{"id":"https://openalex.org/W1970378328","doi":"https://doi.org/10.1145/1854776.1854797","title":"Random forest-based prediction of protein sumoylation sites from sequence features","display_name":"Random forest-based prediction of protein sumoylation sites from sequence features","publication_year":2010,"publication_date":"2010-08-02","ids":{"openalex":"https://openalex.org/W1970378328","doi":"https://doi.org/10.1145/1854776.1854797","mag":"1970378328"},"language":"en","primary_location":{"id":"doi:10.1145/1854776.1854797","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1854776.1854797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First ACM International Conference on Bioinformatics and Computational Biology","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081951768","display_name":"Shaolei Teng","orcid":"https://orcid.org/0000-0001-8326-9889"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaolei Teng","raw_affiliation_strings":["Clemson University, Clemson, SC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clemson University, Clemson, SC","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009156606","display_name":"Hong Luo","orcid":"https://orcid.org/0000-0001-9223-1786"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Luo","raw_affiliation_strings":["Clemson University, Clemson, SC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clemson University, Clemson, SC","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080695941","display_name":"Liangjiang Wang","orcid":"https://orcid.org/0000-0002-6316-7962"},"institutions":[{"id":"https://openalex.org/I4210149064","display_name":"Greenwood Genetic Center","ror":"https://ror.org/03p64mj41","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210149064"]},{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liangjiang Wang","raw_affiliation_strings":["Clemson University, Clemson, SC and Greenwood Genetic Center, Greenwood, SC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clemson University, Clemson, SC and Greenwood Genetic Center, Greenwood, SC","institution_ids":["https://openalex.org/I4210149064","https://openalex.org/I8078737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"120","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9995999932289124,"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":0.9995999932289124,"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/T11041","display_name":"Ubiquitin and proteasome pathways","score":0.9979000091552734,"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/T10602","display_name":"Glycosylation and Glycoproteins Research","score":0.9958999752998352,"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/sumo-protein","display_name":"SUMO protein","score":0.8606580495834351},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8573287725448608},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.8473842144012451},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.7724564075469971},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6311101913452148},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6065239310264587},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.586031973361969},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.5355363488197327},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5121902823448181},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5010063648223877},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.43951547145843506},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35547199845314026},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1909770369529724},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.16879802942276},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1051521897315979},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.08336207270622253}],"concepts":[{"id":"https://openalex.org/C171350616","wikidata":"https://www.wikidata.org/wiki/Q61506","display_name":"SUMO protein","level":4,"score":0.8606580495834351},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8573287725448608},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.8473842144012451},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7724564075469971},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6311101913452148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6065239310264587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.586031973361969},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.5355363488197327},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5121902823448181},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5010063648223877},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43951547145843506},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35547199845314026},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1909770369529724},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.16879802942276},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1051521897315979},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.08336207270622253},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C25602115","wikidata":"https://www.wikidata.org/wiki/Q407111","display_name":"Ubiquitin","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1854776.1854797","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1854776.1854797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First ACM International Conference on Bioinformatics and Computational Biology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G5040933461","display_name":null,"funder_award_id":"SC-1700355","funder_id":"https://openalex.org/F4320306114","funder_display_name":"U.S. Department of Agriculture"},{"id":"https://openalex.org/G7464182799","display_name":null,"funder_award_id":"SC-1700355","funder_id":"https://openalex.org/F4320332483","funder_display_name":"Cooperative State Research, Education, and Extension Service"}],"funders":[{"id":"https://openalex.org/F4320306114","display_name":"U.S. Department of Agriculture","ror":"https://ror.org/01na82s61"},{"id":"https://openalex.org/F4320332483","display_name":"Cooperative State Research, Education, and Extension Service","ror":"https://ror.org/01na82s61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W243303449","https://openalex.org/W1543773936","https://openalex.org/W1964940342","https://openalex.org/W1965226335","https://openalex.org/W1971894358","https://openalex.org/W1990748933","https://openalex.org/W2001341780","https://openalex.org/W2003810144","https://openalex.org/W2013108773","https://openalex.org/W2014731953","https://openalex.org/W2018686658","https://openalex.org/W2023540360","https://openalex.org/W2041877620","https://openalex.org/W2068858732","https://openalex.org/W2089716128","https://openalex.org/W2122231230","https://openalex.org/W2136956610","https://openalex.org/W2152763796","https://openalex.org/W2153240444","https://openalex.org/W2155653793","https://openalex.org/W2170909437","https://openalex.org/W4213345021","https://openalex.org/W7074172428"],"related_works":["https://openalex.org/W2053523004","https://openalex.org/W2001367558","https://openalex.org/W3032751721","https://openalex.org/W2088695563","https://openalex.org/W2048124721","https://openalex.org/W2164237668","https://openalex.org/W2091611701","https://openalex.org/W4399500913","https://openalex.org/W2889302474","https://openalex.org/W2017375993"],"abstract_inverted_index":{"Protein":[0],"sumoylation":[1,30,88,144],"play":[2],"essential":[3],"roles":[4],"in":[5,12,101],"the":[6,29,56,84,91,97,102,105,126,130,136],"eukaryotic":[7],"cell":[8],"and":[9,49,90],"any":[10],"alterations":[11],"this":[13],"process":[14],"may":[15],"cause":[16],"various":[17],"human":[18],"diseases.":[19],"This":[20],"paper":[21],"describes":[22],"a":[23,43],"new":[24],"machine":[25,122],"learning":[26],"approach":[27],"for":[28,70,139],"site":[31],"prediction":[32,141],"from":[33,59,146],"protein":[34,143],"sequence":[35,66,85,147],"information.":[36],"Random":[37],"Forests":[38],"(RFs),":[39],"which":[40],"can":[41],"handle":[42],"large":[44],"number":[45],"of":[46,87,93,142],"input":[47,71],"variables":[48],"avoid":[50],"model":[51],"overfitting,":[52],"were":[53,68,115],"trained":[54],"with":[55,96],"data":[57],"collected":[58],"literature.":[60],"To":[61],"construct":[62],"accurate":[63,140],"classifiers,":[64],"forty":[65],"features":[67],"selected":[69],"vector":[72,121],"encoding.":[73],"The":[74,112],"results":[75],"suggested":[76],"that":[77],"RF":[78,113,131],"classifier":[79],"performance":[80,107],"was":[81],"affected":[82],"by":[83],"context":[86],"sites,":[89],"use":[92],"eighteen":[94],"residues":[95],"core":[98],"motif":[99],"\u03c8KXE":[100],"middle":[103],"gave":[104],"highest":[106],"(ROC":[108],"AUC":[109],"=":[110],"0.9328).":[111],"classifiers":[114],"also":[116],"found":[117],"to":[118,134],"outperform":[119],"support":[120],"(SVM)":[123],"models":[124],"on":[125],"same":[127],"dataset.":[128],"Thus,":[129],"algorithm":[132],"appears":[133],"be":[135],"best":[137],"choice":[138],"sites":[145],"features.":[148]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}