{"id":"https://openalex.org/W4393730165","doi":"https://doi.org/10.5281/zenodo.10120639","title":"Scripts, data, and analyses for extending flavoprotein (FLX) domains C-terminally to form extended FLX domains (eFLX) & performing structural predictions & alignments using AlphaFold2, RoseTTAFold, FoldSeek, and DALI","display_name":"Scripts, data, and analyses for extending flavoprotein (FLX) domains C-terminally to form extended FLX domains (eFLX) & performing structural predictions & alignments using AlphaFold2, RoseTTAFold, FoldSeek, and DALI","publication_year":2023,"publication_date":"2023-11-14","ids":{"openalex":"https://openalex.org/W4393730165","doi":"https://doi.org/10.5281/zenodo.10120639"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10120639","doi":"https://doi.org/10.5281/zenodo.10120639","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10120639","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.10120639","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067476384","display_name":"Timothy\u00a0R. Fallon","orcid":"https://orcid.org/0000-0002-3048-7679","observed_orcids":["https://orcid.org/0000-0002-3048-7679"]},"institutions":[{"id":"https://openalex.org/I150209017","display_name":"Scripps Institution of Oceanography","ror":"https://ror.org/04v7hvq31","country_code":"US","type":"facility","lineage":["https://openalex.org/I150209017","https://openalex.org/I36258959"]},{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fallon, Timothy","raw_affiliation_strings":["Scripps Institution of Oceanography","University of California, San Diego"],"raw_orcid":"https://orcid.org/0000-0002-3048-7679","affiliations":[{"raw_affiliation_string":"Scripps Institution of Oceanography","institution_ids":["https://openalex.org/I150209017"]},{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5067476384"],"corresponding_institution_ids":["https://openalex.org/I150209017","https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9189000129699707,"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":0.9189000129699707,"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":0.06849999725818634,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.00419999985024333,"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/c-terminal-extension","display_name":"C-terminal extension","score":0.8100000023841858},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"protein structure prediction","score":0.7369999885559082},{"id":"https://openalex.org/keywords/structural-homology","display_name":"structural homology","score":0.8569999933242798},{"id":"https://openalex.org/keywords/protein-domain-annotation","display_name":"protein domain annotation","score":0.5059999823570251},{"id":"https://openalex.org/keywords/interproscan","display_name":"InterProScan","score":0.6639999747276306},{"id":"https://openalex.org/keywords/rosettafold","display_name":"RoseTTAFold","score":0.8289999961853027},{"id":"https://openalex.org/keywords/alphafold2","display_name":"AlphaFold2","score":0.9890000224113464},{"id":"https://openalex.org/keywords/dali","display_name":"Dali","score":0.7089999914169312},{"id":"https://openalex.org/keywords/foldseek","display_name":"Foldseek","score":0.9089999794960022},{"id":"https://openalex.org/keywords/protein-superfamilies","display_name":"protein superfamilies","score":0.40299999713897705},{"id":"https://openalex.org/keywords/flavoprotein","display_name":"flavoprotein","score":0.5920000076293945},{"id":"https://openalex.org/keywords/protein-sequence-alignment","display_name":"protein sequence alignment","score":0.5109999775886536},{"id":"https://openalex.org/keywords/protein-structure-comparison","display_name":"protein structure comparison","score":0.5}],"concepts":[{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.7374544143676758},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.51498943567276},{"id":"https://openalex.org/C71995715","wikidata":"https://www.wikidata.org/wiki/Q78574842","display_name":"Flavoprotein","level":3,"score":0.4698680341243744},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.39068490266799927},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.24439382553100586},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15580999851226807},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.05421513319015503},{"id":"https://openalex.org/C181199279","wikidata":"https://www.wikidata.org/wiki/Q8047","display_name":"Enzyme","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.10120639","doi":"https://doi.org/10.5281/zenodo.10120639","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10120639","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.10120640","doi":"https://doi.org/10.5281/zenodo.10120640","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10120640","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.10120639","doi":"https://doi.org/10.5281/zenodo.10120639","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10120639","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5917382247","display_name":"Elucidating