{"id":"https://openalex.org/W4393834100","doi":"https://doi.org/10.5281/zenodo.5137961","title":"Data Sets and Results for \"Improved data sets and evaluation methods for the automatic prediction of DNA-binding proteins\"","display_name":"Data Sets and Results for \"Improved data sets and evaluation methods for the automatic prediction of DNA-binding proteins\"","publication_year":2021,"publication_date":"2021-08-02","ids":{"openalex":"https://openalex.org/W4393834100","doi":"https://doi.org/10.5281/zenodo.5137961"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:5137962","doi":null,"is_oa":true,"landing_page_url":"https://zenodo.org/record/5137962","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"dataset"},"volume":null,"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/5137962","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019205480","display_name":"Alexander Zaitzeff","orcid":"https://orcid.org/0000-0001-9731-1873","observed_orcids":["https://orcid.org/0000-0001-9731-1873"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zaitzeff, Alexander","raw_affiliation_strings":["Two Six Technologies"],"raw_orcid":"https://orcid.org/0000-0001-9731-1873","affiliations":[{"raw_affiliation_string":"Two Six Technologies","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074145359","display_name":"Nick Leiby","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leiby, Nick","raw_affiliation_strings":["Two Six Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Two Six Technologies","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014650825","display_name":"Francis C. Motta","orcid":"https://orcid.org/0000-0002-0364-5440","observed_orcids":["https://orcid.org/0000-0002-0364-5440"]},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Motta, Francis","raw_affiliation_strings":["Florida Atlantic University"],"raw_orcid":"https://orcid.org/0000-0002-0364-5440","affiliations":[{"raw_affiliation_string":"Florida Atlantic University","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065188919","display_name":"Steven B. Haase","orcid":"https://orcid.org/0000-0001-8127-8992","observed_orcids":["https://orcid.org/0000-0001-8127-8992"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haase, Steven","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052322423","display_name":"Jedediah M. Singer","orcid":"https://orcid.org/0000-0002-5255-4473","observed_orcids":["https://orcid.org/0000-0002-5255-4473"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Singer, Jedediah","raw_affiliation_strings":["Two Six Technologies"],"raw_orcid":"https://orcid.org/0000-0002-5255-4473","affiliations":[{"raw_affiliation_string":"Two Six Technologies","institution_ids":[]}]}],"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9980000257492065,"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":0.9980000257492065,"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":0.0012000000569969416,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":9.999999747378752e-05,"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/dna-binding-proteins","display_name":"DNA-binding proteins","score":0.9369999766349792},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"protein function prediction","score":0.8840000033378601},{"id":"https://openalex.org/keywords/protein-sequence-classification","display_name":"protein sequence classification","score":0.5329999923706055},{"id":"https://openalex.org/keywords/assessment-methods","display_name":"assessment methods","score":0.5920000076293945},{"id":"https://openalex.org/keywords/xgboost","display_name":"XGBoost","score":0.9800000190734863},{"id":"https://openalex.org/keywords/bacterial-proteins","display_name":"bacterial proteins","score":0.5659999847412109},{"id":"https://openalex.org/keywords/uniprot","display_name":"UniProt","score":0.5649999976158142}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5654512643814087},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.49656015634536743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4730623960494995},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43941396474838257},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2856959104537964},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.24164283275604248}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:zenodo.org:5137962","doi":null,"is_oa":true,"landing_page_url":"https://zenodo.org/record/5137962","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"dataset"},{"id":"doi:10.5281/zenodo.5137961","doi":"https://doi.org/10.5281/zenodo.5137961","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.5137961","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.5137962","doi":"https://doi.org/10.5281/zenodo.5137962","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.5137962","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.5153906","doi":"https://doi.org/10.5281/zenodo.5153906","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.5153906","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:5137962","doi":null,"is_oa":true,"landing_page_url":"https://zenodo.org/record/5137962","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6912462859","https://openalex.org/W3195367207","https://openalex.org/W7125983135","https://openalex.org/W4392817839","https://openalex.org/W2029964710","https://openalex.org/W6929962532","https://openalex.org/W4289812859","https://openalex.org/W7096639848","https://openalex.org/W7100941476","https://openalex.org/W4391311413"],"abstract_inverted_index":{"Data":[0],"set":[1],"and":[2,8,24,65],"results":[3,52],"for":[4,11],"\"Improved":[5],"data":[6,59],"sets":[7,26,60],"evaluation":[9],"methods":[10],"the":[12,22,28,74],"automatic":[13],"prediction":[14],"of":[15],"DNA-binding":[16],"proteins\"":[17],"The":[18,51,57,69],"file":[19],"\"dna_binding_protein_sequences.zip\"":[20],"has":[21],"testing":[23],"training":[25],"from":[27,63],"paper:":[29],"RLL":[30,39],"-":[31,34,37,49],"\"random_<train/test>_full_1000.csv\"":[32],"RSL":[33],"\"random_<train/test>_50.csv\"":[35],"RS&LL":[36],"\"random_<train/test>_50_1000.csv\"":[38],"where":[40],"included":[41],"positive":[42],"examples":[43],"have":[44],"verified":[45],"DNA":[46],"binding":[47],"activity":[48],"\"random_<train/test>_hq_1000.csv\"":[50],"files":[53],"are":[54,61,77],"named":[55],"similarly.":[56],"species":[58],"derived":[62],"\"uniprot_data_bac.tab\"":[64],"\"uniprot_data_not_bac.tab.\"":[66],"See":[67],"code.":[68],"ESM":[70],"embeddings":[71],"used":[72],"by":[73],"XGBoost":[75],"model":[76],"in":[78],"\"dna_binding_protein_esm.zip\"":[79]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2024-04-03T00:00:00"}
