clustermq
Clustermq is an R package to enhance the performance of high-performance computing (HPC) clusters for large-scale bioinformatics analysis and modeling. Recognizing the critical role of HPC clusters in the field, clustermq addresses a common challenge: the scalability issues of existing R packages intended for submitting analyses as jobs on HPC schedulers. Traditional packages, while functional, often falter when scaling to high numbers of tasks, where the processing overhead can become a significant bottleneck, limiting the efficiency and speed of data processing.
Clustermq significantly outperforms these traditional methods, offering a solution that can process analyses up to three orders of magnitude faster. This remarkable improvement in speed is particularly beneficial for complex tasks such as investigating genomic associations of drug sensitivity in cancer cell lines, among other parallelizable workflows. Such an enhancement not only accelerates the research process but also enables the handling of more extensive datasets and more complex analyses, which are increasingly common in bioinformatics.
Topic
Computer science;Literature and language;Epigenomics
Detail
Software interface: Library
Language: R,Shell
License: Apache License, Version 2.0
Cost: Free with restrictions
Version name: -
Credit: -
Input: -
Output: -
Contact: Michael Schubert m.schubert@rug.nl
Collection: -
Maturity: Stable
Publications
- clustermq enables efficient parallelization of genomic analyses.
- Schubert M. clustermq enables efficient parallelization of genomic analyses. clustermq enables efficient parallelization of genomic analyses. 2019; 35:4493-4495. doi: 10.1093/bioinformatics/btz284
- https://doi.org/10.1093/BIOINFORMATICS/BTZ284
- PMID: 31134271
- PMC: PMC6821287
Download and documentation
Documentation: https://github.com/mschubert/clustermq/blob/master/README.md
Home page: https://github.com/mschubert/clustermq
< Back to DB search