the Biosynthesis of a Model Ladder-Frame Polyether Toxin","funder_award_id":"F32ES032276","funder_id":"https://openalex.org/F4320337361","funder_display_name":"National Institute of Environmental Health Sciences"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337361","display_name":"National Institute of Environmental Health Sciences","ror":"https://ror.org/00j4k1h63"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4390629199","https://openalex.org/W7133359289","https://openalex.org/W4312032102","https://openalex.org/W4392844094","https://openalex.org/W7155496969","https://openalex.org/W4393305449","https://openalex.org/W7171523675","https://openalex.org/W1979132333","https://openalex.org/W4410775456","https://openalex.org/W4401872102"],"abstract_inverted_index":{"See":[0],"associated":[1],"manuscript":[2],"for":[3,14,62,123,139,163],"more":[4],"details.":[5],"To":[6],"capture":[7],"unannotated":[8],"regions":[9],"of":[10,29,38,73,161,185],"the":[11,27,30,36,39,49,66,87,99,108,130,140],"FLX":[12,33],"domains":[13,76],"structural":[15,124,141,146],"modeling,":[16,107],"an":[17],"extended":[18],"flavin":[19],"oxygenase":[20],"domain":[21,67],"(eFLX)":[22],"was":[23,51,137],"annotated":[24],"by":[25,53],"extending":[26],"C-terminus":[28],"G3DSA:3.50.50.60":[31],"InterProScan":[32],"annotation":[34,50],"to":[35,60,81,144,219],"N-terminus":[37],"downstream":[40,59],"annotation,":[41],"using":[42,84,96,98,190],"bedtools":[43],"closest":[44],"[1]":[45,149],"and":[46,58,79,91,112,118,153,188,211,260,282],"awk.":[47],"Next,":[48],"expanded":[52],"50":[54],"residues":[55],"both":[56],"upstream":[57],"account":[61],"potential":[63],"inaccuracy":[64],"in":[65],"annotations.":[68],"The":[69,134],"peptide":[70],"FASTA":[71],"representation":[72],"these":[74],"eFLX":[75],"were":[77,121],"extracted,":[78],"subjected":[80],"3D":[82],"modelling":[83],"RoseTTAFold":[85],"via":[86,129],"Robetta":[88],"server":[89,132],"[2],":[90],"AlphaFold2":[92,95,117],"(ColabFold":[93],"v1.5.2-patch:":[94],"MMseqs2)":[97],"ColabFold":[100],"Google":[101],"Collaboratory":[102],"notebooks":[103],"[3],":[104],"[4].":[105],"After":[106],"rank":[109],"1":[110,114],"model":[111,113,115],"from":[116],"RoseTTAFold,":[119],"respectively,":[120],"used":[122,138],"similarity":[125,142],"searches":[126],"with":[127,244,265],"FoldSeek":[128,131],"[5].":[133],"DALI":[135],"webserver":[136],"search":[143,264],"establish":[145],"homology":[147],"[6].":[148],"A.":[150,278],"R.":[151],"Quinlan":[152],"I.":[154],"M.":[155,179,201,212,254,283],"Hall,":[156],"\"BEDTools:":[157],"a":[158,191,287],"flexible":[159],"suite":[160],"utilities":[162],"comparing":[164],"genomic":[165],"features,\"":[166],"Bioinformatics,":[167],"vol.":[168,223,297],"26,":[169],"no.":[170,225,228,299],"6,":[171,226,229],"pp.":[172,247,269],"841\u2013842,":[173],"Mar.":[174],"2010,":[175],"doi:":[176,198,232,251,273,304],"10.1093/bioinformatics/btq033.":[177],"[2]":[178],"Baek":[180],"et":[181,237,257],"al.,":[182,238,258],"\"Accurate":[183],"prediction":[184,243],"protein":[186,216,241,262],"structures":[187],"interactions":[189],"three-track":[192],"neural":[193],"network,\"":[194],"Science,":[195],"Jul.":[196,249],"2021,":[197,250],"10.1126/science.abj8754.":[199],"[3]":[200],"Mirdita,":[202],"K.":[203],"Sch\u00fctze,":[204],"Y.":[205],"Moriwaki,":[206],"L.":[207,276],"Heo,":[208],"S.":[209],"Ovchinnikov,":[210],"Steinegger,":[213],"\"ColabFold:":[214],"making":[215],"folding":[217],"accessible":[218],"all,\"":[220],"Nat.":[221,267],"Methods,":[222],"19,":[224],"Art.":[227],"Jun.":[230],"2022,":[231],"10.1038/s41592-022-01488-1.":[233],"[4]":[234],"J.":[235],"Jumper":[236],"\"Highly":[239],"accurate":[240,261],"structure":[242,263],"AlphaFold,\"":[245],"Nature,":[246],"1\u201311,":[248],"10.1038/s41586-021-03819-2.":[252],"[5]":[253],"van":[255],"Kempen":[256],"\"Fast":[259],"Foldseek,\"":[266],"Biotechnol.,":[268],"1\u20134,":[270],"May":[271],"2023,":[272,303],"10.1038/s41587-023-01773-0.":[274],"[6]":[275],"Holm,":[277],"Laiho,":[279],"P.":[280],"T\u00f6r\u00f6nen,":[281],"Salgado,":[284],"\"DALI":[285],"shines":[286],"light":[288],"on":[289],"remote":[290],"homologs:":[291],"One":[292],"hundred":[293],"discoveries,\"":[294],"Protein":[295],"Sci.,":[296],"32,":[298],"1,":[300],"p.":[301],"e4519,":[302],"10.1002/pro.4519.":[305]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2024-04-03T00:00:00"}