{"id":"https://openalex.org/W4407084952","doi":"https://doi.org/10.1186/s13040-024-00415-8","title":"XGBoost-enhanced ensemble model using discriminative hybrid features for the prediction of sumoylation sites","display_name":"XGBoost-enhanced ensemble model using discriminative hybrid features for the prediction of sumoylation sites","publication_year":2025,"publication_date":"2025-02-03","ids":{"openalex":"https://openalex.org/W4407084952","doi":"https://doi.org/10.1186/s13040-024-00415-8","pmid":"https://pubmed.ncbi.nlm.nih.gov/39901279"},"language":"en","primary_location":{"id":"doi:10.1186/s13040-024-00415-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-024-00415-8","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13040-024-00415-8.pdf","source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1186/s13040-024-00415-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101483979","display_name":"Salman Khan","orcid":"https://orcid.org/0000-0002-2905-1755"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Salman Khan","raw_affiliation_strings":["New Emerging Technologies and 5G Network and Beyond Research Chair, Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Emerging Technologies and 5G Network and Beyond Research Chair, Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023753969","display_name":"Sumaiya Noor","orcid":"https://orcid.org/0000-0001-9739-4592"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]},{"id":"https://openalex.org/I4210155590","display_name":"Management Sciences (United States)","ror":"https://ror.org/05shz5j84","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sumaiya Noor","raw_affiliation_strings":["Business and Management Sciences Department, Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Business and Management Sciences Department, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219","https://openalex.org/I4210155590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057643236","display_name":"Tahir Javed","orcid":null},"institutions":[{"id":"https://openalex.org/I181355716","display_name":"Allama Iqbal Open University","ror":"https://ror.org/04vympt94","country_code":"PK","type":"education","lineage":["https://openalex.org/I181355716"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Tahir Javed","raw_affiliation_strings":["Department of Computer Science, Allama Iqbal Open University, Islamabad, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Allama Iqbal Open University, Islamabad, Pakistan","institution_ids":["https://openalex.org/I181355716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077902362","display_name":"Afshan Naseem","orcid":"https://orcid.org/0000-0002-4766-8070"},"institutions":[{"id":"https://openalex.org/I157696592","display_name":"Universiti Malaysia Terengganu","ror":"https://ror.org/02474f074","country_code":"MY","type":"education","lineage":["https://openalex.org/I157696592"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Afshan Naseem","raw_affiliation_strings":["Institute of Oceanography and Environment (INOS), Universiti Malaysia Terengganu, Kuala Nerus, Terengganu, 21030, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Oceanography and Environment (INOS), Universiti Malaysia Terengganu, Kuala Nerus, Terengganu, 21030, Malaysia","institution_ids":["https://openalex.org/I157696592"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062493427","display_name":"Fahad Aslam","orcid":null},"institutions":[{"id":"https://openalex.org/I157696592","display_name":"Universiti Malaysia Terengganu","ror":"https://ror.org/02474f074","country_code":"MY","type":"education","lineage":["https://openalex.org/I157696592"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Fahad Aslam","raw_affiliation_strings":["Institute of Oceanography and Environment (INOS), Universiti Malaysia Terengganu, Kuala Nerus, Terengganu, 21030, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Oceanography and Environment (INOS), Universiti Malaysia Terengganu, Kuala Nerus, Terengganu, 21030, Malaysia","institution_ids":["https://openalex.org/I157696592"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046464125","display_name":"Salman A. AlQahtani","orcid":"https://orcid.org/0000-0003-1233-1774"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Salman A. AlQahtani","raw_affiliation_strings":["New Emerging Technologies and 5G Network and Beyond Research Chair, Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Emerging Technologies and 5G Network and Beyond Research Chair, Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101211329","display_name":"Nijad Ahmad","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150210","display_name":"Khurasan University","ror":"https://ror.org/050k1mp73","country_code":"AF","type":"education","lineage":["https://openalex.org/I4210150210"]}],"countries":["AF"],"is_corresponding":true,"raw_author_name":"Nijad Ahmad","raw_affiliation_strings":["Department of Computer Science, Khurasan University Jalalabad, Jalalabad, Afghanistan. Nijad@khurasan.edu.af","Department of Computer Science, Khurasan University Jalalabad, Jalalabad, Afghanistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Khurasan University Jalalabad, Jalalabad, Afghanistan. Nijad@khurasan.edu.af","institution_ids":["https://openalex.org/I4210150210"]},{"raw_affiliation_string":"Department of Computer Science, Khurasan University Jalalabad, Jalalabad, Afghanistan","institution_ids":["https://openalex.org/I4210150210"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101211329"],"corresponding_institution_ids":["https://openalex.org/I4210150210"],"apc_list":{"value":2690,"currency":"USD","value_usd":2690},"apc_paid":{"value":2690,"currency":"USD","value_usd":2690},"fwci":20.0848,"has_fulltext":true,"cited_by_count":55,"citation_normalized_percentile":{"value":0.99715952,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"18","issue":"1","first_page":"12","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9990000128746033,"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":0.9990000128746033,"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/T10015","display_name":"Genomics and Phylogenetic Studies","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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.9886999726295471,"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":0.8289821743965149},{"id":"https://openalex.org/keywords/sumo-protein","display_name":"SUMO protein","score":0.6584689617156982},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.641577422618866},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.4301597476005554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40899255871772766},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3831169307231903},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.0668962299823761}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8289821743965149},{"id":"https://openalex.org/C171350616","wikidata":"https://www.wikidata.org/wiki/Q61506","display_name":"SUMO