{"id":"https://openalex.org/W3017143673","doi":"https://doi.org/10.1101/2020.04.18.048439","title":"ProtTox: Toxin identification from Protein Sequences","display_name":"ProtTox: Toxin identification from Protein Sequences","publication_year":2020,"publication_date":"2020-04-20","ids":{"openalex":"https://openalex.org/W3017143673","doi":"https://doi.org/10.1101/2020.04.18.048439","mag":"3017143673"},"language":"en","primary_location":{"id":"doi:10.1101/2020.04.18.048439","doi":"https://doi.org/10.1101/2020.04.18.048439","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2020.04.18.048439","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2020/04/20/2020.04.18.048439.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2020/04/20/2020.04.18.048439.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037626731","display_name":"Sathappan Muthiah","orcid":"https://orcid.org/0009-0009-3687-3392","observed_orcids":["https://orcid.org/0009-0009-3687-3392"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sathappan Muthiah","raw_affiliation_strings":["Department of Computer Science, Virginia Tech, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053069327","display_name":"Debanjan Datta","orcid":"https://orcid.org/0000-0001-5997-5142","observed_orcids":["https://orcid.org/0000-0001-5997-5142"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Debanjan Datta","raw_affiliation_strings":["Department of Computer Science, Virginia Tech, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113684309","display_name":"Mohammad Raihanul Islam","orcid":"https://orcid.org/0000-0001-7109-9878","observed_orcids":["https://orcid.org/0000-0001-7109-9878"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Raihanul Islam","raw_affiliation_strings":["Department of Computer Science, Virginia Tech, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061966723","display_name":"P. J. Butler","orcid":"https://orcid.org/0000-0003-0468-6794","observed_orcids":["https://orcid.org/0000-0003-0468-6794"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Butler","raw_affiliation_strings":["Department of Computer Science, Virginia Tech, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016058860","display_name":"Andrew S. Warren","orcid":"https://orcid.org/0000-0003-2660-0103","observed_orcids":["https://orcid.org/0000-0003-2660-0103"]},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Warren","raw_affiliation_strings":["Biocomplexity Institute and Initiative, University of Virginia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biocomplexity Institute and Initiative, University of Virginia, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035052603","display_name":"Naren Ramakrishnan","orcid":"https://orcid.org/0000-0002-1821-9743","observed_orcids":["https://orcid.org/0000-0002-1821-9743"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naren Ramakrishnan","raw_affiliation_strings":["Department of Computer Science, Virginia Tech, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053069327"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.9779999852180481,"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":0.9779999852180481,"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":0.004800000227987766,"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/T11353","display_name":"Venomous Animal Envenomation and Studies","score":0.002199999988079071,"subfield":{"id":"https://openalex.org/subfields/3005","display_name":"Toxicology"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/toxin-identification","display_name":"toxin identification","score":0.8790000081062317},{"id":"https://openalex.org/keywords/protein-sequence-classification","display_name":"protein sequence classification","score":0.6840000152587891},{"id":"https://openalex.org/keywords/deep-learning","display_name":"deep learning","score":0.8920000195503235},{"id":"https://openalex.org/keywords/protein-function-annotation","display_name":"protein annotation","score":0.4230000078678131},{"id":"https://openalex.org/keywords/homology","display_name":"homology","score":0.718999981880188},{"id":"https://openalex.org/keywords/multifunctionality","display_name":"multifunctionality","score":0.8870000243186951},{"id":"https://openalex.org/keywords/structural-diversity","display_name":"structural diversity","score":0.8799999952316284}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6588698625564575},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6504613757133484},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5698177814483643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.566399872303009},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5603696703910828},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4934765100479126},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.45963436365127563},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4275355935096741},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1893579363822937},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12709832191467285},{"id":"https://openalex.org/C505870484","wikidata":"https://www.wikidata.org/wiki/Q180538","display_name":"Fishery","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1101/2020.04.18.048439","doi":"https://doi.org/10.1101/2020.04.18.048439","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2020.04.18.048439","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2020/04/20/2020.04.18.048439.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.1101/2020.04.18.048439","doi":"https://doi.org/10.1101/2020.04.18.048439","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2020.04.18.048439","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2020/04/20/2020.04.18.048439.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3141641755","display_name":null,"funder_award_id":"W911NF-17","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320312530","display_name":"Office of the Director of National Intelligence","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320337349","display_name":"NIH Office of the Director","ror":"https://ror.org/00fj8a872"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3017143673.pdf","grobid_xml":"https://content.openalex.org/works/W3017143673.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1549740192","https://openalex.org/W1806891645","https://openalex.org/W1967195968","https://openalex.org/W1986708244","https://openalex.org/W1990075477","https://openalex.org/W2036595331","https://openalex.org/W2103148772","https://openalex.org/W2148853951","https://openalex.org/W2154775341","https://openalex.org/W2165347905","https://openalex.org/W2173913502","https://openalex.org/W2530149620","https://openalex.org/W2626778328","https://openalex.org/W2765953894","https://openalex.org/W2909727437","https://openalex.org/W2944360550","https://openalex.org/W2964301648"],"related_works":["https://openalex.org/W4239714150","https://openalex.org/W4394756259","https://openalex.org/W2530149620","https://openalex.org/W4414043998","https://openalex.org/W3194998621","https://openalex.org/W3173561065","https://openalex.org/W4394817662","https://openalex.org/W7214209985","https://openalex.org/W4414704439","https://openalex.org/W3044326329"],"abstract_inverted_index":{"Abstract":[0],"Toxin":[1],"classification":[2],"of":[3,25,31,46,71,74,89],"protein":[4],"sequences":[5],"is":[6,93],"a":[7,59,87],"challenging":[8],"task":[9],"with":[10],"real":[11],"world":[12],"applications":[13],"in":[14,54,77],"healthcare":[15],"and":[16,27,49],"synthetic":[17],"biology.":[18],"Due":[19],"to":[20,43,68],"an":[21],"ever":[22],"expanding":[23],"database":[24],"proteins":[26,53,79],"the":[28,72,98],"inordinate":[29],"cost":[30],"manual":[32],"annotation,":[33],"automated":[34],"machine":[35],"learning":[36,62],"based":[37,63],"approaches":[38,76],"are":[39],"crucial.":[40],"Approaches":[41],"need":[42],"overcome":[44],"challenges":[45],"homology,":[47],"multi-functionality,":[48],"structural":[50],"diversity":[51],"among":[52],"this":[55],"task.":[56],"We":[57],"propose":[58],"novel":[60],"deep":[61],"method":[64,85],"ProtTox,":[65],"that":[66],"aims":[67],"address":[69],"some":[70],"shortcomings":[73],"previous":[75],"classifying":[78],"as":[80],"toxins":[81],"or":[82],"not.":[83],"Our":[84],"achieves":[86],"performance":[88],"0.812":[90],"F1-score":[91],"which":[92],"about":[94],"5%":[95],"higher":[96],"than":[97],"closest":[99],"performing":[100],"baseline.":[101]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2020-04-24T00:00:00"}
