Rxivist logo

MethylationToActivity: a deep-learning framework that reveals promoter activity landscapes from DNA methylomes in individual tumors

By Justin Williams, Beisi Xu, Daniel Putnam, Andrew Thrasher, Chunliang Li, Jun Yang, Xiang Chen

Posted 11 Jun 2020
bioRxiv DOI: 10.1101/2020.06.09.143172 (published DOI: 10.1186/s13059-020-02220-y)

Although genome-wide DNA methylomes have demonstrated their clinical value as reliable biomarkers for tumor detection, subtyping, and classification, their direct biological impacts at the individual gene level remain elusive. Here we present MethylationToActivity (M2A), a machine learning framework that uses convolutional neural networks to infer promoter activities (H3K4me3 and H3K27ac enrichment) from DNA methylation patterns for individual genes. Using publicly available datasets in real-world test scenarios, we demonstrate that M2A is highly accurate and robust in revealing promoter activity landscapes in various pediatric and adult cancers, including both solid and hematologic malignant neoplasms. ### Competing Interest Statement The authors have declared no competing interest.

Download data

  • Downloaded 407 times
  • Download rankings, all-time:
    • Site-wide: 94,493
    • In genomics: 5,852
  • Year to date:
    • Site-wide: 92,921
  • Since beginning of last month:
    • Site-wide: 131,894

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide