{"id":"https://openalex.org/W7214209985","doi":"https://doi.org/10.64898/2026.09.18.752542","title":"NeoToxPred: a fine-tuned protein language model with orthologous and length-stratified negative controls for robust toxicity classification","display_name":"NeoToxPred: a fine-tuned protein language model with orthologous and length-stratified negative controls for robust toxicity classification","publication_year":2026,"publication_date":"2026-09-24","ids":{"openalex":"https://openalex.org/W7214209985","doi":"https://doi.org/10.64898/2026.09.18.752542"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.18.752542","doi":"https://doi.org/10.64898/2026.09.18.752542","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.18.752542","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/24/2026.09.18.752542.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/24/2026.09.18.752542.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004614402","display_name":"S J Kim","orcid":"https://orcid.org/0009-0008-4930-4263","observed_orcids":["https://orcid.org/0009-0008-4930-4263"]},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seongmin Kim","raw_affiliation_strings":["Institute of Systems Biology & Life Science Informatics, Chonnam National University, Yongbong-ro 77, Gwangju 61186, Republic of Korea","School of Biological Sciences and Technology, Chonnam National University, Yongbong-ro 77, Gwangju 61186, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Systems Biology & Life Science Informatics, Chonnam National University, Yongbong-ro 77, Gwangju 61186, Republic of Korea","institution_ids":["https://openalex.org/I111277659"]},{"raw_affiliation_string":"School of Biological Sciences and Technology, Chonnam National University, Yongbong-ro 77, Gwangju 61186, Republic of Korea","institution_ids":["https://openalex.org/I111277659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100680042","display_name":"Min\u2010Seok Kim","orcid":"https://orcid.org/0000-0003-3425-882X","observed_orcids":["https://orcid.org/0000-0003-3425-882X","https://orcid.org/0009-0001-0567-3875"]},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Min-Seok Kim","raw_affiliation_strings":["Dental Science Research Institute, School of Dentistry, Chonnam National University, Yongbong-ro 77, Gwangju 61186, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dental Science Research Institute, School of Dentistry, Chonnam National University, Yongbong-ro 77, Gwangju 61186, Republic of Korea","institution_ids":["https://openalex.org/I111277659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036941709","display_name":"Chungoo Park","orcid":"https://orcid.org/0000-0002-9545-6654","observed_orcids":["https://orcid.org/0000-0002-9545-6654"]},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Chungoo Park","raw_affiliation_strings":["Institute of Systems Biology & Life Science Informatics, Chonnam National University, Yongbong-ro 77, Gwangju 61186, Republic of Korea","School of Biological Sciences and Technology, Chonnam National University, Yongbong-ro 77, Gwangju 61186, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-9545-6654","affiliations":[{"raw_affiliation_string":"Institute of Systems Biology & Life Science Informatics, Chonnam National University, Yongbong-ro 77, Gwangju 61186, Republic of Korea","institution_ids":["https://openalex.org/I111277659"]},{"raw_affiliation_string":"School of Biological Sciences and Technology, Chonnam National University, Yongbong-ro 77, Gwangju 61186, Republic of Korea","institution_ids":["https://openalex.org/I111277659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5036941709"],"corresponding_institution_ids":["https://openalex.org/I111277659"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.9179999828338623,"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":0.9179999828338623,"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":0.030700000002980232,"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"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.012900000438094139,"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/toxicity-classification","display_name":"toxicity classification","score":0.8500000238418579},{"id":"https://openalex.org/keywords/protein-language-models","display_name":"protein language models","score":0.8730000257492065},{"id":"https://openalex.org/keywords/training-data-curation","display_name":"training data curation","score":0.6079999804496765},{"id":"https://openalex.org/keywords/alanine-scanning","display_name":"alanine scanning","score":0.8240000009536743}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5666999816894531},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.515500009059906},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5059999823570251},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4918000102043152},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.4864000082015991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48260000348091125},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4797999858856201},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4722000062465668},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4207000136375427},{"id":"https://openalex.org/C104397665","wikidata":"https://www.wikidata.org/wiki/Q860947","display_name":"Proteome","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.41029998660087585},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.38359999656677246},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.36970001459121704},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C171897839","wikidata":"https://www.wikidata.org/wiki/Q417841","display_name":"Protein