{"id":"https://openalex.org/W2070312329","doi":"https://doi.org/10.1186/1471-2105-14-96","title":"Mining for class-specific motifs in protein sequence classification","display_name":"Mining for class-specific motifs in protein sequence classification","publication_year":2013,"publication_date":"2013-03-15","ids":{"openalex":"https://openalex.org/W2070312329","doi":"https://doi.org/10.1186/1471-2105-14-96","mag":"2070312329","pmid":"https://pubmed.ncbi.nlm.nih.gov/23496846"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-14-96","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-14-96","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-14-96","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/10.1186/1471-2105-14-96","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021929717","display_name":"Satish Srinivasan","orcid":"https://orcid.org/0000-0003-1377-3726"},"institutions":[{"id":"https://openalex.org/I59130452","display_name":"University of Nebraska Medical Center","ror":"https://ror.org/00thqtb16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I59130452"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Satish M Srinivasan","raw_affiliation_strings":["Department of Genetics, Cell Biology and Anatomy, University of Nebraska Medical Center, Omaha, NE 68198-5145, USA","Department of Genetics, Cell Biology and Anatomy, University of Nebraska Medical Center, Omaha, NE, 68198-5145, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Genetics, Cell Biology and Anatomy, University of Nebraska Medical Center, Omaha, NE 68198-5145, USA","institution_ids":["https://openalex.org/I59130452"]},{"raw_affiliation_string":"Department of Genetics, Cell Biology and Anatomy, University of Nebraska Medical Center, Omaha, NE, 68198-5145, USA","institution_ids":["https://openalex.org/I59130452"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034242219","display_name":"Suleyman Vural","orcid":"https://orcid.org/0000-0002-7777-5256"},"institutions":[{"id":"https://openalex.org/I59130452","display_name":"University of Nebraska Medical Center","ror":"https://ror.org/00thqtb16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I59130452"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suleyman Vural","raw_affiliation_strings":["Department of Genetics, Cell Biology and Anatomy, University of Nebraska Medical Center, Omaha, NE, 68198-5145, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Genetics, Cell Biology and Anatomy, University of Nebraska Medical Center, Omaha, NE, 68198-5145, USA","institution_ids":["https://openalex.org/I59130452"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062573510","display_name":"Brian R. King","orcid":"https://orcid.org/0000-0002-8703-6596"},"institutions":[{"id":"https://openalex.org/I131221577","display_name":"Bucknell University","ror":"https://ror.org/00fc1qt65","country_code":"US","type":"education","lineage":["https://openalex.org/I131221577"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian R King","raw_affiliation_strings":["Department of Computer Science, Bucknell University, One Dent Drive, Lewisburg, PA, 17837, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Bucknell University, One Dent Drive, Lewisburg, PA, 17837, USA","institution_ids":["https://openalex.org/I131221577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050528341","display_name":"Chittibabu Guda","orcid":"https://orcid.org/0000-0002-5393-9316"},"institutions":[{"id":"https://openalex.org/I59130452","display_name":"University of Nebraska Medical Center","ror":"https://ror.org/00thqtb16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I59130452"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chittibabu Guda","raw_affiliation_strings":["Bioinformatics and Systems Biology Core, University of Nebraska Medical Center, Omaha, NE, 68198-5145, USA","Department of Genetics, Cell Biology and Anatomy, University of Nebraska Medical Center, Omaha, NE, 68198-5145, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics and Systems Biology Core, University of Nebraska Medical Center, Omaha, NE, 68198-5145, USA","institution_ids":["https://openalex.org/I59130452"]},{"raw_affiliation_string":"Department of Genetics, Cell Biology and Anatomy, University of Nebraska Medical Center, Omaha, NE, 68198-5145, USA","institution_ids":["https://openalex.org/I59130452"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5050528341"],"corresponding_institution_ids":["https://openalex.org/I59130452"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":1.3742,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.80400244,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"14","issue":"1","first_page":"96","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9154000282287598,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9154000282287598,"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.017999999225139618,"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":0.01360000018030405,"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/discriminative-model","display_name":"Discriminative model","score":0.8749853372573853},{"id":"https://openalex.org/keywords/substitution","display_name":"Substitution (logic)","score":0.6070916652679443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5779178738594055},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5673140287399292},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5654765963554382},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5537796020507812},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4805658161640167},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4737183451652527},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4643248915672302},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4553842842578888},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.4411121904850006},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"Protein function prediction","score":0.4108659327030182},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34077781438827515},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3387189507484436},{"id":"https://openalex.org/keywords/protein-function","display_name":"Protein function","score":0.31200307607650757},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.28549742698669434},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.24111682176589966},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.23562979698181152},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08218371868133545}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8749853372573853},{"id":"https://openalex.org/C2778220771","wikidata":"https://www.wikidata.org/wiki/Q1522579","display_name":"Substitution (logic)","level":2,"score":0.6070916652679443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5779178738594055},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5673140287399292},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5654765963554382},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5537796020507812},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4805658161640167},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4737183451652527},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4643248915672302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4553842842578888},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.4411121904850006},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.4108659327030182},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34077781438827515},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3387189507484436},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.31200307607650757},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.28549742698669434},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.24111682176589966},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.23562979698181152},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08218371868133545},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004798","descriptor_name":"Enzymes","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D019943","descriptor_name":"Amino Acid Substitution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019943","descriptor_name":"Amino Acid Substitution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019943","descriptor_name":"Amino Acid Substitution","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":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1186/1471-2105-14-96","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-14-96","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-14-96","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:23496846","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23496846","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:europepmc.org:2613828","is_oa":true,"landing_page_url":"http://europepmc.org/articles/PMC3610217","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:3610217","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3610217","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"},{"id":"pmh:oai:digitalcommons.bucknell.edu:fac_journ-1554","is_oa":false,"landing_page_url":"https://digitalcommons.bucknell.edu/fac_journ/707","pdf_url":null,"source":{"id":"https://openalex.org/S4377196650","display_name":"Bucknell Digital Commons (Bucknell University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I131221577","host_organization_name":"Bucknell University","host_organization_lineage":["https://openalex.org/I131221577"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Journal Articles","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-14-96","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-14-96","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-14-96","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":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1351631278","display_name":null,"funder_award_id":"R01 GM086533","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G6460538931","display_name":null,"funder_award_id":"1R01GM086533","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2070312329.pdf","grobid_xml":"https://content.openalex.org/works/W2070312329.