{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:34:00Z","timestamp":1772138040402,"version":"3.50.1"},"reference-count":51,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2020,7,19]],"date-time":"2020-07-19T00:00:00Z","timestamp":1595116800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U24-CA220441"],"award-info":[{"award-number":["U24-CA220441"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01-HG004483"],"award-info":[{"award-number":["R01-HG004483"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01-GM080203"],"award-info":[{"award-number":["R01-GM080203"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010890","name":"Oxford Nanopore Technologies","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010890","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,4,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Many software libraries for using Hidden Markov Models in bioinformatics focus on inference tasks, such as likelihood calculation, parameter-fitting and alignment. However, construction of the state machines can be a laborious task, automation of which would be time-saving and less error-prone.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We present Machine Boss, a software tool implementing not just inference and parameter-fitting algorithms, but also a set of operations for manipulating and combining automata. The aim is to make prototyping of bioinformatics HMMs as quick and easy as the construction of regular expressions, with one-line \u2018recipes\u2019 for many common applications. We report data from several illustrative examples involving protein-to-DNA alignment, DNA data storage and nanopore sequence analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Machine Boss is released under the BSD-3 open source license and is available from http:\/\/machineboss.org\/.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Supplementary information<\/jats:title>\n                    <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaa633","type":"journal-article","created":{"date-parts":[[2020,7,13]],"date-time":"2020-07-13T15:13:41Z","timestamp":1594653221000},"page":"29-35","source":"Crossref","is-referenced-by-count":3,"title":["Machine Boss: rapid prototyping of bioinformatic automata"],"prefix":"10.1093","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6520-5790","authenticated-orcid":false,"given":"Jordi","family":"Silvestre-Ryan","sequence":"first","affiliation":[{"name":"Department of Bioengineering, University of California , Berkeley, CA 94720, USA"}]},{"given":"Yujie","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, University of California , Berkeley, CA 94720, USA"}]},{"given":"Mehak","family":"Sharma","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, University of California , Berkeley, CA 94720, USA"}]},{"given":"Stephen","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, University of California , Berkeley, CA 94720, USA"}]},{"given":"Yolanda","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, University of California , Berkeley, CA 94720, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9647-3643","authenticated-orcid":false,"given":"Shihab","family":"Dider","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, University of California , Berkeley, CA 94720, USA"}]},{"given":"Ian","family":"Holmes","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, University of California , Berkeley, CA 94720, USA"}]}],"member":"286","published-online":{"date-parts":[[2020,7,19]]},"reference":[{"key":"2023051510485157800_btaa633-B1"},{"key":"2023051510485157800_btaa633-B2","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1101\/gr.424203","article-title":"SLAM: cross-species gene finding and alignment with a generalized pair hidden Markov model","volume":"13","author":"Alexandersson","year":"2003","journal-title":"Genome Res"},{"key":"2023051510485157800_btaa633-B3","first-page":"56","volume-title":"Proceedings of the Fifth","author":"Birney","year":"1997"},{"key":"2023051510485157800_btaa633-B4","doi-asserted-by":"crossref","first-page":"988","DOI":"10.1101\/gr.1865504","article-title":"GeneWise and GenomeWise","volume":"14","author":"Birney","year":"2004","journal-title":"Genome Res"},{"key":"2023051510485157800_btaa633-B5","doi-asserted-by":"crossref","first-page":"2529","DOI":"10.1007\/s11538-013-9906-6","article-title":"A note on probabilistic models over strings: the linear algebra approach","volume":"75","author":"Bouchard-C\u00f4t\u00e9","year":"2013","journal-title":"Bull. Math. Biol"},{"key":"2023051510485157800_btaa633-B6","doi-asserted-by":"crossref","first-page":"e0178751","DOI":"10.1371\/journal.pone.0178751","article-title":"DeepNano: deep recurrent neural networks for base calling in MinION nanopore reads","volume":"12","author":"Boza","year":"2017","journal-title":"PLoS ONE"},{"key":"2023051510485157800_btaa633-B7","first-page":"47","volume-title":"Proceedings of the First","author":"Brown","year":"1993"},{"key":"2023051510485157800_btaa633-B8","first-page":"44","volume-title":"Proceedings of the Fourth","author":"Bucher","year":"1996"},{"key":"2023051510485157800_btaa633-B9","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1006\/jmbi.1997.0951","article-title":"Prediction of complete gene structures in human genomic