family","level":3,"score":0.34360000491142273},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.3221000134944916},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C94795543","wikidata":"https://www.wikidata.org/wiki/Q3813754","display_name":"Human proteome project","level":4,"score":0.296999990940094},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.29679998755455017},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C164085508","wikidata":"https://www.wikidata.org/wiki/Q4811327","display_name":"Matthews correlation coefficient","level":3,"score":0.2939999997615814},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29170000553131104},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.29100000858306885},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.2703999876976013},{"id":"https://openalex.org/C2778924833","wikidata":"https://www.wikidata.org/wiki/Q7064603","display_name":"Novelty detection","level":3,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.18.752542","doi":"https://doi.org/10.64898/2026.09.18.752542","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.18.752542","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/24/2026.09.18.752542.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.18.752542","doi":"https://doi.org/10.64898/2026.09.18.752542","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.18.752542","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/24/2026.09.18.752542.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.504800021648407,"id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G187717830","display_name":null,"funder_award_id":"RS-2024-00442775","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G244371914","display_name":null,"funder_award_id":"RS-2024-00442775","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G3082893331","display_name":null,"funder_award_id":"RS-2025-02292973","funder_id":"https://openalex.org/F4320327222","funder_display_name":"Korea Institute of Marine Science and Technology promotion"},{"id":"https://openalex.org/G485438945","display_name":null,"funder_award_id":"RS-2025-24523548","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G5423668780","display_name":null,"funder_award_id":"RS\u20102024\u201000442775","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G5817749580","display_name":null,"funder_award_id":"RS-2025-24523548","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G7175247418","display_name":null,"funder_award_id":"RS-2025-02309093","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G7295706357","display_name":null,"funder_award_id":"RS\u20102025\u201002217886","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G7515796954","display_name":null,"funder_award_id":"RS-2025-02217886","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G7737415359","display_name":null,"funder_award_id":"RS-2025-02309093","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G7901101397","display_name":null,"funder_award_id":"RS-2025-02292973","funder_id":"https://openalex.org/F4320322011","funder_display_name":"Ministry of Oceans and Fisheries"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322011","display_name":"Ministry of Oceans and Fisheries","ror":"https://ror.org/00c5s4a53"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320327222","display_name":"Korea Institute of Marine Science and Technology promotion","ror":"https://ror.org/04cqyfy93"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214209985.pdf","grobid_xml":"https://content.openalex.org/works/W7214209985.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1970294718","https://openalex.org/W2006951143","https://openalex.org/W2019591778","https://openalex.org/W2038464976","https://openalex.org/W2041386815","https://openalex.org/W2042655455","https://openalex.org/W2080967293","https://openalex.org/W2103018059","https://openalex.org/W2103111028","https://openalex.org/W2103546835","https://openalex.org/W2106449364","https://openalex.org/W2118578832","https://openalex.org/W2128312954","https://openalex.org/W2142678478","https://openalex.org/W2145100181","https://openalex.org/W2156125289","https://openalex.org/W2163545771","https://openalex.org/W2170747616","https://openalex.org/W2198606573","https://openalex.org/W2340497515","https://openalex.org/W2765935088","https://openalex.org/W2767170939","https://openalex.org/W2811245004","https://openalex.org/W2899663614","https://openalex.org/W2964121744","https://openalex.org/W3021745639","https://openalex.org/W3034854196","https://openalex.org/W3045196858","https://openalex.org/W3145990216","https://openalex.org/W3146944767","https://openalex.org/W3179485843","https://openalex.org/W4206722897","https://openalex.org/W4210601043","https://openalex.org/W4281790889","https://openalex.org/W4292678539","https://openalex.org/W4318480056","https://openalex.org/W4385768