{"id":"https://openalex.org/W3088911218","doi":"https://doi.org/10.1093/bioinformatics/btaa810","title":"A novel sequence alignment algorithm based on deep learning of the protein folding code","display_name":"A novel sequence alignment algorithm based on deep learning of the protein folding code","publication_year":2020,"publication_date":"2020-09-08","ids":{"openalex":"https://openalex.org/W3088911218","doi":"https://doi.org/10.1093/bioinformatics/btaa810","mag":"3088911218","pmid":"https://pubmed.ncbi.nlm.nih.gov/32960943"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaa810","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa810","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8599902","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000947559","display_name":"Mu Gao","orcid":"https://orcid.org/0000-0002-0378-3704"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mu Gao","raw_affiliation_strings":["Center for the Study of Systems Biology, School of Biological Sciences, Georgia Institute of Technology , Atlanta, GA 30332, USA"],"raw_orcid":"https://orcid.org/0000-0002-0378-3704","affiliations":[{"raw_affiliation_string":"Center for the Study of Systems Biology, School of Biological Sciences, Georgia Institute of Technology , Atlanta, GA 30332, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010808261","display_name":"Jeffrey Skolnick","orcid":"https://orcid.org/0000-0002-1877-4958"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jeffrey Skolnick","raw_affiliation_strings":["Center for the Study of Systems Biology, School of Biological Sciences, Georgia Institute of Technology , Atlanta, GA 30332, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for the Study of Systems Biology, School of Biological Sciences, Georgia Institute of Technology , Atlanta, GA 30332, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000947559","https://openalex.org/A5010808261"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.501,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.82568523,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"37","issue":"4","first_page":"490","last_page":"496"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.8138999938964844,"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":0.8138999938964844,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.05660000070929527,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.04360000044107437,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7111935615539551},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6143189668655396},{"id":"https://openalex.org/keywords/folding","display_name":"Folding (DSP implementation)","score":0.5744257569313049},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.5646018981933594},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5641554594039917},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"Protein structure prediction","score":0.5342575311660767},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5280143618583679},{"id":"https://openalex.org/keywords/alignment-free-sequence-analysis","display_name":"Alignment-free sequence analysis","score":0.5273797512054443},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5236192345619202},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.5158818960189819},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5056190490722656},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.49337783455848694},{"id":"https://openalex.org/keywords/structural-alignment","display_name":"Structural alignment","score":0.4927709400653839},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4266206622123718},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41861405968666077},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.3644861578941345},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.1926194429397583},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.13684138655662537},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.1277359127998352},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.105335533618927},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.08493241667747498}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7111935615539551},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6143189668655396},{"id":"https://openalex.org/C2776545253","wikidata":"https://www.wikidata.org/wiki/Q5464292","display_name":"Folding (DSP implementation)","level":2,"score":0.5744257569313049},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.5646018981933594},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5641554594039917},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.5342575311660767},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5280143618583679},{"id":"https://openalex.org/C180384323","wikidata":"https://www.wikidata.org/wiki/Q16335137","display_name":"Alignment-free sequence