Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model
Publication Date
January 05, 2017
Authors
Sheng Wang, Siqi Sun, Zhen Li, Renyu Zhang, et al
Volume
13
Issue
1
Pages
e1005324
DOI
http://doi.org/10.1371/journal.pcbi.1005324
Publisher URL
http://journals.plos.org/ploscompbiol/article?id=10.1371%2Fjournal.pcbi.1005324
Scopus
85011370897
Mendeley
http://www.mendeley.com/research/accurate-novo-prediction-protein-contact-map-ultradeep-learning-model-1
Events
Loading … Spinner

Mendeley | Further Information

{"title"=>"Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model", "type"=>"journal", "authors"=>[{"first_name"=>"Sheng", "last_name"=>"Wang", "scopus_author_id"=>"55789487300"}, {"first_name"=>"Siqi", "last_name"=>"Sun", "scopus_author_id"=>"57056718200"}, {"first_name"=>"Zhen", "last_name"=>"Li", "scopus_author_id"=>"57193167902"}, {"first_name"=>"Renyu", "last_name"=>"Zhang", "scopus_author_id"=>"57193161476"}, {"first_name"=>"Jinbo", "last_name"=>"Xu", "scopus_author_id"=>"57056625200"}], "year"=>2017, "source"=>"PLoS Computational Biology", "identifiers"=>{"pui"=>"614304559", "scopus"=>"2-s2.0-85011370897", "isbn"=>"1111111111", "pmid"=>"28056090", "arxiv"=>"1609.00680", "sgr"=>"85011370897", "issn"=>"15537358", "doi"=>"10.1371/journal.pcbi.1005324"}, "id"=>"998fde5f-d020-3ead-9752-f5063dd67b76", "abstract"=>"Recently exciting progress has been made on protein contact prediction, but the predicted contacts for proteins without many sequence homologs is still of low quality and not very useful for de novo structure prediction. This paper presents a new deep learning method that predicts contacts by integrating both evolutionary coupling (EC) and sequence conservation information through an ultra-deep neural network formed by two deep residual networks. This deep neural network allows us to model very complex sequence-contact relationship as well as long-range inter-contact correlation. Our method greatly outperforms existing contact prediction methods and leads to much more accurate contact-assisted protein folding. Tested on three datasets of 579 proteins, the average top L long-range prediction accuracy obtained our method, the representative EC method CCMpred and the CASP11 winner MetaPSICOV is 0.47, 0.21 and 0.30, respectively; the average top L/10 long-range accuracy of our method, CCMpred and MetaPSICOV is 0.77, 0.47 and 0.59, respectively. Ab initio folding using our predicted contacts as restraints can yield correct folds (i.e., TMscore>0.6) for 203 test proteins, while that using MetaPSICOV- and CCMpred-predicted contacts can do so for only 79 and 62 proteins, respectively. Further, our contact-assisted models have much better quality than template-based models. Using our predicted contacts as restraints, we can (ab initio) fold 208 of the 398 membrane proteins with TMscore>0.5. By contrast, when the training proteins of our method are used as templates, homology modeling can only do so for 10 of them. One interesting finding is that even if we do not train our prediction models with any membrane proteins, our method works very well on membrane protein prediction. Finally, in recent blind CAMEO benchmark our method successfully folded 5 test proteins with a novel fold.", "link"=>"http://www.mendeley.com/research/accurate-novo-prediction-protein-contact-map-ultradeep-learning-model-1", "reader_count"=>189, "reader_count_by_academic_status"=>{"Unspecified"=>2, "Professor > Associate Professor"=>9, "Student > Doctoral Student"=>8, "Researcher"=>45, "Student > Ph. D. Student"=>54, "Student > Postgraduate"=>10, "Student > Master"=>32, "Other"=>5, "Student > Bachelor"=>21, "Lecturer"=>1, "Professor"=>2}, "reader_count_by_user_role"=>{"Unspecified"=>2, "Professor > Associate Professor"=>9, "Student > Doctoral Student"=>8, "Researcher"=>45, "Student > Ph. D. Student"=>54, "Student > Postgraduate"=>10, "Student > Master"=>32, "Other"=>5, "Student > Bachelor"=>21, "Lecturer"=>1, "Professor"=>2}, "reader_count_by_subject_area"=>{"Unspecified"=>7, "Agricultural and Biological Sciences"=>49, "Chemistry"=>19, "Computer Science"=>46, "Engineering"=>9, "Environmental Science"=>1, "Biochemistry, Genetics and Molecular Biology"=>44, "Nursing and Health Professions"=>1, "Materials Science"=>1, "Mathematics"=>1, "Medicine and Dentistry"=>3, "Neuroscience"=>2, "Pharmacology, Toxicology and Pharmaceutical Science"=>1, "Physics and Astronomy"=>5}, "reader_count_by_subdiscipline"=>{"Materials Science"=>{"Materials Science"=>1}, "Medicine and Dentistry"=>{"Medicine and Dentistry"=>3}, "Physics and Astronomy"=>{"Physics and Astronomy"=>5}, "Mathematics"=>{"Mathematics"=>1}, "Unspecified"=>{"Unspecified"=>7}, "Environmental Science"=>{"Environmental Science"=>1}, "Pharmacology, Toxicology and Pharmaceutical Science"=>{"Pharmacology, Toxicology and Pharmaceutical Science"=>1}, "Engineering"=>{"Engineering"=>9}, "Chemistry"=>{"Chemistry"=>19}, "Neuroscience"=>{"Neuroscience"=>2}, "Agricultural and Biological Sciences"=>{"Agricultural and Biological Sciences"=>49}, "Computer Science"=>{"Computer Science"=>46}, "Nursing and Health Professions"=>{"Nursing and Health Professions"=>1}, "Biochemistry, Genetics and Molecular Biology"=>{"Biochemistry, Genetics and Molecular Biology"=>44}}, "reader_count_by_country"=>{"Canada"=>1, "Netherlands"=>1, "Korea (South)"=>1, "United States"=>5, "Australia"=>1, "Germany"=>3, "Spain"=>1, "India"=>2}, "group_count"=>10}

