Protein function predictions articles from across Nature Portfolio

With structural models now available on a proteome scale, Malatesta et al. show that structure-based screening can help identify proteins catalyzing orphan reactions in metabolic pathways, offering functional insights beyond sequence-based approaches.

Multiscale molecular dynamics simulations reveal rapidly exchanging lipid binding sites on the nicotinic acetylcholine receptor, including sites with high affinity for phosphatidic acid and promiscuous cholesterol sites in inter-α-helix grooves.

Andre Berndt and colleagues introduce a machine learning approach to enhance the biophysical characteristics of genetically encoded fluorescent indicators, deriving and testing in vitro new GCaMP mutations that surpass the performance of existing fast GCaMP indicators.

A recent study introduces a machine learning approach to investigate the effects of mutations on protein sensors commonly employed in fluorescence microscopy, thus enabling the discovery of high-performance sensors.

Transcription factors containing disordered regions can now be mapped across the genome, aiding functional studies.

Constraining metabolic models by enzyme capacities greatly improves genotype–phenotype predictions. Now, a method for estimating enzyme turnovers based on deep learning has been developed and used to reconstruct enzyme-constrained genome-scale metabolic models for more than 300 yeast species.

Determining the functional properties of a protein from its structure is challenging. This study presents an interpretable deep learning model that directly learns function-bearing structural motifs from raw data, allowing accurate mapping of protein binding sites and antibody epitopes onto a protein structure.

The splendid computational success of AlphaFold and RoseTTAFold in solving the 60-year-old problem of protein folding raises an obvious question: what new avenues should structural biology explore? We propose a strong pivot toward the goal of reading mechanism and function directly from the amino acid sequence. This ambitious goal will require new data analytical tools and an extensive database of the atomic-level structural trajectories traced out on energy landscapes as proteins perform their function.