{"id":"https://openalex.org/W2737787616","doi":"https://doi.org/10.1093/bioinformatics/btx451","title":"PySeqLab: an open source Python package for sequence labeling and segmentation","display_name":"PySeqLab: an open source Python package for sequence labeling and segmentation","publication_year":2017,"publication_date":"2017-07-20","ids":{"openalex":"https://openalex.org/W2737787616","doi":"https://doi.org/10.1093/bioinformatics/btx451","mag":"2737787616","pmid":"https://pubmed.ncbi.nlm.nih.gov/29036277"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btx451","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx451","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/21/3497/25166073/btx451.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":null,"license_id":null,"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":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/33/21/3497/25166073/btx451.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062401184","display_name":"Ahmed Allam","orcid":"https://orcid.org/0000-0003-0871-1977"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ahmed Allam","raw_affiliation_strings":["Department of Pathology, Yale School of Medicine, New Haven, CT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pathology, Yale School of Medicine, New Haven, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025057284","display_name":"Michael Krauthammer","orcid":"https://orcid.org/0000-0002-4808-1845"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael Krauthammer","raw_affiliation_strings":["Department of Pathology, Yale School of Medicine, New Haven, CT, USA","Program in Computational Biology and Bioinformatics, Yale University, New Haven, CT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pathology, Yale School of Medicine, New Haven, CT, USA","institution_ids":["https://openalex.org/I32971472"]},{"raw_affiliation_string":"Program in Computational Biology and Bioinformatics, Yale University, New Haven, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025057284","https://openalex.org/A5062401184"],"corresponding_institution_ids":["https://openalex.org/I32971472"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.2243,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.5629238,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"33","issue":"21","first_page":"3497","last_page":"3499"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.5074999928474426,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.5074999928474426,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.04129999876022339,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.041099999099969864,"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/python","display_name":"Python (programming language)","score":0.8696192502975464},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.7359753251075745},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6609926223754883},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5315900444984436},{"id":"https://openalex.org/keywords/open-source-software","display_name":"Open source software","score":0.4511522352695465},{"id":"https://openalex.org/keywords/r-package","display_name":"R package","score":0.4421963393688202},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.44094738364219666},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4244147837162018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34294021129608154},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3365193009376526},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12373241782188416},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.11626097559928894}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8696192502975464},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.7359753251075745},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6609926223754883},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5315900444984436},{"id":"https://openalex.org/C2988343187","wikidata":"https://www.wikidata.org/wiki/Q1130645","display_name":"Open source software","level":3,"score":0.4511522352695465},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.4421963393688202},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.44094738364219666},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4244147837162018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34294021129608154},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3365193009376526},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12373241782188416},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.11626097559928894}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","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}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btx451","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx451","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/21/3497/25166073/btx451.