{"id":"https://openalex.org/W4240404008","doi":"https://doi.org/10.1186/s12859-015-0625-x","title":"Evaluation of BLAST-based edge-weighting metrics used for homology inference with the Markov Clustering algorithm","display_name":"Evaluation of BLAST-based edge-weighting metrics used for homology inference with the Markov Clustering algorithm","publication_year":2015,"publication_date":"2015-07-09","ids":{"openalex":"https://openalex.org/W4240404008","doi":"https://doi.org/10.1186/s12859-015-0625-x","pmid":"https://pubmed.ncbi.nlm.nih.gov/26160651"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-015-0625-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-015-0625-x","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-015-0625-x","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-015-0625-x","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046038978","display_name":"Theodore Gibbons","orcid":null},"institutions":[{"id":"https://openalex.org/I126744593","display_name":"University of Maryland, Baltimore","ror":"https://ror.org/04rq5mt64","country_code":"US","type":"education","lineage":["https://openalex.org/I126744593"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Theodore R. Gibbons","raw_affiliation_strings":["Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, Baltimore, 20742, Maryland. trgibbons@gmail.com","Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, Baltimore, Maryland, 20742, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, Baltimore, 20742, Maryland. trgibbons@gmail.com","institution_ids":["https://openalex.org/I126744593","https://openalex.org/I66946132"]},{"raw_affiliation_string":"Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, Baltimore, Maryland, 20742, USA","institution_ids":["https://openalex.org/I126744593","https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040594310","display_name":"Stephen M. Mount","orcid":"https://orcid.org/0000-0003-2748-8205"},"institutions":[{"id":"https://openalex.org/I126744593","display_name":"University of Maryland, Baltimore","ror":"https://ror.org/04rq5mt64","country_code":"US","type":"education","lineage":["https://openalex.org/I126744593"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen M. Mount","raw_affiliation_strings":["Center for Bioinformatics and Computational Biology, University of Maryland, College Park, Baltimore, 20742, Maryland. smount@umd.edu","Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, Baltimore, 20742, Maryland. smount@umd.edu","Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, Baltimore, Maryland, 20742, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Bioinformatics and Computational Biology, University of Maryland, College Park, Baltimore, 20742, Maryland. smount@umd.edu","institution_ids":["https://openalex.org/I126744593","https://openalex.org/I66946132"]},{"raw_affiliation_string":"Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, Baltimore, 20742, Maryland. smount@umd.edu","institution_ids":["https://openalex.org/I126744593","https://openalex.org/I66946132"]},{"raw_affiliation_string":"Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, Baltimore, Maryland, 20742, USA","institution_ids":["https://openalex.org/I126744593","https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035852115","display_name":"Endymion D. Cooper","orcid":"https://orcid.org/0000-0002-6186-5628"},"institutions":[{"id":"https://openalex.org/I126744593","display_name":"University of Maryland, Baltimore","ror":"https://ror.org/04rq5mt64","country_code":"US","type":"education","lineage":["https://openalex.org/I126744593"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Endymion D. Cooper","raw_affiliation_strings":["Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, Baltimore, 20742, Maryland. endymion.dante.cooper@gmail.com","Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, Baltimore, Maryland, 20742, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, Baltimore, 20742, Maryland. endymion.dante.cooper@gmail.com","institution_ids":["https://openalex.org/I126744593","https://openalex.org/I66946132"]},{"raw_affiliation_string":"Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, Baltimore, Maryland, 20742, USA","institution_ids":["https://openalex.org/I126744593","https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032751148","display_name":"Charles F. Delwiche","orcid":"https://orcid.org/0000-0001-7854-8584"},"institutions":[{"id":"https://openalex.org/I126744593","display_name":"University of Maryland, Baltimore","ror":"https://ror.org/04rq5mt64","country_code":"US","type":"education","lineage":["https://openalex.org/I126744593"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles F. Delwiche","raw_affiliation_strings":["Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, Baltimore, 20742, Maryland. delwiche@umd.edu","Maryland Agricultural Experiment Station, University of Maryland, College Park, Baltimore, 20742, Maryland. delwiche@umd.edu","Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, Baltimore, Maryland, 20742, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, Baltimore, 20742, Maryland. delwiche@umd.edu","institution_ids":["https://openalex.org/I126744593","https://openalex.org/I66946132"]},{"raw_affiliation_string":"Maryland Agricultural Experiment Station, University of