{"id":"https://openalex.org/W4387310732","doi":"https://doi.org/10.1186/s12859-023-05498-4","title":"SeqPredNN: a neural network that generates protein sequences that fold into specified tertiary structures","display_name":"SeqPredNN: a neural network that generates protein sequences that fold into specified tertiary structures","publication_year":2023,"publication_date":"2023-10-03","ids":{"openalex":"https://openalex.org/W4387310732","doi":"https://doi.org/10.1186/s12859-023-05498-4","pmid":"https://pubmed.ncbi.nlm.nih.gov/37789284"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-023-05498-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05498-4","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05498-4","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05498-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057557205","display_name":"F. Adriaan Lategan","orcid":"https://orcid.org/0000-0003-0456-0892"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"F. Adriaan Lategan","raw_affiliation_strings":["Center for Bioinformatics and Computational Biology, Stellenbosch University, Stellenbosch, 7600, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Bioinformatics and Computational Biology, Stellenbosch University, Stellenbosch, 7600, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049582415","display_name":"Caroline Schreiber","orcid":"https://orcid.org/0000-0001-7919-4597"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Caroline Schreiber","raw_affiliation_strings":["Center for Bioinformatics and Computational Biology, Stellenbosch University, Stellenbosch, 7600, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Bioinformatics and Computational Biology, Stellenbosch University, Stellenbosch, 7600, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085152348","display_name":"Hugh\u2010G. Patterton","orcid":"https://orcid.org/0000-0003-2550-0493"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Hugh G. Patterton","raw_affiliation_strings":["Center for Bioinformatics and Computational Biology, Stellenbosch University, Stellenbosch, 7600, South Africa. hpatterton@sun.ac.za","Center for Bioinformatics and Computational Biology, Stellenbosch University, Stellenbosch, 7600, South Africa"],"raw_orcid":"https://orcid.org/0000-0003-2550-0493","affiliations":[{"raw_affiliation_string":"Center for Bioinformatics and Computational Biology, Stellenbosch University, Stellenbosch, 7600, South Africa. hpatterton@sun.ac.za","institution_ids":["https://openalex.org/I26092322"]},{"raw_affiliation_string":"Center for Bioinformatics and Computational Biology, Stellenbosch University, Stellenbosch, 7600, South Africa","institution_ids":["https://openalex.org/I26092322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5085152348"],"corresponding_institution_ids":["https://openalex.org/I26092322"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.6554,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.65292419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"24","issue":"1","first_page":"373","last_page":"373"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.2671999931335449,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.2671999931335449,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.23999999463558197,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11162","display_name":"Enzyme Structure and Function","score":0.1324000060558319,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/fold","display_name":"Fold (higher-order function)","score":0.726575493812561},{"id":"https://openalex.org/keywords/protein-tertiary-structure","display_name":"Protein tertiary structure","score":0.5654690861701965},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5573917031288147},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45361024141311646},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.442444771528244},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4412633776664734},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.3639828562736511},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3608490526676178},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25229084491729736},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.24037787318229675},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13863351941108704},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.13143190741539001},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.10198232531547546},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.09535038471221924}],"concepts":[{"id":"https://openalex.org/C53942344","wikidata":"https://www.wikidata.org/wiki/Q951651","display_name":"Fold (higher-order function)","level":2,"score":0.726575493812561},{"id":"https://openalex.org/C75599170","wikidata":"https://www.wikidata.org/wiki/Q898483","display_name":"Protein tertiary structure","level":2,"score":0.5654690861701965},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5573917031288147},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45361024141311646},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.442444771528244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4412633776664734},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3639828562736511},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3608490526676178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25229084491729736},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.24037787318229675},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13863351941108704},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.13143190741539001},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.10198232531547546},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.09535038471221924}],"mesh":[{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-023-05498-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05498-4","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05498-4","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:37789284","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37789284","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10546711","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10546711","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10546711/pdf/12859_2023_Article_5498.