{"id":"https://openalex.org/W2888673908","doi":"https://doi.org/10.1145/3233547.3233646","title":"A Novel Approach for Increasing Taxonomic Resolution in Protein-Based Alignments","display_name":"A Novel Approach for Increasing Taxonomic Resolution in Protein-Based Alignments","publication_year":2018,"publication_date":"2018-08-15","ids":{"openalex":"https://openalex.org/W2888673908","doi":"https://doi.org/10.1145/3233547.3233646","mag":"2888673908"},"language":"en","primary_location":{"id":"doi:10.1145/3233547.3233646","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3233547.3233646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009416012","display_name":"Cooper J. Park","orcid":null},"institutions":[{"id":"https://openalex.org/I161057412","display_name":"University of New Hampshire","ror":"https://ror.org/01rmh9n78","country_code":"US","type":"education","lineage":["https://openalex.org/I161057412"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cooper J. Park","raw_affiliation_strings":["University of New Hampshire, Durham, NH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Hampshire, Durham, NH, USA","institution_ids":["https://openalex.org/I161057412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016008457","display_name":"Keir J. Macartney","orcid":"https://orcid.org/0000-0002-9461-0445"},"institutions":[{"id":"https://openalex.org/I161057412","display_name":"University of New Hampshire","ror":"https://ror.org/01rmh9n78","country_code":"US","type":"education","lineage":["https://openalex.org/I161057412"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keir J. Macartney","raw_affiliation_strings":["University of New Hampshire, Durham, NH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Hampshire, Durham, NH, USA","institution_ids":["https://openalex.org/I161057412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026179090","display_name":"Jun-Fu Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I161057412","display_name":"University of New Hampshire","ror":"https://ror.org/01rmh9n78","country_code":"US","type":"education","lineage":["https://openalex.org/I161057412"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junfu Shen","raw_affiliation_strings":["University of New Hampshire, Durham, NH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Hampshire, Durham, NH, USA","institution_ids":["https://openalex.org/I161057412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102770065","display_name":"Kunpeng Xie","orcid":"https://orcid.org/0000-0001-9857-5352"},"institutions":[{"id":"https://openalex.org/I161057412","display_name":"University of New Hampshire","ror":"https://ror.org/01rmh9n78","country_code":"US","type":"education","lineage":["https://openalex.org/I161057412"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kunpeng Xie","raw_affiliation_strings":["University of New Hampshire, Durham, NH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Hampshire, Durham, NH, USA","institution_ids":["https://openalex.org/I161057412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327423","display_name":"Xin Zhang","orcid":"https://orcid.org/0000-0002-2300-1036"},"institutions":[{"id":"https://openalex.org/I161057412","display_name":"University of New Hampshire","ror":"https://ror.org/01rmh9n78","country_code":"US","type":"education","lineage":["https://openalex.org/I161057412"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["University of New Hampshire, Durham, NH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Hampshire, Durham, NH, USA","institution_ids":["https://openalex.org/I161057412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043713217","display_name":"R. Daniel Bergeron","orcid":null},"institutions":[{"id":"https://openalex.org/I161057412","display_name":"University of New Hampshire","ror":"https://ror.org/01rmh9n78","country_code":"US","type":"education","lineage":["https://openalex.org/I161057412"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Daniel Bergeron","raw_affiliation_strings":["University of New Hampshire, Durham, NH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Hampshire, Durham, NH, USA","institution_ids":["https://openalex.org/I161057412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108523801","display_name":"W. Kelley Thomas","orcid":null},"institutions":[{"id":"https://openalex.org/I161057412","display_name":"University of New Hampshire","ror":"https://ror.org/01rmh9n78","country_code":"US","type":"education","lineage":["https://openalex.org/I161057412"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W. Kelley Thomas","raw_affiliation_strings":["University of New Hampshire, Durham, NH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Hampshire, Durham, NH, USA","institution_ids":["https://openalex.org/I161057412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041001443","display_name":"Cheryl P. Andam","orcid":"https://orcid.org/0000-0003-4428-0924"},"institutions":[{"id":"https://openalex.org/I161057412","display_name":"University of New Hampshire","ror":"https://ror.org/01rmh9n78","country_code":"US","type":"education","lineage":["https://openalex.org/I161057412"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheryl P. Andam","raw_affiliation_strings":["University of New Hampshire, Durham, NH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Hampshire, Durham, NH, USA","institution_ids":["https://openalex.org/I161057412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066603555","display_name":"Anthony Westbrook","orcid":"https://orcid.org/0000-0001-5398-6916"},"institutions":[{"id":"https://openalex.org/I161057412","display_name":"University of New Hampshire","ror":"https://ror.org/01rmh9n78","country_code":"US","type":"education","lineage":["https://openalex.org/I161057412"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony Westbrook","raw_affiliation_strings":["University of New