{"id":"https://openalex.org/W4313302964","doi":"https://doi.org/10.1142/s0219720022500287","title":"PTGAC Model: A machine learning approach for constructing phylogenetic tree to compare protein sequences","display_name":"PTGAC Model: A machine learning approach for constructing phylogenetic tree to compare protein sequences","publication_year":2022,"publication_date":"2022-12-16","ids":{"openalex":"https://openalex.org/W4313302964","doi":"https://doi.org/10.1142/s0219720022500287","pmid":"https://pubmed.ncbi.nlm.nih.gov/36775259"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720022500287","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720022500287","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5038132842","display_name":"Jayanta Pal","orcid":"https://orcid.org/0000-0001-9300-2248"},"institutions":[{"id":"https://openalex.org/I155837530","display_name":"National Institute of Technology Durgapur","ror":"https://ror.org/04ds0jm32","country_code":"IN","type":"education","lineage":["https://openalex.org/I155837530"]},{"id":"https://openalex.org/I99601430","display_name":"Maulana Abul Kalam Azad University of Technology, West Bengal","ror":"https://ror.org/030tcae29","country_code":"IN","type":"education","lineage":["https://openalex.org/I99601430"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jayanta Pal","raw_affiliation_strings":["Department of CSE, Narula Institute of Technology, Kolkata, West Bengal 700109, India","Department of ECE, National Institute of Technology, Durgapur, West Bengal 713209, India"],"raw_orcid":"https://orcid.org/0000-0001-9300-2248","affiliations":[{"raw_affiliation_string":"Department of CSE, Narula Institute of Technology, Kolkata, West Bengal 700109, India","institution_ids":["https://openalex.org/I99601430"]},{"raw_affiliation_string":"Department of ECE, National Institute of Technology, Durgapur, West Bengal 713209, India","institution_ids":["https://openalex.org/I155837530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051854259","display_name":"Sourav Saha","orcid":"https://orcid.org/0000-0001-7242-5540"},"institutions":[{"id":"https://openalex.org/I99601430","display_name":"Maulana Abul Kalam Azad University of Technology, West Bengal","ror":"https://ror.org/030tcae29","country_code":"IN","type":"education","lineage":["https://openalex.org/I99601430"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sourav Saha","raw_affiliation_strings":["Department of CSE, Narula Institute of Technology, Kolkata, West Bengal 700109, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of CSE, Narula Institute of Technology, Kolkata, West Bengal 700109, India","institution_ids":["https://openalex.org/I99601430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053165964","display_name":"Bansibadan Maji","orcid":"https://orcid.org/0009-0000-8463-1595"},"institutions":[{"id":"https://openalex.org/I155837530","display_name":"National Institute of Technology Durgapur","ror":"https://ror.org/04ds0jm32","country_code":"IN","type":"education","lineage":["https://openalex.org/I155837530"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Bansibadan Maji","raw_affiliation_strings":["Department of ECE, National Institute of Technology, Durgapur, West Bengal 713209, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of ECE, National Institute of Technology, Durgapur, West Bengal 713209, India","institution_ids":["https://openalex.org/I155837530"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103933502","display_name":"Dilip Kumar Bhattacharya","orcid":null},"institutions":[{"id":"https://openalex.org/I106542073","display_name":"University of Calcutta","ror":"https://ror.org/01e7v7w47","country_code":"IN","type":"education","lineage":["https://openalex.org/I106542073"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dilip Kumar Bhattacharya","raw_affiliation_strings":["Department of Pure Mathematics, Calcutta University, Kolkata, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pure Mathematics, Calcutta University, Kolkata, India","institution_ids":["https://openalex.org/I106542073"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1679,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.48033696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"21","issue":"01","first_page":"2250028","last_page":"2250028"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","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/T12946","display_name":"Fractal and DNA sequence analysis","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/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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9957000017166138,"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/phylogenetic-tree","display_name":"Phylogenetic tree","score":0.7772858142852783},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.6886637210845947},{"id":"https://openalex.org/keywords/upgma","display_name":"UPGMA","score":0.6315434575080872},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.6076785922050476},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.571042537689209},{"id":"https://openalex.org/keywords/distance-matrix","display_name":"Distance matrix","score":0.5678301453590393},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5674741268157959},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5485962629318237},{"id":"https://openalex.org/keywords/distance-matrices-in-phylogeny","display_name":"Distance matrices in