Generative modeling

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

Inverse folding

Glutamate- and lysine-rich designs are susceptible to expression failure resulting from adenosine-rich sequences

High rates of glutamate and lysine introduction are a staple of structure-based sequence design by ProteinMPNN and related models, regardless of who trains them[1]. Recently, an analysis of the Bits in Bio competition showed that high glutamate/lysine content is predictive of expression failure[2]: The authors traced this

Generative modeling

Language models matter less than search algorithms for difficult protein design tasks

Two papers from the last week show how search algorithms improve the performance of deep learning-based protein design when design restraints are available. The first compared AbLang-2, ESM-2, and other models, finding middling success rates and low variance when used as-is[1]. However, a noticeable performance boost was observed when

Structure prediction

Diffusion-based structure prediction can be guided by backpropagating to the conditioning embeddings rather than the atomic coordinates directly, and such embeddings can be re-refined in subsequent iterations

Diffusion-based biomolecular structure prediction, which is used in latest-generation methods like AlphaFold3[1] and BioEmu[2], can be guided or steered into specific conformations by backpropagating to the conditioning representations rather than the atomic coordinates being diffused [3][4]. This was recently shown by two methods, EmbedOpt and IT-Optimization. There