RT Journal Article
T1 Predicting MHC I restricted T cell epitopes in mice with NAP-CNB, a novel online tool
A1 Wert Carvajal, Carlos
A1 Sánchez García, Rubén
A1 Macías, José R.
A1 Sanz Pamplona, Rebeca
A1 Méndez Pérez, Almudena
A1 Alemany, Ramon
A1 Veiga, Esteban
A1 Sánchez Sorzano, Carlos Óscar
A1 Muñoz Barrutia, María Arrate
AB Lack of a dedicated integrated pipeline for neoantigen discovery in mice hinders cancerimmunotherapy research. Novel sequential approaches through recurrent neural networks canimprove the accuracy of T-cell epitope binding affinity predictions in mice, and a simplified variantselection process can reduce operational requirements. We have developed a web server tool (NAPCNB)for a full and automatic pipeline based on recurrent neural networks, to predict putativeneoantigens from tumoral RNA sequencing reads. The developed software can estimate H-2 peptideligands, with an AUC comparable or superior to state-of-the-art methods, directly from tumorsamples. As a proof-of-concept, we used the B16 melanoma model to test the system’s predictivecapabilities, and we report its putative neoantigens. NAP-CNB web server is freely available at http://bioco mp. cnb. csic. es/ Neoan tigen sApp/ with scripts and datasets accessible through the downloadsection.
PB Springer Science and Business Media LLC
SN 2045-2322
YR 2021
FD 2021-05-24
LK http://hdl.handle.net/10016/34809
UL http://hdl.handle.net/10016/34809
LA eng
NO This work was funded by the Spanish Ministry of Economy, Industry and Competitiveness (TEC2016-28052-R,RTC2017-6600-1, SAF2017-84091-R, BFERO2020.04), the Spanish Ministry of Science and Innovation(FPU18/03199, PID2019-109820RB-I00), the “la Caixa” Foundation (LCF/BQ/EU19/11710071), FERO foundationand Centro Superior de Investigaciones Científicas (JAEINT18/EX/0636).
DS e-Archivo
RD 28 abr. 2024