{"id":"https://openalex.org/W2605412425","doi":"https://doi.org/10.1186/s13015-017-0102-3","title":"Core column prediction for protein multiple sequence alignments","display_name":"Core column prediction for protein multiple sequence alignments","publication_year":2017,"publication_date":"2017-04-19","ids":{"openalex":"https://openalex.org/W2605412425","doi":"https://doi.org/10.1186/s13015-017-0102-3","mag":"2605412425","pmid":"https://pubmed.ncbi.nlm.nih.gov/28435440"},"language":"en","primary_location":{"id":"doi:10.1186/s13015-017-0102-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-017-0102-3","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/s13015-017-0102-3","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"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":"Algorithms for Molecular Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/s13015-017-0102-3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014004628","display_name":"Dan DeBlasio","orcid":"https://orcid.org/0000-0003-4110-4431"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dan DeBlasio","raw_affiliation_strings":["Computational Biology Department, Carnegie Mellon University, Pittsburgh, PA 15213 USA","Department of Computer Science, The University of Arizona, Tucson, AZ 85721 USA","Department of Computer Science, The University of Arizona, Tucson, AZ, 85721, USA"],"raw_orcid":"https://orcid.org/0000-0003-4110-4431","affiliations":[{"raw_affiliation_string":"Computational Biology Department, Carnegie Mellon University, Pittsburgh, PA 15213 USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Department of Computer Science, The University of Arizona, Tucson, AZ 85721 USA","institution_ids":["https://openalex.org/I138006243"]},{"raw_affiliation_string":"Department of Computer Science, The University of Arizona, Tucson, AZ, 85721, USA","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083998316","display_name":"John Kececioglu","orcid":"https://orcid.org/0000-0003-1204-6535"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Kececioglu","raw_affiliation_strings":["Department of Computer Science, The University of Arizona, Tucson, AZ 85721 USA","Department of Computer Science, The University of Arizona, Tucson, AZ, 85721, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Arizona, Tucson, AZ 85721 USA","institution_ids":["https://openalex.org/I138006243"]},{"raw_affiliation_string":"Department of Computer Science, The University of Arizona, Tucson, AZ, 85721, USA","institution_ids":["https://openalex.org/I138006243"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5014004628"],"corresponding_institution_ids":["https://openalex.org/I138006243","https://openalex.org/I74973139"],"apc_list":{"value":1490,"currency":"GBP","value_usd":1827},"apc_paid":{"value":1490,"currency":"GBP","value_usd":1827},"fwci":0.1122,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49507354,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"12","issue":"1","first_page":"11","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9984999895095825,"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/T10602","display_name":"Glycosylation and Glycoproteins Research","score":0.9976000189781189,"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/column","display_name":"Column (typography)","score":0.6646232008934021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6614128351211548},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.6261221170425415},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5361933708190918},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4986405372619629},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3296426832675934},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1329006850719452},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.06875842809677124},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.06817123293876648}],"concepts":[{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.6646232008934021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6614128351211548},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.6261221170425415},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5361933708190918},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4986405372619629},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3296426832675934},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1329006850719452},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.06875842809677124},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.06817123293876648},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13015-017-0102-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-017-0102-3","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/s13015-017-0102-3","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"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":"Algorithms for Molecular Biology","raw_type":"journal-article"},{"id":"pmid:28435440","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28435440","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":"Algorithms for molecular biology : AMB","raw_type":null},{"id":"pmh:oai:repository.arizona.edu:10150/623957","is_oa":true,"landing_page_url":"http://hdl.handle.net/10150/623957","pdf_url":null,"source":{"id":"https://openalex.org/S4306400271","display_name":"UA Campus Repository (The University of Arizona)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138006243","host_organization_name":"University of Arizona","host_organization_lineage":["https://openalex.org/I138006243"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:doaj.org/article:76f852add7e241a29b363ca308c4368d","is_oa":true,"landing_page_url":"https://doaj.org/article/76f852add7e241a29b363ca308c4368d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms for Molecular Biology, Vol 12, Iss 1, Pp 1-16 (2017)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:5397798","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5397798","pdf_url":null,"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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms