{"id":"https://openalex.org/W2057859760","doi":"https://doi.org/10.1142/s0219720009004436","title":"SIRIUS PSB: A GENERIC SYSTEM FOR ANALYSIS OF BIOLOGICAL SEQUENCES","display_name":"SIRIUS PSB: A GENERIC SYSTEM FOR ANALYSIS OF BIOLOGICAL SEQUENCES","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2057859760","doi":"https://doi.org/10.1142/s0219720009004436","mag":"2057859760","pmid":"https://pubmed.ncbi.nlm.nih.gov/20014474"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720009004436","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720009004436","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5012980019","display_name":"Chuan Hock Koh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126319","display_name":"Duke-NUS Medical School","ror":"https://ror.org/02j1m6098","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596","https://openalex.org/I170897317","https://openalex.org/I4210126319"]},{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"CHUAN HOCK KOH","raw_affiliation_strings":["NUS Graduate School for Integrative Sciences and Engineering, 117597, Singapore","School of Computing, National University of Singapore, COM1, Computing Drive, 117417, Singapore"],"affiliations":[{"raw_affiliation_string":"NUS Graduate School for Integrative Sciences and Engineering, 117597, Singapore","institution_ids":["https://openalex.org/I4210126319"]},{"raw_affiliation_string":"School of Computing, National University of Singapore, COM1, Computing Drive, 117417, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006671887","display_name":"SHARENE LIN","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"SHARENE LIN","raw_affiliation_strings":["School of Computing, National University of Singapore, COM1, Computing Drive, 117417, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, COM1, Computing Drive, 117417, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050256110","display_name":"Gregory Jedd","orcid":"https://orcid.org/0000-0002-5428-3873"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I162266279","display_name":"Temasek Life Sciences Laboratory","ror":"https://ror.org/0574eex11","country_code":"SG","type":"facility","lineage":["https://openalex.org/I162266279"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"GREGORY JEDD","raw_affiliation_strings":["Temasek Life Sciences Laboratory and Department of Biological Sciences, National University of Singapore, 117604, Singapore"],"affiliations":[{"raw_affiliation_string":"Temasek Life Sciences Laboratory and Department of Biological Sciences, National University of Singapore, 117604, Singapore","institution_ids":["https://openalex.org/I162266279","https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012381970","display_name":"Limsoon Wong","orcid":"https://orcid.org/0000-0003-1241-5441"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"LIMSOON WONG","raw_affiliation_strings":["School of Computing, National University of Singapore, COM1, Computing Drive, 117417, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, COM1, Computing Drive, 117417, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012980019"],"corresponding_institution_ids":["https://openalex.org/I165932596","https://openalex.org/I4210126319"],"apc_list":null,"apc_paid":null,"fwci":0.5392,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66408576,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"07","issue":"06","first_page":"973","last_page":"990"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.9969000220298767,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.9969000220298767,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9968000054359436,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9961000084877014,"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/sirius","display_name":"Sirius","score":0.8619440793991089},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.5064347982406616},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.41420358419418335},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3120362162590027},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07866278290748596}],"concepts":[{"id":"https://openalex.org/C2778323849","wikidata":"https://www.wikidata.org/wiki/Q3409","display_name":"Sirius","level":3,"score":0.8619440793991089},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5064347982406616},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.41420358419418335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3120362162590027},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07866278290748596},{"id":"https://openalex.org/C150846664","wikidata":"https://www.wikidata.org/wiki/Q7602306","display_name":"Stars","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","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":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","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":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","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":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1142/s0219720009004436","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720009004436","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},{"id":"pmid:20014474","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20014474","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":"Journal