{"id":"https://openalex.org/W7163575371","doi":"https://doi.org/10.1186/s12859-026-06509-w","title":"CB-Search: a method for searching for similar protein motifs with biased compositions","display_name":"CB-Search: a method for searching for similar protein motifs with biased compositions","publication_year":2026,"publication_date":"2026-06-04","ids":{"openalex":"https://openalex.org/W7163575371","doi":"https://doi.org/10.1186/s12859-026-06509-w","pmid":"https://pubmed.ncbi.nlm.nih.gov/42243666"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-026-06509-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06509-w","pdf_url":null,"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","datacite","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s12859-026-06509-w","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011890249","display_name":"Patryk Jarnot","orcid":"https://orcid.org/0000-0002-8318-2270"},"institutions":[{"id":"https://openalex.org/I119004910","display_name":"Silesian University of Technology","ror":"https://ror.org/02dyjk442","country_code":"PL","type":"education","lineage":["https://openalex.org/I119004910"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Patryk Jarnot","raw_affiliation_strings":["Department of Computer Networks and Systems, Silesian University of Technology, Akademicka 2A, 44-100, Gliwice, Poland. patryk.jarnot@polsl.pl"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Networks and Systems, Silesian University of Technology, Akademicka 2A, 44-100, Gliwice, Poland. patryk.jarnot@polsl.pl","institution_ids":["https://openalex.org/I119004910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5011890249"],"corresponding_institution_ids":["https://openalex.org/I119004910"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50431385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.675000011920929,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.675000011920929,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.07919999957084656,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.06069999933242798,"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/sequence-alignment","display_name":"Sequence alignment","score":0.5378000140190125},{"id":"https://openalex.org/keywords/sequence-motif","display_name":"Sequence motif","score":0.49720001220703125},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.46639999747276306},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.4657999873161316},{"id":"https://openalex.org/keywords/transmembrane-protein","display_name":"Transmembrane protein","score":0.45509999990463257},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.45489999651908875},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.43389999866485596},{"id":"https://openalex.org/keywords/homology","display_name":"Homology (biology)","score":0.43230000138282776},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.42820000648498535},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.3928000032901764}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.7013999819755554},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.5378000140190125},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5284000039100647},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.49720001220703125},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.46639999747276306},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.4657999873161316},{"id":"https://openalex.org/C24530287","wikidata":"https://www.wikidata.org/wiki/Q424204","display_name":"Transmembrane protein","level":3,"score":0.45509999990463257},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.45489999651908875},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.43389999866485596},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.43230000138282776},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.42820000648498535},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4047999978065491},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.36719998717308044},{"id":"https://openalex.org/C118892022","wikidata":"https://www.wikidata.org/wiki/Q7834587","display_name":"Transmembrane domain","level":3,"score":0.36550000309944153},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.3637999892234802},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3628999888896942},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.36000001430511475},{"id":"https://openalex.org/C132677234","wikidata":"https://www.wikidata.org/wiki/Q3273544","display_name":"Structural motif","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C104292427","wikidata":"https://www.wikidata.org/wiki/Q899781","display_name":"Protein