In the course of evolution, proteins undergo important changes in their amino acid
sequences, while their three-dimensional folded structure and their biological function …

It has long been recognized that certain sites within a protein, such as sites in the protein
core or catalytic residues in enzymes, are evolutionarily more conserved than other sites …

Abstract Machine learning-based models of protein fitness typically learn from either
unlabeled, evolutionarily related sequences or variant sequences with experimentally …

Molecular dynamics simulations with coarse-grained or simplified Hamiltonians have proven
to be an effective means of capturing the functionally important long-time and large-length …

The quantitative characterization of mutational landscapes is a task of outstanding
importance in evolutionary and medical biology: It is, for example, of central importance for …

Generative models emerge as promising candidates for novel sequence-data driven
approaches to protein design, and for the extraction of structural and functional information …

Heavy metal contamination is a global environmental issue as it poses a significant threat to
public health, and exposure to metals above a certain threshold level can cause deleterious …

The heme iron complex is one of the most important cofactors in biological systems (Figure
1). The major functions of the heme iron complex are to serve as the O2 binding site for …

Variational autoencoders are unsupervised learning models with generative capabilities,
when applied to protein data, they classify sequences by phylogeny and generate de novo …

Predicting the effects of one or more mutations to the in vivo or in vitro properties of a wild-
type protein is a major computational challenge, due to the presence of epistasis, that is, of …