{"id":"https://openalex.org/W4362554368","doi":"https://doi.org/10.1186/s12859-023-05195-2","title":"Shine: A novel strategy to extract specific, sensitive and well-conserved biomarkers from massive microbial genomic datasets","display_name":"Shine: A novel strategy to extract specific, sensitive and well-conserved biomarkers from massive microbial genomic datasets","publication_year":2023,"publication_date":"2023-04-04","ids":{"openalex":"https://openalex.org/W4362554368","doi":"https://doi.org/10.1186/s12859-023-05195-2","pmid":"https://pubmed.ncbi.nlm.nih.gov/37016282"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-023-05195-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05195-2","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05195-2","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05195-2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016137328","display_name":"Cong Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146919","display_name":"Shanghai Industrial Technology Institute","ror":"https://ror.org/03j1pdd39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210146919"]},{"id":"https://openalex.org/I4210148639","display_name":"Wuhan Engineering Science & Technology Institute","ror":"https://ror.org/04ez3r306","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210148639"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cong Ji","raw_affiliation_strings":["Liferiver Science and Technology Institute, Shanghai ZJ Bio-Tech Co., Ltd., Shanghai, China. c_ji@liferiver.com.cn","Liferiver Science and Technology Institute, Shanghai ZJ Bio-Tech Co., Ltd., Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7012-0193","affiliations":[{"raw_affiliation_string":"Liferiver Science and Technology Institute, Shanghai ZJ Bio-Tech Co., Ltd., Shanghai, China. c_ji@liferiver.com.cn","institution_ids":["https://openalex.org/I4210146919"]},{"raw_affiliation_string":"Liferiver Science and Technology Institute, Shanghai ZJ Bio-Tech Co., Ltd., Shanghai, China","institution_ids":["https://openalex.org/I4210148639"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112905722","display_name":"Junbin Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146919","display_name":"Shanghai Industrial Technology Institute","ror":"https://ror.org/03j1pdd39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210146919"]},{"id":"https://openalex.org/I4210148639","display_name":"Wuhan Engineering Science & Technology Institute","ror":"https://ror.org/04ez3r306","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210148639"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junbin Shao","raw_affiliation_strings":["Liferiver Science and Technology Institute, Shanghai ZJ Bio-Tech Co., Ltd., Shanghai, China. junbin_shao@liferiver.com.cn","Liferiver Science and Technology Institute, Shanghai ZJ Bio-Tech Co., Ltd., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Liferiver Science and Technology Institute, Shanghai ZJ Bio-Tech Co., Ltd., Shanghai, China. junbin_shao@liferiver.com.cn","institution_ids":["https://openalex.org/I4210146919"]},{"raw_affiliation_string":"Liferiver Science and Technology Institute, Shanghai ZJ Bio-Tech Co., Ltd., Shanghai, China","institution_ids":["https://openalex.org/I4210148639"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5016137328","https://openalex.org/A5112905722"],"corresponding_institution_ids":["https://openalex.org/I4210146919","https://openalex.org/I4210148639"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.1752,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50394668,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"24","issue":"1","first_page":"128","last_page":"128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12167","display_name":"Bacterial Identification and Susceptibility Testing","score":0.3995000123977661,"subfield":{"id":"https://openalex.org/subfields/1308","display_name":"Clinical Biochemistry"},"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/T12167","display_name":"Bacterial Identification and Susceptibility Testing","score":0.3995000123977661,"subfield":{"id":"https://openalex.org/subfields/1308","display_name":"Clinical Biochemistry"},"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":0.11840000003576279,"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/T11551","display_name":"Infective Endocarditis Diagnosis and Management","score":0.09669999778270721,"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/computational-biology","display_name":"Computational biology","score":0.6292614936828613},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5405814051628113},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.5133813619613647},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.4870500862598419},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4499935209751129},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4152308702468872},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2817065417766571},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1876133382320404}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6292614936828613},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5405814051628113},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.5133813619613647},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4870500862598419},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4499935209751129},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4152308702468872},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2817065417766571},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1876133382320404},{"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/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","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":"D012336","descriptor_name":"RNA, Ribosomal, 16S","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012336","descriptor_name":"RNA, Ribosomal, 16S","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012336","descriptor_name":"RNA, Ribosomal, 16S","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015415","descriptor_name":"Biomarkers","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015415","descriptor_name":"Biomarkers","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015415","descriptor_name":"Biomarkers","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D064349","descriptor_name":"Genome, Microbial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064349","descriptor_name":"Genome, Microbial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064349","descriptor_name":"Genome, Microbial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-023-05195-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05195-2","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05195-2","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:37016282","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37016282","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10071469","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10071469","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10071469/pdf/12859_2023_Article_5195.pdf","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":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:856cb50e09f94fed8768c1666190894c","is_oa":true,"landing_page_url":"https://doaj.org/article/856cb50e09f94fed8768c1666190894c","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":"BMC