Fitness prediction

Epistasis

Not all high-fitness sequences have plausible evolutionary paths from lower-fitness starting points via sequential introduction of mutations

I first saw this precise idea articulated by Weinreich et al. in their aptly named "Darwinian evolution can follow only very few mutational paths to fitter proteins"[1]. Many mutation combinations don't have additive effects on every aspect governing protein fitness (expression, stability, function, etc.), and

Fitness prediction

Essential proteins are more thermostable and over-expressed than non-essential proteins

Several properties of proteins have a sigmoid-like effect on cellular fitness. Thermostability is one of them: beyond a certain threshold, increases in protein thermostability confer no benefit, and decreases impose no penalty[1]: This concept, termed the principle of marginal stability[2], is somewhat contradicted by the observation that essential

Inverse folding

Training inverse folding models with label smoothing improves fitness prediction performance

BERT protein language models and inverse folding models learn to predict masked tokens[1]; coevolutionary patterns and propensities are expected to emerge from training in an unsupervised manner[2]. This works fine when training on sequence data, which is plentiful. However, it is not clear that there are enough experimental