hi everyone! i’m william, long time python machine learning geek, currently doing applied ML research in cancer biology with a lab at the dana-farber cancer institute and the broad institute. i do lots of data and ML pipelining type work, and am interested in using dagster to orchestrate my data flows and implement memoization (to prevent re-compute of DataFrame-like assets).

Welcome - you are in good company for ML in life sciences.

thanks, fraser 🙂 glad to hear it! do you know off hand of any other ml people or organizations using dagster? perhaps with single cell sequencing data? i do research on immunotherapies and work with single cell RNA-seq of melanoma.

I can’t really share anything that is not in the public domain already, but I will recommend you take a look at https://dagster.io/blog/zephyr-ai-case-study Also we have another case study in the works that I will send over when we publish (hopefully soon, it’s in final review).