{"id":"https://openalex.org/W3028364110","doi":"https://doi.org/10.1145/3386052.3386077","title":"Identification of the Association between Hepatitis B Virus and Liver Cancer using Machine Learning Approaches based on Amino Acid","display_name":"Identification of the Association between Hepatitis B Virus and Liver Cancer using Machine Learning Approaches based on Amino Acid","publication_year":2020,"publication_date":"2020-01-19","ids":{"openalex":"https://openalex.org/W3028364110","doi":"https://doi.org/10.1145/3386052.3386077","mag":"3028364110"},"language":"en","primary_location":{"id":"doi:10.1145/3386052.3386077","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3386052.3386077","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 10th International Conference on Bioscience, Biochemistry and Bioinformatics","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/A5014339011","display_name":"Zhaoyang Cao","orcid":"https://orcid.org/0009-0004-4060-6549"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Zhaoyang Cao","raw_affiliation_strings":["University of British Columbia"],"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5014339011"],"corresponding_institution_ids":["https://openalex.org/I141945490"],"apc_list":null,"apc_paid":null,"fwci":0.2894,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.58838659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"56","last_page":"63"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10340","display_name":"Hepatitis B Virus Studies","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10340","display_name":"Hepatitis B Virus Studies","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10151","display_name":"Hepatitis C virus research","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2721","display_name":"Hepatology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10351","display_name":"Liver Disease Diagnosis and Treatment","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.8118661642074585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7032514214515686},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6693452000617981},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48005211353302},{"id":"https://openalex.org/keywords/hepatitis-b-virus","display_name":"Hepatitis B virus","score":0.47448089718818665},{"id":"https://openalex.org/keywords/liver-cancer","display_name":"Liver cancer","score":0.47260740399360657},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4660566747188568},{"id":"https://openalex.org/keywords/cancer","display_name":"Cancer","score":0.45102518796920776},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.4162137508392334},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41129791736602783},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.34987694025039673},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.26001808047294617},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2508384585380554},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.18863162398338318},{"id":"https://openalex.org/keywords/virus","display_name":"Virus","score":0.1617361307144165},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1484328806400299},{"id":"https://openalex.org/keywords/internal-medicine","display_name":"Internal medicine","score":0.14724811911582947},{"id":"https://openalex.org/keywords/virology","display_name":"Virology","score":0.138270765542984},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.11875110864639282}],"concepts":[{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.8118661642074585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7032514214515686},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6693452000617981},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48005211353302},{"id":"https://openalex.org/C2780593183","wikidata":"https://www.wikidata.org/wiki/Q6844","display_name":"Hepatitis B virus","level":3,"score":0.47448089718818665},{"id":"https://openalex.org/C2776231280","wikidata":"https://www.wikidata.org/wiki/Q623031","display_name":"Liver cancer","level":3,"score":0.47260740399360657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4660566747188568},{"id":"https://openalex.org/C121608353","wikidata":"https://www.wikidata.org/wiki/Q12078","display_name":"Cancer","level":2,"score":0.45102518796920776},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.4162137508392334},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41129791736602783},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.34987694025039673},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.26001808047294617},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2508384585380554},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.18863162398338318},{"id":"https://openalex.org/C2522874641","wikidata":"https://www.wikidata.org/wiki/Q808","display_name":"Virus","level":2,"score":0.1617361307144165},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1484328806400299},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.14724811911582947},{"id":"https://openalex.org/C159047783","wikidata":"https://www.wikidata.org/wiki/Q7215","display_name":"Virology","level":1,"score":0.138270765542984},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.11875110864639282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3386052.3386077","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3386052.3386077","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 