Study

WXS of 147 lung cancer patients treated with immunotherapy

Study ID Alternative Stable ID Type
EGAS00001003781 Other

Study Description

We first attempted to predict MHC-binding neoantigens at high accuracy with convolutional neural networks. This prediction model outperformed previous methods in > 70% of test cases. Importantly, our method remarkably increased the predictive value of neoantigen load especially in combination with known resistance parameters. We then developed a classifier that can predict resistance from point mutations that are deleterious to protein function. Notably, genes involved in the adaptive immune response, cytokine signaling,and EGFR signaling held high explanatory power. Furthermore, when integrated with our neoantigen profiling, these anti-immunogenic mutations revealed significantly higher predictive power than known resistance factors.

Study Datasets 1 dataset.

Click on a Dataset ID in the table below to learn more, and to find out who to contact about access to these data

Dataset ID Description Technology Samples
EGAD00001005211
This data includes whole exome sequencing of matched normal-tumor samples of patients who have received immunotherapy. '-1' refers to matched normal sample and '-2' refers to matched tumor sample.
Illumina HiSeq 2500 294

Who archives the data?

There are no publications available