{"id":"https://openalex.org/W4400517741","doi":"https://doi.org/10.1093/bioinformatics/btae428","title":"Efficient protein structure archiving using ProteStAr","display_name":"Efficient protein structure archiving using ProteStAr","publication_year":2024,"publication_date":"2024-07-01","ids":{"openalex":"https://openalex.org/W4400517741","doi":"https://doi.org/10.1093/bioinformatics/btae428","pmid":"https://pubmed.ncbi.nlm.nih.gov/38984796","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/11239224"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btae428","doi":"https://doi.org/10.1093/bioinformatics/btae428","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae428","pdf_url":null,"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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1093/bioinformatics/btae428","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041822808","display_name":"Sebastian Deorowicz","orcid":"https://orcid.org/0000-0002-9496-733X","observed_orcids":["https://orcid.org/0000-0002-9496-733X"]},"institutions":[{"id":"https://openalex.org/I119004910","display_name":"Silesian University of Technology","ror":"https://ror.org/02dyjk442","country_code":"PL","type":"education","lineage":["https://openalex.org/I119004910"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Sebastian Deorowicz","raw_affiliation_strings":["Department of Algorithmics and Software, Silesian University of Technology , Akademicka 16 , Gliwice, PL-44100, Poland"],"raw_orcid":"https://orcid.org/0000-0002-9496-733X","affiliations":[{"raw_affiliation_string":"Department of Algorithmics and Software, Silesian University of Technology , Akademicka 16 , Gliwice, PL-44100, Poland","institution_ids":["https://openalex.org/I119004910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017711795","display_name":"Adam Gudy\u015b","orcid":"https://orcid.org/0000-0002-5508-0090","observed_orcids":["https://orcid.org/0000-0002-5508-0090"]},"institutions":[{"id":"https://openalex.org/I119004910","display_name":"Silesian University of Technology","ror":"https://ror.org/02dyjk442","country_code":"PL","type":"education","lineage":["https://openalex.org/I119004910"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Adam Gudy\u015b","raw_affiliation_strings":["Department of Algorithmics and Software, Silesian University of Technology , Akademicka 16 , Gliwice, PL-44100, Poland"],"raw_orcid":"https://orcid.org/0000-0002-5508-0090","affiliations":[{"raw_affiliation_string":"Department of Algorithmics and Software, Silesian University of Technology , Akademicka 16 , Gliwice, PL-44100, Poland","institution_ids":["https://openalex.org/I119004910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5017711795","https://openalex.org/A5041822808"],"corresponding_institution_ids":["https://openalex.org/I119004910"],"apc_list":{"value":4188,"currency":"USD","value_usd":4188},"apc_paid":{"value":4188,"currency":"USD","value_usd":4188},"fwci":0.7536,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6489649,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"40","issue":"7","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.6449999809265137,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.6449999809265137,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.22419999539852142,"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":0.09969999641180038,"subfield":{"id":"https://openalex.org/subfields/1315","display_name":"Structural 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/coordinate-prediction","display_name":"coordinate prediction","score":0.492000013589859},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"lossless compression","score":0.8420000076293945},{"id":"https://openalex.org/keywords/lossy-compression","display_name":"lossy compression","score":0.9860000014305115},{"id":"https://openalex.org/keywords/alphafold","display_name":"AlphaFold","score":0.46299999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6720038652420044},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.39135777950286865},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1542164385318756}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btae428","doi":"https://doi.org/10.1093/bioinformatics/btae428","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae428","pdf_url":null,"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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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":"doi:10.1101/2023.07.20.549913","doi":"https://doi.org/10.1101/2023.07.20.549913","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2023.07.20.549913","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2023/07/22/2023.07.20.549913.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},{"id":"pmh:oai:pubmedcentral.nih.gov:11239224","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11239224","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11239224/pdf/btae428.