phylogeny","score":0.5482174158096313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5140539407730103},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46111205220222473},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.39027976989746094},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.23548904061317444},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1538693606853485}],"concepts":[{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.7772858142852783},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.6886637210845947},{"id":"https://openalex.org/C194898557","wikidata":"https://www.wikidata.org/wiki/Q1779497","display_name":"UPGMA","level":4,"score":0.6315434575080872},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.6076785922050476},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.571042537689209},{"id":"https://openalex.org/C111208986","wikidata":"https://www.wikidata.org/wiki/Q901698","display_name":"Distance matrix","level":2,"score":0.5678301453590393},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5674741268157959},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5485962629318237},{"id":"https://openalex.org/C5349765","wikidata":"https://www.wikidata.org/wiki/Q5282866","display_name":"Distance matrices in phylogeny","level":2,"score":0.5482174158096313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5140539407730103},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46111205220222473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39027976989746094},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.23548904061317444},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1538693606853485},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","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":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","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":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","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":false}],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219720022500287","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720022500287","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},{"id":"pmid:36775259","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36775259","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":"Journal of bioinformatics and computational biology","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2021314219","https://openalex.org/W2052359334","https://openalex.org/W2058392210","https://openalex.org/W2072743932","https://openalex.org/W2079830359","https://openalex.org/W2080258087","https://openalex.org/W2103903366","https://openalex.org/W2171963266","https://openalex.org/W2172615757","https://openalex.org/W2580767461","https://openalex.org/W2581735288","https://openalex.org/W2734297307","https://openalex.org/W2761430568","https://openalex.org/W2990530493","https://openalex.org/W4251751280"],"related_works":["https://openalex.org/W2350990509","https://openalex.org/W2001076853","https://openalex.org/W1872375678","https://openalex.org/W4387171312","https://openalex.org/W3088345466","https://openalex.org/W4388316203","https://openalex.org/W2189266547","https://openalex.org/W2111496408","https://openalex.org/W4206923957","https://openalex.org/W2577956156"],"abstract_inverted_index":{"This":[0],"work":[1],"proposes":[2],"a":[3,33,96,118,123,148,152],"machine":[4],"learning-based":[5],"phylogenetic":[6,153,187,213],"tree":[7,154,214],"generation":[8],"model":[9,29,138,241],"based":[10,103,161,227],"on":[11,104,162,228,249],"agglomerative":[12,159],"clustering":[13,160],"(PTGAC)":[14],"that":[15],"compares":[16],"protein":[17,278],"sequences":[18,102,279],"considering":[19,218],"all":[20],"known":[21,73],"chemical":[22,74],"properties":[23],"of":[24,67,88,100,112,122,126,129,179,184,204,211,266,275,280],"amino":[25,69,84],"acids.":[26],"The":[27,86,166,208],"proposed":[28,61,116,137,206,240],"can":[30],"serve":[31],"as":[32,117,196],"suitable":[34],"alternative":[35],"to":[36,63,94,146,261],"the":[37,60,65,101,136,144,163,171,180,186,202,205,212,222,235,239,250],"Unweighted":[38],"Pair":[39],"Group":[40],"Method":[41],"with":[42,170,277],"Arithmetic":[43],"Mean":[44],"(UPGMA),":[45],"which":[46,120],"is":[47,57,91,115,155,215,225,259,273],"inherently":[48],"time-consuming":[49],"in":[50,59,177,264],"nature.":[51],"Initially,":[52],"principal":[53],"component":[54],"analysis":[55,193,210,224],"(PCA)":[56],"used":[58,93],"scheme":[62],"reduce":[64],"dimensions":[66],"20":[68,77,106],"acids":[70],"using":[71,157],"seven":[72],"characteristics,":[75],"yielding":[76],"TP":[78,107],"(Total":[79],"Points)":[80],"values":[81],"for":[82,200],"each":[83],"acid.":[85],"approach":[87],"cumulative":[89],"summing":[90],"then":[92],"give":[95],"non-degenerate":[97],"numeric":[98],"representation":[99],"these":[105],"values.":[108],"A":[109],"special":[110],"kind":[111],"three-component":[113],"vector":[114],"descriptor,":[119],"consists":[121],"new":[124],"type":[125],"non-central":[127],"moment":[128],"orders":[130],"one,":[131],"two,":[132],"and":[133,173,182,191,269,272],"three.":[134],"Subsequently,":[135],"uses":[139],"Euclidean":[140],"Distance":[141],"measures":[142],"among":[143],"descriptors":[145],"create":[147],"distance":[149,164,230],"matrix.":[150,165],"Finally,":[151],"constructed":[156],"hierarchical":[158],"results":[167,236],"are":[168,194,242],"compared":[169],"UPGMA":[172],"other":[174,254],"existing":[175],"methods":[176],"terms":[178,265],"quality":[181],"time":[183,268],"constructing":[185],"tree.":[188],"Both":[189],"qualitative":[190,209],"quantitative":[192,223],"performed":[195,216,226],"key":[197],"assessment":[198],"criteria":[199],"analyzing":[201],"performance":[203],"model.":[207],"by":[217,238,253],"rationalized":[219],"perception,":[220],"while":[221],"symmetric":[229],"(SD).":[231],"On":[232],"both":[233,267],"criteria,":[234],"obtained":[237],"more":[243],"satisfactory":[244],"than":[245],"those":[246],"produced":[247],"earlier":[248],"same":[251],"species":[252],"methods.":[255],"Notably,":[256],"this":[257],"method":[258],"found":[260],"be":[262],"efficient":[263],"space":[270],"requirements":[271],"capable":[274],"dealing":[276],"varying":[281],"lengths.":[282]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}