biostudies-literatureWells DKParker Institute for Cancer ImmunotherapyNIAID NIH HHSNHGRI NIH HHSNCI NIH HHSNational Institutes of HealthCancer Research InstituteNIGMS NIH HHS818-834.e13https://www.ebi.ac.uk/biostudies/studies/S-EPMC7652061biostudies-literatureUnknown183(3)Many approaches to identify therapeutically relevant neoantigens couple tumor sequencing with bioinformatic algorithms and inferred rules of tumor epitope immunogenicity. However, there are no reference data to compare these approaches, and the parameters governing tumor epitope immunogenicity remain unclear. Here, we assembled a global consortium wherein each participant predicted immunogenic epitopes from shared tumor sequencing data. 608 epitopes were subsequently assessed for T cell binding in patient-matched samples. By integrating peptide features associated with presentation and recognition, we developed a model of tumor epitope immunogenicity that filtered out 98% of non-immunogenic peptides with a precision above 0.70. Pipelines prioritizing model features had superior performanceCellKey Parameters of Tumor Epitope Immunogenicity Revealed Through a Consortium Approach Improve Neoantigen Prediction.PMC7652061P30 CA091842T32 GM008042P30 CA016042P30 CA008748T32 CA009120T32 HG002295R21 AI134127R50 CA211482Sette AHiggs BWShah PSebastian YPrinciotta MSidney JCarreno BMHellmann MDChour WShcheglova TMorehouse CAManning PSchreiber RDHsu YHKvistborg PGfeller DBartha GTumor Neoantigen Selection AllianceZaretsky JMCampbell KMJosipovic VRaicevic NMIMueller MHacohen NRao AASi HRamsdell FGuinney JHu QSteiner GMRibas ADang KKKetelaars SLCRizvi HFu WPerera JFHundal JKooi ILower MBoyle SMHeath JRvan Buuren MMBerent-Maoz BZiman RKessler JHArtyomov MNLi BLee LJZornig IChang HWei LGupta Rvan Beek DJongeneel PLazic AMMRichard GTadmor ADJager DWard JPJhunjhunwala SHuang ZHalama NShukla SASchuepbach TBlazquez ABLugade ASchrors BStevenson BJPei BLang MSridhar SPeters BXenarios IAl Seesi SMilicevic OSWang JWells DKGreshock JSheehan KCFBlake JComin-Anduix BQiu SKodysh JTanden PWu SGellert PIseli CChen RKrebber WJMacabali MDefranoux NARobine NEsaulova EYang NKojicic MRCoukos GVormehr MLamb ASrivastava PKMelief CJMSalama SGreenbaum JACharoentong PBassani-Sternberg MFrentzen AAEBalli DSkundric NMLiu SChen JMArcila FSlagter MSherafat EMiller CAShelton JMMandoiu ISzustakowski JKuziora MHilker RNg AHCConway JPKhan AAPuig-Saus CKolom ASong BFanchi LFForman JGuex NDoan XCRech AJYalcin ZKHaussler DBhardwaj NSarkizova SHubbard-Lucey VMCreasy THSchumacher TNKovacevic VBMerghoub TCortes EHarris JPetit RYu TVSelinsky CSasson ASLiu GfalseKey Parameters of Tumor Epitope Immunogenicity Revealed Through a Consortium Approach Improve Neoantigen Prediction.Many approaches to identify therapeutically relevant neoantigens couple tumor sequencing with bioinformatic algorithms and inferred rules of tumor epitope immunogenicity. However, there are no reference data to compare these approaches, and the parameters governing tumor epitope immunogenicity remain unclear. Here, we assembled a global consortium wherein each participant predicted immunogenic epitopes from shared tumor sequencing data. 608 epitopes were subsequently assessed for T cell binding in patient-matched samples. By integrating peptide features associated with presentation and recognition, we developed a model of tumor epitope immunogenicity that filtered out 98% of non-immunogenic peptides with a precision above 0.70. Pipelines prioritizing model features had superior performance2020-01-01T00:00:00Z2020 Oct2026-05-02T12:50:49.826Z2026-04-07T18:00:10.137ZS-EPMC76520613303834210.1016/j.cell.2020.09.015