{"id":"https://openalex.org/W2129220104","doi":"https://doi.org/10.1093/bioinformatics/btm608","title":"A machine-learning approach to combined evidence validation of genome assemblies","display_name":"A machine-learning approach to combined evidence validation of genome assemblies","publication_year":2008,"publication_date":"2008-01-18","ids":{"openalex":"https://openalex.org/W2129220104","doi":"https://doi.org/10.1093/bioinformatics/btm608","mag":"2129220104","pmid":"https://pubmed.ncbi.nlm.nih.gov/18204064"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btm608","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btm608","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/6/744/49045755/bioinformatics_24_6_744.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/24/6/744/49045755/bioinformatics_24_6_744.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060349629","display_name":"Jeong\u2010Hyeon Choi","orcid":"https://orcid.org/0000-0003-2870-1231"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jeong-Hyeon Choi","raw_affiliation_strings":["1 The Center for Genomics and Bioinformatics, 2School of Informatics and 3Department of Biology, Indiana University, IN 47405, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 The Center for Genomics and Bioinformatics, 2School of Informatics and 3Department of Biology, Indiana University, IN 47405, USA","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460452","display_name":"Sun Kim","orcid":"https://orcid.org/0000-0003-3072-6649"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sun Kim","raw_affiliation_strings":["1 The Center for Genomics and Bioinformatics, 2School of Informatics and 3Department of Biology, Indiana University, IN 47405, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 The Center for Genomics and Bioinformatics, 2School of Informatics and 3Department of Biology, Indiana University, IN 47405, USA","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078007096","display_name":"Haixu Tang","orcid":"https://orcid.org/0000-0001-8963-8155"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haixu Tang","raw_affiliation_strings":["1 The Center for Genomics and Bioinformatics, 2School of Informatics and 3Department of Biology, Indiana University, IN 47405, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 The Center for Genomics and Bioinformatics, 2School of Informatics and 3Department of Biology, Indiana University, IN 47405, USA","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005430422","display_name":"Justen Andrews","orcid":null},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justen Andrews","raw_affiliation_strings":["1 The Center for Genomics and Bioinformatics, 2School of Informatics and 3Department of Biology, Indiana University, IN 47405, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 The Center for Genomics and Bioinformatics, 2School of Informatics and 3Department of Biology, Indiana University, IN 47405, USA","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057245442","display_name":"Don Gilbert","orcid":"https://orcid.org/0000-0002-6646-7274"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Don G. Gilbert","raw_affiliation_strings":["1 The Center for Genomics and Bioinformatics, 2School of Informatics and 3Department of Biology, Indiana University, IN 47405, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 The Center for Genomics and Bioinformatics, 2School of Informatics and 3Department of Biology, Indiana University, IN 47405, USA","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084728639","display_name":"John K. Colbourne","orcid":"https://orcid.org/0000-0002-6966-2972"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John K. Colbourne","raw_affiliation_strings":["1 The Center for Genomics and Bioinformatics, 2School of Informatics and 3Department of Biology, Indiana University, IN 47405, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 The Center for Genomics and Bioinformatics, 2School of Informatics and 3Department of Biology, Indiana University, IN 47405, USA","institution_ids":["https://openalex.org/I592451"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5060349629"],"corresponding_institution_ids":["https://openalex.org/I592451"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":{"value":3989,"currency":"USD","value_usd":3989},"fwci":0.7966,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.71820018,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"24","issue":"6","first_page":"744","last_page":"750"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.7524999976158142,"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":0.7524999976158142,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.054999999701976776,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.039900001138448715,"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/contig","display_name":"Contig","score":0.8012028932571411},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