{"id":"https://openalex.org/W2109497857","doi":"https://doi.org/10.1186/1471-2105-5-157","title":"Gapped alignment of protein sequence motifs through Monte Carlo optimization of a hidden Markov model","display_name":"Gapped alignment of protein sequence motifs through Monte Carlo optimization of a hidden Markov model","publication_year":2004,"publication_date":"2004-10-25","ids":{"openalex":"https://openalex.org/W2109497857","doi":"https://doi.org/10.1186/1471-2105-5-157","mag":"2109497857","pmid":"https://pubmed.ncbi.nlm.nih.gov/15504234"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-5-157","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-5-157","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-5-157","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-5-157","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010571747","display_name":"Andrew F. Neuwald","orcid":"https://orcid.org/0000-0002-0086-5755"},"institutions":[{"id":"https://openalex.org/I2750212522","display_name":"Cold Spring Harbor Laboratory","ror":"https://ror.org/02qz8b764","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2750212522"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew F Neuwald","raw_affiliation_strings":["Cold Spring Harbor Laboratory, 1 Bungtown Road, P,O, Box 100, Cold Spring Harbor, NY 11724, USA. neuwald@cshl.org","Cold Spring Harbor Laboratory Cold Spring Harbor USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cold Spring Harbor Laboratory, 1 Bungtown Road, P,O, Box 100, Cold Spring Harbor, NY 11724, USA. neuwald@cshl.org","institution_ids":["https://openalex.org/I2750212522"]},{"raw_affiliation_string":"Cold Spring Harbor Laboratory Cold Spring Harbor USA","institution_ids":["https://openalex.org/I2750212522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012820890","display_name":"Jun S. Liu","orcid":"https://orcid.org/0000-0002-4450-7239"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun S Liu","raw_affiliation_strings":["Department of Statistics, Harvard University, 1 Oxford Street, Cambridge, MA, 02138, USA","Dept of Statistics, Harvard University, Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Harvard University, 1 Oxford Street, Cambridge, MA, 02138, USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Dept of Statistics, Harvard University, Cambridge, USA","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010571747"],"corresponding_institution_ids":["https://openalex.org/I2750212522"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":1.5872,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":{"value":0.81870146,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"5","issue":"1","first_page":"157","last_page":"157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.7591999769210815,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.7591999769210815,"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/T12505","display_name":"Peptidase Inhibition and Analysis","score":0.023399999365210533,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.021800000220537186,"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/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.7764215469360352},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.6351094841957092},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6251856088638306},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.604804277420044},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5770180225372314},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5196253657341003},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5107543468475342},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4497497081756592},{"id":"https://openalex.org/keywords/alignment-free-sequence-analysis","display_name":"Alignment-free sequence analysis","score":0.4330310821533203},{"id":"https://openalex.org/keywords/conserved-sequence","display_name":"Conserved sequence","score":0.4161013662815094},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3617742359638214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24743065237998962},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.239446759223938},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20972105860710144},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.19066956639289856},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1220259964466095}],"concepts":[{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.7764215469360352},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.6351094841957092},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6251856088638306},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.604804277420044},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5770180225372314},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5196253657341003},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5107543468475342},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4497497081756592},{"id":"https://openalex.org/C180384323","wikidata":"https://www.wikidata.org/wiki/Q16335137","display_name":"Alignment-free sequence analysis","level":5,"score":0.4330310821533203},{"id":"https://openalex.org/C199216141","wikidata":"https://www.wikidata.org/wiki/Q4995178","display_name":"Conserved