{"id":"https://openalex.org/W2605513936","doi":"https://doi.org/10.1504/ijcbdd.2017.10004575","title":"Improving de novo metatranscriptome assembly via machine learning algorithms","display_name":"Improving de novo metatranscriptome assembly via machine learning algorithms","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2605513936","doi":"https://doi.org/10.1504/ijcbdd.2017.10004575","mag":"2605513936"},"language":"en","primary_location":{"id":"doi:10.1504/ijcbdd.2017.10004575","is_oa":false,"landing_page_url":"https://doi.org/10.1504/ijcbdd.2017.10004575","pdf_url":null,"source":{"id":"https://openalex.org/S200215862","display_name":"International Journal of Computational Biology and Drug Design","issn_l":"1756-0756","issn":["1756-0756","1756-0764"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310317825","host_organization_name":"Inderscience Publishers","host_organization_lineage":["https://openalex.org/P4310317825"],"host_organization_lineage_names":["Inderscience Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computational Biology and Drug Design","raw_type":"journal-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/A5009800564","display_name":"Hussein Mohsen","orcid":"https://orcid.org/0000-0002-6263-8865"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hussein Mohsen","raw_affiliation_strings":["School of Informatics and Computing, Indiana University, Bloomington, IN 47405, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics and Computing, Indiana University, Bloomington, IN 47405, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082620694","display_name":"Yuzhen Ye","orcid":"https://orcid.org/0000-0003-3707-3185"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuzhen Ye","raw_affiliation_strings":["School of Informatics and Computing, Indiana University, Bloomington, IN 47405, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics and Computing, Indiana University, Bloomington, IN 47405, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078007096","display_name":"Haixu Tang","orcid":"https://orcid.org/0000-0001-8963-8155"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haixu Tang","raw_affiliation_strings":["School of Informatics and Computing, Indiana University, Bloomington, IN 47405, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics and Computing, Indiana University, Bloomington, IN 47405, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2243,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55321396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"10","issue":"2","first_page":"91","last_page":"91"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998999834060669,"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":0.9998999834060669,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9952999949455261,"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/T11970","display_name":"Molecular Biology Techniques and Applications","score":0.9890999794006348,"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":0.9116634130477905},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.8316457271575928},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7218875885009766},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6084645390510559},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5373240113258362},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.42331764101982117},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4185864329338074},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33634915947914124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33359479904174805},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3252963423728943},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.26133573055267334},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.169927179813385},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.13881438970565796},{"id":"https://openalex.org/keywords/transcriptome","display_name":"Transcriptome","score":0.12211978435516357},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10624745488166809}],"concepts":[{"id":"https://openalex.org/C59582021","wikidata":"https://www.wikidata.org/wiki/Q1128751","display_name":"Contig","level":4,"score":0.9116634130477905},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.8316457271575928},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7218875885009766},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6084645390510559},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5373240113258362},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.42331764101982117},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4185864329338074},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33634915947914124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33359479904174805},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3252963423728943},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.26133573055267334},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.169927179813385},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.13881438970565796},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.12211978435516357},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10624745488166809},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1504/ijcbdd.2017.10004575","is_oa":false,"landing_page_url":"https://doi.org/10.1504/ijcbdd.2017.10004575","pdf_url":null,"source":{"id":"https://openalex.org/S200215862","display_name":"International Journal of Computational Biology and Drug Design","issn_l":"1756-0756","issn":["1756-0756","1756-0764"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310317825","host_organization_name":"Inderscience Publishers","host_organization_lineage":["https://openalex.org/P4310317825"],"host_organization_lineage_names":["Inderscience Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computational Biology and Drug Design","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.550000011920929,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2020006618","https://openalex.org/W2089480001","https://openalex.org/W3167837387","https://openalex.org/W2885619582","https://openalex.org/W54719527","https://openalex.org/W4250462852","https://openalex.org/W2944010518","https://openalex.org/W2993223466","https://openalex.org/W2105191441","https://openalex.org/W4381279187"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"DNPipe,":[5],"a":[6,59],"Pipeline":[7],"that":[8,43,75],"processes":[9],"and":[10,40,87,106],"filters":[11],"the":[12,26,80,94,107,110],"transcript":[13,48],"contigs":[14,95],"reported":[15],"by":[16,64,97,113,129],"existing":[17],"De":[18],"Novo":[19],"metatranscriptome":[20,83],"assembly":[21,31,111],"algorithms,":[22],"aiming":[23],"to":[24,103,115],"improve":[25,79],"quality":[27,81,125],"of":[28,32,37,47,82,93,109,123],"de":[29],"novo":[30],"metatranscriptomic":[33,55],"sequences.":[34],"DNPipe":[35,52,76,120,134],"consists":[36],"expectation-maximisation":[38],"(EM)":[39],"sampling":[41],"approaches":[42],"utilise":[44],"abundance":[45],"information":[46],"contigs.":[49],"We":[50],"tested":[51],"on":[53],"six":[54],"datasets":[56],"acquired":[57],"from":[58],"mock":[60],"microbial":[61],"community":[62],"dominated":[63],"three":[65],"(among":[66],"more":[67,88],"than":[68,126],"15)":[69],"known":[70],"bacterial":[71],"genomes.":[72],"Results":[73],"show":[74],"can":[77,136],"substantially":[78],"assembly,":[84],"producing":[85],"longer":[86],"accurate":[89],"transcripts.":[90],"The":[91,133],"N50":[92],"increases":[96],"19%":[98],"(from":[99],"around":[100],"1880":[101],"bps":[102],"2250":[104],"bps),":[105],"precision":[108],"improves":[112],"up":[114],"8.7%,":[116],"achieving":[117],"about":[118],"81%.":[119],"assemblies":[121],"are":[122],"higher":[124],"those":[127],"assembled":[128],"Trinity":[130],"as":[131,139],"well.":[132],"tool":[135],"be":[137],"downloaded":[138],"open":[140],"source":[141],"software":[142],"at":[143],"https://sourceforge.net/projects/dnpipe/files/.":[144]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}