Rxivist logo

Identifying complex motifs in massive omics data with a variable-convolutional layer in deep neural network

By Jing-Yi Li, Shen Jin, Xin-Ming Tu, Yang Ding, Ge Gao

Posted 31 Dec 2018
bioRxiv DOI: 10.1101/508242

Motif identification is among the most common and essential computational tasks for bioinformatics and genomics. Here we proposed a novel convolutional layer for deep neural network, named Variable Convolutional (vConv) layer, for effective motif identification in high-throughput omics data by learning kernel length from data adaptively. Empirical evaluations on DNA-protein binding and DNase footprinting cases well demonstrated that vConv-based networks have superior performance to their convolutional counterparts regardless of model complexity. Meanwhile, vConv could be readily integrated into multi-layer neural networks as an "in-place replacement" of canonical convolutional layer. All source codes are freely available on GitHub for academic usage.

Download data

  • Downloaded 780 times
  • Download rankings, all-time:
    • Site-wide: 35,546
    • In bioinformatics: 3,868
  • Year to date:
    • Site-wide: 17,835
  • Since beginning of last month:
    • Site-wide: 113,258

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide