Z., Zhang, R. & Xu, J. Accurate de novo prediction of protein contact map by ultra-deep learning model. PLoS Comput. Biol. 13, e1005324 (2017).","journal-title":"PLoS Comput. Biol."},{"key":"75_CR23","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1016\/j.cels.2017.09.001","volume":"5","author":"S Wang","year":"2017","unstructured":"Wang, S., Li, Z., Yu, Y. & Xu, J. Folding membrane proteins by deep transfer learning. Cell Syst. 5, 202\u2013211 e203 (2017).","journal-title":"Cell Syst."},{"key":"75_CR24","first-page":"2403","volume":"35","author":"K Paliwal","year":"2018","unstructured":"Paliwal, K., Hanson, J., Litfin, T., Zhou, Y. & Yang, 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 35, 2403\u20132410 (2018).","journal-title":"Bioinformatics"},{"key":"75_CR25","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput. 9, 1735\u20131780 (1997).","journal-title":"Neural Comput."},{"key":"75_CR26","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z. & He, K. Aggregated residual transformations for deep neural networks. In Proc.Conf. Computer Vision and Pattern Recognition 5987\u20135995 (IEEE, 2017).","DOI":"10.1109\/CVPR.2017.634"},{"key":"75_CR27","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster, M. & Paliwal, K. K. Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45, 2673\u20132681 (1997).","journal-title":"IEEE Trans. Signal Process."},{"key":"75_CR28","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 33, 2842\u20132849 (2017).","journal-title":"Bioinformatics"},{"key":"75_CR29","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. Preprint at https:\/\/arxiv.org\/abs\/1512.03385 (2015).","DOI":"10.1109\/CVPR.2016.90"},{"key":"75_CR30","unstructured":"Hinton, G., Vinyals, O. & Dean, J. Distilling the knowledge in a neural network. Preprint at https:\/\/arxiv.org\/abs\/1503.02531 (2015)."},{"key":"75_CR31","unstructured":"Yu, F. & Koltun, V. Multi-scale context aggregation by dilated convolutions. Preprint at https:\/\/arxiv.org\/abs\/1511.07122 (2015)."},{"key":"75_CR32","doi-asserted-by":"publisher","first-page":"3389","DOI":"10.1093\/nar\/25.17.3389","volume":"25","author":"SF Altschul","year":"1997","unstructured":"Altschul, S. F. et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. Nucleic Acids Res. 25, 3389\u20133402 (1997).","journal-title":"Nucleic Acids Res."},{"key":"75_CR33","doi-asserted-by":"publisher","first-page":"702","DOI":"10.1002\/prot.20264","volume":"57","author":"Y Zhang","year":"2004","unstructured":"Zhang, Y. & Skolnick, J. Scoring function for automated assessment of protein structure template quality. Proteins 57, 702\u2013710 (2004).","journal-title":"Proteins"},{"key":"75_CR34","doi-asserted-by":"publisher","first-page":"1589","DOI":"10.1093\/bioinformatics\/btg224","volume":"19","author":"G Wang","year":"2003","unstructured":"Wang, G. & Dunbrack, R. L. Jr. PISCES: a protein sequence culling server. Bioinformatics 19, 1589\u20131591 (2003).","journal-title":"Bioinformatics"},{"key":"75_CR35","doi-asserted-by":"publisher","first-page":"2577","DOI":"10.1002\/bip.360221211","volume":"22","author":"W Kabsch","year":"1983","unstructured":"Kabsch, W. & Sander, C. Dictionary of protein secondary structure\u2014pattern-recognition of hydrogen-bonded and geometrical features. Biopolymers 22, 2577\u20132637 (1983).","journal-title":"Biopolymers"},{"key":"75_CR36","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1093\/nar\/28.1.235","volume":"28","author":"HM Berman","year":"2000","unstructured":"Berman, H. M. et al. The protein data bank. Nucleic Acids Res. 28, 235\u2013242 (2000).","journal-title":"Nucleic Acids Res."},{"key":"75_CR37","doi-asserted-by":"publisher","first-page":"D304","DOI":"10.1093\/nar\/gkt1240","volume":"42","author":"NK Fox","year":"2014","unstructured":"Fox, N. K., Brenner, S. E. & Chandonia, J. M. SCOPe: Structural classification of proteins\u2014extended, integrating SCOP and ASTRAL data and classification of new structures. Nucleic Acids Res. 42, D304\u2013D309 (2014).","journal-title":"Nucleic Acids Res."