MHCflurry 2.0: Improved Pan-Allele Prediction of MHC Class I-Presented Peptides by Incorporating Antigen Processing
Timothy J. O’Donnell, Alex Rubinsteyn, Uri Laserson
Abstract
(Cell Systems 11, 42–48.e1–e7; July 22, 2020) In the original published version of this paper, the axes of Figure 3B were mislabeled. The tick marks on the x and y axes were labeled as –0.1 and 1.0. This was not correct; the correct tick marks on both axes are 0.0, 0.5, and 1.0. The x and y axes of Figure 3B have been corrected, and the authors apologize for any confusion these errors may have caused. This change does not affect the conclusions of the study.Figure 3. The MHCflurry 2.0 PS Model Combines BA and AP Prediction (Original)View Large Image Figure ViewerDownload Hi-res image Download (PPT) MHCflurry 2.0: Improved Pan-Allele Prediction of MHC Class I-Presented Peptides by Incorporating Antigen ProcessingO’Donnell et al.Cell SystemsJuly 14, 2020In BriefO’Donnell et al. developed improved models for predicting the antigens available for recognition by cytotoxic T cells. Separate predictors of MHC class I binding and antigen processing were trained using published datasets of peptides naturally presented on MHC. The software is open source and readily incorporated into workflows for neoantigen discovery and vaccine design. Full-Text PDF Open Access