SkinDeepRESEARCHSteve Seguin

Use case · Idea to test

Protein research

Score candidates without treating scores as proof.

  1. Candidate representations
  2. Rank a research objective
  3. Check measured outcomes
Illustration of the proposed workflow.

The earlier whitepaper proposed protein design as another domain for candidate scoring. Here it remains an untested research idea with no biological results claimed.

Where the small model fits

A suitable domain model would provide representations. A small head could rank a defined objective, provided relevant training labels and an independent evaluation were available.

What would need to work

Evaluate against measured outcomes on unseen candidates. Structural plausibility or a learned score is not evidence that a proposed protein performs a desired function.

Related experiments and evidence