sequence","level":4,"score":0.4161013662815094},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3617742359638214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24743065237998962},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.239446759223938},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20972105860710144},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.19066956639289856},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1220259964466095},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000085822","descriptor_name":"Prolyl Oligopeptidases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000085822","descriptor_name":"Prolyl Oligopeptidases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000085822","descriptor_name":"Prolyl Oligopeptidases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D006867","descriptor_name":"Hydrolases","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D006867","descriptor_name":"Hydrolases","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D006867","descriptor_name":"Hydrolases","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009010","descriptor_name":"Monte Carlo Method","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009010","descriptor_name":"Monte Carlo Method","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009010","descriptor_name":"Monte Carlo Method","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012697","descriptor_name":"Serine Endopeptidases","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012697","descriptor_name":"Serine Endopeptidases","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012697","descriptor_name":"Serine Endopeptidases","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D015801","descriptor_name":"Helminth Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D015801","descriptor_name":"Helminth Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D015801","descriptor_name":"Helminth Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017434","descriptor_name":"Protein Structure, Tertiary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017434","descriptor_name":"Protein Structure, Tertiary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017434","descriptor_name":"Protein Structure, Tertiary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019843","descriptor_name":"Archaeal Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D019843","descriptor_name":"Archaeal Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D019843","descriptor_name":"Archaeal Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D020558","descriptor_name":"GTP Phosphohydrolases","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D020558","descriptor_name":"GTP Phosphohydrolases","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D020558","descriptor_name":"GTP Phosphohydrolases","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1186/1471-2105-5-157","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-5-157","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-5-157","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:15504234","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15504234","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:repository.cshl.edu:22449","is_oa":true,"landing_page_url":null,"pdf_url":"http://repository.cshl.edu/22449/1/Neuwald%20BMC%20Bioinformatics%202005.pdf","source":{"id":"https://openalex.org/S4306402288","display_name":"Cold Spring Harbor Laboratory Institutional Repository (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Paper"},{"id":"pmh:oai:dash.harvard.edu:1/4460793","is_oa":true,"landing_page_url":"http://nrs.harvard.edu/urn-3:HUL.InstRepos:4460793","pdf_url":null,"source":{"id":"https://openalex.org/S4306401540","display_name":"Digital Access to Scholarship at Harvard (DASH) (Harvard University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I136199984","host_organization_name":"Harvard University","host_organization_lineage":["https://openalex.org/I136199984"],"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":"","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:5d85b558e2a54df3bed6f1a920d6d031","is_oa":false,"landing_page_url":"https://doaj.org/article/5d85b558e2a54df3bed6f1a920d6d031","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 5, Iss 1, p 157 (2004)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:538276","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/538276","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":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-5-157","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-5-157","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-5-157","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Life in Land","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/15"}],"awards":[{"id":"https://openalex.org/G50761733","display_name":null,"funder_award_id":"LM06747","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G7565911052","display_name":null,"funder_award_id":"R01 LM006747","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2109497857.pdf","grobid_xml":"https://content.openalex.org/works/W2109497857.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1519266993","https://openalex.org/W1875835053","https://openalex.org/W1970999032","https://openalex.org/W1973715716","https://openalex.org/W1992671721","https://openalex.org/W2010958487","https://openalex.org/W2011269026","https://openalex.org/W2024060531","https://openalex.org/W2028904598","https://openalex.org/W2034079834","https://openalex.org/W2038580923","https://openalex.org/W2045312812","https://openalex.org/W2047745952","https://openalex.org/W2051151530","https://openalex.org/W2067911054","https://openalex.org/W2069739265","https://openalex.org/W2077013196","https://openalex.org/W2082628285","https://openalex.org/W2089657469","https://openalex.org/W2097555181","https://openalex.org/W2101026479","https://openalex.org/W2106882534","https://openalex.org/W2114479908","https://openalex.org/W2120527610","https://openalex.org/W2127774996","https://openalex.org/W2132926880","https://openalex.org/W2134043769","https://openalex.org/W2140244239","https://openalex.org/W2144362290","https://openalex.org/W2145295592","https://openalex.org/W2148311769","https://openalex.org/W2151831732","https://openalex.org/W2158714788","https://openalex.org/W2163507574","https://openalex.org/W2414307244","https://openalex.org/W4244250644"],"related_works":["https://openalex.org/W2051969447","https://openalex.org/W2133116680","https://openalex.org/W2111937814","https://openalex.org/W2141411672","https://openalex.org/W2091678889","https://openalex.org/W1482324242","https://openalex.org/W187239587","https://openalex.org/W2730968108","https://openalex.org/W4386770652","https://openalex.org/W2158700816"],"abstract_inverted_index":{"BACKGROUND:":[0],"Certain":[1],"protein":[2,26,223],"families":[3],"are":[4,29,168,209,303],"highly":[5],"conserved":[6,129],"across":[7],"distantly":[8,135,263],"related":[9,136,264],"organisms":[10],"and":[11,15,47,80,123,150,174,229,266,300],"belong":[12],"to":[13,31,44,125],"large":[14,132],"functionally":[16],"diverse":[17],"superfamilies.":[18],"The":[19,102,164],"patterns":[20,62,97],"of":[21,66,89,92,104,112,120,128,134,160,193,218,221,273,287],"conservation":[22],"present":[23],"in":[24,98,206],"these":[25,61,255,279,298],"sequences":[27,265],"presumably":[28],"due":[30],"selective":[32,93,274],"constraints":[33,42,94],"maintaining":[34],"important":[35],"but":[36],"unknown":[37],"structural":[38],"mechanisms":[39],"with":[40,211],"some":[41,277],"specific":[43,178],"each":[45],"family":[46],"others":[48],"shared":[49],"by":[50,55],"a":[51,64,72,99,142,270,284],"larger":[52],"subset":[53],"or":[54],"the":[56,87,110,113,216,306],"entire":[57],"superfamily.":[58],"To":[59],"exploit":[60],"as":[63,196,198,290],"source":[65],"functional":[67],"information,":[68],"we":[69,140,291],"recently":[70],"devised":[71],"statistically":[73],"based":[74,213,242],"approach":[75,106],"called":[76],"contrast":[77],"hierarchical":[78],"alignment":[79,127,159,172,184,194],"interaction":[81],"network":[82],"(CHAIN)":[83],"analysis,":[84],"which":[85,116,244],"infers":[86],"strengths":[88],"various":[90],"categories":[91],"from":[95,305],"co-conserved":[96],"multiple":[100,114,161],"alignment.":[101],"power":[103],"this":[105,207,253],"strongly":[107],"depends":[108],"on":[109],"quality":[111,195],"alignments,":[115,243],"thus":[117,267],"motivated":[118],"development":[119],"theoretical":[121],"concepts":[122],"strategies":[124,157,167],"improve":[126],"motifs":[130],"within":[131,215],"sets":[133],"sequences.":[137],"RESULTS:":[138],"Here":[139],"describe":[141],"hidden":[143],"Markov":[144,151],"model":[145],"(HMM),":[146],"an":[147,190],"algebraic":[148],"system,":[149],"chain":[152],"Monte":[153],"Carlo":[154],"(MCMC)":[155],"sampling":[156,166],"for":[158,171,175,183,249,293],"sequence":[162],"motifs.":[163],"MCMC":[165],"useful":[169],"both":[170],"optimization":[173],"adjusting":[176],"position":[177],"background":[179],"amino":[180],"acid":[181],"frequencies":[182],"uncertainties.":[185],"Associated":[186],"statistical":[187],"formulations":[188],"provide":[189,269,283],"objective":[191],"measure":[192,272],"well":[197],"automatic":[199],"gap":[200],"penalty":[201],"optimization.":[202],"Improved":[203],"alignments":[204,214],"obtained":[205],"way":[208],"compared":[210],"PSI-BLAST":[212,241],"context":[217],"CHAIN":[219,250],"analysis":[220,251],"three":[222],"families:":[224],"Gialpha":[225],"subunits,":[226],"prolyl":[227],"oligopeptidases,":[228],"transitional":[230],"endoplasmic":[231],"reticulum":[232],"(p97)":[233],"AAA+":[234],"ATPases.":[235,295],"CONCLUSION:":[236],"While":[237],"not":[238],"entirely":[239],"replacing":[240],"likewise":[245],"may":[246],"be":[247],"optimized":[248],"using":[252],"approach,":[254],"motif-based":[256],"methods":[257],"often":[258],"more":[259],"accurately":[260],"align":[261],"very":[262],"can":[268],"better":[271,285],"constraints.":[275],"In":[276],"instances,":[278],"new":[280],"approaches":[281],"also":[282],"understanding":[286],"family-specific":[288],"constraints,":[289],"illustrate":[292],"p97":[294],"Programs":[296],"implementing":[297],"procedures":[299],"supplementary":[301],"information":[302],"available":[304],"authors.":[307]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}