AI Article Synopsis
- Current genomics methods need to scale from handling thousands of samples to millions to keep up with rapid data generation in biomedical science.
- By using general-purpose libraries like PyTorch and TensorFlow on GPUs, researchers can significantly reduce runtime and costs, achieving over 200 times faster processing and 5-10 times lower costs compared to traditional CPUs.
- The increased accessibility of these GPU libraries is expected to encourage more widespread use of GPU technology in the field of computational genomics.
Article Abstract
Current genomics methods are designed to handle tens to thousands of samples but will need to scale to millions to match the pace of data and hypothesis generation in biomedical science. Here, we show that high efficiency at low cost can be achieved by leveraging general-purpose libraries for computing using graphics processing units (GPUs), such as PyTorch and TensorFlow. We demonstrate > 200-fold decreases in runtime and ~ 5-10-fold reductions in cost relative to CPUs. We anticipate that the accessibility of these libraries will lead to a widespread adoption of GPUs in computational genomics.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6823959 | PMC |
| http://dx.doi.org/10.1186/s13059-019-1836-7 | DOI Listing |
Publication Analysis
Top Keywords
computational genomics
8
scaling computational
4
genomics millions
4
millions individuals
4
individuals gpus
4
gpus current
4
current genomics
4
genomics methods
4
methods designed
4
designed handle
4
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!