591","https://openalex.org/W4386530496","https://openalex.org/W4392236243","https://openalex.org/W4394694796","https://openalex.org/W4399917261","https://openalex.org/W4400864148","https://openalex.org/W4403338304","https://openalex.org/W4404458588","https://openalex.org/W4404516811","https://openalex.org/W4404531735","https://openalex.org/W4406816260","https://openalex.org/W4409154153","https://openalex.org/W4409257324","https://openalex.org/W4410799875","https://openalex.org/W4414396418","https://openalex.org/W4414760252","https://openalex.org/W4415077954","https://openalex.org/W7163532908"],"related_works":["https://openalex.org/W7222081262","https://openalex.org/W4226068113","https://openalex.org/W4409154153","https://openalex.org/W4399395538","https://openalex.org/W3017143673","https://openalex.org/W4400864148","https://openalex.org/W4412489124","https://openalex.org/W4414704439","https://openalex.org/W4403469487","https://openalex.org/W4318480056"],"abstract_inverted_index":{"Abstract":[0],"Although":[1,121],"protein":[2,111],"toxins":[3,23,263],"represent":[4],"valuable":[5],"pharmacological":[6],"templates,":[7],"predicting":[8],"toxicity":[9],"directly":[10],"from":[11,64,150],"primary":[12],"sequences":[13,212],"is":[14,125],"inherently":[15],"challenging":[16],"because":[17],"of":[18,49,135,203,208,216,247,259],"their":[19,25],"evolutionary":[20,235],"dynamics.":[21],"Active":[22],"and":[24,33,68,177,205,213,234],"benign":[26],"homologues":[27],"frequently":[28],"share":[29],"identical":[30],"structural":[31],"scaffolds":[32],"differ":[34],"by":[35,189],"only":[36],"a":[37,101,116,164,174,179,198,238,267],"few":[38],"key":[39],"residue":[40],"substitutions,":[41],"making":[42],"global":[43,80],"sequence":[44,171,232,310],"similarity":[45],"an":[46,145,206,214],"unreliable":[47],"indicator":[48],"function.":[50],"Conventional":[51],"predictors":[52,225],"compound":[53],"this":[54],"challenge":[55],"through":[56,71],"flawed":[57],"negative-set":[58,300],"designs":[59],"that":[60,83,105,282,298],"sample":[61],"non-toxic":[62],"controls":[63],"arbitrary":[65],"background":[66],"proteins":[67],"reduce":[69],"redundancy":[70],"identity-based":[72],"clustering":[73],"under":[74,155],"random":[75],"partitioning.":[76],"This":[77],"practice":[78],"introduces":[79],"confounding":[81],"shortcuts":[82],"inflate":[84],"benchmark":[85],"performance":[86,186,229],"while":[87,226],"failing":[88],"to":[89,128,159,169,184,289],"capture":[90],"true":[91],"functional":[92],"boundaries.":[93],"To":[94],"address":[95],"these":[96,295],"limitations,":[97],"we":[98],"developed":[99],"NeoToxPred,":[100],"sequence-only":[102],"binary":[103],"classifier":[104],"fine-tunes":[106],"the":[107,122,132,136,151,243,248,283],"pretrained":[108],"ESM-C":[109],"600M":[110],"language":[112],"model":[113],"end-to-end":[114],"with":[115],"six-layer":[117],"feed-forward":[118],"classification":[119],"head.":[120],"neural":[123],"architecture":[124],"intentionally":[126],"standard":[127],"ensure":[129],"computational":[130],"scalability,":[131],"core":[133],"novelty":[134],"framework":[137,284],"lies":[138],"in":[139,308],"its":[140,287],"rigorous":[141],"training-data":[142],"curation:":[143],"(i)":[144],"orthologous":[146],"negative":[147,166],"set":[148,168],"drawn":[149],"same":[152],"InterPro":[153],"families":[154],"controlled":[156],"taxonomic":[157],"proximity":[158],"eliminate":[160,170],"phylogenetic":[161],"shortcuts,":[162],"(ii)":[163],"length-stratified":[165],"control":[167],"length":[172],"as":[173],"predictive":[175],"cue,":[176],"(iii)":[178],"strict":[180],"family-disjoint":[181],"splitting":[182],"strategy":[183],"prevent":[185],"inflation":[187],"caused":[188],"pattern":[190],"memorization.":[191],"On":[192],"held-out":[193],"internal":[194],"benchmarks,":[195],"NeoToxPred":[196,255],"achieved":[197],"Matthews":[199],"correlation":[200],"coefficient":[201],"(MCC)":[202],"0.897":[204],"F1-score":[207],"0.949":[209],"on":[210,218],"long":[211],"MCC":[215],"0.869":[217],"short":[219],"peptides,":[220],"decisively":[221],"outperforming":[222],"five":[223],"recent":[224],"maintaining":[227],"stable":[228],"across":[230],"varying":[231],"lengths":[233],"distances.":[236],"In":[237],"genome-scale":[239],"external":[240],"validation":[241],"using":[242],"previously":[244],"unseen":[245],"proteome":[246],"redfin":[249],"waspfish":[250],"(":[251],"Paracentropogon":[252],"rubripinnis":[253],"),":[254],"successfully":[256],"recovered":[257],"11":[258],"16":[260],"empirically":[261],"validated":[262],"without":[264],"collapsing":[265],"into":[266],"single-class":[268],"prediction,":[269],"whereas":[270],"structure-dependent":[271],"baselines":[272],"identified":[273],"substantially":[274],"fewer":[275],"positives.":[276],"Computational":[277],"alanine":[278],"scanning":[279],"further":[280],"confirmed":[281],"contextually":[285],"localizes":[286],"predictions":[288],"functionally":[290],"active":[291],"residues.":[292],"Taken":[293],"together,":[294],"findings":[296],"suggest":[297],"systematic":[299],"design":[301],"should":[302],"be":[303],"prioritized":[304],"alongside":[305],"algorithmic":[306],"complexity":[307],"biological":[309],"classification.":[311]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-09-25T00:00:00"}