protein","level":4,"score":0.6584689617156982},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.641577422618866},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.4301597476005554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40899255871772766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3831169307231903},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0668962299823761},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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":4,"locations":[{"id":"doi:10.1186/s13040-024-00415-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-024-00415-8","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13040-024-00415-8.pdf","source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},{"id":"pmid:39901279","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39901279","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":"BioData mining","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:11792219","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11792219","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11792219/pdf/13040_2024_Article_415.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BioData Min","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:af46290e133248f2ab4f09bd7be5149d","is_oa":true,"landing_page_url":"https://doaj.org/article/af46290e133248f2ab4f09bd7be5149d","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":"BioData Mining, Vol 18, Iss 1, Pp 1-18 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13040-024-00415-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-024-00415-8","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13040-024-00415-8.pdf","source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321145","display_name":"King Saud University","ror":"https://ror.org/02f81g417"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407084952.pdf","grobid_xml":"https://content.openalex.org/works/W4407084952.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W1494484168","https://openalex.org/W1969051510","https://openalex.org/W1975092906","https://openalex.org/W1980897319","https://openalex.org/W2006141083","https://openalex.org/W2008767710","https://openalex.org/W2022922908","https://openalex.org/W2023540360","https://openalex.org/W2041961150","https://openalex.org/W2046838044","https://openalex.org/W2052929547","https://openalex.org/W2054406517","https://openalex.org/W2055397908","https://openalex.org/W2058434102","https://openalex.org/W2067696771","https://openalex.org/W2068858732","https://openalex.org/W2079056345","https://openalex.org/W2116062594","https://openalex.org/W2118893892","https://openalex.org/W2143538182","https://openalex.org/W2167660970","https://openalex.org/W2343726927","https://openalex.org/W2471518332","https://openalex.org/W2807846544","https://openalex.org/W2936064937","https://openalex.org/W2946492269","https://openalex.org/W3044140833","https://openalex.org/W3087595142","https://openalex.org/W3109659125","https://openalex.org/W3117145375","https://openalex.org/W3194982939","https://openalex.org/W3206048862","https://openalex.org/W3208498407","https://openalex.org/W4205807395","https://openalex.org/W4210522876","https://openalex.org/W4220831705","https://openalex.org/W4226182837","https://openalex.org/W4237590128","https://openalex.org/W4284973298","https://openalex.org/W4286494306","https://openalex.org/W4298325713","https://openalex.org/W4310493984","https://openalex.org/W4310641985","https://openalex.org/W4379209740","https://openalex.org/W4380484932","https://openalex.org/W4382195656","https://openalex.org/W4382585000","https://openalex.org/W4382599338","https://openalex.org/W4383815683","https://openalex.org/W4388233414","https://openalex.org/W4391592452","https://openalex.org/W4392358980","https://openalex.org/W4392562486","https://openalex.org/W4393187479","https://openalex.org/W4396707011","https://openalex.org/W4401315156","https://openalex.org/W4402071909","https://openalex.org/W4402314649","https://openalex.org/W4403001755","https://openalex.org/W4403420423"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Posttranslational":[0],"modifications":[1],"(PTMs)":[2],"are":[3],"essential":[4],"for":[5,104,114,163,168],"regulating":[6],"protein":[7,31,37,66],"localization":[8],"and":[9,17,51,68,81,108,129,147,155],"stability,":[10],"significantly":[11],"affecting":[12],"gene":[13],"expression,":[14],"biological":[15],"functions,":[16],"genome":[18],"replication.":[19],"Among":[20],"these,":[21],"sumoylation":[22,40,62],"a":[23,27,33,57,74,136,160],"PTM":[24],"that":[25],"attaches":[26],"chemical":[28],"group":[29],"to":[30,46,49,60,78],"sequences-plays":[32],"critical":[34],"role":[35],"in":[36,170],"function.":[38],"Identifying":[39],"sites":[41,63],"is":[42],"particularly":[43],"important":[44],"due":[45],"their":[47],"links":[48],"Parkinson's":[50],"Alzheimer's.":[52],"This":[53,134],"study":[54],"introduces":[55],"XGBoost-Sumo,":[56],"robust":[58],"model":[59,72],"predict":[61],"by":[64,142],"integrating":[65],"structure":[67],"sequence":[69],"data.":[70],"The":[71,152],"utilizes":[73],"transformer-based":[75],"attention":[76],"mechanism":[77],"encode":[79],"peptides":[80],"extract":[82],"evolutionary":[83,94],"features":[84],"through":[85],"the":[86,98],"PsePSSM-DWT":[87],"approach.":[88],"By":[89],"fusing":[90],"word":[91],"embeddings":[92],"with":[93,165],"descriptors,":[95],"it":[96,159],"applies":[97],"SHapley":[99],"Additive":[100],"exPlanations":[101],"(SHAP)":[102],"algorithm":[103],"optimal":[105],"feature":[106],"selection":[107],"uses":[109],"eXtreme":[110],"Gradient":[111],"Boosting":[112],"(XGBoost)":[113],"classification.":[115],"XGBoost-Sumo":[116],"achieved":[117],"an":[118],"impressive":[119],"accuracy":[120],"of":[121],"99.68%":[122],"on":[123,131,144,149],"benchmark":[124],"datasets":[125],"using":[126],"10-fold":[127],"cross-validation":[128],"96.08%":[130],"independent":[132,150],"samples.":[133],"marks":[135],"significant":[137],"improvement,":[138],"outperforming":[139],"existing":[140],"models":[141],"10.31%":[143],"training":[145],"data":[146],"2.74%":[148],"tests.":[151],"model's":[153],"reliability":[154],"high":[156],"performance":[157],"make":[158],"valuable":[161],"resource":[162],"researchers,":[164],"strong":[166],"potential":[167],"applications":[169],"pharmaceutical":[171],"development.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":24},{"year":2025,"cited_by_count":31}],"updated_date":"2026-09-01T08:31:24.195828","created_date":"2025-10-10T00:00:00"}