What Is Data Science?
summary
Defines data science by concrete problems and results: analyzing proteomics mass‑spectrometer traces (~8 GB wiggle files) to identify peptides from ~18,000 active proteins drawn from ~20–25k genes, turning a brute‑force 30‑day matching run into 30 days to 12 hours via parallel algorithms, comparing implementations including 800 lines of SQL on appliances like Teradata versus big‑data approaches, building custom visualizations, and emphasizing tools (R, NoSQL, Erlang), curiosity, and iterative algorithm development.
AI-written summary · about
chapters (8)
- 0:00Introduction
- 5:37Defining data science and its appeal
- 8:41Data science with proteomics
- 27:42Algorithmic efficiency
- 34:29Unstructured data challenges
- 39:45Oil rig monitoring
- 44:04Skills for data scientists
- 50:55Q&A
related talks
41mData Science – The New Troublemaker in the Delivery Pipeline
19mData science demystified
44mPeople, Technology, Culture: How to make Data Science work
13mData Science: Where are We Going?
38mData Science from the Trenches
42mWhy Big Data Is Not Data Science
32mThe tale of data science
24mData Science: the best path to align business objectives