},{"key":"75_CR38","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1006\/jmbi.1999.3091","volume":"292","author":"DT Jones","year":"1999","unstructured":"Jones, D. T. Protein secondary structure prediction based on position-specific scoring matrices. J. Mol. Biol. 292, 195\u2013202 (1999).","journal-title":"J. Mol. Biol."},{"key":"75_CR39","doi-asserted-by":"publisher","first-page":"17747","DOI":"10.1073\/pnas.0605580103","volume":"103","author":"IA Hubner","year":"2006","unstructured":"Hubner, I. A., Deeds, E. J. & Shakhnovich, E. I. Understanding ensemble protein folding at atomic detail. Proc. Natl Acad. Sci. USA 103, 17747\u201317752 (2006).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"75_CR40","doi-asserted-by":"publisher","first-page":"1470","DOI":"10.1110\/ps.690101","volume":"10","author":"O Carugo","year":"2001","unstructured":"Carugo, O. & Pongor, S. A normalized root-mean-square distance for comparing protein three-dimensional structures. Protein Sci. 10, 1470\u20131473 (2001).","journal-title":"Protein Sci."},{"key":"75_CR41","doi-asserted-by":"publisher","first-page":"10915","DOI":"10.1073\/pnas.89.22.10915","volume":"89","author":"S Henikoff","year":"1992","unstructured":"Henikoff, S. & Henikoff, J. G. Amino acid substitution matrices from protein blocks. Proc. Natl Acad. Sci. USA 89, 10915\u201310919 (1992).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"75_CR42","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/BF01025492","volume":"4","author":"A Kidera","year":"1985","unstructured":"Kidera, A., Konishi, Y., Oka, M., Ooi, T. & Scheraga, H. A. Statistical analysis of the physical properties of the 20 naturally occurring amino acids. J. Protein Chem. 4, 23\u201355 (1985).","journal-title":"J. Protein Chem."},{"key":"75_CR43","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I. & Salakhutdinov, R. Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929\u20131958 (2014).","journal-title":"J. Mach. Learn. Res."},{"key":"75_CR44","unstructured":"Kingma, D. P. & Ba, J. Adam: a method for stochastic optimization. Preprint at https:\/\/arxiv.org\/abs\/1412.6980 (2014)."},{"key":"75_CR45","unstructured":"Keskar, N. S. & Socher, R. Improving generalization performance by switching from Adam to SGD. Preprint at https:\/\/arxiv.org\/abs\/1712.07628 (2017)."},{"key":"75_CR46","unstructured":"Ioffe, S. & Szegedy, C. Batch normalization: accelerating deep network training by reducing internal covariate shift. In Proc. 32nd Int. Conf. Machine Learning. Vol. 37 (JMLR, 2015)."},{"key":"75_CR47","unstructured":"Abadi, M. et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems (TensorFlow, 2015); http:\/\/download.tensorflow.org\/paper\/whitepaper2015.pdf"},{"key":"75_CR48","doi-asserted-by":"publisher","first-page":"2302","DOI":"10.1093\/nar\/gki524","volume":"33","author":"Y Zhang","year":"2005","unstructured":"Zhang, Y. & Skolnick, J. TM-align: a protein structure alignment algorithm based on the TM-score. Nucleic Acids Res. 33, 2302\u20132309 (2005).","journal-title":"Nucleic Acids Res."},{"key":"75_CR49","doi-asserted-by":"publisher","unstructured":"Tong, W. et al. Improved fragment sampling for ab initio protein structure prediction using deep neural networks (Code Ocean, 2019); https:\/\/doi.org\/10.24433\/CO.3579011.v1","DOI":"10.24433\/CO.3579011.v1"}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-019-0075-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-019-0075-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-019-0075-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T23:54:51Z","timestamp":1695081291000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-019-0075-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,9]]},"references-count":49,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2019,8]]}},"alternative-id":["75"],"URL":"https:\/\/doi.org\/10.1038\/s42256-019-0075-7","relation":{},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8,9]]},"assertion":[{"value":"8 March 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 August 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}