Show simple item record

dc.contributor.authorWang, Sheng
dc.contributor.authorFei, Shiyang
dc.contributor.authorWang, Zongan
dc.contributor.authorLi, Yu
dc.contributor.authorXu, Jinbo
dc.contributor.authorZhao, Feng
dc.contributor.authorGao, Xin
dc.date.accessioned2018-09-03T13:22:21Z
dc.date.available2018-09-03T13:22:21Z
dc.date.issued2018-08-04
dc.identifier.citationWang S, Fei S, Wang Z, Li Y, Xu J, et al. (2018) PredMP: a web server for de novo prediction and visualization of membrane proteins. Bioinformatics. Available: http://dx.doi.org/10.1093/bioinformatics/bty684.
dc.identifier.issn1367-4803
dc.identifier.issn1460-2059
dc.identifier.doi10.1093/bioinformatics/bty684
dc.identifier.urihttp://hdl.handle.net/10754/628418
dc.description.abstractSummary \nPredMP is the first web service, to our knowledge, that aims at de novo prediction of the membrane protein (MP) 3D structure followed by the embedding of the MP into the lipid bilayer for visualization. Our approach is based on a high-throughput Deep Transfer Learning (DTL) method that first predicts MP contacts by learning from non-MPs and then predicts the 3D model of the MP using the predicted contacts as distance restraints. This algorithm is derived from our previous Deep Learning (DL) method originally developed for soluble protein contact prediction, which has been officially ranked No. 1 in CASP12. The DTL framework in our approach overcomes the challenge that there are only a limited number of solved MP structures for training the deep learning model. There are three modules in the PredMP server: (a) The DTL framework followed by the contact-assisted folding protocol has already been implemented in RaptorX-Contact, which serves as the key module for 3D model generation; (b) The 1D annotation module, implemented in RaptorX-Property, is used to predict the secondary structure and disordered regions; and (c) the visualization module to display the predicted MPs embedded in the lipid bilayer guided by the predicted transmembrane topology. \nResults \nTested on 510 non-redundant MPs, our server predicts correct folds for ∼290 MPs, which significantly outperforms existing methods. Tested on a blind and live benchmark CAMEO from Sep 2016 to Jan 2018, PredMP can successfully model all 10 MPs belonging to the hard category.
dc.publisherOxford University Press (OUP)
dc.relation.urlhttps://academic.oup.com/bioinformatics/advance-article/doi/10.1093/bioinformatics/bty684/5066440
dc.rightsThis is a pre-copyedited, author-produced PDF of an article accepted for publication in Bioinformatics following peer review. The version of record is available online at: https://academic.oup.com/bioinformatics/advance-article/doi/10.1093/bioinformatics/bty684/5066440.
dc.titlePredMP: a web server for de novo prediction and visualization of membrane proteins
dc.typeArticle
dc.contributor.departmentComputational Bioscience Research Center (CBRC)
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.identifier.journalBioinformatics
dc.eprint.versionPost-print
dc.contributor.institutionCOMPASS, New York, USA
dc.contributor.institutionDepartment of Chemistry, University of Chicago, USA
dc.contributor.institutionToyota Technological Institute at Chicago, USA
dc.contributor.institutionProspect Institute of Fatty Acids and Health, Qingdao University, China
kaust.personWang, Sheng
kaust.personLi, Yu
kaust.personGao , Xin
refterms.dateFOA2018-09-10T07:26:59Z
dc.date.published-online2018-08-04
dc.date.published-print2019-02-15


Files in this item

Thumbnail
Name:
bty684.pdf
Size:
186.0Kb
Format:
PDF
Description:
Accepted Manuscript
Thumbnail
Name:
bty684_supp.pdf
Size:
2.744Mb
Format:
PDF
Description:
Supplemental files

This item appears in the following Collection(s)

Show simple item record