Aether is an intuitive, easy to use, cost-effective, and scalable framework that uses linear programming (LP) to optimally bid on and deploy combinations of underutilized cloud computing resources. Our approach simultaneously minimizes the cost of data analysis while maximizing efficiency and speed. Through its optimized instance bidding, Aether is able to reduce cloud computing costs by nearly ninety percent. Aether was developed jointly by the Kostic and Patel labs at Harvard Medical School. Source code is available here.
Installation and Configuration¶
Detailed instructions for software setup as well as additional documentation are available in the tutorial section.
A step-by-step tutorial for using Aether is located in the tutorial section. If you have further questions about Aether, you may want to file an issue on GitHub. Before filing an issue, make sure to read our contribution guidelines and use our issue template.
Aether is published in OUP Bioinformatics. Please cite our manuscript if you use Aether:
Jacob M Luber, Braden T Tierney, Evan M Cofer, Chirag J Patel, Aleksandar D Kostic; Aether: Leveraging Linear Programming For Optimal Cloud Computing In Genomics, Bioinformatics,btx787, https://doi.org/10.1093/bioinformatics/btx787
If you have questions, consider reading the tutorials or frequently asked questions. Alternatively, you can reach out to us following the instructions here. Guidelines for filing feature requests, documentation requests, bug reports, and general issues are also available here.