{"id":"https://openalex.org/W7118087012","doi":"https://doi.org/10.1186/s13015-025-00293-7","title":"Improving spliced alignment by modeling splice sites with deep learning","display_name":"Improving spliced alignment by modeling splice sites with deep learning","publication_year":2026,"publication_date":"2026-01-02","ids":{"openalex":"https://openalex.org/W7118087012","doi":"https://doi.org/10.1186/s13015-025-00293-7","pmid":"https://pubmed.ncbi.nlm.nih.gov/41484786"},"language":"en","primary_location":{"id":"doi:10.1186/s13015-025-00293-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-025-00293-7","pdf_url":null,"source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"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":"Algorithms for Molecular Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s13015-025-00293-7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Siying Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I2801543288","display_name":"Lemuel Shattuck Hospital","ror":"https://ror.org/01wpqwr25","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801543288"]},{"id":"https://openalex.org/I4210117453","display_name":"Dana-Farber Cancer Institute","ror":"https://ror.org/02jzgtq86","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210117453"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siying Yang","raw_affiliation_strings":["Department of Biomedical Informatics, Harvard Medical School, 10 Shattuck St, Boston, MA, 02215, USA","Department of Data Science, Dana-Farber Cancer Institute, 450 Brookline Ave, Boston, MA, 02215, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Harvard Medical School, 10 Shattuck St, Boston, MA, 02215, USA","institution_ids":["https://openalex.org/I136199984","https://openalex.org/I2801543288"]},{"raw_affiliation_string":"Department of Data Science, Dana-Farber Cancer Institute, 450 Brookline Ave, Boston, MA, 02215, USA","institution_ids":["https://openalex.org/I4210117453"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Neng Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I2801543288","display_name":"Lemuel Shattuck Hospital","ror":"https://ror.org/01wpqwr25","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801543288"]},{"id":"https://openalex.org/I4210117453","display_name":"Dana-Farber Cancer Institute","ror":"https://ror.org/02jzgtq86","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210117453"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neng Huang","raw_affiliation_strings":["Department of Biomedical Informatics, Harvard Medical School, 10 Shattuck St, Boston, MA, 02215, USA","Department of Data Science, Dana-Farber Cancer Institute, 450 Brookline Ave, Boston, MA, 02215, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Harvard Medical School, 10 Shattuck St, Boston, MA, 02215, USA","institution_ids":["https://openalex.org/I136199984","https://openalex.org/I2801543288"]},{"raw_affiliation_string":"Department of Data Science, Dana-Farber Cancer Institute, 450 Brookline Ave, Boston, MA, 02215, USA","institution_ids":["https://openalex.org/I4210117453"]}]},{"author_position":"last","author":{"id":null,"display_name":"Heng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I107606265","display_name":"Broad Institute","ror":"https://ror.org/05a0ya142","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I107606265"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I4210117453","display_name":"Dana-Farber Cancer Institute","ror":"https://ror.org/02jzgtq86","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210117453"]},{"id":"https://openalex.org/I4210134579","display_name":"Dana-Farber/Harvard Cancer Center","ror":"https://ror.org/03pvyf116","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I136199984","https://openalex.org/I4210117453","https://openalex.org/I4210134579"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Heng Li","raw_affiliation_strings":["Broad Institute of MIT and Harvard, 415 Main St, Cambridge, MA, 02142, USA. hli@ds.dfci.harvard.edu","Department of Biomedical Informatics, Harvard Medical School, 10 Shattuck St, Boston, MA, 02215, USA. hli@ds.dfci.harvard.edu","Department of Data Science, Dana-Farber Cancer Institute, 450 Brookline Ave, Boston, MA, 02215, USA. hli@ds.dfci.harvard.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Broad Institute of MIT and Harvard, 415 Main St, Cambridge, MA, 02142, USA. hli@ds.dfci.harvard.edu","institution_ids":["https://openalex.org/I107606265"]},{"raw_affiliation_string":"Department of Biomedical Informatics, Harvard Medical School, 10 Shattuck St, Boston, MA, 02215, USA. hli@ds.dfci.harvard.edu","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Department of Data Science, Dana-Farber Cancer Institute, 450 Brookline Ave, Boston, MA, 02215, USA. hli@ds.dfci.harvard.edu","institution_ids":["https://openalex.org/I4210117453","https://openalex.org/I4210134579"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I107606265","https://openalex.org/I136199984","https://openalex.org/I4210117453","https://openalex.org/I4210134579"],"apc_list":{"value":2290,"currency":"USD","value_usd":2290},"apc_paid":{"value":2290,"currency":"USD","value_usd":2290},"fwci":3.8186,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86051636,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"21","issue":"1","first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10604","display_name":"RNA Research and Splicing","score":0.9293000102043152,"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/T10604","display_name":"RNA Research and Splicing","score":0.9293000102043152,"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":0.045499999076128006,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.009800000116229057,"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/deep-learning","display_name":"Deep learning","score":0.781000018119812},{"id":"https://openalex.org/keywords/splice","display_name":"splice","score":0.6625999808311462},{"id":"https://openalex.org/keywords/rna-splicing","display_name":"RNA