Crackling Cloud: an event-driven, cloud-based CRISPR-Cas9 guide RNA design tool
Bradford, J.; Joy, D.; Winsen, M.; Meurant, N.; Wilkins, M.; Wilson, L.; Bauer, D.; Perrin, D.
Show abstract
Gene editing has been revolutionised by the CRISPR-Cas9 technology. The versatility and ease-of-use of the technology far exceeds its predecessors, however, the selection of a high-quality guide RNA (gRNA) is critical to directing it to a target site. Selecting gRNA calls upon high-performance algorithms that evaluate nuclease activity at on-target and off-target sites. While there are a suite of programs available, many struggle to analyse the largest genomes, or their predictive accuracy is low. We have previously published a program, named Crackling that is amongst the fastest and most accurate tools available, however, it requires an end-user to have access to a traditional high-performance computing environment. Here, we present an adaptation of Crackling, named Crackling Cloud, that takes advantage of modern serverless cloud technologies that are widely available to anyone, and do not consume resources and incur costs when sitting idle, but can scale to use large volumes of resources when analyses require that. Crackling Cloud is provided as a templated solution using technologies of Amazon Web Services, and is available for free on GitHub under the terms of the BSD 3-clause licence: https://github.com/bmds-lab/Crackling-AWS
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.