English

Convolutional Kitchen Sinks for Transcription Factor Binding Site Prediction

Genomics 2017-06-02 v1

Abstract

We present a simple and efficient method for prediction of transcription factor binding sites from DNA sequence. Our method computes a random approximation of a convolutional kernel feature map from DNA sequence and then learns a linear model from the approximated feature map. Our method outperforms state-of-the-art deep learning methods on five out of six test datasets from the ENCODE consortium, while training in less than one eighth the time.

Keywords

Cite

@article{arxiv.1706.00125,
  title  = {Convolutional Kitchen Sinks for Transcription Factor Binding Site Prediction},
  author = {Alyssa Morrow and Vaishaal Shankar and Devin Petersohn and Anthony Joseph and Benjamin Recht and Nir Yosef},
  journal= {arXiv preprint arXiv:1706.00125},
  year   = {2017}
}

Comments

5 pages, 2 tables, NIPS MLCB Workshop 2016

R2 v1 2026-06-22T20:05:40.783Z