{"id":"https://openalex.org/W4316926647","doi":"https://doi.org/10.1093/bioinformatics/btad014","title":"Protein-to-genome alignment with miniprot","display_name":"Protein-to-genome alignment with miniprot","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4316926647","doi":"https://doi.org/10.1093/bioinformatics/btad014","pmid":"https://pubmed.ncbi.nlm.nih.gov/36648328"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btad014","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad014","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btad014/48827638/btad014.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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","license_id":"https://openalex.org/licenses/cc-by","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":"gold","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btad014/48827638/btad014.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100338825","display_name":"Heng Li","orcid":"https://orcid.org/0000-0003-4874-2874"},"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/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":true,"raw_author_name":"Heng Li","raw_affiliation_strings":["Department of Biomedical Informatics, Harvard Medical School , Boston, MA 02115, USA","Department of Data Sciences, Dana-Farber Cancer Institute , Boston, MA 02215, USA"],"raw_orcid":"https://orcid.org/0000-0003-4874-2874","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Harvard Medical School , Boston, MA 02115, USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Department of Data Sciences, Dana-Farber Cancer Institute , Boston, MA 02215, USA","institution_ids":["https://openalex.org/I4210117453"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100338825"],"corresponding_institution_ids":["https://openalex.org/I136199984","https://openalex.org/I4210117453"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":40.8959,"has_fulltext":true,"cited_by_count":449,"citation_normalized_percentile":{"value":0.99927861,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"39","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.5827999711036682,"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":0.5827999711036682,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.09000000357627869,"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":0.07460000365972519,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7332521080970764},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.7096925377845764},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.6997407674789429},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.42725181579589844},{"id":"https://openalex.org/keywords/genome-project","display_name":"Genome project","score":0.4153469204902649},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.2835318148136139},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.19493231177330017},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1748121678829193},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12637892365455627}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7332521080970764},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.7096925377845764},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.6997407674789429},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.42725181579589844},{"id":"https://openalex.org/C89566754","wikidata":"https://www.wikidata.org/wiki/Q2273828","display_name":"Genome project","level":4,"score":0.4153469204902649},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2835318148136139},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.19493231177330017},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1748121678829193},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12637892365455627}],"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":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","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":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btad014","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad014","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btad014/48827638/btad014.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:36648328","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36648328","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":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9869432","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9869432","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC9869432/pdf/btad014.pdf","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btad014","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad014","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btad014/48827638/btad014.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","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"},{"id":"https://openalex.org/G4594819197","display_name":null,"funder_award_id":"237653","funder_id":"https://openalex.org/F4320315474","funder_display_name":"Chan Zuckerberg Initiative"}],"funders":[{"id":"https://openalex.org/F4320315474","display_name":"Chan Zuckerberg Initiative","ror":"https://ror.org/02qenvm24"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4316926647.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1767772592","https://openalex.org/W1978156257","https://openalex.org/W1983265703","https://openalex.org/W1987423713","https://openalex.org/W1993204833","https://openalex.org/W1998268440","https://openalex.org/W2006290495","https://openalex.org/W2039984281","https://openalex.org/W2040770546","https://openalex.org/W2099753867","https://openalex.org/W2103074382","https://openalex.org/W2106678197","https://openalex.org/W2108108770","https://openalex.org/W2108787198","https://openalex.org/W2138122982","https://openalex.org/W2143210482","https://openalex.org/W2146379626","https://openalex.org/W2149428644","https://openalex.org/W2162889091","https://openalex.org/W2168292723","https://openalex.org/W2169456326","https://openalex.org/W2169669582","https://openalex.org/W2194172909","https://openalex.org/W2415174329","https://openalex.org/W2464717012","https://openalex.org/W2610344215","https://openalex.org/W2789843538","https://openalex.org/W2802282671","https://openalex.org/W2941885741","https://openalex.org/W2950954328","https://openalex.org/W2952306768","https://openalex.org/W2968499116","https://openalex.org/W2995527562","https://openalex.org/W3015796860","https://openalex.org/W3025319533","https://openalex.org/W3047598142","https://openalex.org/W3049406222","https://openalex.org/W3113162057","https://openalex.org/W3119984181","https://openalex.org/W3128198169","https://openalex.org/W3159728495","https://openalex.org/W3186309583","https://openalex.org/W3193844559","https://openalex.org/W4220668127","https://openalex.org/W4236356242","https://openalex.org/W6675739661"],"related_works":["https://openalex.org/W2773247701","https://openalex.org/W2951353021","https://openalex.org/W1969895229","https://openalex.org/W1560725704","https://openalex.org/W3047903919","https://openalex.org/W4386028668","https://openalex.org/W2045048100","https://openalex.org/W2132017020","https://openalex.org/W2135598780","https://openalex.org/W2670416469"],"abstract_inverted_index":{"MOTIVATION:":[0],"Protein-to-genome":[1],"alignment":[2,37],"is":[3,88],"critical":[4],"to":[5,71],"annotating":[6],"genes":[7],"in":[8,36],"non-model":[9],"organisms.":[10],"While":[11],"there":[12],"are":[13,40],"a":[14,64,72],"few":[15],"tools":[16,95],"for":[17,67],"this":[18],"purpose,":[19],"all":[20],"of":[21,51,90],"them":[22],"were":[23],"developed":[24],"over":[25],"10":[26],"years":[27],"ago":[28],"and":[29,42,54,83],"did":[30],"not":[31,44],"incorporate":[32],"the":[33,48],"latest":[34],"advances":[35],"algorithms.":[38],"They":[39],"inefficient":[41],"could":[43],"keep":[45],"up":[46],"with":[47],"rapid":[49],"production":[50],"new":[52,65],"genomes":[53],"quickly":[55],"growing":[56],"protein":[57,69],"databases.":[58],"RESULTS:":[59],"Here,":[60],"we":[61],"describe":[62],"miniprot,":[63],"aligner":[66],"mapping":[68],"sequences":[70],"complete":[73],"genome.":[74],"Miniprot":[75],"integrates":[76],"recent":[77],"techniques":[78],"such":[79],"as":[80],"k-mer":[81],"sketch":[82],"vectorized":[84],"dynamic":[85],"programming.":[86],"It":[87],"tens":[89],"times":[91],"faster":[92],"than":[93],"existing":[94],"while":[96],"achieving":[97],"comparable":[98],"accuracy":[99],"on":[100],"real":[101],"data.":[102],"AVAILABILITY":[103],"AND":[104],"IMPLEMENTATION:":[105],"https://github.com/lh3/miniport.":[106]},"counts_by_year":[{"year":2026,"cited_by_count":97},{"year":2025,"cited_by_count":194},{"year":2024,"cited_by_count":111},{"year":2023,"cited_by_count":45},{"year":2022,"cited_by_count":2}],"updated_date":"2026-08-14T07:06:38.338062","created_date":"2025-10-10T00:00:00"}