DNA","volume":"268","author":"Burge","year":"1997","journal-title":"J. Mol. Biol"},{"key":"2023051510485157800_btaa633-B10","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1093\/bioinformatics\/btw569","article-title":"Nanocall: an open source basecaller for Oxford Nanopore sequencing data","volume":"33","author":"David","year":"2017","journal-title":"Bioinformatics"},{"key":"2023051510485157800_btaa633-B11","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1101\/gr.2821705","article-title":"ProbCons: probabilistic consistency-based multiple sequence alignment","volume":"15","author":"Do","year":"2005","journal-title":"Genome Res"},{"key":"2023051510485157800_btaa633-B12","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511790492","volume-title":"Biological Sequence Analysis: Probabilistic Models of Proteins and Nucleic Acids","author":"Durbin","year":"1998"},{"key":"2023051510485157800_btaa633-B13","first-page":"205","article-title":"A new generation of homology search tools based on probabilistic inference","volume":"23","author":"Eddy","year":"2009","journal-title":"Genome Inform"},{"key":"2023051510485157800_btaa633-B14","doi-asserted-by":"crossref","first-page":"D427","DOI":"10.1093\/nar\/gky995","article-title":"The Pfam protein families database in 2019","volume":"47","author":"El-Gebali","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023051510485157800_btaa633-B15","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1038\/nature11875","article-title":"Towards practical, high-capacity, low-maintenance information storage in synthesized DNA","volume":"494","author":"Goldman","year":"2013","journal-title":"Nature"},{"key":"2023051510485157800_btaa633-B16","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1016\/0022-2836(82)90398-9","article-title":"An improved algorithm for matching biological sequences","volume":"162","author":"Gotoh","year":"1982","journal-title":"J. Mol. Biol"},{"key":"2023051510485157800_btaa633-B17","first-page":"369","author":"Graves","year":"2006"},{"key":"2023051510485157800_btaa633-B18","doi-asserted-by":"crossref","first-page":"4355","DOI":"10.1073\/pnas.84.13.4355","article-title":"Profile analysis: detection of distantly related proteins","volume":"84","author":"Gribskov","year":"1987","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023051510485157800_btaa633-B19"},{"key":"2023051510485157800_btaa633-B20","doi-asserted-by":"crossref","first-page":"1227","DOI":"10.1093\/bioinformatics\/btw791","article-title":"Historian: accurate reconstruction of ancestral sequences and evolutionary rates","volume":"33","author":"Holmes","year":"2017","journal-title":"Bioinformatics"},{"key":"2023051510485157800_btaa633-B21","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1093\/bioinformatics\/17.9.803","article-title":"Evolutionary HMMs: a Bayesian approach to multiple alignment","volume":"17","author":"Holmes","year":"2001","journal-title":"Bioinformatics"},{"key":"2023051510485157800_btaa633-B22","doi-asserted-by":"crossref","first-page":"D81","DOI":"10.1093\/nar\/gkv1272","article-title":"The Dfam database of repetitive DNA families","volume":"44","author":"Hubley","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023051510485157800_btaa633-B23","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1038\/nmeth.3290","article-title":"Improved data analysis for the MinION nanopore sequencer","volume":"12","author":"Jain","year":"2015","journal-title":"Nat. Methods"},{"key":"2023051510485157800_btaa633-B24","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1038\/nbt.4060","article-title":"Nanopore sequencing and assembly of a human genome with ultra-long reads","volume":"36","author":"Jain","year":"2018","journal-title":"Nat. Biotechnol"},{"key":"2023051510485157800_btaa633-B25","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/B978-1-4832-3211-9.50009-7","volume-title":"Mammalian Protein Metabolism","author":"Jukes","year":"1969"},{"key":"2023051510485157800_btaa633-B26"},{"key":"2023051510485157800_btaa633-B27","doi-asserted-by":"crossref","first-page":"e139","DOI":"10.1093\/nar\/gkp662","article-title":"HMMCONVERTER 1.0: a toolbox for hidden Markov models","volume":"37","author":"Lam","year":"2009","journal-title":"Nucleic Acids Res"},{"key":"2023051510485157800_btaa633-B28","doi-asserted-by":"crossref","first-page":"3094","DOI":"10.1093\/bioinformatics\/bty191","article-title":"Minimap2: pairwise alignment for nucleotide sequences","volume":"34","author":"Li","year":"2018","journal-title":"Bioinformatics"},{"key":"2023051510485157800_btaa633-B29","doi-asserted-by":"crossref","first-page":"1625","DOI":"10.1093\/bioinformatics\/btu057","article-title":"StochHMM: a flexible hidden Markov model tool and C++ library","volume":"30","author":"Lott","year":"2014","journal-title":"Bioinformatics"},{"key":"2023051510485157800_btaa633-B30","doi-asserted-by":"crossref","first-page":"10557","DOI":"10.1073\/pnas.0409137102","article-title":"An algorithm for progressive multiple alignment of sequences with insertions","volume":"102","author":"L\u00f6ytynoja","year":"2005","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023051510485157800_btaa633-B31","doi-asserted-by":"crossref","first-page":"2485","DOI":"10.1093\/bioinformatics\/btm350","article-title":"HMMoC\u2014a compiler for hidden Markov models","volume":"23","author":"Lunter","year":"2007","journal-title":"Bioinformatics"},{"key":"2023051510485157800_btaa633-B32","doi-asserted-by":"crossref","first-page":"776","DOI":"10.1093\/nar\/gkh211","article-title":"Gene