Small-molecule binding and sensing with a designed protein family.

Despite transformative advances in protein design with deep learning, the design of small-molecule-binding proteins and sensors for arbitrary ligands remains a grand challenge. Here we combine deep learning and physics-based methods to generate a family of proteins with diverse and designable pocket geometries, which we employ to computationally design binders for six chemically and structurally distinct small-molecule targets. Biophysical characterization of the designed binders revealed nanomolar to low micromolar binding affinities and atomic-level design accuracy. The bound ligands are exposed at one edge of the binding pocket, enabling the de novo design of chemically induced dimerization (CID) systems; we take advantage of this to create a biosensor with nanomolar sensitivity for cortisol. Our approach provides a general method to design proteins that bind and sense small molecules for a wide range of analytical, environmental, and biomedical applications.

De novo design of small beta barrel proteins.

Small beta barrel proteins are attractive targets for computational design because of their considerable functional diversity despite their very small size (<70 amino acids). However, there are considerable challenges to designing such structures, and there has been little success thus far. Because of the small size, the hydrophobic core stabilizing the fold is necessarily very small, and the conformational strain of barrel closure can oppose folding; also intermolecular aggregation through free beta strand edges can compete with proper monomer folding. Here, we explore the de novo design of small beta barrel topologies using both Rosetta energy-based methods and deep learning approaches to design four small beta barrel folds: Src homology 3 (SH3) and oligonucleotide/oligosaccharide-binding (OB) topologies found in nature and five and six up-and-down-stranded barrels rarely if ever seen in nature. Both approaches yielded successful designs with high thermal stability and experimentally determined structures with less than 2.4 Å rmsd from the designed models. Using deep learning for backbone generation and Rosetta for sequence design yielded higher design success rates and increased structural diversity than Rosetta alone. The ability to design a large and structurally diverse set of small beta barrel proteins greatly increases the protein shape space available for designing binders to protein targets of interest.

De novo design of luciferases using deep learning.

De novo enzyme design has sought to introduce active sites and substrate-binding pockets that are predicted to catalyse a reaction of interest into geometrically compatible native scaffolds1,2, but has been limited by a lack of suitable protein structures and the complexity of native protein sequence-structure relationships. Here we describe a deep-learning-based 'family-wide hallucination' approach that generates large numbers of idealized protein structures containing diverse pocket shapes and designed sequences that encode them. We use these scaffolds to design artificial luciferases that selectively catalyse the oxidative chemiluminescence of the synthetic luciferin substrates diphenylterazine3 and 2-deoxycoelenterazine. The designed active sites position an arginine guanidinium group adjacent to an anion that develops during the reaction in a binding pocket with high shape complementarity. For both luciferin substrates, we obtain designed luciferases with high selectivity; the most active of these is a small (13.9 kDa) and thermostable (with a melting temperature higher than 95 °C) enzyme that has a catalytic efficiency on diphenylterazine (kcat/Km = 106 M-1 s-1) comparable to that of native luciferases, but a much higher substrate specificity. The creation of highly active and specific biocatalysts from scratch with broad applications in biomedicine is a key milestone for computational enzyme design, and our approach should enable generation of a wide range of luciferases and other enzymes.

Scaffolding protein functional sites using deep learning.

The binding and catalytic functions of proteins are generally mediated by a small number of functional residues held in place by the overall protein structure. Here, we describe deep learning approaches for scaffolding such functional sites without needing to prespecify the fold or secondary structure of the scaffold. The first approach, "constrained hallucination," optimizes sequences such that their predicted structures contain the desired functional site. The second approach, "inpainting," starts from the functional site and fills in additional sequence and structure to create a viable protein scaffold in a single forward pass through a specifically trained RoseTTAFold network. We use these two methods to design candidate immunogens, receptor traps, metalloproteins, enzymes, and protein-binding proteins and validate the designs using a combination of in silico and experimental tests.

Protein sequence design by conformational landscape optimization.

The protein design problem is to identify an amino acid sequence that folds to a desired structure. Given Anfinsen's thermodynamic hypothesis of folding, this can be recast as finding an amino acid sequence for which the desired structure is the lowest energy state. As this calculation involves not only all possible amino acid sequences but also, all possible structures, most current approaches focus instead on the more tractable problem of finding the lowest-energy amino acid sequence for the desired structure, often checking by protein structure prediction in a second step that the desired structure is indeed the lowest-energy conformation for the designed sequence, and typically discarding a large fraction of designed sequences for which this is not the case. Here, we show that by backpropagating gradients through the transform-restrained Rosetta (trRosetta) structure prediction network from the desired structure to the input amino acid sequence, we can directly optimize over all possible amino acid sequences and all possible structures in a single calculation. We find that trRosetta calculations, which consider the full conformational landscape, can be more effective than Rosetta single-point energy estimations in predicting folding and stability of de novo designed proteins. We compare sequence design by conformational landscape optimization with the standard energy-based sequence design methodology in Rosetta and show that the former can result in energy landscapes with fewer alternative energy minima. We show further that more funneled energy landscapes can be designed by combining the strengths of the two approaches: the low-resolution trRosetta model serves to disfavor alternative states, and the high-resolution Rosetta model serves to create a deep energy minimum at the design target structure.

Optogenetic Tuning of Protein-protein Binding in Bilayers Using LOVTRAP.

Modern microscopy methods are powerful tools for studying live cell signaling and biochemical reactions, enabling us to observe when and where these reactions take place from the level of a cell down to single molecules. With microscopy, each cell or molecule can be observed both before and after a given perturbation, facilitating better inference of cause and effect than is possible with destructive modes of signaling quantitation. As many inputs to cell signaling and biochemical systems originate as protein-protein interactions near the cell membrane, an outstanding challenge lies in controlling the timing, location and the magnitude of protein-protein interactions in these unique environments. Here, we detail our procedure for manipulating such spatial and temporal protein-protein interactions in a closed microscopy system using a LOVTRAP-based light-responsive protein-protein interaction system on a supported lipid bilayer. The system responds in seconds and can pattern details down to the one micron level. We used this technique to unlock fundamental aspects of T cell signaling, and this approach is generalizable to many other cell signaling and biochemical contexts.

Light-based tuning of ligand half-life supports kinetic proofreading model of T cell signaling.

T cells are thought to discriminate self from foreign peptides by converting small differences in ligand binding half-life into large changes in cell signaling. Such a kinetic proofreading model has been difficult to test directly, as existing methods of altering ligand binding half-life also change other potentially important biophysical parameters, most notably the mechanical stability of the receptor-ligand interaction. Here we develop an optogenetic approach to specifically tune the binding half-life of a chimeric antigen receptor without changing other binding parameters and provide direct evidence of kinetic proofreading in T cell signaling. This half-life discrimination is executed in the proximal signaling pathway, downstream of ZAP70 recruitment and upstream of diacylglycerol accumulation. Our methods represent a general tool for temporal and spatial control of T cell signaling and extend the reach of optogenetics to probe pathways where the individual molecular kinetics, rather than the ensemble average, gates downstream signaling.

Illuminating cell signalling with optogenetic tools.

The light-based control of ion channels has been transformative for the neurosciences, but the optogenetic toolkit does not stop there. An expanding number of proteins and cellular functions have been shown to be controlled by light, and the practical considerations in deciding between reversible optogenetic systems (such as systems that use light-oxygen-voltage domains, phytochrome proteins, cryptochrome proteins and the fluorescent protein Dronpa) are well defined. The field is moving beyond proof of concept to answering real biological questions, such as how cell signalling is regulated in space and time, that were difficult or impossible to address with previous tools.