Mol Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13015-017-0102-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-017-0102-3","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/s13015-017-0102-3","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"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":"Algorithms for Molecular Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1325684988","display_name":null,"funder_award_id":"CCF-1256087","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2375335175","display_name":null,"funder_award_id":"IIS-1217886","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3062111663","display_name":"III: Small: Parameter Inference and Parameter Advising in Computational Biology","funder_award_id":"1217886","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3068176952","display_name":null,"funder_award_id":"R01HG007104","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3355402586","display_name":"Carl Kingsford Investigator Award","funder_award_id":"GBMF4554","funder_id":"https://openalex.org/F4320306202","funder_display_name":"Gordon and Betty Moore Foundation"},{"id":"https://openalex.org/G3641969089","display_name":"CAREER: Model-based Reconstruction of Ancient Biological Networks","funder_award_id":"1256087","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7981293496","display_name":null,"funder_award_id":"IIS-1217886","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306202","display_name":"Gordon and Betty Moore Foundation","ror":"https://ror.org/006wxqw41"},{"id":"https://openalex.org/F4320310160","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45"},{"id":"https://openalex.org/F4320310207","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2605412425.pdf","grobid_xml":"https://content.openalex.org/works/W2605412425.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W171034855","https://openalex.org/W1519266993","https://openalex.org/W1963957860","https://openalex.org/W1993414412","https://openalex.org/W2007924998","https://openalex.org/W2009570821","https://openalex.org/W2021883973","https://openalex.org/W2035594133","https://openalex.org/W2074830661","https://openalex.org/W2075451741","https://openalex.org/W2102502076","https://openalex.org/W2106053110","https://openalex.org/W2110919845","https://openalex.org/W2114320077","https://openalex.org/W2114616367","https://openalex.org/W2115888213","https://openalex.org/W2127322768","https://openalex.org/W2127556561","https://openalex.org/W2130625618","https://openalex.org/W2133296809","https://openalex.org/W2140890018","https://openalex.org/W2143210482","https://openalex.org/W2146712012","https://openalex.org/W2149956330","https://openalex.org/W2153187042","https://openalex.org/W2154952425","https://openalex.org/W2493400422","https://openalex.org/W2523931589","https://openalex.org/W2776985701","https://openalex.org/W4245668478","https://openalex.org/W4285719527","https://openalex.org/W4300568064"],"related_works":["https://openalex.org/W2181722423","https://openalex.org/W2347222412","https://openalex.org/W2085601491","https://openalex.org/W2375996887","https://openalex.org/W4322723290","https://openalex.org/W2368976073","https://openalex.org/W2376548177","https://openalex.org/W2808994565","https://openalex.org/W2769449614","https://openalex.org/W1956179383"],"abstract_inverted_index":{"In":[0,32],"a":[1,10,82,92,114,136,154,185,189,200,206,233,238,261],"computed":[2,90,155],"protein":[3,36,83,142],"multiple":[4,84,143],"sequence":[5,85,144],"alignment,":[6],"the":[7,13,25,39,43,61,67,71,76,79,100,104,121,133,163,220,257],"coreness":[8,122,140,170,186,214],"of":[9,15,24,29,35,42,70,75,81,103,123,138,153,222,237,241],"column":[11,62,139],"is":[12,94,117,171],"fraction":[14],"its":[16,30,124],"substitutions":[17],"that":[18,48,87,204,245],"are":[19,46,157],"in":[20,60,66,111,264],"so-called":[21],"core":[22,40,101],"columns":[23,41,102,125,152],"gold-standard":[26],"reference":[27,37,44,105,115],"alignment":[28,45,86,110,116,156,236,265],"proteins.":[31,77],"benchmark":[33,93],"suites":[34],"alignments,":[38],"those":[47],"can":[49,126],"be":[50,128],"confidently":[51],"labeled":[52],"as":[53],"correct,":[54],"usually":[55],"due":[56],"to":[57,99,149,168,173,216,231],"all":[58],"residues":[59],"being":[63],"sufficiently":[64],"close":[65],"spatial":[68],"superposition":[69],"known":[72],"three-dimensional":[73],"structures":[74],"Typically":[78],"accuracy":[80],"has":[88],"been":[89],"for":[91,132,141,226,246],"only":[95,127],"measured":[96],"with":[97],"respect":[98],"alignment.":[106],"When":[107],"computing":[108],"an":[109,195,227],"practice,":[112],"however,":[113],"not":[118],"known,":[119],"so":[120],"predicted.":[129],"We":[130,211,243],"develop":[131],"first":[134],"time":[135],"predictor":[137,215,250],"alignments.":[145],"This":[146],"allows":[147],"us":[148],"predict":[150],"which":[151],"core,":[158],"and":[159,192,259],"hence":[160],"better":[161],"estimate":[162],"alignment\u2019s":[164],"accuracy.":[165,266],"Our":[166],"approach":[167],"predicting":[169],"similar":[172],"nearest-neighbor":[174,182],"classification":[175],"from":[176,256],"machine":[177],"learning,":[178],"except":[179],"we":[180,193],"transform":[181],"distances":[183],"into":[184],"prediction":[187],"via":[188],"regression":[190],"function,":[191],"learn":[194],"appropriate":[196],"distance":[197],"function":[198,230],"through":[199],"new":[201],"optimization":[202],"formulation":[203],"solves":[205],"large-scale":[207],"linear":[208],"programming":[209],"problem.":[210],"apply":[212],"our":[213,249],"parameter":[217,224],"advising":[218],",":[219],"task":[221],"choosing":[223],"values":[225],"aligner\u2019s":[228],"scoring":[229],"obtain":[232],"more":[234],"accurate":[235],"specific":[239],"set":[240],"sequences.":[242],"show":[244],"this":[247],"task,":[248],"strongly":[251],"outperforms":[252],"other":[253],"column-confidence":[254],"estimators":[255],"literature,":[258],"affords":[260],"substantial":[262],"boost":[263]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}