Succeed in the Life Sciences with R/Python and the Cloud
summary
Shows how to run R and Python at scale using Posit Workbench, how to provision IDEs on Azure ML and Databricks, and why a data lake-centric design with Parquet/OneLake matters. Gives concrete steps: mount storage, use Spark/SparklyR, and deploy compute instances or ML runtimes. Case study: a Belgian rare disease cohort where querying hundreds of VCFs in Databricks finds genotype-phenotype hits in about 30 minutes, enabling follow-up analysis and a paper.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 1:45Cloud computing in life sciences
- 3:32Cloud storage and data lakes
- 8:07Querying and analyzing data
- 10:14Scaling analyses with cloud
- 11:38R/Python IDEs in the cloud
- 14:28Polyglot notebooks and workflows
- 15:31Rare disease research case study
- 17:36Summary
- 18:18Q&A
related talks
49mExperimenting with Large Data Volumes Using Notebooks
31mProductizing Machine Learning over Big Data with AWS tools
40mData Lake House in the Cloud: The Azure Solutions
28mUsing Python in a Data Hackathon
20mHow the cloud changed the way I do analytics and research
19mLessons from Building a Large-scale, Multi-cloud Data Platform at Databricks
07mCloud architecture for population-scale analyses of genomes and AI.
27mVisualizing Cloud Systems