.7085805535316467},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7073750495910645},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6496126651763916},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.48461589217185974},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4734725058078766},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4697072207927704},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.446990430355072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4184448719024658},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4025863707065582},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.38610342144966125},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3269144892692566},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.15175357460975647},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.13664299249649048},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1327202320098877},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.13233286142349243},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.09116300940513611}],"concepts":[{"id":"https://openalex.org/C59582021","wikidata":"https://www.wikidata.org/wiki/Q1128751","display_name":"Contig","level":4,"score":0.8012028932571411},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.7085805535316467},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7073750495910645},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6496126651763916},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.48461589217185974},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4734725058078766},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4697072207927704},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.446990430355072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4184448719024658},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4025863707065582},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.38610342144966125},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3269144892692566},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.15175357460975647},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.13664299249649048},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1327202320098877},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13233286142349243},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.09116300940513611},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","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},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004330","descriptor_name":"Drosophila","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004330","descriptor_name":"Drosophila","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004330","descriptor_name":"Drosophila","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020451","descriptor_name":"Contig Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020451","descriptor_name":"Contig Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020451","descriptor_name":"Contig Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btm608","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btm608","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/6/744/49045755/bioinformatics_24_6_744.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:18204064","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18204064","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":"Bioinformatics (Oxford, England)","raw_type":"Evaluation Study"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.988.358","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.988.358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/content/early/2008/01/18/bioinformatics.btm608.full.pdf","raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/8fb24fd9-0d13-4d1e-b6f2-299dd4982ed0","is_oa":false,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/8fb24fd9-0d13-4d1e-b6f2-299dd4982ed0","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Choi, J, Kim, S, Tang, H, Andrews, J, Gilbert, D G & Colbourne, J K 2008, 'A machine-learning approach to combined evidence validation of genome assemblies', Bioinformatics, vol. 24, no. 6, pp. 744-750. https://doi.org/10.1093/bioinformatics/btm608","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btm608","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btm608","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/6/744/49045755/bioinformatics_24_6_744.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7590759746","display_name":"CAREER: A Computational Environment for Prokaryotic Genome Projects","funder_award_id":"0237901","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307758","display_name":"Eli Lilly and Company","ror":"https://ror.org/01qat3289"},{"id":"https://openalex.org/F4320309409","display_name":"Lilly Endowment","ror":"https://ror.org/00cpsd622"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2129220104.pdf","grobid_xml":"https://content.openalex.org/works/W2129220104.