Predictive tools reviewed in this study
Model | Category | Performance AUC | Year/Citation |
---|---|---|---|
ProteaSMM c/i | i | 0.71/0.74 | 2005 [39] |
NetCTLpan | i | 0.94 | 2010 [40] |
NetMHCstabpan | i | 0.97 | 2016 [43] |
HLAthena | i | N/A | 2020 [44] |
iPCPS | i | N/A | 2020 [45] |
MHCflurry BA/AP | i | 0.91/0.85 | 2020 [46] |
NetCleave | i | 0.58 | 2021 [47] |
NetMHCpanexp | i | 0.82 | 2022 [50] |
NetMHCpan | N/A | 0.99 | 2017 [55] |
MixMHCpred | N/A | 0.98 | 2017 [54] |
Kernel | ii | 0.8 | 2012 [64] |
Antigen.garnish dissimilarity/IEDB score | ii | 0.85/0.70 | 2019 [65] |
Pairwise sequence similarity | ii | N/A | 2019 [20] |
IEDB immunogenicity | iii | 0.61 | 2013 [66] |
DeepNetBim | iii | 0.94 | 2021 [70] |
DeepImmuno | iii | 0.85 | 2021 [72] |
DeepHLApan | iv | 0.81 | 2019 [75] |
INeo-Epp | iv | 0.78 | 2020 [76] |
TA predictor | iv | 0.82 | 2021 [77] |
PRIME | iv | 0.81 | 2021 [80] |
iTTCA-RF | iv | 0.78 | 2021 [81] |
Tools are grouped by categories established in this article (i: biological features; ii: similarity metrics; iii: pathogen immunogenicity; iv: tumor immunogenicity), and sorted by year of publication. The AUCs were reported by the authors in the original articles. The performance corresponds to independent evaluations on epitope or neoepitope datasets, if available. If multiple evaluations were made, the average AUC is displayed. *: These methods have been evaluated with datasets that contain immunogenic peptides as positives, and other peptides as negatives. The latter may not bind to MHC molecules; †: These methods have been evaluated with datasets that contain immunogenic peptides as positives and non-immunogenic peptides as negatives, but both categories may have the same likelihood of binding to MHC. This approach is comparable to the evaluation performed in this work; ‡: This method was evaluated and included in the pTuneos pipeline. For this reason, its performance can not be assessed individually; §: The AUC corresponds to performance in cross validation; N/A: not applicable; AUC: area under the curve
The supplementary Figure, Tables, and Supplementary methods in Supplementary materials for this article are available at: https://www.explorationpub.com/uploads/Article/file/100391_sup_1.xlsx and https://www.explorationpub.com/uploads/Article/file/100391_sup_2.pdf.
We dedicate this work to our patients. This work has been performed using the Danish National Life Science Supercomputing Center, Computerome. We thank Emilio Fenoy for insightful discussions about this research.
IC, MN, and MMB: Conceptualization, Writing—original draft. IC: Formal analysis. IC, ES, EP, and HMGA: Investigation. IC and HMGA: Software. IC: Visualization. JM, MN, and MMB: Funding acquisition, Resources. MMB: Supervision. IC, ES, EP, HMGA, JM, MN, and MMB: Writing—review & editing. All authors read and approved the submitted version.
The authors declare that they have no conflicts of interest.
The CASVAC-0401 study was carried out after approval of the Ethics Committee of the Instituto Alexander Fleming. The study was also approved by the Argentine Regulatory Agency (ANMAT, Disposition 1299/09).
Informed written consent to participate in the CASVAC study and for the use of their samples in the research projects associated with the vaccination protocol was obtained from all participants.
Not applicable.
The dataset generated for this study is included in the supplementary files.
This work was supported by grants from CONICET, Agencia Nacional de Promoción Científica y Tecnológica (ANPCyT), Instituto Nacional del Cáncer—Ministerio de Salud de la Nación Argentina (INC-MSal), Fundación Sales, Fundación Cáncer, and Fundación Pedro F. Mosoteguy, Argentina. The CASVAC-0401 Phase II clinical study (Clinical Trials.gov, NCT 01729663) was sponsored by Laboratorio Pablo Cassará S.R.L. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
© The Author(s) 2023.