Flow matching and diffusion perform comparably on biomolecular structure prediction[1]. This is, to my knowledge, the only head-to-head comparison of these two approaches for protein structure modeling or design. References 1. Gong, C., Chen, X., Zhang, Y., Song, Y., Zhou, H., & Xiao, W. (2025). Protenix-Mini: Efficient Structure Predictor
Epistasis
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
Antibody-antigen binding
Antibody V-regions improve their affinity for targets by both creating more high-energy interactions and reducing the conformational entropy of their antigen-binding loops[1][2]. Entropy's importance in antibody-antigen affinity seems obvious, given that loop residues largely mediate binding[3][4]. But for de novo-designed miniprotein binders, which often
Inverse folding
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
Fitness prediction
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
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
Inverse folding
Predicted protein structures, particularly monomeric structures, have become ubiquitous thanks to the release of the AlphaFold Database[1] and its successors[2]. Yet training structure-based neural networks exclusively on these synthetic structures has now been widely shown to worsen performance on experimental structures. Hsu et al., who trained the structure-based
Generative modeling
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 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
Epistasis
Antibodies undergo somatic mutation during affinity maturation in ways that show evidence of epistasis in biophysical properties like expression and polyspecificity, but not binding [1][2]. In a study by Kirby et al 2025[1:1] on 12 anti-SARS-CoV-2 antibodies using deep mutational scanning and yeast display, no combination of
Structure prediction
The recent report of Protenix-v1[1] contained an architecturally identical second model trained with a more recent train:test split. Unlike other outstanding problems in biomolecular structure prediction, antibody-antigen complex prediction showed remarkable improvement in the fraction of models achieving a cutoff of DockQ≥0.23, shown in the third