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1976062896","https://openalex.org/W1978937741","https://openalex.org/W1986250503","https://openalex.org/W1994716877","https://openalex.org/W2000937352","https://openalex.org/W2001150129","https://openalex.org/W2020969907","https://openalex.org/W2055043387","https://openalex.org/W2064701032","https://openalex.org/W2069516894","https://openalex.org/W2092067718","https://openalex.org/W2093163894","https://openalex.org/W2101968184","https://openalex.org/W2117502874","https://openalex.org/W2123552972","https://openalex.org/W2132343764","https://openalex.org/W2141885858","https://openalex.org/W2143210482","https://openalex.org/W2156125289","https://openalex.org/W2164620224","https://openalex.org/W2170871934","https://openalex.org/W2170960297","https://openalex.org/W2312723074","https://openalex.org/W2738391309","https://openalex.org/W4231056502","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2159663778","https://openalex.org/W2065993463","https://openalex.org/W2181899571","https://openalex.org/W2135470984","https://openalex.org/W2082535576","https://openalex.org/W1568877569","https://openalex.org/W2015809665","https://openalex.org/W2935275081","https://openalex.org/W2111105050","https://openalex.org/W2348674368"],"abstract_inverted_index":{"BACKGROUND:":[0],"In":[1,99],"protein":[2,150,266,278,335,358,406],"sequence":[3,8,42,63,336,407],"classification,":[4],"identification":[5],"of":[6,30,144,152,160,195,204,209,300,362,385,405,417],"the":[7,25,47,62,141,149,156,161,171,182,193,201,205,207,210,223,233,237,265,304,310,357,371,376,383,386],"motifs":[9,69,276,302,307,332,351,400,416],"or":[10,94],"n-grams":[11,77,112,129,159,197,211,224,234,262,271,354],"that":[12,51,70,82,113,130,225,248,272,318,394],"can":[13,57,131,325,397],"precisely":[14],"discriminate":[15,71,133],"between":[16,72,134],"classes":[17,73,154,229,408],"is":[18,173,321,346],"a":[19,104,118,123,189,215,255,402,410],"more":[20,220],"interesting":[21],"scientific":[22],"question":[23],"than":[24],"classification":[26,31,36,337],"itself.":[27],"A":[28],"number":[29,194],"methods":[32],"aim":[33],"at":[34],"accurate":[35],"but":[37,89],"fail":[38],"to":[39,46,60,66,117,146,166,200,222,243,252,264,285,329,348,374,413],"explain":[40],"which":[41,218],"features":[43],"indeed":[44],"contribute":[45],"accuracy.":[48],"We":[49,121,294,316],"hypothesize":[50],"sequences":[52,81,151],"in":[53,86,96,155,181,188,192,227,277,333],"lower":[54],"denominations":[55],"(n-grams)":[56],"be":[58,253,326],"used":[59],"explore":[61],"landscape":[64],"and":[65,230,313,344,370],"identify":[67,349],"class-specific":[68,275,301,331,350,399],"during":[74],"classification.":[75],"Discriminative":[76],"are":[78,83,90,114,164,212,235,249],"short":[79,274],"peptide":[80],"highly":[84,115],"frequent":[85,250],"one":[87],"class":[88,247],"either":[91],"minimally":[92],"present":[93,103,122],"absent":[95],"other":[97],"classes.":[98,135],"this":[100,319,395],"study,":[101],"we":[102,268],"new":[105,168],"substitution-based":[106],"scoring":[107,124,137,238,342,387],"function":[108,125,239,343],"for":[109,245,367],"identifying":[110],"discriminative":[111,128,241,261,353],"specific":[116],"class.":[119],"RESULTS:":[120],"based":[126],"on":[127,382],"effectively":[132],"The":[136,340,360],"function,":[138],"initially,":[139],"harvests":[140],"entire":[142],"set":[143,299],"4-":[145,242],"8-grams":[147,244],"from":[148,309,356,401],"different":[153,418],"dataset.":[157],"Similar":[158],"same":[162],"size":[163],"combined":[165],"form":[167],"n-grams,":[169],"where":[170],"similarity":[172,368],"defined":[174],"by":[175],"positive":[176],"amino":[177,363],"acid":[178,364],"substitution":[179,365],"scores":[180,366],"BLOSUM62":[183],"matrix.":[184],"Substitution":[185],"has":[186],"resulted":[187],"large":[190],"increase":[191],"discriminatory":[196],"harvested.":[198],"Due":[199],"unbalanced":[202,377],"nature":[203],"dataset,":[206],"frequencies":[208],"normalized":[213],"using":[214,352],"dampening":[216,372],"factor,":[217],"gives":[219],"weightage":[221],"appear":[226],"fewer":[228],"vice-versa.":[231],"After":[232],"normalized,":[236],"identifies":[240],"each":[246],"enough":[251],"above":[254],"selection":[256],"threshold.":[257],"By":[258],"mapping":[259],"these":[260],"back":[263],"sequences,":[267],"obtained":[269,308],"contiguous":[270],"represent":[273],"sequences.":[279,359],"Our":[280,389],"method":[281,290,320,396],"fared":[282],"well":[283],"compared":[284],"an":[286],"existing":[287],"motif":[288],"finding":[289],"known":[291],"as":[292],"Wordspy.":[293],"have":[295,379],"validated":[296],"our":[297],"enriched":[298],"against":[303],"functionally":[305],"important":[306],"NLSdb,":[311],"Prosite":[312],"ELM":[314],"databases.":[315],"demonstrate":[317,393],"very":[322],"generic;":[323],"thus":[324],"widely":[327],"applied":[328],"detect":[330,398],"many":[334],"tasks.":[338],"CONCLUSION:":[339],"proposed":[341],"methodology":[345],"able":[347],"derived":[355],"implementation":[361],"detection,":[369],"factor":[373],"normalize":[375],"datasets":[378],"significant":[380],"effect":[381],"performance":[384],"function.":[388],"multipronged":[390],"validation":[391],"tests":[392],"wide":[403],"variety":[404],"with":[409],"potential":[411],"application":[412],"detecting":[414],"proteome-specific":[415],"organisms.":[419]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}