{"id":"https://openalex.org/W2962631801","doi":"https://doi.org/10.1093/bioinformatics/btz368","title":"Statistical compression of protein sequences and inference of marginal probability landscapes over competing alignments using finite state models and Dirichlet priors","display_name":"Statistical compression of protein sequences and inference of marginal probability landscapes over competing alignments using finite state models and Dirichlet priors","publication_year":2019,"publication_date":"2019-05-10","ids":{"openalex":"https://openalex.org/W2962631801","doi":"https://doi.org/10.1093/bioinformatics/btz368","mag":"2962631801","pmid":"https://pubmed.ncbi.nlm.nih.gov/31510703"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btz368","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz368","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/14/i360/28913693/btz368.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":null,"license_id":null,"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":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/35/14/i360/28913693/btz368.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019059813","display_name":"Dinithi Sumanaweera","orcid":"https://orcid.org/0000-0003-4515-0988"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dinithi Sumanaweera","raw_affiliation_strings":["Faculty of Information Technology, Monash University, Clayton, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Monash University, Clayton, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065385022","display_name":"Lloyd Allison","orcid":"https://orcid.org/0000-0002-9020-3164"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Lloyd Allison","raw_affiliation_strings":["Faculty of Information Technology, Monash University, Clayton, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Monash University, Clayton, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081792355","display_name":"Arun S. Konagurthu","orcid":"https://orcid.org/0000-0002-1610-8329"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Arun S Konagurthu","raw_affiliation_strings":["Faculty of Information Technology, Monash University, Clayton, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Monash University, Clayton, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065385022","https://openalex.org/A5081792355"],"corresponding_institution_ids":["https://openalex.org/I56590836"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.4294,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.62253124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"35","issue":"14","first_page":"i360","last_page":"i369"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998000264167786,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998000264167786,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9934999942779541,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9929999709129333,"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/computer-science","display_name":"Computer science","score":0.7127385139465332},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6420746445655823},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5323814153671265},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.5129287242889404},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5032770037651062},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.48567330837249756},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.47142475843429565},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4484095275402069},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4363164007663727},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.41225284337997437},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3274523913860321},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.30671459436416626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2936772108078003},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.2709367871284485},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1993667483329773},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.12555667757987976}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7127385139465332},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6420746445655823},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5323814153671265},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.5129287242889404},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5032770037651062},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.48567330837249756},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.47142475843429565},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4484095275402069},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4363164007663727},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.41225284337997437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3274523913860321},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30671459436416626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2936772108078003},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2709367871284485},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1993667483329773},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.12555667757987976},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[{"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":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","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":false},{"descriptor_ui":"D012984","descriptor_name":"Software","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":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btz368","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz368","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/14/i360/28913693/btz368.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:31510703","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31510703","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:monash.edu:publications/fd746787-001e-41fe-8c8c-c3957a5a679b","is_oa":true,"landing_page_url":"https://research.monash.edu/en/publications/fd746787-001e-41fe-8c8c-c3957a5a679b","pdf_url":null,"source":{"id":"https://openalex.org/S4306402625","display_name":"Monash University Research Portal (Monash University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I56590836","host_organization_name":"Monash University","host_organization_lineage":["https://openalex.org/I56590836"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sumanaweera , D , Allison , L &amp; Konagurthu , A 2019 , ' Statistical compression of protein sequences and inference of marginal probability landscapes over competing alignments using finite state models and Dirichlet priors ' , Bioinformatics , vol. 35 , no. 14 , btz368 , pp. i360-i369 . https://doi.org/10.1093/bioinformatics/btz368","raw_type":"article"},{"id":"pmh:oai:europepmc.org:5588670","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6612809","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btz368","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz368","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/14/i360/28913693/btz368.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G230780840","display_name":null,"funder_award_id":"DP150100894","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962631801.pdf","grobid_xml":"https://content.openalex.org/works/W2962631801.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W170307911","https://openalex.org/W1500214331","https://openalex.org/W1518146300","https://openalex.org/W1518339893","https://openalex.org/W1534506107","https://openalex.org/W1584305148","https://openalex.org/W1590240800","https://openalex.org/W1864487875","https://openalex.org/W1963866954","https://openalex.org/W1964145490","https://openalex.org/W1995875735","https://openalex.org/W1999905104","https://openalex.org/W2004575181","https://openalex.org/W2009570821","https://openalex.org/W2014660704","https://openalex.org/W2014753445","https://openalex.org/W2017777683","https://openalex.org/W2018140810","https://openalex.org/W2019572077","https://openalex.org/W2085277871","https://openalex.org/W2110381504","https://openalex.org/W2116153836","https://openalex.org/W2119511059","https://openalex.org/W2132926880","https://openalex.org/W2137015675","https://openalex.org/W2140872496","https://openalex.org/W2143210482","https://openalex.org/W2143292980","https://openalex.org/W2144362290","https://openalex.org/W2154139219","https://openalex.org/W2157451851","https://openalex.org/W2160378127","https://openalex.org/W2196315986","https://openalex.org/W2201551179","https://openalex.org/W2409138684","https://openalex.org/W2600349519","https://openalex.org/W2601913882","https://openalex.org/W2800631698","https://openalex.org/W2883829347","https://openalex.org/W2890938948","https://openalex.org/W4210702584","https://openalex.org/W4231440644","https://openalex.org/W4245668478","https://openalex.org/W4255049408","https://openalex.org/W4255598207","https://openalex.org/W4386771068","https://openalex.org/W6655297870"],"related_works":["https://openalex.org/W2891616219","https://openalex.org/W2796920963","https://openalex.org/W2064483411","https://openalex.org/W2086004744","https://openalex.org/W2017516907","https://openalex.org/W2952919399","https://openalex.org/W2150149003","https://openalex.org/W3204672119","https://openalex.org/W119193395","https://openalex.org/W2167421762"],"abstract_inverted_index":{"Supplementary":[0],"data":[1],"are":[2],"available":[3],"at":[4],"Bioinformatics":[5],"online.":[6]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
