YAMDA: thousandfold speedup of EM-based motif discovery using deep learning libraries and GPU

Abstract Motivation Motif discovery in large biopolymer sequence datasets can be computationally demanding, presenting significant challenges for discovery in omics research. MEME, arguably one of the most popular motif discovery software, takes quadratic time with respect to dataset size, leading t...

Full description

Saved in:
Bibliographic Details
Published in:Bioinformatics 2018-10, Vol.34 (20), p.3578-3580
Main Authors: Quang, Daniel, Guan, Yuanfang, Parker, Stephen C J
Format: Article
Language:English
Subjects:
Applications Notes
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract Motivation Motif discovery in large biopolymer sequence datasets can be computationally demanding, presenting significant challenges for discovery in omics research. MEME, arguably one of the most popular motif discovery software, takes quadratic time with respect to dataset size, leading to excessively long runtimes for large datasets. Therefore, there is a demand for fast programs that can generate results of the same quality as MEME. Results Here we describe YAMDA, a highly scalable motif discovery software package. It is built on Pytorch, a tensor computation deep learning library with strong GPU acceleration that is highly optimized for tensor operations that are also useful for motifs. YAMDA takes linear time to find motifs as accurately as MEME, completing in seconds or minutes, which translates to speedups over a thousandfold. Availability and implementation YAMDA is freely available on Github (https://github.com/daquang/YAMDA). Supplementary information Supplementary data are available at Bioinformatics online.
ISSN:1367-4803
1460-2059
1367-4811
DOI:10.1093/bioinformatics/bty396