splicing","score":0.3431999981403351},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3327000141143799},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.2912999987602234}],"concepts":[{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.781000018119812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6656000018119812},{"id":"https://openalex.org/C2780989783","wikidata":"https://www.wikidata.org/wiki/Q7578557","display_name":"splice","level":3,"score":0.6625999808311462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.646399974822998},{"id":"https://openalex.org/C54458228","wikidata":"https://www.wikidata.org/wiki/Q237218","display_name":"RNA splicing","level":4,"score":0.3431999981403351},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3212999999523163},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3089999854564667},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.27720001339912415},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13015-025-00293-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-025-00293-7","pdf_url":null,"source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"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":"Algorithms for Molecular Biology","raw_type":"journal-article"},{"id":"pmid:41484786","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41484786","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":"Algorithms for molecular biology : AMB","raw_type":null},{"id":"pmh:oai:doaj.org/article:c13f4d453e284828bbe8e69738a3e613","is_oa":true,"landing_page_url":"https://doaj.org/article/c13f4d453e284828bbe8e69738a3e613","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":"Algorithms for Molecular Biology, Vol 21, Iss 1, Pp 1-16 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12766944","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12766944/","pdf_url":null,"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":"Algorithms Mol Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13015-025-00293-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-025-00293-7","pdf_url":null,"source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"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":"Algorithms for Molecular Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3516633646","display_name":null,"funder_award_id":"R01 HG010040","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1767772592","https://openalex.org/W1978156257","https://openalex.org/W1987423713","https://openalex.org/W1990210083","https://openalex.org/W1998268440","https://openalex.org/W2034691490","https://openalex.org/W2035564383","https://openalex.org/W2040770546","https://openalex.org/W2074860825","https://openalex.org/W2090544079","https://openalex.org/W2092464006","https://openalex.org/W2096441981","https://openalex.org/W2105360874","https://openalex.org/W2106678197","https://openalex.org/W2107694985","https://openalex.org/W2108787198","https://openalex.org/W2143210482","https://openalex.org/W2149428644","https://openalex.org/W2162889091","https://openalex.org/W2166187656","https://openalex.org/W2166960413","https://openalex.org/W2415174329","https://openalex.org/W2619903165","https://openalex.org/W2789843538","https://openalex.org/W2809541759","https://openalex.org/W2889474202","https://openalex.org/W2906125480","https://openalex.org/W2909194804","https://openalex.org/W2962988145","https://openalex.org/W4226065462","https://openalex.org/W4247292500","https://openalex.org/W4251417264","https://openalex.org/W4319300114","https://openalex.org/W4381802598","https://openalex.org/W4386980271","https://openalex.org/W4394763992","https://openalex.org/W4396730850","https://openalex.org/W4401021906","https://openalex.org/W4401666005","https://openalex.org/W4402582093","https://openalex.org/W4403072018","https://openalex.org/W4403685034","https://openalex.org/W4404473260","https://openalex.org/W4404509621","https://openalex.org/W4404821554","https://openalex.org/W4407820212","https://openalex.org/W4409351113","https://openalex.org/W4409838397"],"related_works":[],"abstract_inverted_index":{"MOTIVATION:":[0],"Spliced":[1],"alignment":[2,6,33],"refers":[3],"to":[4,14,58,93,101,119],"the":[5,26,103,141],"of":[7,28,37,152],"messenger":[8],"RNA":[9],"(mRNA)":[10],"or":[11],"protein":[12,134],"sequences":[13],"eukaryotic":[15],"genomes.":[16,80],"It":[17,81],"plays":[18],"a":[19,63,71],"critical":[20],"role":[21],"in":[22,112],"gene":[23,29],"annotation":[24],"and":[25,69,78,88,95,110,114,117,132,150],"study":[27],"functions.":[30],"Accurate":[31],"spliced":[32],"demands":[34],"sophisticated":[35],"modeling":[36],"splice":[38,60,84],"sites,":[39],"but":[40],"current":[41],"aligners":[42],"use":[43],"simple":[44],"models,":[45],"which":[46],"may":[47],"affect":[48],"their":[49],"accuracy":[50,143],"given":[51],"dissimilar":[52],"sequences.":[53],"RESULTS:":[54],"We":[55,97],"implemented":[56],"minisplice":[57],"learn":[59],"signals":[61,85],"with":[62,73],"one-dimensional":[64],"convolutional":[65],"neural":[66],"network":[67],"(1D-CNN)":[68],"trained":[70],"model":[72,100],"7026":[74],"parameters":[75],"for":[76,107,145],"vertebrate":[77],"insect":[79],"captures":[82],"conserved":[83],"across":[86],"phyla":[87],"reveals":[89],"GC-rich":[90],"introns":[91],"specific":[92],"mammals":[94],"birds.":[96],"used":[98],"this":[99],"estimate":[102],"empirical":[104],"splicing":[105,122],"probability":[106,123],"every":[108],"GT":[109],"AG":[111],"genomes,":[113],"modified":[115],"minimap2":[116],"miniprot":[118],"leverage":[120],"pre-computed":[121],"during":[124],"alignment.":[125],"Evaluation":[126],"on":[127],"human":[128],"long-read":[129],"RNA-seq":[130,148],"data":[131],"cross-species":[133],"datasets":[135],"showed":[136],"our":[137],"method":[138],"greatly":[139],"improves":[140],"junction":[142],"especially":[144],"noisy":[146],"long":[147],"reads":[149],"proteins":[151],"distant":[153],"homology.":[154],"AVAILABILITY":[155],"AND":[156],"IMPLEMENTATION:":[157],"https://github.com/lh3/minisplice.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}