{"id":"https://openalex.org/W2002527557","doi":"https://doi.org/10.1186/1471-2105-11-52","title":"Sites Inferred by Metabolic Background Assertion Labeling (SIMBAL): adapting the Partial Phylogenetic Profiling algorithm to scan sequences for signatures that predict protein function","display_name":"Sites Inferred by Metabolic Background Assertion Labeling (SIMBAL): adapting the Partial Phylogenetic Profiling algorithm to scan sequences for signatures that predict protein function","publication_year":2010,"publication_date":"2010-01-26","ids":{"openalex":"https://openalex.org/W2002527557","doi":"https://doi.org/10.1186/1471-2105-11-52","mag":"2002527557","pmid":"https://pubmed.ncbi.nlm.nih.gov/20102603"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-11-52","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-52","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-52","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/10.1186/1471-2105-11-52","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038878923","display_name":"Jeremy Selengut","orcid":null},"institutions":[{"id":"https://openalex.org/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jeremy D Selengut","raw_affiliation_strings":["J, Craig Venter Institute, 9704 Medical Center Drive, Rockville, MD 20850, USA. selengut@jcvi.org","J. Craig Venter Institute,Rockville,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"J, Craig Venter Institute, 9704 Medical Center Drive, Rockville, MD 20850, USA. selengut@jcvi.org","institution_ids":["https://openalex.org/I1301553790"]},{"raw_affiliation_string":"J. Craig Venter Institute,Rockville,USA","institution_ids":["https://openalex.org/I1301553790"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034349178","display_name":"Douglas B. Rusch","orcid":"https://orcid.org/0000-0002-1066-2687"},"institutions":[{"id":"https://openalex.org/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas B Rusch","raw_affiliation_strings":["J. Craig Venter Institute, 9704 Medical Center Drive, Rockville, MD, USA, 20850","J. Craig Venter Institute,Rockville,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"J. Craig Venter Institute, 9704 Medical Center Drive, Rockville, MD, USA, 20850","institution_ids":["https://openalex.org/I1301553790"]},{"raw_affiliation_string":"J. Craig Venter Institute,Rockville,USA","institution_ids":["https://openalex.org/I1301553790"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027242690","display_name":"Daniel H. Haft","orcid":"https://orcid.org/0000-0001-8101-4938"},"institutions":[{"id":"https://openalex.org/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel H Haft","raw_affiliation_strings":["J. Craig Venter Institute, 9704 Medical Center Drive, Rockville, MD, USA, 20850","J. Craig Venter Institute,Rockville,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"J. Craig Venter Institute, 9704 Medical Center Drive, Rockville, MD, USA, 20850","institution_ids":["https://openalex.org/I1301553790"]},{"raw_affiliation_string":"J. Craig Venter Institute,Rockville,USA","institution_ids":["https://openalex.org/I1301553790"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038878923"],"corresponding_institution_ids":["https://openalex.org/I1301553790"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":1.5887,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.82604714,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"11","issue":"1","first_page":"52","last_page":"52"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11162","display_name":"Enzyme Structure and Function","score":0.1995999962091446,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11162","display_name":"Enzyme Structure and Function","score":0.1995999962091446,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.16689999401569366,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.11699999868869781,"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/biology","display_name":"Biology","score":0.5498478412628174},{"id":"https://openalex.org/keywords/phylogenetic-tree","display_name":"Phylogenetic tree","score":0.5082287788391113},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5036115050315857},{"id":"https://openalex.org/keywords/permease","display_name":"Permease","score":0.47433844208717346},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.47083401679992676},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.45899254083633423},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.4475661516189575},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.4375855028629303},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.4316372871398926},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39961370825767517},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.2742874026298523},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.2572261095046997},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.25038886070251465}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5498478412628174},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.5082287788391113},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5036115050315857},{"id":"https://openalex.org/C190114821","wikidata":"https://www.wikidata.org/wiki/Q412861","display_name":"Permease","level":4,"score":0.47433844208717346},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.47083401679992676},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.45899254083633423},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.4475661516189575},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.4375855028629303},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.4316372871398926},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39961370825767517},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2742874026298523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2572261095046997},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.25038886070251465},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0},{"id":"https://openalex.org/C149011108","wikidata":"https://www.wikidata.org/wiki/Q652985","display_name":"Transporter","level":3,"score":0.0}],"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":"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":"D000595","descriptor_name":"Amino Acid