Show simple item record

dc.contributor.authorHeffernan, Rhys
dc.contributor.authorPaliwal, Kuldip
dc.contributor.authorLyons, James
dc.contributor.authorSingh, Jaswinder
dc.contributor.authorYang, Yuedong
dc.contributor.authorZhou, Yaoqi
dc.date.accessioned2019-06-07T01:44:05Z
dc.date.available2019-06-07T01:44:05Z
dc.date.issued2018
dc.identifier.issn0192-8651
dc.identifier.doi10.1002/jcc.25534
dc.identifier.urihttp://hdl.handle.net/10072/382158
dc.description.abstractPredicting protein structure from sequence alone is challenging. Thus, the majority of methods for protein structure prediction rely on evolutionary information from multiple sequence alignments. In previous work we showed that Long Short‐Term Bidirectional Recurrent Neural Networks (LSTM‐BRNNs) improved over regular neural networks by better capturing intra‐sequence dependencies. Here we show a single‐sequence‐based prediction method employing LSTM‐BRNNs (SPIDER3‐Single), that consistently achieves Q3 accuracy of 72.5%, and correlation coefficient of 0.67 between predicted and actual solvent accessible surface area. Moreover, it yields reasonably accurate prediction of eight‐state secondary structure, main‐chain angles (backbone ϕ and ψ torsion angles and C α‐atom‐based θ and τ angles), half‐sphere exposure, and contact number. The method is more accurate than the corresponding evolutionary‐based method for proteins with few sequence homologs, and computationally efficient for large‐scale screening of protein‐structural properties. It is available as an option in the SPIDER3 server, and a standalone version for download, at http://sparks-lab.org. © 2018 Wiley Periodicals, Inc.
dc.description.peerreviewedYes
dc.languageEnglish
dc.publisherJohn Wiley & Sons
dc.publisher.placeUnited States
dc.relation.ispartofpagefrom2210
dc.relation.ispartofpageto2216
dc.relation.ispartofissue26
dc.relation.ispartofjournalJournal of Computational Chemistry
dc.relation.ispartofvolume39
dc.subject.fieldofresearchTheoretical and Computational Chemistry not elsewhere classified
dc.subject.fieldofresearchPhysical Chemistry (incl. Structural)
dc.subject.fieldofresearchTheoretical and Computational Chemistry
dc.subject.fieldofresearchcode030799
dc.subject.fieldofresearchcode0306
dc.subject.fieldofresearchcode0307
dc.subject.keywordsBackbone angles
dc.subject.keywordsProtein structure prediction
dc.subject.keywordsContact prediction
dc.subject.keywordsSolvent accessibility prediction
dc.subject.keywordsSecondary structure prediction
dc.titleSingle-sequence-based prediction of protein secondary structures and solvent accessibility by deep whole-sequence learning
dc.typeJournal article
dc.type.descriptionC1 - Articles
dc.type.codeC - Journal Articles
gro.facultyGriffith Sciences, School of Engineering and Built Environment
gro.hasfulltextNo Full Text
gro.griffith.authorPaliwal, Kuldip K.
gro.griffith.authorLyons, James
gro.griffith.authorHeffernan, Rhys
gro.griffith.authorZhou, Yaoqi
gro.griffith.authorSingh, Jaswinder
gro.griffith.authorYang, Yuedong


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record