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:f961713668b444b5a08fdac3b99c85d2","is_oa":true,"landing_page_url":"https://doaj.org/article/f961713668b444b5a08fdac3b99c85d2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 24, Iss 1, Pp 1-14 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s12859-023-05498-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05498-4","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05498-4","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Clean water and sanitation","id":"https://metadata.un.org/sdg/6"}],"awards":[{"id":"https://openalex.org/G3571252242","display_name":null,"funder_award_id":"5U24HG006941","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G887021552","display_name":null,"funder_award_id":"U24 HG006941","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320322663","display_name":"Universiteit Stellenbosch","ror":"https://ror.org/05bk57929"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4387310732.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W113688923","https://openalex.org/W2006431107","https://openalex.org/W2045777307","https://openalex.org/W2115540209","https://openalex.org/W2135815512","https://openalex.org/W2148792677","https://openalex.org/W2153153865","https://openalex.org/W2161151688","https://openalex.org/W2201713963","https://openalex.org/W2735621019","https://openalex.org/W2898210859","https://openalex.org/W2971733377","https://openalex.org/W2996986155","https://openalex.org/W3083406432","https://openalex.org/W3088578860","https://openalex.org/W3106745904","https://openalex.org/W3137550543","https://openalex.org/W3177828909","https://openalex.org/W3186179742","https://openalex.org/W3201855069","https://openalex.org/W4281790889","https://openalex.org/W4295165394","https://openalex.org/W4323075934"],"related_works":["https://openalex.org/W1181095405","https://openalex.org/W3014426369","https://openalex.org/W4240318783","https://openalex.org/W2311285072","https://openalex.org/W1573293794","https://openalex.org/W783636722","https://openalex.org/W2292230535","https://openalex.org/W4243341329","https://openalex.org/W2999866037","https://openalex.org/W2005410385"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,287,316],"relationship":[2],"between":[3,15],"the":[4,12,30,53,71,77,102,121,137,151,158,169,183,197,200,210,213,219,237,254,257,277,296],"sequence":[5,40,78,184,255,289,298],"of":[6,33,55,67,79,91,106,123,139,160,177,185,199,212,232,256,273,279,291,320,322],"a":[7,21,46,80,85,118,141,164,186,192,226,229,267,325],"protein,":[8],"its":[9,16,292],"structure,":[10],"and":[11,18,97,99,104,173,195,205,249,284,313,318],"resulting":[13],"connection":[14],"structure":[17,35,166,194,227,239,275],"function,":[19],"is":[20,65,70],"foundational":[22],"principle":[23],"in":[24,94,163],"biological":[25],"science.":[26],"Only":[27],"recently":[28],"has":[29],"computational":[31],"prediction":[32,201],"protein":[34,39,56,73,81,95,165,187,330],"based":[36],"only":[37,168,250],"on":[38],"been":[41],"addressed":[42],"effectively":[43],"by":[44,222],"AlphaFold,":[45],"neural":[47,143],"network":[48,144],"approach":[49],"that":[50,64,82,109,218,263],"can":[51],"predict":[52,157,182],"majority":[54],"structures":[57,116,149],"with":[58,128,146,228,305],"X-ray":[59,147],"crystallographic":[60,148],"accuracy.":[61],"A":[62],"question":[63],"now":[66],"acute":[68],"relevance":[69],"\"inverse":[72],"folding":[74],"problem\":":[75],"predicting":[76],"folds":[83],"into":[84,114,191,225],"specified":[86,115,193],"structure.":[87],"This":[88],"will":[89,100,265],"be":[90,266],"immense":[92],"value":[93],"engineering":[96],"biotechnology,":[98],"allow":[101],"design":[103,278,331],"expression":[105],"recombinant":[107,124],"proteins":[108,272,304],"can,":[110],"for":[111,120,276,302],"instance,":[112],"fold":[113,190,211,224],"as":[117,310],"scaffold":[119],"attachment":[122],"antigens,":[125],"or":[126,130],"enzymes":[127],"modified":[129,306],"novel":[131,280],"catalytic":[132],"activities.":[133],"Here":[134],"we":[135],"describe":[136],"development":[138],"SeqPredNN,":[140],"feed-forward":[142],"trained":[145],"from":[150],"RCSB":[152],"Protein":[153],"Data":[154],"Bank":[155],"to":[156,189,207,236,241,253,270,295],"identity":[159,290],"amino":[161],"acids":[162],"using":[167,202],"relative":[170],"positions,":[171],"orientations,":[172],"backbone":[174],"dihedral":[175],"angles":[176],"nearby":[178],"residues.":[179],"RESULTS:":[180],"We":[181,216,261],"expected":[188],"assess":[196],"accuracy":[198],"both":[203],"AlphaFold":[204,242],"RoseTTAFold":[206],"computationally":[208],"generate":[209,271],"derived":[214],"sequence.":[215],"show":[217],"sequences":[220,246],"predicted":[221],"SeqPredNN":[223,264,323],"median":[230],"TM-score":[231],"0.638":[233],"when":[234],"compared":[235,294],"crystal":[238],"according":[240],"predictions,":[243],"yet":[244],"these":[245],"are":[247],"unique":[248],"28.4%":[251],"identical":[252],"crystallized":[258],"protein.":[259],"CONCLUSIONS:":[260],"propose":[262],"valuable":[268],"tool":[269],"defined":[274],"biomaterials,":[281],"pharmaceuticals,":[282],"catalysts,":[283],"reporter":[285],"systems.":[286],"low":[288],"predictions":[293],"native":[297],"could":[299],"prove":[300],"useful":[301],"developing":[303],"physical":[307],"properties,":[308],"such":[309],"water":[311],"solubility":[312],"thermal":[314],"stability.":[315],"speed":[317],"ease":[319],"use":[321],"offers":[324],"significant":[326],"advantage":[327],"over":[328],"physics-based":[329],"methods.":[332]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}