RAMPART: a workflow management system for de novo genome assembly

Abstract

Motivation: The de novo assembly of genomes from whole- genome shotgun sequence data is a computationally intensive, multi-stage task and it is not known a priori which methods and parameter settings will produce optimal results. In current de novo assembly projects, a popular strategy involves trying many approaches, using different tools and settings, and then comparing and contrasting the results in order to select a final assembly for publication.

Results: Herein, we present RAMPART, a configurable workflow management system for de novo genome assembly, which helps the user identify combinations of third-party tools and settings that provide good results for their particular genome and sequenced reads. RAMPART is designed to exploit High performance computing environments, such as clusters and shared memory systems, where available.

Availability and implementation: RAMPART is available under the GPLv3 license at: https://github.com/TGAC/RAMPART.

Fig. 1.

A simplified representation of RAMPART’s architecture. Although user’s workflow must conform to the linear structure depicted here, each stage is optional and highly configurable. Most stages allow the user to select which third-party tool(s) and parameters are used, although primary input and output parameters to all tools are managed automatically. The most important pipeline stage, MASS, allows the user to execute multiple assemblers, with varying parameters. In the subsequent step, the resultant assemblies are analyzed before a single assembly is selected for use in the second half of the pipeline. Input to the MASS and AMP stages can be selected from any raw input library or from any modified libraries generated during the MECQ stage