Small World Asynchronous Parallel Model for Genome Assembly

Abstract : Large de bruijn graph based algorithm is widely used in genome assembly and metagenetic assembly. The scale of this kind of graphs - in some cases billions of vertices and edges - poses challenges to genome assembly problem. In this paper, a one-step bi-directed graph is used to abstract the problem of genome assembly. After that small world asynchronous parallel model (SWAP) is proposed to handle the edge merging operation predefined in the graph. SWAP aims at making use of the locality of computing and communication to explore parallelism for graph algorithm. Based on the above graph abstraction and SWAP model, an assembler is developed, and experiment results shows that a factor of 20 times speedup is achieved when the number of processors scales from 10 to 640 when testing on processing C.elegans data.
Document type :
Conference papers
Complete list of metadatas

Cited literature [23 references]  Display  Hide  Download

https://hal.inria.fr/hal-01551319
Contributor : Hal Ifip <>
Submitted on : Friday, June 30, 2017 - 10:35:37 AM
Last modification on : Friday, December 1, 2017 - 1:10:01 AM
Long-term archiving on : Monday, January 22, 2018 - 9:16:34 PM

File

978-3-642-35606-3_17_Chapter.p...
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Jintao Meng, Jianrui Yuan, Jiefeng Cheng, Yanjie Wei, Shengzhong Feng. Small World Asynchronous Parallel Model for Genome Assembly. 9th International Conference on Network and Parallel Computing (NPC), Sep 2012, Gwangju, South Korea. pp.145-155, ⟨10.1007/978-3-642-35606-3_17⟩. ⟨hal-01551319⟩

Share

Metrics

Record views

64

Files downloads

100