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W62450904","https://openalex.org/W1517993545","https://openalex.org/W1605688901","https://openalex.org/W1970939265","https://openalex.org/W1974885145","https://openalex.org/W1975768217","https://openalex.org/W1984236772","https://openalex.org/W2008235493","https://openalex.org/W2016974511","https://openalex.org/W2032379826","https://openalex.org/W2056554987","https://openalex.org/W2062681025","https://openalex.org/W2073497058","https://openalex.org/W2084134149","https://openalex.org/W2104046507","https://openalex.org/W2106097547","https://openalex.org/W2114611642","https://openalex.org/W2117030637","https://openalex.org/W2120414630","https://openalex.org/W2125055259","https://openalex.org/W2127230663","https://openalex.org/W2144662851","https://openalex.org/W2151464048","https://openalex.org/W2164207497","https://openalex.org/W2167719518","https://openalex.org/W2168148721","https://openalex.org/W2170112109","https://openalex.org/W2242722348","https://openalex.org/W2292905290","https://openalex.org/W2442149594","https://openalex.org/W2911964244","https://openalex.org/W2966207845","https://openalex.org/W3017143921","https://openalex.org/W4292239814","https://openalex.org/W6602593173"],"related_works":["https://openalex.org/W4281620341","https://openalex.org/W2925048800","https://openalex.org/W1992950355","https://openalex.org/W4381279187","https://openalex.org/W2574304546","https://openalex.org/W2200318732","https://openalex.org/W4313598112","https://openalex.org/W2008826985","https://openalex.org/W3128872455","https://openalex.org/W2078447778"],"abstract_inverted_index":{"MOTIVATION:":[0],"While":[1],"it":[2,13,22],"is":[3,23,70,103],"common":[4],"to":[5,7,72,108,123,209,240],"refer":[6],"'the":[8],"genome":[9],"sequence'":[10],"as":[11],"if":[12,105],"were":[14],"a":[15,84,120,230,242],"single,":[16],"complete":[17],"and":[18,40,48,173,195,257,269],"contiguous":[19],"DNA":[20,34,44,62],"string,":[21],"in":[24,66,127,131,191],"fact":[25],"an":[26],"assembly":[27,79,86,97,125,135,199],"of":[28,30,94,101,224,262],"millions":[29],"small,":[31],"partially":[32],"overlapping":[33],"fragments.":[35],"Sophisticated":[36],"computer":[37],"algorithms":[38],"(assemblers":[39],"scaffolders)":[41],"merge":[42],"these":[43,50,151,226,237],"fragments":[45],"into":[46,52],"contigs,":[47],"place":[49],"contigs":[51],"sequence":[53,115,128],"scaffolds":[54],"using":[55],"the":[56,76,95,113,162,166,169,174,183,189,222,255,265,272,276],"paired-end":[57],"sequences":[58],"derived":[59],"from":[60,112],"large-insert":[61],"libraries.":[63],"Each":[64],"step":[65],"this":[67],"automated":[68],"process":[69],"susceptible":[71],"producing":[73],"errors;":[74],"hence,":[75],"resulting":[77],"draft":[78,96,147],"represents":[80],"(in":[81],"practice)":[82],"only":[83],"likely":[85,99],"that":[87,158,182,235],"requires":[88],"further":[89,217],"validation.":[90],"Knowing":[91],"which":[92],"parts":[93],"are":[98,107],"free":[100],"errors":[102,126],"critical":[104],"researchers":[106],"draw":[109],"reliable":[110],"conclusions":[111],"assembled":[114],"data.":[116],"RESULTS:":[117],"We":[118],"develop":[119,229],"machine-learning":[121],"method":[122,205],"detect":[124,211],"assemblies.":[129],"Several":[130],"silico":[132],"measures":[133,157,239,267],"for":[134,198,216],"validation":[136],"have":[137],"been":[138],"proposed":[139],"by":[140],"various":[141],"researchers.":[142],"Using":[143],"three":[144],"benchmarking":[145,277],"Drosophila":[146],"genomes,":[148],"we":[149,159,228],"evaluate":[150],"techniques":[152],"along":[153],"with":[154],"some":[155],"new":[156],"propose,":[160],"including":[161],"good-minus-bad":[163],"coverage":[164],"(GMB),":[165],"good-to-bad-ratio":[167],"(RGB),":[168],"average":[170,175],"Z-score":[171,177],"(AZ)":[172],"absolute":[176],"(ASZ).":[178],"Our":[179,250],"results":[180],"show":[181],"GMB":[184],"measure":[185],"performs":[186,206],"better":[187],"than":[188,248],"others":[190],"both":[192],"its":[193,196],"sensitivity":[194],"specificity":[197],"error":[200],"detection.":[201],"Nevertheless,":[202],"no":[203],"single":[204],"sufficiently":[207],"well":[208],"reliably":[210],"genomic":[212],"regions":[213],"requiring":[214],"attention":[215],"experimental":[218],"verification.":[219],"To":[220],"utilize":[221],"advantages":[223],"all":[225],"measures,":[227],"novel":[231],"machine":[232],"learning":[233],"approach":[234,253],"combines":[236],"individual":[238,266],"achieve":[241],"higher":[243],"prediction":[244],"accuracy":[245],"(i.e.":[246],"greater":[247],"90%).":[249],"combined":[251],"evidence":[252],"avoids":[254],"difficult":[256],"often":[258],"ad":[259],"hoc":[260],"selection":[261],"many":[263],"parameters":[264],"require,":[268],"significantly":[270],"improves":[271],"overall":[273],"precisions":[274],"on":[275],"data":[278],"sets.":[279]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}
