SPATIAL GRAPH ATTENTION AND CURIOSITY-DRIVEN POLICY FOR ANTIVIRAL DRUG DISCOVERY

Yulun Wu; Mikaela Cashman; Nicholas Choma; Érica T. Prates; Verónica Melesse Vergara; Manesh Shah; Andrew Chen; Austin Clyde; Thomas S. Brettin; Wibe A. de Jong; Neeraj Kumar; Martha S. Head; Rick L. Stevens; Peter Nugent; Daniel A. Jacobson; James B. Brown

SPATIAL GRAPH ATTENTION AND CURIOSITY-DRIVEN POLICY FOR ANTIVIRAL DRUG DISCOVERY

Yulun Wu, Mikaela Cashman, Nicholas Choma, Érica T. Prates, Verónica Melesse Vergara, Manesh Shah, Andrew Chen, Austin Clyde, Thomas S. Brettin, Wibe A. de Jong, Neeraj Kumar, Martha S. Head, Rick L. Stevens, Peter Nugent, Daniel A. Jacobson, James B. Brown

Computational and Predictive Biology

Research output: Contribution to conference › Paper › peer-review

1 Scopus citations

Abstract

We developed Distilled Graph Attention Policy Network (DGAPN), a reinforcement learning model to generate novel graph-structured chemical representations that optimize user-defined objectives by efficiently navigating a physically constrained domain. The framework is examined on the task of generating molecules that are designed to bind, noncovalently, to functional sites of SARS-CoV-2 proteins. We present a spatial Graph Attention (sGAT) mechanism that leverages self-attention over both node and edge attributes as well as encoding the spatial structure - this capability is of considerable interest in synthetic biology and drug discovery. An attentional policy network is introduced to learn the decision rules for a dynamic, fragment-based chemical environment, and state-of-the-art policy gradient techniques are employed to train the network with stability. Exploration is driven by the stochasticity of the action space design and the innovation reward bonuses learned and proposed by random network distillation. In experiments, our framework achieved outstanding results compared to state-of-the-art algorithms, while reducing the complexity of paths to chemical synthesis.

Original language	English
State	Published - 2022
Event	10th International Conference on Learning Representations, ICLR 2022 - Virtual, Online Duration: Apr 25 2022 → Apr 29 2022

Conference

Conference	10th International Conference on Learning Representations, ICLR 2022
City	Virtual, Online
Period	04/25/22 → 04/29/22

Funding

This work was funded via the DOE Office of Science through the National Virtual Biotechnology Laboratory (NVBL), a consortium of DOE national laboratories focused on the response to COVID-19, with funding provided by the Coronavirus CARES Act. This research used resources of the Oak Ridge Leadership Computing Facility (OLCF) at the Oak Ridge National Laboratory, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725. This manuscript has been coauthored by UT-Battelle, LLC under contract no. DE-AC05-00OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a nonexclusive, paid-up, irrevocable, world-wide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan, last accessed September 16, 2020).

Funders	Funder number
DOE Public Access Plan
National Virtual Biotechnology Laboratory
United States Government
U.S. Department of Energy	DE-AC05-00OR22725
Office of Science
UT-Battelle

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Cite this

Wu, Y., Cashman, M., Choma, N., Prates, É. T., Vergara, V. M., Shah, M., Chen, A., Clyde, A., Brettin, T. S., de Jong, W. A., Kumar, N., Head, M. S., Stevens, R. L., Nugent, P., Jacobson, D. A., & Brown, J. B. (2022). SPATIAL GRAPH ATTENTION AND CURIOSITY-DRIVEN POLICY FOR ANTIVIRAL DRUG DISCOVERY. Paper presented at 10th International Conference on Learning Representations, ICLR 2022, Virtual, Online.

@conference{63521b9579e340ce8fe2f51c07b8695d,

title = "SPATIAL GRAPH ATTENTION AND CURIOSITY-DRIVEN POLICY FOR ANTIVIRAL DRUG DISCOVERY",

abstract = "We developed Distilled Graph Attention Policy Network (DGAPN), a reinforcement learning model to generate novel graph-structured chemical representations that optimize user-defined objectives by efficiently navigating a physically constrained domain. The framework is examined on the task of generating molecules that are designed to bind, noncovalently, to functional sites of SARS-CoV-2 proteins. We present a spatial Graph Attention (sGAT) mechanism that leverages self-attention over both node and edge attributes as well as encoding the spatial structure - this capability is of considerable interest in synthetic biology and drug discovery. An attentional policy network is introduced to learn the decision rules for a dynamic, fragment-based chemical environment, and state-of-the-art policy gradient techniques are employed to train the network with stability. Exploration is driven by the stochasticity of the action space design and the innovation reward bonuses learned and proposed by random network distillation. In experiments, our framework achieved outstanding results compared to state-of-the-art algorithms, while reducing the complexity of paths to chemical synthesis.",