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,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"Text"},{"id":"pmid:38984796","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38984796","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,"listed_in":[],"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":"Journal Article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btae428","doi":"https://doi.org/10.1093/bioinformatics/btae428","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae428","pdf_url":null,"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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1520548123","display_name":null,"funder_award_id":"02/080/RGJ23/0034","funder_id":"https://openalex.org/F4320324727","funder_display_name":"Silesian University of Technology"},{"id":"https://openalex.org/G1978885471","display_name":null,"funder_award_id":"02/080/RGJ23/0032","funder_id":"https://openalex.org/F4320324727","funder_display_name":"Silesian University of Technology"},{"id":"https://openalex.org/G2558457178","display_name":null,"funder_award_id":"DEC-2022/45/B/ST6/03032","funder_id":"https://openalex.org/F4320322511","funder_display_name":"Narodowe Centrum Nauki"},{"id":"https://openalex.org/G2879583958","display_name":null,"funder_award_id":"DEC-2022/45/B/ST6/03032","funder_id":"https://openalex.org/F4320322650","funder_display_name":"Narodowym Centrum Nauki"}],"funders":[{"id":"https://openalex.org/F4320322511","display_name":"Narodowe Centrum Nauki","ror":"https://ror.org/03ha2q922"},{"id":"https://openalex.org/F4320322650","display_name":"Narodowym Centrum Nauki","ror":"https://ror.org/03ha2q922"},{"id":"https://openalex.org/F4320324727","display_name":"Silesian University of Technology","ror":"https://ror.org/02dyjk442"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400517741.pdf","grobid_xml":"https://content.openalex.org/works/W4400517741.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1489608363","https://openalex.org/W1580101844","https://openalex.org/W2111270835","https://openalex.org/W2130479394","https://openalex.org/W2518435514","https://openalex.org/W2950192635","https://openalex.org/W2971904947","https://openalex.org/W3093323969","https://openalex.org/W3177828909","https://openalex.org/W3211795435","https://openalex.org/W4224303521","https://openalex.org/W4327550249","https://openalex.org/W4360807834","https://openalex.org/W4362515170","https://openalex.org/W4388866605"],"related_works":["https://openalex.org/W4360807834","https://openalex.org/W4388866605","https://openalex.org/W4362515170","https://openalex.org/W4285483966","https://openalex.org/W3211795435","https://openalex.org/W2084520950","https://openalex.org/W4414278761","https://openalex.org/W4388464011","https://openalex.org/W4414651077","https://openalex.org/W7162645658"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,116,190,208],"introduction":[2],"of":[3,12,29,31,51,53,60,96,105,111,131,161,173,177,186,192,201,211],"Deep":[4],"Minds'":[5],"Alpha":[6],"Fold":[7],"2":[8],"enabled":[9],"the":[10,57,94,97,106,108,112,123,139,158,169,174,199,202],"prediction":[11],"protein":[13,113],"structures":[14,32,62],"at":[15,153,163,215],"an":[16],"unprecedented":[17],"scale.":[18],"AlphaFold":[19],"Protein":[20],"Structure":[21],"Database":[22],"and":[23,166,182,194],"ESM":[24],"Metagenomic":[25],"Atlas":[26],"contain":[27],"hundreds":[28],"millions":[30],"stored":[33],"in":[34,63],"CIF":[35],"and/or":[36],"PDB":[37],"formats.":[38],"When":[39],"compressed":[40],"with":[41,126,184],"a":[42,71,86,127,149],"general-purpose":[43],"utility":[44],"like":[45],"gzip,":[46],"this":[47],"translates":[48],"to":[49,74,89,138],"tens":[50],"terabytes":[52],"data,":[54],"which":[55],"hinders":[56],"effective":[58],"use":[59,160],"predicted":[61],"large-scale":[64],"analyses.":[65],"RESULTS:":[66],"Here,":[67],"we":[68],"present":[69],"ProteStAr,":[70],"compressor":[72],"dedicated":[73],"CIF/PDB,":[75],"as":[76,78],"well":[77],"supplementary":[79],"PAE":[80],"files.":[81,115],"Its":[82],"main":[83],"contribution":[84],"is":[85,118,134,213],"novel":[87],"approach":[88,147],"predicting":[90],"atom":[91],"coordinates":[92,132],"on":[93],"basis":[95],"previously":[98],"analyzed":[99],"atoms.":[100],"This":[101],"allows":[102],"efficient":[103,159],"encoding":[104],"coordinates,":[107],"largest":[109],"component":[110],"structure":[114],"compression":[117,151,165],"lossless":[119],"by":[120],"default,":[121],"though":[122],"lossy":[124],"mode":[125],"controlled":[128],"maximum":[129],"error":[130],"reconstruction":[133,155],"also":[135],"present.":[136],"Compared":[137],"competing":[140],"packages,":[141],"i.e.":[142],"BinaryCIF,":[143],"Foldcomp,":[144],"PDC,":[145],"our":[146],"offers":[148],"superior":[150],"ratio":[152],"established":[154],"accuracy.":[156],"By":[157],"threads":[162],"both":[164],"decompression":[167],"stages,":[168],"algorithm":[170],"takes":[171],"advantage":[172],"multicore":[175],"architecture":[176],"current":[178],"central":[179],"processing":[180],"units":[181],"operates":[183],"speeds":[185],"about":[187],"1":[188],"GB/s.":[189],"presence":[191],"Python":[193],"C++":[195],"API":[196],"further":[197],"increases":[198],"usability":[200],"presented":[203],"method.":[204],"AVAILABILITY":[205],"AND":[206],"IMPLEMENTATION:":[207],"source":[209],"code":[210],"ProteStAr":[212],"available":[214],"https://github.com/refresh-bio/protestar.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2024-07-11T00:00:00"}
