{"id":"https://openalex.org/W2972864473","doi":"https://doi.org/10.1145/3307339.3343463","title":"MirLibSpark","display_name":"MirLibSpark","publication_year":2019,"publication_date":"2019-09-04","ids":{"openalex":"https://openalex.org/W2972864473","doi":"https://doi.org/10.1145/3307339.3343463","mag":"2972864473"},"language":"en","primary_location":{"id":"doi:10.1145/3307339.3343463","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3307339.3343463","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.17998","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007989945","display_name":"Chao\u2010Jung Wu","orcid":"https://orcid.org/0000-0002-5867-9402"},"institutions":[{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Chao-Jung Wu","raw_affiliation_strings":["Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al, Montr\u00e9al, PQ, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al, Montr\u00e9al, PQ, Canada","institution_ids":["https://openalex.org/I159129438"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013030971","display_name":"Mohamed Amine Remita","orcid":"https://orcid.org/0000-0003-4471-3195"},"institutions":[{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Amine M. Remita","raw_affiliation_strings":["Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al, Montr\u00e9al, PQ, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al, Montr\u00e9al, PQ, Canada","institution_ids":["https://openalex.org/I159129438"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061553529","display_name":"Abdoulaye Banir\u00e9 Diallo","orcid":"https://orcid.org/0000-0002-1168-9371"},"institutions":[{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Abdoulaye Banir\u00e9 Diallo","raw_affiliation_strings":["Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al, Montreal, PQ, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al, Montreal, PQ, Canada","institution_ids":["https://openalex.org/I159129438"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I159129438"],"apc_list":null,"apc_paid":null,"fwci":0.0828,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46449618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"669","last_page":"674"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11482","display_name":"RNA modifications and cancer","score":0.9988999962806702,"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/T11482","display_name":"RNA modifications and cancer","score":0.9988999962806702,"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/T10062","display_name":"MicroRNA in disease regulation","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7610846161842346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.757536768913269},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7498505711555481},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.6818775534629822},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.594205915927887},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4509354531764984},{"id":"https://openalex.org/keywords/microrna","display_name":"microRNA","score":0.44798827171325684},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.267221599817276},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18677201867103577},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09386411309242249},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07960900664329529},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.07773873209953308}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7610846161842346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.757536768913269},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7498505711555481},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.6818775534629822},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.594205915927887},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4509354531764984},{"id":"https://openalex.org/C145059251","wikidata":"https://www.wikidata.org/wiki/Q310899","display_name":"microRNA","level":3,"score":0.44798827171325684},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.267221599817276},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18677201867103577},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09386411309242249},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07960900664329529},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.07773873209953308},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3307339.3343463","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3307339.3343463","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2501.17998","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.17998","pdf_url":"https://arxiv.org/pdf/2501.17998","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.17998","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.17998","pdf_url":"https://arxiv.org/pdf/2501.17998","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2972864473.pdf"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1973862547","https://openalex.org/W2109525082","https://openalex.org/W2110131043","https://openalex.org/W2121673931","https://openalex.org/W2143407915","https://openalex.org/W2145251517","https://openalex.org/W2220012389","https://openalex.org/W2559588208","https://openalex.org/W2566265666","https://openalex.org/W2949470979"],"related_works":["https://openalex.org/W1981780420","https://openalex.org/W1975949872","https://openalex.org/W3159871278","https://openalex.org/W2230552005","https://openalex.org/W2182707996","https://openalex.org/W2905242764","https://openalex.org/W45233828","https://openalex.org/W2964988449","https://openalex.org/W3083262785","https://openalex.org/W2799508461"],"abstract_inverted_index":{"The":[0],"emergence":[1],"of":[2,11,35],"the":[3,9,68,75,86,93,121],"Next":[4],"Generation":[5],"Sequencing":[6],"increases":[7],"drastically":[8],"volume":[10,34,60],"transcriptomic":[12],"data.":[13],"Although":[14],"many":[15],"standalone":[16,101],"algorithms":[17],"and":[18,41,79,102,110],"workflows":[19],"for":[20,31,57],"novel":[21],"microRNA":[22],"(miRNA)":[23],"prediction":[24],"have":[25],"been":[26],"proposed,":[27],"few":[28],"are":[29],"designed":[30],"processing":[32],"large":[33,39],"sequence":[36],"data":[37,61],"from":[38],"genomes,":[40],"even":[42],"fewer":[43],"further":[44],"annotate":[45],"functional":[46,96,115],"miRNAs":[47],"by":[48,63],"analyzing":[49],"multiple":[50],"libraries.":[51],"We":[52],"propose":[53],"an":[54,81,108],"improved":[55],"pipeline":[56,73],"a":[58,100],"high":[59],"facility":[62],"implementing":[64],"mirLibSpark":[65],"based":[66],"on":[67,124],"Apache":[69],"Spark":[70],"framework.":[71],"This":[72],"is":[74,107],"fastest":[76],"actual":[77],"method,":[78],"provides":[80],"accuracy":[82],"improvement":[83],"compared":[84],"to":[85],"standard.":[87],"In":[88],"this":[89],"paper,":[90],"we":[91],"deliver":[92],"first":[94],"distributed":[95],"miRNA":[97,112,126],"predictor":[98,113],"as":[99],"fully":[103],"automated":[104],"package.":[105],"It":[106],"efficient":[109],"accurate":[111],"with":[114,120],"insight.":[116],"Furthermore,":[117],"it":[118],"compiles":[119],"gold-standard":[122],"requirement":[123],"plant":[125],"predictions.":[127]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2019-09-19T00:00:00"}