structure conservation aids similarity based gene prediction","volume":"32","author":"Meyer","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2023051510485157800_btaa633-B33","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1006\/csla.2001.0184","article-title":"Weighted finite-state transducers in speech recognition","volume":"16","author":"Mohri","year":"2002","journal-title":"Comput. Speech Lang"},{"key":"2023051510485157800_btaa633-B34","first-page":"129","volume-title":"Automata Studies","author":"Moore","year":"1956"},{"key":"2023051510485157800_btaa633-B35","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1016\/0022-2836(70)90057-4","article-title":"A general method applicable to the search for similarities in the amino acid sequence of two proteins","volume":"48","author":"Needleman","year":"1970","journal-title":"J. Mol. Biol"},{"key":"2023051510485157800_btaa633-B36","doi-asserted-by":"crossref","first-page":"e1004409","DOI":"10.1371\/journal.pcbi.1004409","article-title":"Consistency of VDJ rearrangement and substitution parameters enables accurate B cell receptor sequence annotation","volume":"12","author":"Ralph","year":"2016","journal-title":"PLoS Comput. Biol"},{"key":"2023051510485157800_btaa633-B37","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1080\/10635150590947041","article-title":"Joint Bayesian estimation of alignment and phylogeny","volume":"54","author":"Redelings","year":"2005","journal-title":"Syst. Biol"},{"key":"2023051510485157800_btaa633-B38","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1186\/1471-2148-7-40","article-title":"Incorporating indel information into phylogeny estimation for rapidly emerging pathogens","volume":"7","author":"Redelings","year":"2007","journal-title":"BMC Evol. Biol"},{"key":"2023051510485157800_btaa633-B39"},{"key":"2023051510485157800_btaa633-B40","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1093\/molbev\/msh039","article-title":"Phylogenetic estimation of context- dependent substitution rates by maximum likelihood","volume":"21","author":"Siepel","year":"2003","journal-title":"Mol. Biol. Evol"},{"key":"2023051510485157800_btaa633-B41","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1007\/11732990_17","volume-title":"Research in Computational Molecular Biology","author":"Siepel","year":"2006"},{"key":"2023051510485157800_btaa633-B42"},{"key":"2023051510485157800_btaa633-B86356144","author":"and","year":"2020"},{"key":"2023051510485157800_btaa633-B43","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1186\/1471-2105-6-31","article-title":"Automated generation of heuristics for biological sequence comparison","volume":"6","author":"Slater","year":"2005","journal-title":"BMC Bioinformatics"},{"key":"2023051510485157800_btaa633-B44","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/0022-2836(81)90087-5","article-title":"Identification of common molecular subsequences","volume":"147","author":"Smith","year":"1981","journal-title":"J. Mol. Biol"},{"key":"2023051510485157800_btaa633-B45","doi-asserted-by":"crossref","first-page":"2047","DOI":"10.1093\/bioinformatics\/btl175","article-title":"BAli-Phy: simultaneous Bayesian inference of alignment and phylogeny","volume":"22","author":"Suchard","year":"2006","journal-title":"Bioinformatics"},{"key":"2023051510485157800_btaa633-B46"},{"key":"2023051510485157800_btaa633-B47","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1007\/BF02193625","article-title":"An evolutionary model for maximum likelihood alignment of DNA sequences","volume":"33","author":"Thorne","year":"1991","journal-title":"J. Mol. Evol"},{"key":"2023051510485157800_btaa633-B48","doi-asserted-by":"crossref","first-page":"2562","DOI":"10.1093\/bioinformatics\/btw196","article-title":"Muxstep: an open-source C ++ multiplex HMM library for making inferences on multiple data types","volume":"32","author":"Veli\u010dkovi\u0107","year":"2016","journal-title":"Bioinformatics"},{"key":"2023051510485157800_btaa633-B49","doi-asserted-by":"crossref","first-page":"e34572","DOI":"10.1371\/journal.pone.0034572","article-title":"Accurate reconstruction of insertion-deletion histories by statistical phylogenetics","volume":"7","author":"Westesson","year":"2012","journal-title":"PLoS One"},{"key":"2023051510485157800_btaa633-B50","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1186\/s13059-019-1727-y","article-title":"Performance of neural network basecalling tools for Oxford Nanopore sequencing","volume":"20","author":"Wick","year":"2019","journal-title":"Genome Biol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaa633\/35137742\/btaa633.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/1\/29\/50321754\/btaa633.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/1\/29\/50321754\/btaa633.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T06:51:28Z","timestamp":1684133488000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/37\/1\/29\/5873580"}},"subtitle":[],"editor":[{"given":"Jinbo","family":"Xu","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2020,7,19]]},"references-count":51,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,4,9]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa633","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.02.13.945071","asserted-by":"object"}]},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,1,1]]},"published":{"date-parts":[[2020,7,19]]}}}