Maryland, College Park, Baltimore, 20742, Maryland. delwiche@umd.edu","institution_ids":["https://openalex.org/I126744593","https://openalex.org/I66946132"]},{"raw_affiliation_string":"Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, Baltimore, Maryland, 20742, USA","institution_ids":["https://openalex.org/I126744593","https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046038978"],"corresponding_institution_ids":["https://openalex.org/I126744593","https://openalex.org/I66946132"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.9641,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.75639062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"16","issue":"1","first_page":"218","last_page":"218"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.3767000138759613,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.3767000138759613,"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.24449999630451202,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.06759999692440033,"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/weighting","display_name":"Weighting","score":0.6973434686660767},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6486174464225769},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5647348165512085},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4886017441749573},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47639980912208557},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.44966283440589905},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.42827239632606506},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42809563875198364},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4195803701877594},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.4175295829772949},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.39275118708610535},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2773846983909607},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1561860740184784}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6973434686660767},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6486174464225769},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5647348165512085},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4886017441749573},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47639980912208557},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.44966283440589905},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.42827239632606506},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42809563875198364},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4195803701877594},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.4175295829772949},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39275118708610535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2773846983909607},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1561860740184784},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","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":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","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":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":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","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":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-015-0625-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-015-0625-x","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-015-0625-x","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:26160651","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26160651","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:europepmc.org:3461202","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4496851","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"doi:10.13016/miwn-l7oi","is_oa":true,"landing_page_url":"https://doi.org/10.13016/miwn-l7oi","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1186/s12859-015-0625-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-015-0625-x","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-015-0625-x","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1015071479","display_name":"AToL: An Integrated Approach to the Phylogeny of Dinoflagellates","funder_award_id":"0629624","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1573554175","display_name":null,"funder_award_id":"T32 GM080201","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G1758678981","display_name":"Collaborative Research: Assembling the Green Algal Tree of Life (GRAToL)","funder_award_id":"1036506","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3657636347","display_name":"Dimensions: Collaborative Research: Can Evolutionary History Predict How Changes in Biodiversity Impact the Productivity of Ecosystems?","funder_award_id":"1046075","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6448281680","display_name":null,"funder_award_id":"GM080201","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8697301740","display_name":null,"funder_award_id":"T32 GM080201","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4240404008.pdf","grobid_xml":"https://content.openalex.org/works/W4240404008.