{"id":"https://openalex.org/W2126922570","doi":"https://doi.org/10.1109/nabic.2009.5393605","title":"Prosima: Protein similarity algorithm","display_name":"Prosima: Protein similarity algorithm","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2126922570","doi":"https://doi.org/10.1109/nabic.2009.5393605","mag":"2126922570"},"language":"en","primary_location":{"id":"doi:10.1109/nabic.2009.5393605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nabic.2009.5393605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 World Congress on Nature & Biologically Inspired Computing (NaBIC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060467295","display_name":"Tom\u00e1\u0161 Novos\u00e1d","orcid":"https://orcid.org/0000-0003-2291-261X"},"institutions":[{"id":"https://openalex.org/I142208455","display_name":"VSB - Technical University of Ostrava","ror":"https://ror.org/05x8mcb75","country_code":"CZ","type":"education","lineage":["https://openalex.org/I142208455"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Tomas Novosad","raw_affiliation_strings":["Department of Computer Science, V\u0161B Technical University of Ostrava, Ostrava, Czech Republic","Department of Computer Science, V\u00bfB - Technical University of Ostrava, The Czech Republic"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, V\u0161B Technical University of Ostrava, Ostrava, Czech Republic","institution_ids":["https://openalex.org/I142208455"]},{"raw_affiliation_string":"Department of Computer Science, V\u00bfB - Technical University of Ostrava, The Czech Republic","institution_ids":["https://openalex.org/I142208455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011543714","display_name":"V\u00e1clav Sn\u00e5\u0161el","orcid":"https://orcid.org/0000-0002-9600-8319"},"institutions":[{"id":"https://openalex.org/I142208455","display_name":"VSB - Technical University of Ostrava","ror":"https://ror.org/05x8mcb75","country_code":"CZ","type":"education","lineage":["https://openalex.org/I142208455"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Vaclav Snasel","raw_affiliation_strings":["Department of Computer Science, V\u0161B Technical University of Ostrava, Ostrava, Czech Republic","Machine Intelligence Research Labs, MIR Labs, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, V\u0161B Technical University of Ostrava, Ostrava, Czech Republic","institution_ids":["https://openalex.org/I142208455"]},{"raw_affiliation_string":"Machine Intelligence Research Labs, MIR Labs, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087542455","display_name":"Ajith Abraham","orcid":"https://orcid.org/0000-0002-0169-6738"},"institutions":[{"id":"https://openalex.org/I142208455","display_name":"VSB - Technical University of Ostrava","ror":"https://ror.org/05x8mcb75","country_code":"CZ","type":"education","lineage":["https://openalex.org/I142208455"]},{"id":"https://openalex.org/I4210107658","display_name":"Machine Intelligence Research Labs","ror":"https://ror.org/013kgb629","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210107658"]}],"countries":["CZ","US"],"is_corresponding":false,"raw_author_name":"Ajith Abraham","raw_affiliation_strings":["Machine Intelligence Research Laboratories, USA","Department of Computer Science, V\u00bfB - Technical University of Ostrava, The Czech Republic"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Research Laboratories, USA","institution_ids":["https://openalex.org/I4210107658"]},{"raw_affiliation_string":"Department of Computer Science, V\u00bfB - Technical University of Ostrava, The Czech Republic","institution_ids":["https://openalex.org/I142208455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037410384","display_name":"Jack Yang","orcid":"https://orcid.org/0000-0003-3589-6807"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Y Yang","raw_affiliation_strings":["Harvard University, Cambridge, USA","Harvard University, PO Box 400888, Cambridge, Massachusetts 02140-0888, USA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, USA","institution_ids":["https://openalex.org/I2801851002"]},{"raw_affiliation_string":"Harvard University, PO Box 400888, Cambridge, Massachusetts 02140-0888, USA","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5060467295"],"corresponding_institution_ids":["https://openalex.org/I142208455"],"apc_list":null,"apc_paid":null,"fwci":0.4362,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73733035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"84","last_page":"91"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9983000159263611,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9901000261306763,"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/protein-data-bank","display_name":"Protein Data Bank (RCSB PDB)","score":0.7168750762939453},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6600279211997986},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.6115022897720337},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6009650230407715},{"id":"https://openalex.org/keywords/protein-data-bank","display_name":"Protein Data Bank","score":0.5521737337112427},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.5297521352767944},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5219347476959229},{"id":"https://openalex.org/keywords/structural-classification-of-proteins-database","display_name":"Structural Classification of Proteins database","score":0.5033673644065857},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4676826596260071},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.4508195221424103},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.44547465443611145},{"id":"https://openalex.org/keywords/structural-alignment","display_name":"Structural