author = "Yulun Wu and Mikaela Cashman and Nicholas Choma and Prates, {{\'E}rica T.} and Vergara, {Ver{\'o}nica Melesse} and Manesh Shah and Andrew Chen and Austin Clyde and Brettin, {Thomas S.} and {de Jong}, {Wibe A.} and Neeraj Kumar and Head, {Martha S.} and Stevens, {Rick L.} and Peter Nugent and Jacobson, {Daniel A.} and Brown, {James B.}",

note = "Publisher Copyright: {\textcopyright} 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.; 10th International Conference on Learning Representations, ICLR 2022 ; Conference date: 25-04-2022 Through 29-04-2022",

year = "2022",

language = "English",

}

Wu, Y, Cashman, M, Choma, N, Prates, ÉT, Vergara, VM, Shah, M, Chen, A, Clyde, A, Brettin, TS, de Jong, WA, Kumar, N, Head, MS, Stevens, RL, Nugent, P, Jacobson, DA & Brown, JB 2022, 'SPATIAL GRAPH ATTENTION AND CURIOSITY-DRIVEN POLICY FOR ANTIVIRAL DRUG DISCOVERY', Paper presented at 10th International Conference on Learning Representations, ICLR 2022, Virtual, Online, 04/25/22 - 04/29/22.

TY - CONF

T1 - SPATIAL GRAPH ATTENTION AND CURIOSITY-DRIVEN POLICY FOR ANTIVIRAL DRUG DISCOVERY

AU - Wu, Yulun

AU - Cashman, Mikaela

AU - Choma, Nicholas

AU - Prates, Érica T.

AU - Vergara, Verónica Melesse

AU - Shah, Manesh

AU - Chen, Andrew

AU - Clyde, Austin

AU - Brettin, Thomas S.

AU - de Jong, Wibe A.

AU - Kumar, Neeraj

AU - Head, Martha S.

AU - Stevens, Rick L.

AU - Nugent, Peter

AU - Jacobson, Daniel A.

AU - Brown, James B.

PY - 2022

Y1 - 2022

N2 - We developed Distilled Graph Attention Policy Network (DGAPN), a reinforcement learning model to generate novel graph-structured chemical representations that optimize user-defined objectives by efficiently navigating a physically constrained domain. The framework is examined on the task of generating molecules that are designed to bind, noncovalently, to functional sites of SARS-CoV-2 proteins. We present a spatial Graph Attention (sGAT) mechanism that leverages self-attention over both node and edge attributes as well as encoding the spatial structure - this capability is of considerable interest in synthetic biology and drug discovery. An attentional policy network is introduced to learn the decision rules for a dynamic, fragment-based chemical environment, and state-of-the-art policy gradient techniques are employed to train the network with stability. Exploration is driven by the stochasticity of the action space design and the innovation reward bonuses learned and proposed by random network distillation. In experiments, our framework achieved outstanding results compared to state-of-the-art algorithms, while reducing the complexity of paths to chemical synthesis.

AB - We developed Distilled Graph Attention Policy Network (DGAPN), a reinforcement learning model to generate novel graph-structured chemical representations that optimize user-defined objectives by efficiently navigating a physically constrained domain. The framework is examined on the task of generating molecules that are designed to bind, noncovalently, to functional sites of SARS-CoV-2 proteins. We present a spatial Graph Attention (sGAT) mechanism that leverages self-attention over both node and edge attributes as well as encoding the spatial structure - this capability is of considerable interest in synthetic biology and drug discovery. An attentional policy network is introduced to learn the decision rules for a dynamic, fragment-based chemical environment, and state-of-the-art policy gradient techniques are employed to train the network with stability. Exploration is driven by the stochasticity of the action space design and the innovation reward bonuses learned and proposed by random network distillation. In experiments, our framework achieved outstanding results compared to state-of-the-art algorithms, while reducing the complexity of paths to chemical synthesis.

UR - http://www.scopus.com/inward/record.url?scp=85150337397&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85150337397

T2 - 10th International Conference on Learning Representations, ICLR 2022

Y2 - 25 April 2022 through 29 April 2022

ER -

SPATIAL GRAPH ATTENTION AND CURIOSITY-DRIVEN POLICY FOR ANTIVIRAL DRUG DISCOVERY

Abstract

Conference

Funding

UN SDGs

Other files and links

Fingerprint

Cite this