{"id":"https://openalex.org/W4390706227","doi":"https://doi.org/10.1093/bioinformatics/btae002","title":"Guiding discovery of protein sequence-structure-function modeling","display_name":"Guiding discovery of protein sequence-structure-function modeling","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390706227","doi":"https://doi.org/10.1093/bioinformatics/btae002","pmid":"https://pubmed.ncbi.nlm.nih.gov/38195719"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btae002","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae002","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/40/1/btae002/56057157/btae002.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"gold","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/40/1/btae002/56057157/btae002.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102719912","display_name":"Azam Hussain","orcid":"https://orcid.org/0000-0003-1869-3311"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Azam Hussain","raw_affiliation_strings":["Department of Macromolecular Science and Engineering Program, University of Michigan , Ann Arbor, MI 48109-1055, United States"],"raw_orcid":"https://orcid.org/0000-0003-1869-3311","affiliations":[{"raw_affiliation_string":"Department of Macromolecular Science and Engineering Program, University of Michigan , Ann Arbor, MI 48109-1055, United States","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060440052","display_name":"Charles L. Brooks","orcid":"https://orcid.org/0000-0002-8149-5417"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Charles L Brooks III","raw_affiliation_strings":["Department of Chemistry, University of Michigan , Ann Arbor, MI 48109-1055, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, University of Michigan , Ann Arbor, MI 48109-1055, United States","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060440052"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.5992,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64766655,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"40","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10404","display_name":"Enzyme Catalysis and Immobilization","score":0.41519999504089355,"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/T10404","display_name":"Enzyme Catalysis and Immobilization","score":0.41519999504089355,"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/T11162","display_name":"Enzyme Structure and Function","score":0.14030000567436218,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.08720000088214874,"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/sequence","display_name":"Sequence (biology)","score":0.6657760739326477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6137546300888062},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.569801926612854},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5299293398857117},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.23655155301094055},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.13359913229942322}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6657760739326477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6137546300888062},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.569801926612854},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5299293398857117},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.23655155301094055},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.13359913229942322}],"mesh":[{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"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":"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":"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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btae002","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae002","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/40/1/btae002/56057157/btae002.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:38195719","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38195719","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:10789314","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10789314","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10789314/pdf/btae002.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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btae002","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae002","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/40/1/btae002/56057157/btae002.