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:29036277","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29036277","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:europepmc.org:5156283","is_oa":false,"landing_page_url":"http://europepmc.org/pmc/articles/PMC5872256","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:5872256","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5872256","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btx451","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx451","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/21/3497/25166073/btx451.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G3426009499","display_name":null,"funder_award_id":"P01 CA016038","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G4585155553","display_name":null,"funder_award_id":"P2TIP1_161635","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G6799854068","display_name":null,"funder_award_id":"P50 CA121974","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W162171320","https://openalex.org/W1991133427","https://openalex.org/W2008652694","https://openalex.org/W2021738903","https://openalex.org/W2047782770","https://openalex.org/W2073401630","https://openalex.org/W2102486516","https://openalex.org/W2107438106","https://openalex.org/W2114720696","https://openalex.org/W2117667029","https://openalex.org/W2131148434","https://openalex.org/W2147880316","https://openalex.org/W2158188757","https://openalex.org/W2165073960","https://openalex.org/W2562053465","https://openalex.org/W6675672627","https://openalex.org/W6676105031","https://openalex.org/W6677340584","https://openalex.org/W6677588314","https://openalex.org/W6684187845"],"related_works":["https://openalex.org/W4376877853","https://openalex.org/W2557718140","https://openalex.org/W67092138","https://openalex.org/W1493891899","https://openalex.org/W4225687299","https://openalex.org/W4250928611","https://openalex.org/W4232280318","https://openalex.org/W166480398","https://openalex.org/W167327709","https://openalex.org/W4387839566"],"abstract_inverted_index":{"MOTIVATION:":[0],"Text":[1],"and":[2,13,87,113,126,139,146,152,159,169,188,226],"genomic":[3],"data":[4,235],"are":[5,155,236],"composed":[6],"of":[7,41,48,161,213],"sequential":[8,52],"tokens,":[9],"such":[10,106],"as":[11,107],"words":[12],"nucleotides":[14],"that":[15,76],"give":[16],"rise":[17],"to":[18,83,91,197],"higher":[19],"order":[20],"syntactic":[21],"constructs.":[22],"In":[23],"this":[24],"work,":[25],"we":[26,165],"aim":[27],"at":[28,238],"providing":[29],"a":[30,39],"comprehensive":[31],"Python":[32,55],"library":[33],"implementing":[34],"conditional":[35],"random":[36],"fields":[37],"(CRFs),":[38],"class":[40],"probabilistic":[42,134],"graphical":[43],"models,":[44,75],"for":[45,64,102,143,157],"robust":[46],"prediction":[47,70],"these":[49],"constructs":[50],"from":[51,80,88],"data.":[53],"RESULTS:":[54],"Sequence":[56],"Labeling":[57],"(PySeqLab)":[58],"is":[59,77,220],"an":[60,141],"open":[61],"source":[62],"package":[63],"performing":[65],"supervised":[66],"learning":[67,100,136],"in":[68,173,203],"structured":[69,118],"tasks.":[71],"It":[72],"implements":[73],"CRFs":[74,94],"discriminative":[78],"models":[79,167],"(i)":[81,108,177],"first-order":[82,90],"higher-order":[84,92],"linear-chain":[85],"CRFs,":[86],"(ii)":[89,117,183],"semi-Markov":[93],"(semi-CRFs).":[95],"Moreover,":[96],"it":[97],"provides":[98],"multiple":[99,115,121],"algorithms":[101],"estimating":[103],"model":[104],"parameters":[105],"stochastic":[109],"gradient":[110],"descent":[111],"(SGD)":[112],"its":[114],"variations,":[116],"perceptron":[119],"with":[120,224],"averaging":[122],"schemes":[123],"supporting":[124],"exact":[125],"inexact":[127],"search":[128],"using":[129],"'violation-fixing'":[130],"framework,":[131],"(iii)":[132,189],"search-based":[133],"online":[135],"algorithm":[137],"(SAPO)":[138],"(iv)":[140],"interface":[142],"Broyden-Fletcher-Goldfarb-Shanno":[144],"(BFGS)":[145],"the":[147,204,211],"limited-memory":[148],"BFGS":[149],"algorithms.":[150],"Viterbi":[151,153],"A*":[154],"used":[156],"inference":[158],"decoding":[160],"sequences.":[162],"Using":[163],"PySeqLab,":[164],"built":[166],"(classifiers)":[168],"evaluated":[170],"their":[171],"performance":[172,195],"three":[174,205],"different":[175],"domains:":[176],"biomedical":[178],"Natural":[179],"language":[180],"processing":[181],"(NLP),":[182],"predictive":[184],"DNA":[185],"sequence":[186],"analysis":[187],"Human":[190],"activity":[191],"recognition":[192],"(HAR).":[193],"State-of-the-art":[194],"comparable":[196],"machine-learning":[198],"based":[199],"systems":[200],"was":[201],"achieved":[202],"domains":[206],"without":[207],"feature":[208],"engineering":[209],"or":[210,230],"use":[212],"knowledge":[214],"sources.":[215],"AVAILABILITY":[216],"AND":[217],"IMPLEMENTATION:":[218],"PySeqLab":[219],"available":[221,237],"through":[222],"https://bitbucket.org/A_2/pyseqlab":[223],"tutorials":[225],"documentation.":[227],"CONTACT:":[228],"ahmed.allam@yale.edu":[229],"michael.krauthammer@yale.edu.":[231],"SUPPLEMENTARY":[232],"INFORMATION:":[233],"Supplementary":[234],"Bioinformatics":[239],"online.":[240]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
