Although a wide variety of quantum computers are currently being developed, actual computational results have been largely restricted to contrived, artificial tasks. Finding ways to apply quantum computers to useful, real-world computational tasks remains an active research area. Here we describe our mapping of the protein design problem to the D-Wave quantum annealer. We present a system whereby Rosetta, a state-of-the-art protein design software suite, interfaces with the D-Wave quantum processing unit to find amino acid side chain identities and conformations to stabilize a fixed protein backbone. Our approach, which we call the QPacker , uses a large side-chain rotamer library and the full Rosetta energy function, and in no way reduces the design task to a simpler format. We demonstrate that quantum-annealer-based design can be applied to complex real-world design tasks, producing designed molecules comparable to those produced by widely adopted classical design approaches. We also show through large-scale classical folding simulations that the results produced on the quantum annealer can inform wet-lab experiments. For design tasks that scale exponentially on classical computers, the QPacker achieves nearly constant runtime performance, independent of the complexity of the task, up to the limits of the quantum computer's size.
Graph representations are traditionally used to represent protein structures in sequence design protocols in which the protein backbone conformation is known. This infrequently extends to machine learning projects: existing graph convolution algorithms have shortcomings when representing protein environments. One reason for this is the lack of emphasis on edge attributes during massage-passing operations. Another reason is the traditionally shallow nature of graph neural network architectures. Here we introduce an improved message-passing operation that is better equipped to model local kinematics problems such as protein design. Our approach, XENet, pays special attention to both incoming and outgoing edge attributes. We compare XENet against existing graph convolutions in an attempt to decrease rotamer sample counts in Rosetta’s rotamer substitution protocol, used for protein side-chain optimization and sequence design. This use case is motivating because it both reduces the size of the search space for classical side-chain optimization algorithms, and allows larger protein design problems to be solved with quantum algorithms on near-term quantum computers with limited qubit counts. XENet outperformed competing models while also displaying a greater tolerance for deeper architectures. We found that XENet was able to decrease rotamer counts by 40% without loss in quality. This decreased the memory consumption for classical pre-computation of rotamer energies in our use case by more than a factor of 3, the qubit consumption for an existing sequence design quantum algorithm by 40%, and the size of the solution space by a factor of 165. Additionally, XENet displayed an ability to handle deeper architectures than competing convolutions.
Graph representations are traditionally used to represent protein structures in sequence design protocols where the folding pattern is known. This infrequently extends to machine learning projects: existing graph convolution algorithms have shortcomings when representing protein environments. One reason for this is the lack of emphasis on edge attributes during massage-passing operations. Another reason is the traditionally shallow nature of graph neural network architectures. Here we introduce an improved message-passing operation that is better equipped to model local kinematics problems such as protein design. Our approach, XENet, pays special attention to both incoming and outgoing edge attributes.We compare XENet against existing graph convolutions in an attempt to decrease rotamer sample counts in Rosetta’s rotamer substitution protocol. This use case is motivating because it allows larger protein design problems to fit onto near-term quantum computers. XENet outperformed competing models while also displaying a greater tolerance for deeper architectures. We found that XENet was able to decrease rotamer counts by 40% without loss in quality. This decreased the problem size of our use case by more than a factor of 3. Additionally, XENet displayed an ability to handle deeper architectures than competing convolutions.Author summaryGraphs data structures are ubiquitous in the field of protein design and are at the core of the recent advances in artificial intelligence brought forth by graph neural networks (GNNs). GNNs have led to some impressive results in modeling protein interactions, but are not as common as other tensor representations.Most GNN architectures tend to put little to no emphasis on the information stored on edges; however, protein modeling tools often use edges to represent vital geometric relationships about residue pair interactions. In this paper, we show that a more advanced processing of edge attributes can lead to considerable benefits when modeling chemical data.We introduce XENet, a new member of the GNN family that is shown to have improved ability to model protein residue environments based on chemical and geometric data. We use XENet to intelligently simplify the optimization problem that is solved when designing proteins. This task is important to us and others because it allows larger proteins to be designed on near-term quantum computers. We show that XENet is able to train on our protein modeling data better than existing methods, successfully resulting in a dramatic decrease in protein design sample space with no loss in quality.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.