subunit","level":3,"score":0.3463999927043915},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.321399986743927},{"id":"https://openalex.org/C111364199","wikidata":"https://www.wikidata.org/wiki/Q2915896","display_name":"Protein methods","level":4,"score":0.3197000026702881},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.31679999828338623},{"id":"https://openalex.org/C144292202","wikidata":"https://www.wikidata.org/wiki/Q898273","display_name":"Protein domain","level":3,"score":0.30709999799728394},{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C67705224","wikidata":"https://www.wikidata.org/wiki/Q11053","display_name":"RNA","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28369998931884766},{"id":"https://openalex.org/C2779315201","wikidata":"https://www.wikidata.org/wiki/Q414601","display_name":"Sequence homology","level":4,"score":0.26570001244544983},{"id":"https://openalex.org/C169627665","wikidata":"https://www.wikidata.org/wiki/Q5767913","display_name":"Homology modeling","level":3,"score":0.2624000012874603},{"id":"https://openalex.org/C144647389","wikidata":"https://www.wikidata.org/wiki/Q423042","display_name":"Membrane protein","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C82381507","wikidata":"https://www.wikidata.org/wiki/Q416878","display_name":"Polymerase","level":3,"score":0.25679999589920044},{"id":"https://openalex.org/C54985914","wikidata":"https://www.wikidata.org/wiki/Q1295754","display_name":"Consensus sequence","level":4,"score":0.2533999979496002},{"id":"https://openalex.org/C2994376932","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Amino acid residue","level":4,"score":0.25290000438690186},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.25270000100135803},{"id":"https://openalex.org/C199216141","wikidata":"https://www.wikidata.org/wiki/Q4995178","display_name":"Conserved sequence","level":4,"score":0.2524000108242035}],"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":"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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"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":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1186/s12859-026-06509-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06509-w","pdf_url":null,"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:42243666","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42243666","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":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13466491","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13466491/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13466491/pdf/12859_2026_Article_6509.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:6d768fca0d74447baaf8dff09a8830e0","is_oa":false,"landing_page_url":"https://doaj.org/article/6d768fca0d74447baaf8dff09a8830e0","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 27, Iss 1 (2026)","raw_type":"article"},{"id":"doi:10.6084/m9.figshare.c.8650562","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.c.8650562","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Collection"},{"id":"doi:10.6084/m9.figshare.c.8650562.v1","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.c.8650562.v1","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Collection"}],"best_oa_location":{"id":"doi:10.1186/s12859-026-06509-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06509-w","pdf_url":null,"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/G1215397917","display_name":null,"funder_award_id":"2021/41/N/ST6/01919","funder_id":"https://openalex.org/F4320322511","funder_display_name":"Narodowe Centrum Nauki"}],"funders":[{"id":"https://openalex.org/F4320322511","display_name":"Narodowe Centrum Nauki","ror":"https://ror.org/03ha2q922"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1901968134","https://openalex.org/W1966570126","https://openalex.org/W1971147414","https://openalex.org/W1984985542","https://openalex.org/W1991731239","https://openalex.org/W1999114258","https://openalex.org/W2046231927","https://openalex.org/W2051210555","https://openalex.org/W2051916497","https://openalex.org/W2055043387","https://openalex.org/W2074231493","https://openalex.org/W2087064593","https://openalex.org/W2092670169","https://openalex.org/W2094519647","https://openalex.org/W2096950454","https://openalex.org/W2102652793","https://openalex.org/W2104412724","https://openalex.org/W2105538566","https://openalex.org/W2116426890","https://openalex.org/W2118581189","https://openalex.org/W2119948329","https://openalex.org/W2124166542","https://openalex.org/W2137529106","https://openalex.org/W2138122982","https://openalex.org/W2140794408","https://openalex.org/W2154610073","https://openalex.org/W2158714788","https://openalex.org/W2159577277","https://openalex.org/W2166637863","https://openalex.org/W2169059428","https://openalex.org/W2170747616","https://openalex.org/W2770091706","https://openalex.org/W2809127143","https://openalex.org/W2912250830","https://openalex.org/W2950818041","https://openalex.org/W2950954328","https://openalex.org/W2975816879","https://openalex.org/W2989608901","https://openalex.org/W3087512677","https://openalex.org/W3126279595","https://openalex.org/W3164928220","https://openalex.org/W3165745490","https://openalex.org/W3210299387","https://openalex.org/W4289336383","https://openalex.org/W4306362495","https://openalex.org/W4328048187","https://openalex.org/W4366163632","https://openalex.org/W4388302761","https://openalex.org/W4388519950","https://openalex.org/W4389692889","https://openalex.org/W4390605283","https://openalex.org/W4404531735","https://openalex.org/W4405827293","https://openalex.org/W4405896312","https://openalex.org/W4410253470","https://openalex.org/W4414154132","https://openalex.org/W4414850470","https://openalex.org/W4416203497","https://openalex.org/W7123799354"],"related_works":[],"abstract_inverted_index":{"BACKGROUND:":[0],"Methods":[1],"for":[2,78,123,136,179,189,234,283],"analyzing":[3],"protein":[4,52,149],"sequence":[5,270,292],"similarity":[6,216],"focus":[7,141],"mainly":[8,142],"on":[9,143],"identifying":[10,124,180,260],"the":[11,89,145,177,203,237,251,265,268,281],"homologies":[12],"of":[13,88,148,205,224,240,267],"proteins":[14],"with":[15,22,44,126,163,176,250,259],"standard":[16],"amino":[17],"acid":[18],"compositions.":[19],"For":[20],"motifs":[21,43,125,221],"biased":[23,220,285],"compositions,":[24,128],"they":[25,82],"have":[26],"already":[27],"been":[28],"shown":[29],"to":[30,38,63,93,102,187,236],"be":[31,57],"suboptimal;":[32],"thus,":[33],"we":[34,98,112,160,213,231],"lack":[35],"dedicated":[36],"tools":[37],"support":[39],"their":[40,104,153],"analyses.":[41],"However,":[42],"compositional":[45],"biases":[46],"also":[47,232],"play":[48],"key":[49],"roles":[50],"in":[51,59,166],"functions.":[53],"These":[54,139],"domains":[55,74,192],"can":[56],"found":[58,247],"transmembrane":[60,191],"proteins,":[61],"bind":[62],"RNA":[64,242],"through":[65],"RGG":[66,194],"boxes,":[67],"and":[68,86,132,173,193,256],"may":[69],"form":[70],"prions.":[71],"Nevertheless,":[72],"many":[73],"remain":[75],"unknown,":[76],"as":[77],"a":[79,114,133],"long":[80],"time":[81],"were":[83],"considered":[84],"nonfunctional":[85],"most":[87],"methods":[90,186],"mask":[91],"them":[92],"improve":[94],"homology":[95],"searches.":[96],"Therefore,":[97],"need":[99],"better":[100],"solutions":[101,140,200],"infer":[103],"functions":[105],"more":[106,271],"efficiently.":[107],"RESULTS:":[108],"In":[109],"this":[110],"research,":[111],"developed":[113],"new":[115,134],"method":[116,165,275],"incorporating":[117],"three":[118,167],"alignment":[119,175,253,258],"strategies,":[120,254],"an":[121],"algorithm":[122,178],"similar":[127,190,261],"2-mer":[129],"based":[130],"filtering,":[131],"metric":[135],"evaluating":[137],"alignments.":[138],"comparing":[144],"physicochemical":[146],"properties":[147],"sequences":[150],"rather":[151],"than":[152],"evolutionary":[154],"relationships.":[155],"To":[156],"validate":[157],"our":[158,164,199,215],"approach,":[159],"compared":[161,249],"BLAST":[162],"variants":[168],"that":[169,198,248,279],"use":[170],"local,":[171],"global-local,":[172],"global":[174,257],"compositionally":[181,284],"similarities.":[182],"We":[183,196,246],"used":[184],"these":[185],"search":[188,282],"boxes.":[195],"observed":[197],"significantly":[201],"increased":[202],"number":[204],"true":[206],"positives.":[207],"The":[208],"greatest":[209],"increase":[210],"occurred":[211],"after":[212],"applied":[214],"score":[217],"measure.":[218],"Compositionally":[219],"frequently":[222],"consist":[223],"two":[225],"adjacent":[226],"functionally":[227],"important":[228],"motifs;":[229],"therefore,":[230],"searched":[233],"similarities":[235],"K-DE":[238],"motif":[239],"DNA-directed":[241],"polymerase":[243],"subunit":[244],"delta.":[245],"other":[252],"global-local":[255],"regions":[262],"included":[263],"all":[264],"submotifs":[266],"query":[269],"often.":[272],"CONCLUSION:":[273],"Our":[274],"introduces":[276],"novel":[277],"strategies":[278],"enhance":[280],"motifs,":[286],"thereby":[287],"improving":[288],"annotation":[289],"retrieval":[290],"via":[291],"matching.":[293]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-06-05T00:00:00"}