Scopus | Further Information

{"@_fa"=>"true", "link"=>[{"@_fa"=>"true", "@ref"=>"self", "@href"=>"https://api.elsevier.com/content/abstract/scopus_id/85011370897"}, {"@_fa"=>"true", "@ref"=>"author-affiliation", "@href"=>"https://api.elsevier.com/content/abstract/scopus_id/85011370897?field=author,affiliation"}, {"@_fa"=>"true", "@ref"=>"scopus", "@href"=>"https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85011370897&origin=inward"}, {"@_fa"=>"true", "@ref"=>"scopus-citedby", "@href"=>"https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85011370897&origin=inward"}], "prism:url"=>"https://api.elsevier.com/content/abstract/scopus_id/85011370897", "dc:identifier"=>"SCOPUS_ID:85011370897", "eid"=>"2-s2.0-85011370897", "dc:title"=>"Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model", "dc:creator"=>"Wang S.", "prism:publicationName"=>"PLoS Computational Biology", "prism:issn"=>"1553734X", "prism:eIssn"=>"15537358", "prism:volume"=>"13", "prism:issueIdentifier"=>"1", "prism:pageRange"=>nil, "prism:coverDate"=>"2017-01-01", "prism:coverDisplayDate"=>"January 2017", "prism:doi"=>"10.1371/journal.pcbi.1005324", "citedby-count"=>"23", "affiliation"=>[{"@_fa"=>"true", "affilname"=>"Toyota Technological Institute at Chicago", "affiliation-city"=>"Chicago", "affiliation-country"=>"United States"}], "pubmed-id"=>"28056090", "prism:aggregationType"=>"Journal", "subtype"=>"ar", "subtypeDescription"=>"Article", "article-number"=>"e1005324", "source-id"=>"4000151810"}

Twitter

Counter

  • {"month"=>"1", "year"=>"2017", "pdf_views"=>"296", "xml_views"=>"7", "html_views"=>"2355"}
  • {"month"=>"2", "year"=>"2017", "pdf_views"=>"430", "xml_views"=>"3", "html_views"=>"1402"}
  • {"month"=>"3", "year"=>"2017", "pdf_views"=>"240", "xml_views"=>"4", "html_views"=>"971"}
  • {"month"=>"4", "year"=>"2017", "pdf_views"=>"203", "xml_views"=>"1", "html_views"=>"846"}
  • {"month"=>"5", "year"=>"2017", "pdf_views"=>"147", "xml_views"=>"1", "html_views"=>"964"}
  • {"month"=>"6", "year"=>"2017", "pdf_views"=>"171", "xml_views"=>"0", "html_views"=>"832"}
  • {"month"=>"7", "year"=>"2017", "pdf_views"=>"183", "xml_views"=>"2", "html_views"=>"741"}
  • {"month"=>"8", "year"=>"2017", "pdf_views"=>"191", "xml_views"=>"0", "html_views"=>"818"}
  • {"month"=>"9", "year"=>"2017", "pdf_views"=>"181", "xml_views"=>"2", "html_views"=>"800"}
  • {"month"=>"10", "year"=>"2017", "pdf_views"=>"233", "xml_views"=>"2", "html_views"=>"925"}
  • {"month"=>"11", "year"=>"2017", "pdf_views"=>"287", "xml_views"=>"0", "html_views"=>"955"}
  • {"month"=>"12", "year"=>"2017", "pdf_views"=>"100", "xml_views"=>"2", "html_views"=>"317"}

PMC Usage Stats

  • {"unique-ip"=>"29", "full-text"=>"25", "pdf"=>"17", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"6", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"2"}
  • {"unique-ip"=>"28", "full-text"=>"26", "pdf"=>"21", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"3", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"3"}
  • {"unique-ip"=>"15", "full-text"=>"18", "pdf"=>"5", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"4", "supp-data"=>"2", "cited-by"=>"0", "year"=>"2017", "month"=>"4"}
  • {"unique-ip"=>"25", "full-text"=>"26", "pdf"=>"15", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"5"}
  • {"unique-ip"=>"24", "full-text"=>"25", "pdf"=>"14", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"10", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2017", "month"=>"6"}
  • {"unique-ip"=>"26", "full-text"=>"28", "pdf"=>"13", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"7", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2017", "month"=>"7"}
  • {"unique-ip"=>"31", "full-text"=>"39", "pdf"=>"14", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"5", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2017", "month"=>"8"}
  • {"unique-ip"=>"44", "full-text"=>"43", "pdf"=>"10", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"3", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"9"}
  • {"unique-ip"=>"29", "full-text"=>"30", "pdf"=>"13", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"6", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"10"}
Loading … Spinner
There are currently no alerts