A hands-on walkthrough of multi-omics data integration using Snowflake, covering the foundational data engineering steps before any statistical or AI analysis. The tutorial creates tables for gene expression, protein expression, drug response, and compound structure data, then joins them with SQL to build an integrated view. It covers data quality checks, candidate drug extraction, and 3D molecular structure visualization using RDKit inside Snowflake Notebooks (Container Runtime). The session concludes with using Snowflake CoCo, an AI coding agent, to interactively generate additional analysis cells in natural language.
114 Impressions