Sequence","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":"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":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"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":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-11-52","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-52","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-52","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:20102603","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20102603","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:doaj.org/article:bd7cd71f52664b85b020bf059382a410","is_oa":true,"landing_page_url":"https://doaj.org/article/bd7cd71f52664b85b020bf059382a410","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":"BMC Bioinformatics, Vol 11, Iss 1, p 52 (2010)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:3098086","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3098086","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":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-11-52","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-52","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-52","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":[],"awards":[{"id":"https://openalex.org/G2951409970","display_name":null,"funder_award_id":"R01 HG004881","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G7321902618","display_name":"The Genome Properties: Metabolic Reconstruction System","funder_award_id":"0445826","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"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/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2002527557.pdf","grobid_xml":"https://content.openalex.org/works/W2002527557.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1668755435","https://openalex.org/W1728555672","https://openalex.org/W1952641568","https://openalex.org/W1972946979","https://openalex.org/W1984345785","https://openalex.org/W1987641460","https://openalex.org/W1990203942","https://openalex.org/W2006439869","https://openalex.org/W2015586964","https://openalex.org/W2031797010","https://openalex.org/W2044784306","https://openalex.org/W2055269110","https://openalex.org/W2057885377","https://openalex.org/W2087938597","https://openalex.org/W2101466114","https://openalex.org/W2102191780","https://openalex.org/W2103461849","https://openalex.org/W2107060668","https://openalex.org/W2113989263","https://openalex.org/W2114034054","https://openalex.org/W2117466809","https://openalex.org/W2139436782","https://openalex.org/W2141885858","https://openalex.org/W2162566191","https://openalex.org/W2170696850","https://openalex.org/W4248664566","https://openalex.org/W4252706339","https://openalex.org/W6681765588"],"related_works":["https://openalex.org/W2051969447","https://openalex.org/W2111937814","https://openalex.org/W2162923930","https://openalex.org/W1482324242","https://openalex.org/W2133116680","https://openalex.org/W2091678889","https://openalex.org/W2029514038","https://openalex.org/W2804480386","https://openalex.org/W3186624150","https://openalex.org/W65850283"],"abstract_inverted_index":{"BACKGROUND:":[0],"Comparative":[1],"genomics":[2],"methods":[3],"such":[4],"as":[5,231],"phylogenetic":[6],"profiling":[7],"can":[8],"mine":[9],"powerful":[10],"inferences":[11],"from":[12],"inherently":[13],"noisy":[14],"biological":[15],"data":[16],"sets.":[17,81],"We":[18],"introduce":[19],"Sites":[20],"Inferred":[21],"by":[22,62,101,306],"Metabolic":[23],"Background":[24],"Assertion":[25],"Labeling":[26],"(SIMBAL),":[27],"a":[28,40,114,120,140,146,153,224,232],"method":[29,93,169,273],"that":[30,194,255],"applies":[31],"the":[32,57,65,88,91,109,127,150,162,168,178,195,202,211,215,219,237,245,248,258,266,322],"Partial":[33],"Phylogenetic":[34],"Profiling":[35],"(PPP)":[36],"approach":[37,53],"locally":[38],"within":[39],"protein":[41,106,213,225,290],"sequence":[42,46,73,99,151,173,253,301,307],"to":[43,71,94,103,324],"discover":[44],"short":[45,98,293],"signatures":[47,100,174],"associated":[48],"with":[49,177,317],"functional":[50,304,313,328],"sites.":[51,329],"The":[52],"is":[54],"based":[55],"on":[56,201,214],"basic":[58],"scoring":[59],"mechanism":[60,269],"employed":[61],"PPP,":[63],"namely":[64],"use":[66],"of":[67,78,90,116,137,152,165,183,190],"binomial":[68],"distribution":[69],"statistics":[70],"optimize":[72],"similarity":[74],"cutoffs":[75],"during":[76],"searches":[77],"partitioned":[79,113,166,223],"training":[80,275],"RESULTS:":[82],"Here":[83],"we":[84,112,222],"illustrate":[85],"and":[86,155,326],"validate":[87],"ability":[89,323],"SIMBAL":[92,184,251,284,320],"find":[95],"functionally":[96,288],"relevant":[97],"application":[102],"two":[104],"well-characterized":[105],"families.":[107],"In":[108,218,234],"first":[110],"example,":[111,221],"family":[115,132,227],"ABC":[117],"permeases":[118,192],"using":[119,228],"metabolic":[121],"background":[122],"property":[123],"(urea":[124],"utilization).":[125],"Thus,":[126],"TRUE":[128,238],"set":[129,164,239,276],"for":[130,210,247,274,302,311],"this":[131,235],"comprised":[133,240],"members":[134],"whose":[135],"genome":[136],"origin":[138],"encoded":[139,243],"urea":[141,179],"utilization":[142,180],"system.":[143],"By":[144],"moving":[145],"sliding":[147],"window":[148],"across":[149],"permease,":[154],"searching":[156],"each":[157],"subsequence":[158],"in":[159,265,270,287],"turn":[160],"against":[161],"full":[163],"proteins,":[167],"found":[170],"which":[171],"local":[172],"best":[175],"correlated":[176],"trait.":[181],"Mapping":[182],"\"hot":[185],"spots\"":[186],"onto":[187,257],"crystal":[188],"structures":[189],"homologous":[191],"reveals":[193],"significant":[196],"sites":[197,209],"are":[198],"gating":[199],"determinants":[200],"cytosolic":[203],"face":[204],"rather":[205],"than,":[206],"say,":[207],"docking":[208],"substrate-binding":[212,259],"extracellular":[216],"face.":[217],"second":[220],"methyltransferase":[226,267],"gene":[229,246],"proximity":[230],"criterion.":[233],"case,":[236],"those":[241],"methyltransferases":[242],"near":[244],"substrate":[249],"RF-1.":[250],"identifies":[252],"regions":[254,263],"map":[256],"interface":[260],"while":[261],"ignoring":[262],"involved":[264],"reaction":[268],"general.":[271],"Neither":[272],"construction":[277],"requires":[278],"any":[279],"prior":[280],"experimental":[281],"characterization.":[282],"CONCLUSIONS:":[283],"shows":[285],"that,":[286],"divergent":[289],"families,":[291],"selected":[292],"sequences":[294],"often":[295],"significantly":[296],"outperform":[297],"their":[298],"full-length":[299],"parent":[300],"making":[303],"predictions":[305],"similarity,":[308],"suggesting":[309],"avenues":[310],"improved":[312],"classifiers.":[314],"When":[315],"combined":[316],"structural":[318],"data,":[319],"affords":[321],"localize":[325],"model":[327]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2025-10-10T00:00:00"}