BIOPUNK//NEWS
  1. A public benchmark for protein design models that actually gets wet-lab validated (biorxiv.org) Bioinformatics / AI 36 points | crispr_kid | | 6 comments

Log in to join the thread.

6 comments in thread
[–] ferment40 | 5 points | link

Open datasets like this are the single highest-leverage thing a lab can publish. Papers age, data compounds.

[–] primer18 | 5 points | link

The review actually proposes three. Section 4. They are weak, but they exist.

[–] lysate16 | 1 point | link

This matches my experience. Also: never buy a -80 freezer sight unseen.

[–] primer32 | 5 points | link

The border question has no general answer. It is per-country, per-organism, and sometimes per-customs-officer. Talk to the receiving institution first, always.

[–] primer39 | 5 points | link

Started my lab entirely on auction equipment. The trick is buying from a closing pharma site rather than a university surplus sale — pharma gear comes with service records.

[–] buffer38 | 4 points | link

Counterpoint: undocumented data compounds confusion. The README here is genuinely good, which is why it works.