Receba novas skills de DevOps e Infra toda segunda
1 email curto, só com as skills novas de DevOps e Infra. 4 minutos de leitura, sem spam, cancela com 1 clique.
Você confirma o email no primeiro envio. Sem spam. Cancela com 1 clique.
Ler descrição completaRecolher descrição
Zero-Shot Mutation Effect Prediction
Key Distinctions
Masked vs autoregressive: ESM-1v uses MLM — mask position i, compare log-probs. Autoregressive models (ProtGPT2) compare full sequence log-likelihoods.
Single-site vs epistatic: ESM-1v computes single-site marginals independently. For epistatic questions use ESM-IF1 or DMS-fine-tuned models.
ΔΔG vs ΔlogP: ESM scores track evolutionary fitness, not thermodynamic stability — correlated but not identical.
**Benchmark f
[Description truncada. Veja o README completo no GitHub.]