alignment","score":0.4222305417060852},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36887627840042114},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.33729031682014465},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.3089125454425812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29787030816078186},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.17026454210281372},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.0818430483341217}],"concepts":[{"id":"https://openalex.org/C65556437","wikidata":"https://www.wikidata.org/wiki/Q766195","display_name":"Protein Data Bank (RCSB PDB)","level":2,"score":0.7168750762939453},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6600279211997986},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.6115022897720337},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6009650230407715},{"id":"https://openalex.org/C119145174","wikidata":"https://www.wikidata.org/wiki/Q7251429","display_name":"Protein Data Bank","level":3,"score":0.5521737337112427},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.5297521352767944},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5219347476959229},{"id":"https://openalex.org/C58773245","wikidata":"https://www.wikidata.org/wiki/Q4832556","display_name":"Structural Classification of Proteins database","level":3,"score":0.5033673644065857},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4676826596260071},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.4508195221424103},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.44547465443611145},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.4222305417060852},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36887627840042114},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.33729031682014465},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.3089125454425812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29787030816078186},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.17026454210281372},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0818430483341217},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"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},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/nabic.2009.5393605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nabic.2009.5393605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 World Congress on Nature & Biologically Inspired Computing (NaBIC)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.158.7258","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.158.7258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.softcomputing.net/nabic09_5.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W30457518","https://openalex.org/W938539187","https://openalex.org/W1521825230","https://openalex.org/W1532325895","https://openalex.org/W1548843388","https://openalex.org/W1660390307","https://openalex.org/W1978394996","https://openalex.org/W1986152740","https://openalex.org/W1990061958","https://openalex.org/W1995552834","https://openalex.org/W2000982728","https://openalex.org/W2017661493","https://openalex.org/W2022884354","https://openalex.org/W2025330623","https://openalex.org/W2049517479","https://openalex.org/W2059513841","https://openalex.org/W2063634833","https://openalex.org/W2100958137","https://openalex.org/W2104454786","https://openalex.org/W2121252285","https://openalex.org/W2133073361","https://openalex.org/W2133724340","https://openalex.org/W2137763598","https://openalex.org/W2171092071","https://openalex.org/W2533248932","https://openalex.org/W2610179052","https://openalex.org/W4213009331","https://openalex.org/W4251146235","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4220937102","https://openalex.org/W4235583582","https://openalex.org/W4232453105","https://openalex.org/W1997379747","https://openalex.org/W1503558940","https://openalex.org/W2106883599","https://openalex.org/W2058810039","https://openalex.org/W1988384104","https://openalex.org/W2141388583","https://openalex.org/W1975453400"],"abstract_inverted_index":{"In":[0],"this":[1,98,121,154],"article":[2],"we":[3,49,84],"present":[4],"a":[5,51],"novel":[6],"algorithm":[7,23,142],"for":[8,27,136],"measuring":[9],"protein":[10,76,82,162],"similarity":[11,69,83,93],"based":[12,61],"on":[13,62,108],"their":[14],"three":[15],"dimensional":[16],"structure":[17],"(protein":[18],"tertiary":[19],"structure).":[20],"The":[21,95,150],"PROSIMA":[22],"using":[24,86],"suffix":[25],"tress":[26],"discovering":[28],"common":[29,47],"parts":[30,48],"of":[31,33,81,97,111,118,120,138,140,153,165,173],"main-chains":[32],"all":[34,73,75],"proteins":[35,71,166],"appearing":[36],"in":[37,127,169],"current":[38,104],"NCSB":[39],"Protein":[40],"Data":[41],"Bank":[42],"(PDB).":[43],"By":[44],"identifying":[45],"these":[46],"build":[50],"vector":[52,64],"model":[53,65],"and":[54,91],"next":[55,151],"use":[56,101],"classical":[57],"information":[58],"retrieval":[59],"tasks":[60],"the":[63,68,79,102,133,170,174],"to":[66,74,100,157,160],"measure":[67],"between":[70],"-":[72],"similarity.":[77],"For":[78],"calculation":[80],"are":[85],"tf-idf":[87],"term":[88],"weighing":[89],"schema":[90],"cosine":[92],"measure.":[94],"goal":[96],"work":[99,155],"whole":[103],"PDB":[105],"database":[106,135,176],"(downloaded":[107],"June":[109],"2009)":[110],"known":[112],"proteins,":[113],"not":[114,167],"just":[115],"some":[116],"kinds":[117],"selections":[119],"database,":[122],"which":[123],"have":[124,131],"been":[125],"studied":[126],"other":[128],"works.":[129],"We":[130],"chose":[132],"SCOP":[134,163,175],"verification":[137],"precision":[139],"our":[141],"because":[143],"it":[144],"is":[145,156],"maintained":[146],"primarily":[147],"by":[148],"humans.":[149],"success":[152],"be":[158],"able":[159],"determine":[161],"categories":[164],"included":[168],"latest":[171],"version":[172],"(v.":[177],"1.75)":[178],"with":[179],"nearly":[180],"100%":[181],"precision.":[182]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}