{"id":"https://openalex.org/W4402125451","doi":"https://doi.org/10.1109/icton62926.2024.10647830","title":"Effects of Substitution Matrices, Trimming and Outliers on Alignments and Phylogenetic Tree Constructions of Big Dataset","display_name":"Effects of Substitution Matrices, Trimming and Outliers on Alignments and Phylogenetic Tree Constructions of Big Dataset","publication_year":2024,"publication_date":"2024-07-14","ids":{"openalex":"https://openalex.org/W4402125451","doi":"https://doi.org/10.1109/icton62926.2024.10647830"},"language":"en","primary_location":{"id":"doi:10.1109/icton62926.2024.10647830","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icton62926.2024.10647830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 24th International Conference on Transparent Optical Networks (ICTON)","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/A5034316640","display_name":"Guang Wu","orcid":"https://orcid.org/0000-0003-0775-5759"},"institutions":[{"id":"https://openalex.org/I4210165264","display_name":"Guangxi Academy of Sciences","ror":"https://ror.org/054x1kd82","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210165264"]},{"id":"https://openalex.org/I4210150385","display_name":"Innovation Team (China)","ror":"https://ror.org/04ttbbx73","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210150385"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guang Wu","raw_affiliation_strings":["Guangxi Academy of Sciences Nanning,Green Biotransformation and Biomanufacturing Innovation Team,China"],"affiliations":[{"raw_affiliation_string":"Guangxi Academy of Sciences Nanning,Green Biotransformation and Biomanufacturing Innovation Team,China","institution_ids":["https://openalex.org/I4210165264","https://openalex.org/I4210150385"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044041420","display_name":"Shaomin Yan","orcid":"https://orcid.org/0000-0001-7642-3972"},"institutions":[{"id":"https://openalex.org/I4210165264","display_name":"Guangxi Academy of Sciences","ror":"https://ror.org/054x1kd82","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210165264"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaomin Yan","raw_affiliation_strings":["Guangxi Academy of Sciences Nanning,Institute of Biological Sciences and Technology, Guangxi Key Laboratory of Biorefinery,China"],"affiliations":[{"raw_affiliation_string":"Guangxi Academy of Sciences Nanning,Institute of Biological Sciences and Technology, Guangxi Key Laboratory of Biorefinery,China","institution_ids":["https://openalex.org/I4210165264"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5034316640"],"corresponding_institution_ids":["https://openalex.org/I4210150385","https://openalex.org/I4210165264"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13007818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9936000108718872,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9901999831199646,"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/trimming","display_name":"Trimming","score":0.9478778839111328},{"id":"https://openalex.org/keywords/substitution","display_name":"Substitution (logic)","score":0.7944083213806152},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.7541888952255249},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5736182332038879},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5418835282325745},{"id":"https://openalex.org/keywords/phylogenetic-tree","display_name":"Phylogenetic tree","score":0.5298580527305603},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3447553515434265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30249452590942383},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.23224756121635437},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12725096940994263}],"concepts":[{"id":"https://openalex.org/C56951928","wikidata":"https://www.wikidata.org/wiki/Q3539213","display_name":"Trimming","level":2,"score":0.9478778839111328},{"id":"https://openalex.org/C2778220771","wikidata":"https://www.wikidata.org/wiki/Q1522579","display_name":"Substitution (logic)","level":2,"score":0.7944083213806152},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.7541888952255249},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5736182332038879},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5418835282325745},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.5298580527305603},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3447553515434265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30249452590942383},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.23224756121635437},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12725096940994263},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icton62926.2024.10647830","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icton62926.2024.10647830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 24th International Conference on Transparent Optical Networks (ICTON)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320329212","display_name":"Guangxi\u00a0Academy\u00a0of\u00a0Sciences","ror":"https://ror.org/054x1kd82"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1519266993","https://openalex.org/W1936788844","https://openalex.org/W2111647009","https://openalex.org/W2112504441","https://openalex.org/W2115888213","https://openalex.org/W2127322768","https://openalex.org/W2137015675","https://openalex.org/W2174364811","https://openalex.org/W2883251903","https://openalex.org/W4251751280"],"related_works":["https://openalex.org/W2467235537","https://openalex.org/W4243755427","https://openalex.org/W1493074871","https://openalex.org/W2222099502","https://openalex.org/W2128287377","https://openalex.org/W2362218761","https://openalex.org/W2113708670","https://openalex.org/W2062354928","https://openalex.org/W2088120817","https://openalex.org/W2158340599"],"abstract_inverted_index":{"The":[0,118,141,153],"substitution":[1,29,70],"matrix":[2],"is":[3,14],"important":[4],"for":[5,32,93,139],"the":[6,12,26,57,73,78,96,125,144],"multiple":[7],"sequence":[8,121],"alignment":[9,123],"(MSA).":[10],"Thereafter":[11],"MSA":[13],"often":[15],"subject":[16],"to":[17],"trimming":[18,33],"and":[19,34,68,88,90,103,106,115,134,149],"eliminating":[20,35],"of":[21,28,51,130],"detected":[22,92],"outlier":[23,36],"sequences.":[24],"However,":[25],"effects":[27,146],"matrices,":[30],"methods":[31],"sequences":[37,53,136],"in":[38,158],"larger":[39],"datasets":[40],"require":[41],"additional":[42],"attention.":[43],"In":[44],"this":[45],"study,":[46],"(1)":[47],"a":[48,131],"big":[49],"dataset":[50],"3228":[52],"were":[54,75,91,111,137,156],"aligned":[55],"using":[56,77,95],"R":[58,97],"language":[59,98],"package":[60,80,99],"msa":[61],"with":[62,82,101],"BLOSUM30,":[63],"BLOSUM40,":[64],"BLOSUM50,":[65],"BLOSUM65,":[66],"BLOSUM80":[67],"Gonnet":[69],"matrices;":[71],"(2)":[72],"alignments":[74,148],"trimmed":[76,116],"software":[79],"trimA1":[81],"three":[83],"automation":[84],"methods,":[85],"gappyout,":[86],"strict":[87],"strictplus,":[89],"outliers":[94],"OD-seq":[100],"affine":[102],"linear":[104],"methods;":[105],"(3)":[107],"120":[108],"phylogenetic":[109,119,150],"trees":[110],"built":[112],"from":[113],"untrimmed":[114],"alignments.":[117],"information,":[120],"logo,":[122],"statistics,":[124],"normalized":[126],"Robinson-Foulds":[127],"distance,":[128],"locality":[129],"reference":[132],"sequence,":[133],"identical":[135],"used":[138],"analyses.":[140],"results":[142],"demonstrate":[143],"complicated":[145],"on":[147],"tree":[151],"constructions.":[152],"relevant":[154],"implications":[155],"discussed":[157],"detail.":[159]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}