Hampshire, Durham, NH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Hampshire, Durham, NH, USA","institution_ids":["https://openalex.org/I161057412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161057412"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07775782,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"538","last_page":"538"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9997000098228455,"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":0.9997000098228455,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9857000112533569,"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":0.9782999753952026,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/uniprot","display_name":"UniProt","score":0.9017124772071838},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.585431694984436},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.537212073802948},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5252587199211121},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5161265134811401},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.48263177275657654},{"id":"https://openalex.org/keywords/plug-in","display_name":"Plug-in","score":0.4782071113586426},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.4734449088573456},{"id":"https://openalex.org/keywords/nucleic-acid-sequence","display_name":"Nucleic acid sequence","score":0.4202503263950348},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.36541223526000977},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3267063796520233},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32565435767173767},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2717176079750061},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.24257779121398926},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.20265546441078186},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1434703767299652},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.14313095808029175}],"concepts":[{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.9017124772071838},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.585431694984436},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.537212073802948},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5252587199211121},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5161265134811401},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.48263177275657654},{"id":"https://openalex.org/C4924752","wikidata":"https://www.wikidata.org/wiki/Q184148","display_name":"Plug-in","level":2,"score":0.4782071113586426},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.4734449088573456},{"id":"https://openalex.org/C84148353","wikidata":"https://www.wikidata.org/wiki/Q863908","display_name":"Nucleic acid sequence","level":3,"score":0.4202503263950348},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.36541223526000977},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3267063796520233},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32565435767173767},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2717176079750061},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.24257779121398926},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.20265546441078186},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1434703767299652},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.14313095808029175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3233547.3233646","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3233547.3233646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2161189461","https://openalex.org/W2972635466","https://openalex.org/W2803517106","https://openalex.org/W2106830745","https://openalex.org/W2926533301","https://openalex.org/W1994428965","https://openalex.org/W1967142621","https://openalex.org/W4240507550","https://openalex.org/W2161062388","https://openalex.org/W2018564950"],"abstract_inverted_index":{"Most":[0],"of":[1,22,40,75,86,99,106,168,177,189,196,250,274,282],"today's":[2],"genome":[3],"sequencing":[4],"technology":[5],"requires":[6],"that":[7,117],"genomes":[8],"be":[9,223],"sequenced":[10],"in":[11,52,154,172,199,218,231,243],"fragments.":[12],"Typically,":[13],"these":[14,48],"fragments":[15],"are":[16],"then":[17],"aligned":[18,88,170],"using":[19,126,293],"a":[20,31,72,114,178,226,244,279],"variety":[21],"different":[23],"alignment":[24,27,124],"programs.":[25],"All":[26],"tools":[28],"query":[29],"against":[30],"reference":[32],"database":[33,129],"to":[34,103,260,270],"determine":[35],"the":[36,41,83,87,91,97,104,107,127,132,159,169,190,200,205,232,239,253,257,264,272,283],"most":[37,133],"accurate":[38],"reassembly":[39],"original":[42,206],"DNA":[43],"strand's":[44],"nucleotide":[45,54,139,160,191,275],"sequence.":[46,89],"Although":[47],"programs":[49],"can":[50],"align":[51,71],"both":[53],"and":[55,78,130,151,162,216,237,287],"protein":[56,123,202,207],"space,":[57],"each":[58,138,143],"method":[59,95],"comes":[60],"with":[61,142,193,225,290],"its":[62,152],"own":[63],"disadvantages.":[64],"Protein":[65],"aligners":[66],"such":[67],"as":[68,204],"PALADIN":[69,115],"consistently":[70],"greater":[73,80,291],"percent":[74,188,195],"reads":[76,192],"faster":[77],"provide":[79],"insight":[81],"into":[82,252],"functional":[84],"capabilities":[85],"On":[90],"other":[92],"hand,":[93],"this":[94,119,210],"reduces":[96,256],"sensitivity":[98],"taxonomic":[100,135,164,241],"classification":[101],"due":[102],"degeneracy":[105],"genetic":[108],"codes.":[109],"Our":[110,183],"program,":[111],"Renuc,":[112],"is":[113,212],"plugin":[116],"addresses":[118],"issue":[120],"by":[121,156,277],"taking":[122],"results":[125],"UniProt":[128,265],"identifying":[131],"likely":[134],"origin":[136],"for":[137,166],"sequence":[140,161],"associated":[141],"detected":[144],"protein.":[145],"We":[146],"have":[147],"validated":[148],"our":[149,173],"approach":[150],"implementation":[153],"Renuc":[155,234],"successfully":[157],"retrieving":[158],"corresponding":[163],"IDs":[165],"all":[167],"proteins":[171],"test":[174],"dataset":[175,211,227],"consisting":[176],"whole":[179],"Escherichia":[180],"coli":[181],"genome.":[182],"program":[184,254],"aligns":[185],"over":[186],"99":[187],"97":[194],"them":[197],"remaining":[198],"same":[201],"cluster":[203],"alignment.":[208],"However,":[209],"incredibly":[213],"well":[214],"studied":[215],"documented":[217],"UniProt.":[219],"Future":[220],"work":[221],"should":[222],"considered":[224],"containing":[228],"less":[229],"annotations":[230],"database.":[233,266],"quickly":[235],"identifies":[236],"visualizes":[238],"alignment's":[240],"data":[242],"user":[245],"friendly":[246],"way.":[247],"The":[248],"integration":[249],"SQLite":[251],"significantly":[255],"time":[258],"required":[259],"retrieve":[261],"information":[262],"from":[263],"Currently,":[267],"we":[268],"seek":[269],"improve":[271],"retrieval":[273],"sequences":[276],"creating":[278],"local":[280],"cache":[281],"NCBI":[284],"RefSeq":[285],"database,":[286],"visualizing":[288],"taxonomy":[289],"resolution":[292],"RaxML.":[294]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}