Bioinformatics, Vol 24, Iss 1, Pp 1-16 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s12859-023-05195-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05195-2","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05195-2","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4362554368.pdf"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W1764149807","https://openalex.org/W1998601670","https://openalex.org/W2045855653","https://openalex.org/W2055043387","https://openalex.org/W2069534074","https://openalex.org/W2074168377","https://openalex.org/W2074231493","https://openalex.org/W2087064593","https://openalex.org/W2091622989","https://openalex.org/W2093517437","https://openalex.org/W2096566061","https://openalex.org/W2100971877","https://openalex.org/W2110335151","https://openalex.org/W2113683699","https://openalex.org/W2119877497","https://openalex.org/W2124351063","https://openalex.org/W2125233222","https://openalex.org/W2132632499","https://openalex.org/W2133371096","https://openalex.org/W2136145671","https://openalex.org/W2158676715","https://openalex.org/W2159686708","https://openalex.org/W2160378127","https://openalex.org/W2162098634","https://openalex.org/W2163854906","https://openalex.org/W2225557190","https://openalex.org/W2405778770","https://openalex.org/W2490175516","https://openalex.org/W2573027937","https://openalex.org/W2579533542","https://openalex.org/W2587970647","https://openalex.org/W2605343262","https://openalex.org/W2790546589","https://openalex.org/W2806329229","https://openalex.org/W2887692073","https://openalex.org/W2891429033","https://openalex.org/W2896770224","https://openalex.org/W2905392170","https://openalex.org/W2942757983","https://openalex.org/W2942855639","https://openalex.org/W2952806603","https://openalex.org/W2986916574","https://openalex.org/W3001940667","https://openalex.org/W3006004916","https://openalex.org/W3021125892","https://openalex.org/W3045272156","https://openalex.org/W3081898717","https://openalex.org/W3082598395","https://openalex.org/W3084605929","https://openalex.org/W3134105525","https://openalex.org/W3158848144","https://openalex.org/W3162052180","https://openalex.org/W3164737386","https://openalex.org/W4287754014","https://openalex.org/W4295253509"],"related_works":["https://openalex.org/W2082860237","https://openalex.org/W2119695867","https://openalex.org/W2130076355","https://openalex.org/W1990804418","https://openalex.org/W1993764875","https://openalex.org/W2788277189","https://openalex.org/W2013243191","https://openalex.org/W2151865869","https://openalex.org/W2117258802","https://openalex.org/W4234157524"],"abstract_inverted_index":{"BACKGROUND:":[0],"Concentrations":[1],"of":[2,16,74,97,115,183,191,194,201,222,252,266,275],"the":[3,48,72,144,151,188,199,220,223,231,263],"pathogenic":[4,196],"microorganisms'":[5],"DNA":[6,14],"in":[7,40,67,150],"biological":[8],"samples":[9],"are":[10,19,36,91],"typically":[11],"low.":[12],"Therefore,":[13],"diagnostics":[15],"common":[17],"infections":[18],"costly,":[20],"rarely":[21],"accurate,":[22],"and":[23,61,88,118,146,171,186,204,268,272],"challenging.":[24],"Limited":[25],"by":[26],"failing":[27],"to":[28,38,52,83,142,159,180],"cover":[29,156],"updated":[30],"epidemic":[31],"testing":[32],"samples,":[33],"computational":[34,109],"services":[35],"difficult":[37],"implement":[39],"clinical":[41,69,184,227],"applications":[42],"without":[43,198],"complex":[44],"customized":[45],"settings.":[46,70],"Furthermore,":[47],"combined":[49],"biomarkers":[50,120,149],"used":[51],"maintain":[53],"high":[54],"conservation":[55],"may":[56,213],"not":[57,92],"be":[58],"cost":[59],"effective":[60,93],"could":[62],"cause":[63],"several":[64],"experimental":[65],"errors":[66],"many":[68],"Given":[71],"limitations":[73,200],"recent":[75],"developed":[76],"technology,":[77],"16S":[78],"rRNA":[79],"is":[80,241,260],"too":[81],"conserved":[82,164],"distinguish":[84],"closely":[85],"related":[86],"species,":[87],"mosaic":[89],"plasmids":[90],"as":[94],"well":[95],"because":[96],"their":[98],"uneven":[99],"distribution":[100],"across":[101],"prokaryotic":[102],"taxa.":[103],"RESULTS:":[104],"Here,":[105],"we":[106],"provide":[107],"a":[108,136,181],"strategy,":[110],"Shine,":[111],"that":[112],"allows":[113],"extraction":[114],"specific,":[116],"sensitive":[117],"well-conserved":[119],"from":[121],"massive":[122],"microbial":[123],"genomic":[124],"datasets.":[125],"Distinguished":[126],"with":[127,130,234],"simple":[128],"concatenations":[129],"blast-based":[131],"filtering,":[132],"our":[133,210],"method":[134,175],"involves":[135],"de":[137],"novo":[138],"genome":[139,202],"alignment-based":[140],"pipeline":[141],"explore":[143],"original":[145],"specific":[147],"repetitive":[148],"defined":[152],"population.":[153],"It":[154],"can":[155],"all":[157,195],"members":[158],"detect":[160],"newly":[161],"discovered":[162],"multicopy":[163],"species-specific":[165],"or":[166,255],"even":[167],"subspecies-specific":[168],"target":[169],"probes":[170],"primer":[172],"sets.":[173],"The":[174,238],"has":[176,187],"been":[177],"successfully":[178],"applied":[179],"number":[182],"projects":[185],"overwhelming":[189],"advantages":[190],"automated":[192],"detection":[193,228,276],"microorganisms":[197],"annotation":[203],"incompletely":[205],"assembled":[206],"motifs.":[207],"Using":[208],"on":[209,219,230],"pipeline,":[211],"users":[212],"select":[214],"different":[215],"configuration":[216],"parameters":[217],"depending":[218],"purpose":[221],"project":[224],"for":[225,243,262],"routine":[226],"practices":[229],"website":[232],"https://bioinfo.liferiver.com.cn":[233],"easy":[235],"registration.":[236],"CONCLUSIONS:":[237],"proposed":[239],"strategy":[240],"suitable":[242,261],"identifying":[244],"shared":[245],"phylogenetic":[246],"markers":[247],"while":[248],"featuring":[249],"low":[250],"rates":[251],"false":[253,256],"positive":[254],"negative.":[257],"This":[258],"technology":[259],"automatic":[264],"design":[265],"minimal":[267],"efficient":[269],"PCR":[270],"primers":[271],"other":[273],"types":[274],"probes.":[277]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-10-10T00:00:00"}
