Our paper 'A machine readable specification for genomics assays' is now published in Bioinformatics, OUP Bioinformatics. In short, we present a lightweight file format and command-line tool to document the structure of sequencing reads. Coauthored with Xi Chen and Lior Pachter.

Paper:

Great work. The pitfalls section at the beginning is clearly written and important for researchers in all areas to read -- even if you don't do medical image segmentation.

I feel exactly the same way. If my talk wasn't interesting enough for people to have questions, comments, or thoughts worth discussing past empty compliments, something went wrong.

On the other hand, some answers are complicated and should be taken offline.

Several times on the job market I would introduce myself and the person would ask 'oh, from Twitter?' Usually without elaboration on whether that was good or bad.

🚀Exciting news! Our Python package, skglm, is pushing back the limits of sklearn
Last week two industrial feedbacks revealed that it solves problems in seconds that sklearn struggled with for hours

So happy to see our academic work have such impact!

github.com/scikit-learn-c…

Is it just me or is it extremely suspicious for a VPN to advertise heavily in the DC area/airport?

My west coast mind cannot comprehend that it is routine (and not that expensive) on the east coast to get a Lyft from the biggest city in one state to the biggest city in another state. No biggie.

This would have made my early PhD days soo much easier. Amazing set of functionality for sequence-based ML. If this you find this kind of thing useful/exciting, also recommend you check out github.com/ML4GLand. We have a lot of complementary functionality for PyTorch!