of bioinformatics and computational biology","raw_type":null},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/39879","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/39879","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.150.6432","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.150.6432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.comp.nus.edu.sg/~wongls/psZ/sirius-psb-09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.46000000834465027}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309370","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10"},{"id":"https://openalex.org/F4320320698","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320324587","display_name":"Singapore Millennium Foundation","ror":"https://ror.org/024p43m36"},{"id":"https://openalex.org/F4320325677","display_name":"Science for Life Laboratory","ror":"https://ror.org/04ev03g22"},{"id":"https://openalex.org/F4320326604","display_name":"Temasek Life Sciences Laboratory","ror":"https://ror.org/0574eex11"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1541321639","https://openalex.org/W1570448133","https://openalex.org/W1588920293","https://openalex.org/W1976526581","https://openalex.org/W2001648291","https://openalex.org/W2021385006","https://openalex.org/W2023096047","https://openalex.org/W2044336462","https://openalex.org/W2054880642","https://openalex.org/W2097330469","https://openalex.org/W2100276623","https://openalex.org/W2105545925","https://openalex.org/W2119821739","https://openalex.org/W2136546099","https://openalex.org/W2144472358","https://openalex.org/W2152458080","https://openalex.org/W2160973386","https://openalex.org/W2162916842","https://openalex.org/W2163900914","https://openalex.org/W2966207845"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2575675105","https://openalex.org/W2026134093","https://openalex.org/W2505490189","https://openalex.org/W2115560134","https://openalex.org/W2026645820","https://openalex.org/W3002684532","https://openalex.org/W4246792497","https://openalex.org/W2290729595","https://openalex.org/W2739841954"],"abstract_inverted_index":{"Computational":[0],"tools":[1],"are":[2,195,260],"essential":[3],"components":[4],"of":[5,145,149,167,181,191,204,224],"modern":[6],"biological":[7],"research.":[8],"For":[9],"example,":[10],"BLAST":[11,235],"searches":[12],"can":[13,33,244],"be":[14,34],"used":[15,35,134],"to":[16,36,52,93,135,214,238],"identify":[17,136,245],"related":[18,240,247,258],"proteins":[19,91,153,248],"based":[20,201,249],"on":[21,202,250],"sequence":[22,69,128,155],"homology,":[23],"or":[24],"when":[25,234],"a":[26,64,82,86,108,117],"new":[27,65],"genome":[28],"is":[29,133,218,236],"sequenced,":[30],"prediction":[31,174],"models":[32,175,200],"annotate":[37],"functional":[38],"sites":[39,47,50,184],"such":[40],"as":[41],"transcription":[42],"start":[43],"sites,":[44],"translation":[45],"initiation":[46],"and":[48,51,72,98,110,185,211,256],"polyadenylation":[49,183],"predict":[53],"protein":[54],"localization.":[55],"Here":[56],"we":[57,157,170,228],"present":[58],"Sirius":[59,74,101,120,168,225,242,254],"Prediction":[60],"Systems":[61],"Builder":[62],"(PSB),":[63],"computational":[66],"tool":[67],"for":[68,90,151,178,187],"analysis,":[70],"classification":[71],"searching.":[73],"PSB":[75,102,121,243,255],"has":[76,122],"four":[77],"main":[78],"operations:":[79],"(1)":[80],"Building":[81],"classifier,":[83,87],"(2)":[84],"Deploying":[85],"(3)":[88],"Search":[89],"similar":[92,152],"query":[94],"proteins,":[95,241],"(4)":[96],"Preliminary":[97],"post-prediction":[99],"analysis.":[100,129],"supports":[103],"all":[104],"these":[105],"operations":[106],"via":[107,154,160],"simple":[109],"interactive":[111],"graphical":[112],"user":[113],"interface.":[114],"Besides":[115],"being":[116],"convenient":[118],"tool,":[119],"also":[123],"introduced":[124,158],"two":[125,173],"novelties":[126],"in":[127,139],"Firstly,":[130],"genetic":[131],"algorithm":[132],"interesting":[137],"features":[138],"the":[140,146,165,179,188,209,222],"feature":[141],"space.":[142],"Secondly,":[143],"instead":[144],"conventional":[147],"method":[148],"searching":[150,159],"similarity,":[156],"features'":[161],"similarity.":[162],"To":[163],"demonstrate":[164],"capabilities":[166],"PSB,":[169],"have":[171],"built":[172],"-":[176],"one":[177],"recognition":[180],"Arabidopsis":[182],"another":[186],"subcellular":[189],"localization":[190],"proteins.":[192],"Both":[193],"systems":[194],"competitive":[196],"against":[197],"current":[198],"state-of-the-art":[199],"evaluation":[203],"public":[205],"datasets.":[206],"More":[207],"notably,":[208],"time":[210],"effort":[212],"required":[213],"build":[215],"each":[216],"model":[217],"greatly":[219],"reduced":[220],"with":[221],"assistance":[223],"PSB.":[226],"Furthermore,":[227],"show":[229],"that":[230],"under":[231],"certain":[232],"conditions":[233],"unable":[237],"find":[239],"functionally":[246],"their":[251],"biophysical":[252],"similarities.":[253],"its":[257],"supplements":[259],"available":[261],"at:":[262],"http://compbio.ddns.comp.nus.edu.sg/~sirius.":[263]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