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G2883812318","display_name":null,"funder_award_id":"R35 GM130587","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G6674088948","display_name":null,"funder_award_id":"GM130587","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390706227.pdf","grobid_xml":"https://content.openalex.org/works/W4390706227.grobid-xml"},"referenced_works_count":68,"referenced_works":["https://openalex.org/W1607931568","https://openalex.org/W1954202239","https://openalex.org/W1992170964","https://openalex.org/W1993046136","https://openalex.org/W2045332762","https://openalex.org/W2048947602","https://openalex.org/W2059185913","https://openalex.org/W2070753604","https://openalex.org/W2085472819","https://openalex.org/W2099099776","https://openalex.org/W2101234009","https://openalex.org/W2102245393","https://openalex.org/W2105573149","https://openalex.org/W2107432340","https://openalex.org/W2118233996","https://openalex.org/W2127322768","https://openalex.org/W2132262459","https://openalex.org/W2140673705","https://openalex.org/W2141699138","https://openalex.org/W2149775989","https://openalex.org/W2152630148","https://openalex.org/W2160622786","https://openalex.org/W2334483166","https://openalex.org/W2543629455","https://openalex.org/W2555870966","https://openalex.org/W2768348081","https://openalex.org/W2768367491","https://openalex.org/W2781821160","https://openalex.org/W2896431755","https://openalex.org/W2900113977","https://openalex.org/W2911964244","https://openalex.org/W2917580301","https://openalex.org/W2924556932","https://openalex.org/W2949625177","https://openalex.org/W2951149542","https://openalex.org/W2952317511","https://openalex.org/W2956569764","https://openalex.org/W2962862931","https://openalex.org/W2971491142","https://openalex.org/W2972411752","https://openalex.org/W2988881974","https://openalex.org/W2995940204","https://openalex.org/W2999615587","https://openalex.org/W3002681695","https://openalex.org/W3022298391","https://openalex.org/W3023951486","https://openalex.org/W3080211037","https://openalex.org/W3116286104","https://openalex.org/W3168436232","https://openalex.org/W3177828909","https://openalex.org/W3186179742","https://openalex.org/W3203459683","https://openalex.org/W3211795435","https://openalex.org/W4210279159","https://openalex.org/W4281790889","https://openalex.org/W4294719209","https://openalex.org/W4297957988","https://openalex.org/W4310058955","https://openalex.org/W4317815001","https://openalex.org/W4321117954","https://openalex.org/W4327550249","https://openalex.org/W4362521275","https://openalex.org/W4379117440","https://openalex.org/W4384820649","https://openalex.org/W6675354045","https://openalex.org/W6729300673","https://openalex.org/W6737947904","https://openalex.org/W6745609711"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"MOTIVATION:":[0],"Protein":[1],"engineering":[2,184],"techniques":[3,132],"are":[4,27,208],"key":[5,157],"in":[6,19,51,103,159,172,192],"designing":[7],"novel":[8],"catalysts":[9],"for":[10,70],"a":[11,49],"wide":[12],"range":[13],"of":[14,22,34,48,75,91,96,162],"reactions.":[15],"Although":[16],"approaches":[17],"vary":[18],"their":[20],"exploration":[21],"the":[23,31,44,106,142,146,155,160,205],"sequence-structure-function":[24,53,206],"paradigm,":[25],"they":[26],"often":[28],"hampered":[29],"by":[30],"labor-intensive":[32],"steps":[33],"protein":[35,183,193],"expression":[36],"and":[37,46,57,67,83,99,129,137,145,164,197],"screening.":[38],"In":[39],"this":[40,113,116,150],"work,":[41],"we":[42,123],"describe":[43],"development":[45],"testing":[47],"high-throughput":[50],"silico":[52,173],"pipeline":[54,117,175,207],"using":[55],"AlphaFold2":[56],"fast":[58],"Fourier":[59],"transform":[60],"docking":[61],"that":[62,154],"is":[63],"benchmarked":[64],"with":[65,87],"enantioselectivity":[66,104,163],"reactivity":[68,165],"predictions":[69],"an":[71,92,178],"ancestral":[72,195],"sequence":[73,189],"library":[74],"fungal":[76],"flavin-dependent":[77],"monooxygenases.":[78],"RESULTS:":[79],"The":[80,171],"predicted":[81],"enantioselectivities":[82],"reactivities":[84],"correlate":[85],"well":[86],"previously":[88],"described":[89],"screens":[90],"experimentally":[93,168],"available":[94,209],"subset":[95],"these":[97],"proteins":[98,111],"capture":[100],"known":[101],"changes":[102],"across":[105],"phylogenetic":[107],"tree":[108,127],"representing":[109],"ancestorial":[110],"from":[112,186],"family.":[114],"With":[115],"established":[118],"as":[119,177],"our":[120],"functional":[121],"screen,":[122],"apply":[124],"ensemble":[125],"decision":[126],"models":[128,136],"explainable":[130],"AI":[131],"to":[133,167,181],"build":[134],"sequence-function":[135],"extract":[138],"critical":[139],"residues":[140,148,158],"within":[141],"binding":[143],"site":[144],"second-sphere":[147],"around":[149],"site.":[151],"We":[152],"demonstrate":[153],"top-identified":[156],"control":[161],"correspond":[166],"verified":[169],"residues.":[170],"sequence-to-function":[174],"serves":[176],"accelerated":[179],"framework":[180],"inform":[182],"efforts":[185],"vast":[187],"informative":[188],"landscapes":[190],"contained":[191],"families,":[194],"resurrects,":[196],"directed":[198],"evolution":[199],"campaigns.":[200],"AVAILABILITY:":[201],"Jupyter":[202],"notebooks":[203],"detailing":[204],"at":[210],"https://github.com/BrooksResearchGroup-UM/seq_struct_func.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2025-10-10T00:00:00"}
