Notebooks and examples for Spark DeepVariant project.
Spark Deep Variant provides,
- A fully optimized core algorithm that works about twice as fast as the original implementation.
- Well documented interface integrated into Jupyter Notebooks.
- Optimized example generation stage that runs fully in parallel.
- Optimized post processing.
- Streaming mode: drop an input file on S3(or any other distributed file system of your preference) and start getting results in near real-time.
- Optimized Dataset Downloader: download reference datasets in a faster and safer manner through an optimized dataset downloader.
- Ready to use: no IT team required, start an EMR cluster and get running in minutes.
Spark Deep Variant Tutorial video, and sample notebook.
This repo contains examples for our first public release, interested in trialing the product? Contact us at info@orangenomix.com