{"id":"https://openalex.org/W2580187722","doi":"https://doi.org/10.1504/ijbra.2017.10002831","title":"An empirical study of self-training and data balancing techniques for splice site prediction","display_name":"An empirical study of self-training and data balancing techniques for splice site prediction","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2580187722","doi":"https://doi.org/10.1504/ijbra.2017.10002831","mag":"2580187722"},"language":"en","primary_location":{"id":"doi:10.1504/ijbra.2017.10002831","is_oa":false,"landing_page_url":"https://doi.org/10.1504/ijbra.2017.10002831","pdf_url":null,"source":{"id":"https://openalex.org/S207086575","display_name":"International Journal of Bioinformatics Research and Applications","issn_l":"1744-5485","issn":["1744-5485","1744-5493"],"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 Bioinformatics Research and Applications","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/A5067341711","display_name":"Doina Caragea","orcid":"https://orcid.org/0000-0002-6440-0914"},"institutions":[{"id":"https://openalex.org/I189590672","display_name":"Kansas State University","ror":"https://ror.org/05p1j8758","country_code":"US","type":"education","lineage":["https://openalex.org/I189590672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Doina Caragea","raw_affiliation_strings":["Department of Computing and Information Sciences, Kansas State University, Manhattan, KS, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing and Information Sciences, Kansas State University, Manhattan, KS, USA","institution_ids":["https://openalex.org/I189590672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101982240","display_name":"Ana Stanescu","orcid":"https://orcid.org/0000-0002-7760-3788"},"institutions":[{"id":"https://openalex.org/I189590672","display_name":"Kansas State University","ror":"https://ror.org/05p1j8758","country_code":"US","type":"education","lineage":["https://openalex.org/I189590672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ana Stanescu","raw_affiliation_strings":["Department of Computing and Information Sciences, Kansas State University, Manhattan, KS, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing and Information Sciences, Kansas State University, Manhattan, KS, USA","institution_ids":["https://openalex.org/I189590672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189590672"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00901358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"1","first_page":"40","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9830999970436096,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9523000121116638,"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/machine-learning","display_name":"Machine learning","score":0.773654043674469},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7096426486968994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7060774564743042},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.6126799583435059},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.5995753407478333},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.5147857666015625},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.5059825778007507},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.46511319279670715},{"id":"https://openalex.org/keywords/co-training","display_name":"Co-training","score":0.41003862023353577},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32401043176651},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.30411091446876526},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.11492371559143066},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09781104326248169}],"concepts":[{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.773654043674469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7096426486968994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7060774564743042},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.6126799583435059},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.5995753407478333},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.5147857666015625},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.5059825778007507},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.46511319279670715},{"id":"https://openalex.org/C2776959682","wikidata":"https://www.wikidata.org/wiki/Q17005296","display_name":"Co-training","level":3,"score":0.41003862023353577},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32401043176651},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.30411091446876526},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.11492371559143066},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09781104326248169}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1504/ijbra.2017.10002831","is_oa":false,"landing_page_url":"https://doi.org/10.1504/ijbra.2017.10002831","pdf_url":null,"source":{"id":"https://openalex.org/S207086575","display_name":"International Journal of Bioinformatics Research and Applications","issn_l":"1744-5485","issn":["1744-5485","1744-5493"],"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 Bioinformatics Research and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W5236451","https://openalex.org/W1498183065","https://openalex.org/W1578863401","https://openalex.org/W1594145284","https://openalex.org/W1964421503","https://openalex.org/W1976526581","https://openalex.org/W1978654848","https://openalex.org/W1978982221","https://openalex.org/W1980759842","https://openalex.org/W1981813580","https://openalex.org/W2023639956","https://openalex.org/W2027514285","https://openalex.org/W2042147513","https://openalex.org/W2050754297","https://openalex.org/W2052280136","https://openalex.org/W2053943711","https://openalex.org/W2058207467","https://openalex.org/W2063861171","https://openalex.org/W2071072418","https://openalex.org/W2071983711","https://openalex.org/W2079057609","https://openalex.org/W2079545927","https://openalex.org/W2083061393","https://openalex.org/W2097089247","https://openalex.org/W2099619800","https://openalex.org/W2101210369","https://openalex.org/W2109826612","https://openalex.org/W2114718442","https://openalex.org/W2114875384","https://openalex.org/W2118978333","https://openalex.org/W2119500897","https://openalex.org/W2120040939","https://openalex.org/W2123720722","https://openalex.org/W2129416674","https://openalex.org/W2136490963","https://openalex.org/W2141340736","https://openalex.org/W2142875908","https://openalex.org/W2143745416","https://openalex.org/W2147148726","https://openalex.org/W2148143831","https://openalex.org/W2149024119","https://openalex.org/W2149096772","https://openalex.org/W2151801481","https://openalex.org/W2153720577","https://openalex.org/W2164837103","https://openalex.org/W2167277498","https://openalex.org/W2169813832","https://openalex.org/W2183800414","https://openalex.org/W2785349534","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1520691178","https://openalex.org/W2186473728","https://openalex.org/W1586607209","https://openalex.org/W3142880803","https://openalex.org/W2055666585","https://openalex.org/W2891078859","https://openalex.org/W192740413","https://openalex.org/W1532327008","https://openalex.org/W3216395362","https://openalex.org/W2131153761"],"abstract_inverted_index":{"Thanks":[0],"to":[1,24,112],"Next":[2],"Generation":[3],"Sequencing":[4],"technologies,":[5],"unlabelled":[6,37],"data":[7],"is":[8,91,102,115],"now":[9],"generated":[10],"easily,":[11],"while":[12],"the":[13,94,108],"annotation":[14],"process":[15],"remains":[16],"expensive.":[17],"Semi-supervised":[18],"learning":[19,41,71,125],"represents":[20],"a":[21,66,69,128],"cost-effective":[22],"alternative":[23],"supervised":[25,31,133],"learning,":[26],"as":[27],"it":[28,101],"can":[29],"improve":[30],"classifiers":[32],"by":[33],"making":[34],"use":[35],"of":[36,68,96,110],"data.":[38],"However,":[39],"semi-supervised":[40,70,124],"has":[42],"not":[43],"been":[44],"studied":[45],"much":[46],"for":[47,84,106],"problems":[48],"with":[49,79],"highly":[50],"skewed":[51],"class":[52,87],"distributions,":[53],"which":[54,107],"are":[55,127],"prevalent":[56],"in":[57],"bioinformatics.":[58],"To":[59],"address":[60],"this":[61],"limitation,":[62],"we":[63],"carry":[64],"out":[65],"study":[67,90],"algorithm,":[72],"specifically":[73],"self-training":[74],"based":[75,103],"on":[76,81,93,104],"Na\u00efve":[77],"Bayes,":[78],"focus":[80],"data-level":[82],"approaches":[83],"handling":[85],"imbalanced":[86],"distributions.":[88],"Our":[89,117],"conducted":[92],"problem":[95],"predicting":[97],"splice":[98],"sites":[99],"and":[100],"datasets":[105],"ratio":[109],"positive":[111],"negative":[113],"examples":[114],"1-to-99.":[116],"results":[118],"show":[119],"that":[120],"under":[121],"certain":[122],"conditions":[123],"algorithms":[126],"better":[129],"choice":[130],"than":[131],"purely":[132],"classification":[134],"algorithms.":[135]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}