English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Statistical analysis of evolutionary-related protein sequences providesinsights about their structure, function, and history. We show that RestrictedBoltzmann Machines (RBM), designed to learn complex high-dimensional data andtheir statistical features, can efficiently model protein families fromsequence information. We here apply RBM to twenty protein families, and presentdetailed results for two short protein domains, Kunitz and WW, one longchaperone protein, Hsp70, and synthetic lattice proteins for benchmarking. Thefeatures inferred by the RBM are biologically interpretable: they are relatedto structure (such as residue-residue tertiary contacts, extended secondarymotifs ($\alpha$-helix and $\beta$-sheet) and intrinsically disorderedregions), to function (such as activity and ligand specificity), or tophylogenetic identity. In addition, we use RBM to design new protein sequenceswith putative properties by composing and turning up or down the differentmodes at will. Our work therefore shows that RBM are a versatile and practicaltool to unveil and exploit the genotype-phenotype relationship for proteinfamilies.

Learning protein constitutive motifs from sequence data