• The search space for protein engineering grows exponentially with complexity. • A protein of just 100 amino acids has 20100 possible variants-more combinations than atoms in the observable universe. • Traditional engineering methods might test hundreds of variants but limit exploration to narrow regions of the sequence space. • Recent machine learning approaches enable broader searches through computational screening. • However, these approaches still require tens of thousands of measurements, or 5-10 iterative rounds.
Article Summaries:
- A new “lab‑in‑the‑loop” framework promises to accelerate the engineering of complex, multi‑mutant proteins. Traditional methods test only a few hundred variants, limiting exploration of the astronomically large sequence space-e.g., a 100‑amino‑acid protein has 20^100 possible forms. Machine‑learning guided screens broaden the search but still demand tens of thousands of measurements or 5-10 iterative rounds. The new framework integrates computational predictions with rapid, automated laboratory assays, dramatically cutting the number of required experiments and speeding the evolution of proteins with many simultaneous mutations.
Sources: