Protein ML Talks

Recent talks applying the latest protein-ML models for design under the framework of p(sequence, structure, function).

Generative Models for Protein Design

  • Training data of generative models from evolutionary and PSI-BLAST search
  • ESM pseudo-likelihoods are inversely correlated with enzyme thermostability
  • Autoregressive, bidirectional, and graph-based masked-token prediction training tasks
  • Conditioning by adaptive sampling

How Machine Learning can Guide Protein Design