Rxivist logo

neoDL: A novel neoantigen intrinsic feature-based deep learning model identifies IDH wild-type glioblastomas with the longest survival

By Ting Sun, Yufei He, Wendong Li, Guang Liu, Lin Li, Lu Wang, Zixuan Xiao, Xiaohan Han, Hao Wen, Yong Liu, Yifan Chen, Haoyu Wang, Jing Li, Yubo Fan, Wei Zhang, Jing Zhang

Posted 29 Dec 2020
bioRxiv DOI: 10.1101/2020.12.28.424562

BackgroundIDH wild-type glioblastoma (GBM) is the most aggressive tumor in the central nervous system in spite of extensive therapies. Neoantigen based personalized immune therapies achieve promising results in melanoma and lung cancer, but few neoantigen based models perform well in IDH wild-type GBM. Unlike the neoantigen load and occurrence that are well studied and often found useless, the association between neoantigen intrinsic features and prognosis remain unclear in IDH wild-type GBM. ResultsWe presented a novel neoantigen intrinsic feature-based deep learning model (neoDL) to stratify IDH wild-type GBMs into subgroups with different survivals. We first calculated a total of 2928 intrinsic features for each neoantigen and filtered out those not associated with survival, followed by applying neoDL in the TCGA data cohort. Leave one out cross validation (LOOCV) in the TCGA demonstrated that neoDL successfully classified IDH wild-type GBMs into different prognostic subgroups, which was further validated in an independent data cohorts from Asian population. Long-term survival IDH wild-type GBMs identified by neoDL were found characterized by 12 protective neoantigen intrinsic features and enriched in development and cell cycle. ConclusionsOur results provide a novel model, neoDL, that can be therapeutically exploited to identify IDH wild-type GBM with good prognosis who will most likely benefit from neoantigen based personalized immunetherapy.

Download data

  • Downloaded 161 times
  • Download rankings, all-time:
    • Site-wide: 190,467
    • In bioinformatics: 13,723
  • Year to date:
    • Site-wide: 192,834
  • Since beginning of last month:
    • Site-wide: 168,021

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide