{"id":"https://openalex.org/W4360807834","doi":"https://doi.org/10.1093/bioinformatics/btad153","title":"Foldcomp: a library and format for compressing and indexing large protein structure sets","display_name":"Foldcomp: a library and format for compressing and indexing large protein structure sets","publication_year":2023,"publication_date":"2023-03-24","ids":{"openalex":"https://openalex.org/W4360807834","doi":"https://doi.org/10.1093/bioinformatics/btad153","pmid":"https://pubmed.ncbi.nlm.nih.gov/36961332"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btad153","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad153","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad153/49628100/btad153.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/advance-article-pdf/doi/10.1093/bioinformatics/btad153/49628100/btad153.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101876085","display_name":"Hyunbin Kim","orcid":"https://orcid.org/0000-0003-4662-3943"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunbin Kim","raw_affiliation_strings":["Interdisciplinary Program in Bioinformatics, Seoul National University , Seoul 08826, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-4662-3943","affiliations":[{"raw_affiliation_string":"Interdisciplinary Program in Bioinformatics, Seoul National University , Seoul 08826, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016012053","display_name":"Milot Mirdita","orcid":"https://orcid.org/0000-0001-8637-6719"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Milot Mirdita","raw_affiliation_strings":["School of Biological Sciences, Seoul National University , Seoul 08826, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-8637-6719","affiliations":[{"raw_affiliation_string":"School of Biological Sciences, Seoul National University , Seoul 08826, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019985343","display_name":"Martin Steinegger","orcid":"https://orcid.org/0000-0001-8781-9753"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Martin Steinegger","raw_affiliation_strings":["Artificial Intelligence Institute, Seoul National University , Seoul 08826, South Korea","Institute of Molecular Biology and Genetics, Seoul National University , Seoul 08826, South Korea","Interdisciplinary Program in Bioinformatics, Seoul National University , Seoul 08826, South Korea","School of Biological Sciences, Seoul National University , Seoul 08826, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-8781-9753","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Institute, Seoul National University , Seoul 08826, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Institute of Molecular Biology and Genetics, Seoul National University , Seoul 08826, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Interdisciplinary Program in Bioinformatics, Seoul National University , Seoul 08826, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"School of Biological Sciences, Seoul National University , Seoul 08826, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5016012053","https://openalex.org/A5019985343"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":2.7151,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.9135143,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"39","issue":"4","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":0.506600022315979,"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":0.506600022315979,"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":0.14409999549388885,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.052799999713897705,"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/search-engine-indexing","display_name":"Search engine indexing","score":0.8347499966621399},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.712067186832428},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.451965868473053},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.33502721786499023}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8347499966621399},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.712067186832428},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.451965868473053},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.33502721786499023}],"mesh":[{"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":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","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":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":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btad153","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad153","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad153/49628100/btad153.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:36961332","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36961332","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:10085514","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10085514","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10085514/pdf/btad153.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"},{"id":"pmh:oai:s-space.snu.ac.kr:10371/202507","is_oa":false,"landing_page_url":"https://hdl.handle.net/10371/202507","pdf_url":null,"source":{"id":"https://openalex.org/S4306401345","display_name":"Seoul National University Open Repository (Seoul National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139264467","host_organization_name":"Seoul National University","host_organization_lineage":["https://openalex.org/I139264467"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btad153","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad153","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad153/49628100/btad153.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":[],"awards":[{"id":"https://openalex.org/G135080353","display_name":null,"funder_award_id":"2019R1A6A1A10073437, 2020M3A9G7103933, 2021R1C1C102065, 2021M3A9I4021220","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G1549957888","display_name":null,"funder_award_id":"2021R1C1C102065","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G2088101978","display_name":null,"funder_award_id":"2019R1A6A1A10073437","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G3360897862","display_name":null,"funder_award_id":"2019R1A6A1A10073437","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G5689383173","display_name":null,"funder_award_id":"2021M3A9I4021220","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G8959955562","display_name":null,"funder_award_id":"2020M3A9G7103933","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4360807834.pdf"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2104078482","https://openalex.org/W2111270835","https://openalex.org/W2604075160","https://openalex.org/W2950192635","https://openalex.org/W2950954328","https://openalex.org/W3093323969","https://openalex.org/W3177828909","https://openalex.org/W3211795435","https://openalex.org/W4206903088","https://openalex.org/W4224303521","https://openalex.org/W4309160459","https://openalex.org/W4327550249","https://openalex.org/W4375858802","https://openalex.org/W4388866605","https://openalex.org/W6807001990"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3024364549","https://openalex.org/W4206019083","https://openalex.org/W2048865712","https://openalex.org/W1976265003","https://openalex.org/W2370378377","https://openalex.org/W2188505374","https://openalex.org/W1558342070"],"abstract_inverted_index":{"SUMMARY:":[0],"Highly":[1],"accurate":[2],"protein":[3,12,118,134],"structure":[4,31],"predictors":[5],"have":[6],"generated":[7],"hundreds":[8],"of":[9,11,20,45,63,74,117,133],"millions":[10],"structures;":[13],"these":[14],"pose":[15],"a":[16,28,43,51,61,105,124,141],"challenge":[17],"in":[18],"terms":[19],"storage":[21],"and":[22,34,47,50,94,104,114,129,146,151,163],"processing.":[23],"Here,":[24],"we":[25],"present":[26],"Foldcomp,":[27],"novel":[29],"lossy":[30,82],"compression":[32,58],"algorithm,":[33],"indexing":[35],"system":[36],"to":[37,66,79],"address":[38],"this":[39],"challenge.":[40],"By":[41],"using":[42],"combination":[44],"internal":[46],"Cartesian":[48],"coordinates":[49],"bi-directional":[52],"NeRF-based":[53],"strategy,":[54],"Foldcomp":[55,122,139,155],"improves":[56],"the":[57,67,80,90,97,157],"ratio":[59],"by":[60,120],"factor":[62],"three":[64],"compared":[65],"next":[68,91],"best":[69,81],"method.":[70],"Its":[71],"reconstruction":[72],"error":[73],"0.08":[75],"\u00c5":[76],"is":[77,85,123,140],"comparable":[78],"compressor.":[83],"It":[84],"five":[86],"times":[87],"faster":[88],"than":[89],"fastest":[92,98],"compressor":[93],"competes":[95],"with":[96],"decompressors.":[99],"With":[100],"its":[101],"multi-threading":[102],"implementation":[103],"Python":[106],"interface":[107],"that":[108],"allows":[109],"for":[110,127,148],"easy":[111],"database":[112,167],"downloads":[113],"efficient":[115],"querying":[116],"structures":[119],"accession,":[121],"powerful":[125],"tool":[126],"managing":[128],"analysing":[130],"large":[131],"collections":[132],"structures.":[135],"AVAILABILITY":[136],"AND":[137],"IMPLEMENTATION:":[138],"free":[142],"open-source":[143],"software":[144],"(GPLv3)":[145],"available":[147],"Linux,":[149],"macOS,":[150],"Windows":[152],"at":[153],"https://foldcomp.foldseek.com.":[154],"provides":[156],"AlphaFold":[158],"Swiss-Prot":[159],"(2.9GB),":[160],"TrEMBL":[161],"(1.1TB),":[162],"ESMatlas":[164],"HQ":[165],"(114GB)":[166],"ready-for-download.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
