An official website of the United States government
Abstract Designing protein-binding proteins is critical for drug discovery. However, artificial-intelligence-based design of such proteins is challenging due to the complexity of protein–ligand interactions, the flexibility of ligand molecules and amino acid side chains, and sequence–structure dependencies. We introduce PocketGen, a deep generative model that produces residue sequence and atomic structure of the protein regions in which ligand interactions occur. PocketGen promotes consistency between protein sequence and structure by using a graph transformer for structural encoding and a sequence refinement module based on a protein language model. The graph transformer captures interactions at multiple scales, including atom, residue and ligand levels. For sequence refinement, PocketGen integrates a structural adapter into the protein language model, ensuring that structure-based predictions align with sequence-based predictions. PocketGen can generate high-fidelity protein pockets with enhanced binding affinity and structural validity. It operates ten times faster than physics-based methods and achieves a 97% success rate, defined as the percentage of generated pockets with higher binding affinity than reference pockets. Additionally, it attains an amino acid recovery rate exceeding 63%.
more »
« less
Scalable protein design using optimization in a relaxed sequence space
Machine learning (ML)–based design approaches have advanced the field of de novo protein design, with diffusion-based generative methods increasingly dominating protein design pipelines. Here, we report a “hallucination”-based protein design approach that functions in relaxed sequence space, enabling the efficient design of high-quality protein backbones over multiple scales and with broad scope of application without the need for any form of retraining. We experimentally produced and characterized more than 100 proteins. Three high-resolution crystal structures and two cryo–electron microscopy density maps of designed single-chain proteins comprising up to 1000 amino acids validate the accuracy of the method. Our pipeline can also be used to design synthetic protein-protein interactions, as validated experimentally by a set of protein heterodimers. Relaxed sequence optimization offers attractive performance with respect to designability, scope of applicability for different design problems, and scalability across protein sizes.
more »
« less
- Award ID(s):
- 2032259
- PAR ID:
- 10631238
- Publisher / Repository:
- American Association for the Advancement of Science
- Date Published:
- Journal Name:
- Science
- Volume:
- 386
- Issue:
- 6720
- ISSN:
- 0036-8075
- Page Range / eLocation ID:
- 439 to 445
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Computational function prediction is one of the most important problems in bioinformatics as elucidating the function of genes is a central task in molecular biology and genomics. Most of the existing function prediction methods use protein sequences as the primary source of input information because the sequence is the most available information for query proteins. There are attempts to consider other attributes of query proteins. Among these attributes, the three-dimensional (3D) structure of proteins is known to be very useful in identifying the evolutionary relationship of proteins, from which functional similarity can be inferred. Here, we report a novel protein function prediction method, ContactPFP, which uses predicted residue-residue contact maps as input structural features of query proteins. Although 3D structure information is known to be useful, it has not been routinely used in function prediction because the 3D structure is not experimentally determined for many proteins. In ContactPFP, we overcome this limitation by using residue-residue contact prediction, which has become increasingly accurate due to rapid development in the protein structure prediction field. ContactPFP takes a query protein sequence as input and uses predicted residue-residue contact as a proxy for the 3D protein structure. To characterize how predicted contacts contribute to function prediction accuracy, we compared the performance of ContactPFP with several well-established sequence-based function prediction methods. The comparative study revealed the advantages and weaknesses of ContactPFP compared to contemporary sequence-based methods. There were many cases where it showed higher prediction accuracy. We examined factors that affected the accuracy of ContactPFP using several illustrative cases that highlight the strength of our method.more » « less
-
Electrostatics can alter the RNA-binding properties of proteins that display structure selectivity without sequence specificity. Loquacious-PD relies on this broad scope response to mediate the interaction of endonucleases with double stranded RNAs. Multimodal spectroscopic probes with in situ perturbations reveal an efficient and stable binding mechanism that disfavors high protein density complexes and is sensitive to local electrostatics.more » « less
-
Abstract MotivationAs fewer than 1% of proteins have protein function information determined experimentally, computationally predicting the function of proteins is critical for obtaining functional information for most proteins and has been a major challenge in protein bioinformatics. Despite the significant progress made in protein function prediction by the community in the last decade, the general accuracy of protein function prediction is still not high, particularly for rare function terms associated with few proteins in the protein function annotation database such as the UniProt. ResultsWe introduce TransFew, a new transformer model, to learn the representations of both protein sequences and function labels [Gene Ontology (GO) terms] to predict the function of proteins. TransFew leverages a large pre-trained protein language model (ESM2-t48) to learn function-relevant representations of proteins from raw protein sequences and uses a biological natural language model (BioBert) and a graph convolutional neural network-based autoencoder to generate semantic representations of GO terms from their textual definition and hierarchical relationships, which are combined together to predict protein function via the cross-attention. Integrating the protein sequence and label representations not only enhances overall function prediction accuracy, but delivers a robust performance of predicting rare function terms with limited annotations by facilitating annotation transfer between GO terms. Availability and implementationhttps://github.com/BioinfoMachineLearning/TransFew.more » « less
-
The design of completely synthetic proteins from first principles— de novo protein design—is challenging. This is because, despite recent advances in computational protein–structure prediction and design, we do not understand fully the sequence-to-structure relationships for protein folding, assembly, and stabilization. Antiparallel 4-helix bundles are amongst the most studied scaffolds for de novo protein design. We set out to re-examine this target, and to determine clear sequence-to-structure relationships, or design rules, for the structure. Our aim was to determine a common and robust sequence background for designing multiple de novo 4-helix bundles. In turn, this could be used in chemical and synthetic biology to direct protein–protein interactions and as scaffolds for functional protein design. Our approach starts by analyzing known antiparallel 4-helix coiled-coil structures to deduce design rules. In terms of the heptad repeat, abcdefg — i.e. , the sequence signature of many helical bundles—the key features that we identify are: a = Leu, d = Ile, e = Ala, g = Gln, and the use of complementary charged residues at b and c. Next, we implement these rules in the rational design of synthetic peptides to form antiparallel homo- and heterotetramers. Finally, we use the sequence of the homotetramer to derive in one step a single-chain 4-helix-bundle protein for recombinant production in E. coli . All of the assembled designs are confirmed in aqueous solution using biophysical methods, and ultimately by determining high-resolution X-ray crystal structures. Our route from peptides to proteins provides an understanding of the role of each residue in each design.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1126/science.adq1741