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494075612","https://openalex.org/W1529607257","https://openalex.org/W1970392534","https://openalex.org/W1990453950","https://openalex.org/W2008856488","https://openalex.org/W2010562878","https://openalex.org/W2055043387","https://openalex.org/W2059123697","https://openalex.org/W2101786683","https://openalex.org/W2109750550","https://openalex.org/W2110318653","https://openalex.org/W2110467356","https://openalex.org/W2110734043","https://openalex.org/W2116402707","https://openalex.org/W2117936709","https://openalex.org/W2124166542","https://openalex.org/W2126763121","https://openalex.org/W2141652419","https://openalex.org/W2142678478","https://openalex.org/W2143335572","https://openalex.org/W2145100181","https://openalex.org/W2153283265","https://openalex.org/W2155142785","https://openalex.org/W2155606054","https://openalex.org/W2156995961","https://openalex.org/W2159675211","https://openalex.org/W2161855013","https://openalex.org/W2167188257","https://openalex.org/W2168909179","https://openalex.org/W2170258388","https://openalex.org/W4230501579","https://openalex.org/W6638681203"],"related_works":["https://openalex.org/W2162899405","https://openalex.org/W3113091479","https://openalex.org/W941090075","https://openalex.org/W2044987316","https://openalex.org/W3134374554","https://openalex.org/W2237480245","https://openalex.org/W2519167559","https://openalex.org/W2075065631","https://openalex.org/W4288358396","https://openalex.org/W3121164913"],"abstract_inverted_index":{"BACKGROUND:":[0],"Clustering":[1,26],"protein":[2],"sequences":[3,50,171,338],"according":[4],"to":[5,54,68,276,282],"inferred":[6],"homology":[7],"is":[8,65,138],"a":[9,61,265,297,325,341,347],"fundamental":[10],"step":[11],"in":[12,29,216,258,339],"the":[13,21,24,34,87,98,108,115,133,141,169,197,203,214,226,236,240,245,254,271,283,333],"analysis":[14],"of":[15,23,36,41,71,97,101,110,132,168,183,189,205,270,349],"many":[16],"large":[17],"data":[18],"sets.":[19],"Since":[20],"publication":[22],"Markov":[25],"(MCL)":[27],"algorithm":[28],"2002,":[30],"it":[31],"has":[32,91],"been":[33,92],"centerpiece":[35],"several":[37],"popular":[38,242,285],"applications.":[39],"Each":[40],"these":[42,76,231],"approaches":[43,80],"generates":[44],"an":[45],"undirected":[46],"graph":[47,326],"that":[48,289],"represents":[49],"as":[51,164,249],"nodes":[52],"connected":[53],"each":[55],"other":[56,255],"by":[57,74,83,185,224],"edges":[58,331],"weighted":[59],"with":[60,310,327],"BLAST-based":[62,112],"metric.":[63],"MCL":[64,227],"then":[66],"used":[67],"infer":[69],"clusters":[70,184],"homologous":[72],"proteins":[73],"analyzing":[75,157],"graphs.":[77],"The":[78,176,262,287],"various":[79],"differ":[81],"only":[82,319],"how":[84],"they":[85],"weight":[86],"edges,":[88],"yet":[89],"there":[90],"very":[93],"little":[94],"direct":[95],"examination":[96],"relative":[99],"performance":[100,109,281],"alternative":[102],"edge-weighting":[103,113,300],"metrics.":[104],"This":[105,211],"study":[106],"compares":[107],"four":[111],"metrics:":[114],"bit":[116,118,122,237,246,272],"score,":[117,273],"score":[119,123,238,247],"ratio":[120],"(BSR),":[121],"over":[124],"anchored":[125],"length":[126],"(BAL),":[127],"and":[128,178,220,322],"negative":[129],"common":[130],"log":[131],"expectation":[134],"value":[135],"(NLE).":[136],"Performance":[137],"tested":[139],"using":[140,296,343],"Extended":[142],"CEGMA":[143],"KOGs":[144],"(ECK)":[145],"database,":[146],"which":[147,274,317],"we":[148],"introduce":[149],"here.":[150],"RESULTS:":[151],"All":[152],"metrics":[153,232,257],"performed":[154,248],"similarly":[155],"when":[156],"full-length":[158],"sequences,":[159,193],"but":[160,194],"dramatic":[161],"differences":[162],"emerged":[163],"progressively":[165],"larger":[166],"fractions":[167],"test":[170,218],"were":[172],"split":[173],"into":[174],"fragments.":[175],"BSR":[177],"BAL":[179],"successfully":[180],"rescued":[181],"subsets":[182],"strengthening":[186],"certain":[187],"types":[188],"alignments":[190],"between":[191],"fragmented":[192],"also":[195],"shifted":[196],"largest":[198],"correct":[199],"scores":[200,206],"down":[201],"near":[202],"range":[204],"generated":[207],"from":[208],"spurious":[209],"alignments.":[210],"penalty":[212],"outweighed":[213],"benefits":[215],"most":[217],"cases,":[219],"was":[221],"greatly":[222,303],"exacerbated":[223],"increasing":[225],"inflation":[228],"parameter,":[229],"making":[230],"less":[233,344],"robust":[234],"than":[235,253,345],"or":[239,251,279],"more":[241,284,298],"NLE.":[243,286],"Notably,":[244],"well":[250],"better":[252],"three":[256],"all":[259],"scenarios.":[260],"CONCLUSIONS:":[261],"results":[263],"provide":[264],"strong":[266],"case":[267],"for":[268],"use":[269],"appears":[275],"offer":[277],"equivalent":[278],"superior":[280],"insight":[288],"MCL-based":[290],"clustering":[291],"methods":[292],"can":[293,323],"be":[294],"improved":[295],"tractable":[299],"metric":[301],"will":[302],"simplify":[304],"future":[305],"implementations.":[306],"We":[307],"demonstrate":[308],"this":[309],"our":[311],"own":[312],"minimalist":[313],"Python":[314],"implementation:":[315],"Porthos,":[316],"uses":[318],"standard":[320],"libraries":[321],"process":[324],"25":[328],"m":[329],"+":[330,336],"connecting":[332],"60":[334],"k":[335],"KOG":[337],"half":[340,346],"minute":[342],"gigabyte":[348],"memory.":[350]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}