AMix-1: A Pathway to Test-Time Scalable Protein Foundation Model
Researchers have developed AMix-1, a protein foundation model utilizing Bayesian Flow Networks and a novel training methodology. This model demonstrates scalable pretraining, emergent capabilities, and effective in-context learning through multiple sequence alignments. AMix-1 has successfully designed an improved protein variant with a 50x activity increase and incorporates an evolutionary test-time scaling algorithm for enhanced in silico directed evolution. AI
IMPACT Introduces a new foundation model for protein design with potential to accelerate lab-in-the-loop engineering.