analysis","level":5,"score":0.5273797512054443},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5236192345619202},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.5158818960189819},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5056190490722656},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.49337783455848694},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.4927709400653839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4266206622123718},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41861405968666077},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.3644861578941345},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.1926194429397583},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13684138655662537},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.1277359127998352},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.105335533618927},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.08493241667747498},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btaa810","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa810","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:32960943","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32960943","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:8599902","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8599902","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:8599902","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8599902","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1263320119","display_name":null,"funder_award_id":"R35 GM118039","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G3941785802","display_name":null,"funder_award_id":"R35-118039","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1508885706","https://openalex.org/W1663973292","https://openalex.org/W2008708467","https://openalex.org/W2009086942","https://openalex.org/W2018686514","https://openalex.org/W2023790301","https://openalex.org/W2048102092","https://openalex.org/W2062693912","https://openalex.org/W2087064593","https://openalex.org/W2099075703","https://openalex.org/W2101220662","https://openalex.org/W2102245393","https://openalex.org/W2121125726","https://openalex.org/W2121702291","https://openalex.org/W2143210482","https://openalex.org/W2145268834","https://openalex.org/W2150853465","https://openalex.org/W2158714788","https://openalex.org/W2159560083","https://openalex.org/W2161072217","https://openalex.org/W2161151688","https://openalex.org/W2161732286","https://openalex.org/W2194775991","https://openalex.org/W2912918068","https://openalex.org/W2918296775","https://openalex.org/W2967606876","https://openalex.org/W2972411752","https://openalex.org/W2999044305","https://openalex.org/W6687483927"],"related_works":["https://openalex.org/W2051969447","https://openalex.org/W1482324242","https://openalex.org/W2111937814","https://openalex.org/W2133116680","https://openalex.org/W2141411672","https://openalex.org/W2468116983","https://openalex.org/W2029514038","https://openalex.org/W2414840205","https://openalex.org/W1741740882","https://openalex.org/W65850283"],"abstract_inverted_index":{"MOTIVATION:":[0],"From":[1],"evolutionary":[2],"interference,":[3],"function":[4],"annotation":[5],"to":[6,68,166],"structural":[7,31,79],"prediction,":[8],"protein":[9,53,72,84,113],"sequence":[10,19,39,156],"comparison":[11],"has":[12],"provided":[13],"crucial":[14],"biological":[15],"insights.":[16],"While":[17],"many":[18,76],"alignment":[20],"algorithms":[21],"have":[22],"been":[23],"developed,":[24],"existing":[25],"approaches":[26],"often":[27],"cannot":[28],"detect":[29],"hidden":[30],"relationships":[32],"in":[33,154],"the":[34,71,90,148,151],"'twilight":[35],"zone'":[36],"of":[37,58,78,108,161,176,181],"low":[38],"identity.":[40],"To":[41,87],"address":[42],"this":[43],"critical":[44],"problem,":[45],"we":[46,95],"introduce":[47],"a":[48,155],"computational":[49],"algorithm":[50],"that":[51,89,98],"performs":[52],"Sequence":[54],"Alignments":[55,60],"from":[56,75],"deep-Learning":[57],"Structural":[59],"(SAdLSA,":[61],"silent":[62],"'d').":[63],"The":[64,158],"key":[65],"idea":[66],"is":[67,134,163],"implicitly":[69],"learn":[70],"folding":[73,91],"code":[74,92],"thousands":[77],"alignments":[80,142,153],"using":[81],"experimentally":[82],"determined":[83],"structures.":[85],"RESULTS:":[86],"demonstrate":[88],"was":[93],"learned,":[94],"first":[96],"show":[97,124],"SAdLSA":[99,133,162,177],"trained":[100],"on":[101,119],"pure":[102,111],"\u03b1-helical":[103],"proteins":[104,149],"successfully":[105],"recognizes":[106],"pairs":[107],"structurally":[109],"related":[110],"\u03b2-sheet":[112],"domains.":[114],"Subsequent":[115],"training":[116],"and":[117,143,173],"benchmarking":[118],"larger,":[120],"highly":[121],"challenging":[122,131],"datasets":[123],"significant":[125],"improvement":[126],"over":[127],"established":[128],"approaches.":[129],"For":[130],"cases,":[132],"\u223c150%":[135],"better":[136,145],"than":[137],"HHsearch":[138],"for":[139,146,183],"generating":[140],"pairwise":[141],"\u223c50%":[144],"identifying":[147],"with":[150],"best":[152],"library.":[157],"time":[159],"complexity":[160],"O(N)":[164],"thanks":[165],"GPU":[167],"acceleration.":[168],"AVAILABILITY":[169],"AND":[170],"IMPLEMENTATION:":[171],"Datasets":[172],"source":[174],"codes":[175],"are":[178,192],"available":[179,193],"free":[180],"charge":[182],"academic":[184],"users":[185],"at":[186,194],"http://sites.gatech.edu/cssb/sadlsa/.":[187],"SUPPLEMENTARY":[188],"INFORMATION:":[189],"Supplementary":[190],"data":[191],"Bioinformatics":[195],"online.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2025-10-10T00:00:00"}