10th International Conference on Bioscience, Biochemistry and Bioinformatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1835730169","https://openalex.org/W1966398441","https://openalex.org/W1989421625","https://openalex.org/W2000336618","https://openalex.org/W2055043387","https://openalex.org/W2059132084","https://openalex.org/W2069869637","https://openalex.org/W2073757369","https://openalex.org/W2088629624","https://openalex.org/W2092208515","https://openalex.org/W2096555119","https://openalex.org/W2104475038","https://openalex.org/W2120128540","https://openalex.org/W2132846960","https://openalex.org/W2142453541","https://openalex.org/W2144430639","https://openalex.org/W2172776214","https://openalex.org/W2336184200","https://openalex.org/W2787972083","https://openalex.org/W2885967217"],"related_works":["https://openalex.org/W3193043704","https://openalex.org/W4386259002","https://openalex.org/W1546989560","https://openalex.org/W3171520305","https://openalex.org/W3135126032","https://openalex.org/W4396689146","https://openalex.org/W4200112873","https://openalex.org/W2955796858","https://openalex.org/W2004826645","https://openalex.org/W4206989953"],"abstract_inverted_index":{"Primary":[0],"liver":[1,19],"cancer":[2,11,20],"has":[3,49],"been":[4,50],"a":[5],"common":[6,15],"reason":[7],"for":[8,96,192,210,277,317,338,359],"death":[9],"from":[10,324],"globally.":[12],"The":[13,26,129,184,237],"most":[14],"type":[16],"of":[17,29,70,74,93,99,136,213,217,225,228,243,247,259,267,302,307,320,327,334,354,364,367,376,399,405,433],"primary":[18],"is":[21,31,251,357,421],"the":[22,67,71,97,133,155,177,182,188,211,241,255,274,293,298,305,318,321,325,331,335,361,365,409,417,424,431],"hepatocellular":[23],"carcinoma":[24],"(HCC).":[25],"major":[27],"cause":[28],"HCC":[30,81,150,278,299,368],"chronic":[32,85],"infections":[33],"with":[34,148,388,423],"hepatitis":[35],"B":[36,435],"virus":[37],"(HBV).":[38],"In":[39],"this":[40],"research,":[41],"we":[42,104,160,220,393],"used":[43,53,64,105,161,271,290],"next":[44],"generation":[45],"sequencing":[46],"(NGS),":[47],"which":[48,78,250],"very":[51],"widely":[52],"to":[54,65,112,175,272,291],"produce":[55],"deep,":[56],"efficient,":[57],"and":[58,83,118,151,170,180,201,206,231,304,430],"high-quality":[59],"sequence":[60,66],"data.":[61],"NGS":[62,115],"was":[63,288],"pre-S":[68],"region":[69],"HBV":[72,86,308,322],"genome":[73],"total":[75,256],"139":[76],"patients,":[77,303],"contain":[79],"94":[80],"patients":[82,147],"45":[84],"(CHB)":[87],"patients.":[88],"We":[89,144,310],"generated":[90],"two":[91],"types":[92],"datasets.":[94],"Firstly,":[95,379],"data":[98,212],"amino":[100,123,139,218,226,244,268,328,355,400,406],"acid":[101,124,245],"occurrence":[102,134,257,366],"frequency,":[103],"basic":[106,138],"local":[107],"alignment":[108,121],"search":[109],"tool":[110],"(BLAST)":[111],"map":[113],"each":[114,120],"short":[116],"read":[117],"translated":[119],"into":[122],"by":[125,253,370],"DNA":[126],"codon":[127],"table.":[128],"input":[130,238],"features":[131,239],"are":[132,203,240,315,342],"frequencies":[135,224,242,266,353],"20":[137],"acids":[140,227,269,329,356,401,407],"using":[141,234,280],"Shannon":[142],"entropy.":[143],"picked":[145],"40":[146],"27":[149],"13":[152],"CHB":[153],"as":[154],"independent":[156,189],"testing":[157,190],"set.":[158],"Then":[159],"machine":[162,173,194,281,339,381],"learning":[163,195,282,340,382],"methods":[164,196,341,383],"including":[165],"logistic":[166],"regression,":[167,198],"random":[168,199],"forest":[169,200],"support":[171],"vector":[172],"(SVM)":[174],"construct":[176,273],"classification":[178,275,336,386],"models":[179,276,337,387],"make":[181],"prediction.":[183],"AUC":[185,332,390],"values":[186,333],"on":[187,412],"set":[191],"those":[193,413],"(logistic":[197],"SVM)":[202],"0.946,":[204],"0.923":[205],"0.960":[207],"respectively.":[208],"Secondly,":[209],"word":[214,222,246,264,313,351,403],"pattern":[215,223,265,352],"frequency":[216],"acids,":[219],"calculated":[221],"all":[229,260,343,380],"individuals":[230],"compared":[232],"them":[233],"Euclidean":[235],"distance.":[236],"length":[248],"2,":[249],"normalized":[252],"dividing":[254],"number":[258],"words.":[261],"What's":[262],"more,":[263],"were":[270],"status":[279,301,426],"methods.":[283],"Principal":[284],"coordinate":[285],"analysis":[286,319],"(PCoA)":[287],"also":[289],"visualize":[292],"associations":[294],"between":[295],"patient":[296],"clusters,":[297],"disease":[300,425],"fraction":[306,432],"genotypes.":[309],"found":[311],"that":[312,350,408],"patterns":[314,404],"powerful":[316,358],"sequences":[323],"aspect":[326],"because":[330],"above":[344],"0.9.":[345],"Hence,":[346],"our":[347],"study":[348],"showed":[349],"revealing":[360],"underlying":[362],"principles":[363],"triggered":[369],"HBV.":[371],"Our":[372],"essential":[373],"findings":[374],"consist":[375],"three":[377],"parts.":[378],"can":[384,394],"generate":[385],"high":[389],"values.":[391],"Then,":[392],"find":[395],"some":[396],"certain":[397],"positions":[398,414],"or":[402,428],"mutation":[410],"occurred":[411],"will":[415],"induce":[416],"HCC.":[418],"Last,":[419],"PCoA":[420],"associated":[422],"(HCC":[427],"CHB)":[429],"genotype":[434],"(or":[436],"C).":[437]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
