Abstract
3D-MolGNNRL, couples reinforcement learning (RL) to a deep
generative model based on 3D-Scaffold to generate target candidates specific to a protein pocket building up atom by
atom from the core scaffold. 3D-MolGNNRL provides an efficient way to optimize key features within a protein pocket using
a parallel graph neural network model. The agent learns to build molecules in 3D space while optimizing the binding
affinity, potency, and synthetic accessibility of the candidates generated for the SARS-CoV-2 Main protease
- Developers:
-
Kumar, Neeraj [1] ; Bontha, Mridula [1] ; McNaughton, Andrew [1] ; Knutson, Carter [1] ; Pope, Jenna [1]
- Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
- Release Date:
- 2023-01-10
- Project Type:
- Closed Source
- Software Type:
- Scientific
- Licenses:
-
Other (Commercial or Open-Source): https://availabletechnologies.pnnl.gov
- Code ID:
- 98618
- Site Accession Number:
- Battelle IPID 32326-E
- Country of Origin:
- United States
Citation Formats
Kumar, Neeraj, Bontha, Mridula, McNaughton, Andrew, Knutson, Carter, and Pope, Jenna.
3D_MolGNN_RL.
Computer Software.
10 Jan. 2023.
Web.
doi:10.11578/dc.20230110.2.
Kumar, Neeraj, Bontha, Mridula, McNaughton, Andrew, Knutson, Carter, & Pope, Jenna.
(2023, January 10).
3D_MolGNN_RL.
[Computer software].
https://doi.org/10.11578/dc.20230110.2.
Kumar, Neeraj, Bontha, Mridula, McNaughton, Andrew, Knutson, Carter, and Pope, Jenna.
"3D_MolGNN_RL." Computer software.
January 10, 2023.
https://doi.org/10.11578/dc.20230110.2.
@misc{
doecode_98618,
title = {3D_MolGNN_RL},
author = {Kumar, Neeraj and Bontha, Mridula and McNaughton, Andrew and Knutson, Carter and Pope, Jenna},
abstractNote = {3D-MolGNNRL, couples reinforcement learning (RL) to a deep
generative model based on 3D-Scaffold to generate target candidates specific to a protein pocket building up atom by
atom from the core scaffold. 3D-MolGNNRL provides an efficient way to optimize key features within a protein pocket using
a parallel graph neural network model. The agent learns to build molecules in 3D space while optimizing the binding
affinity, potency, and synthetic accessibility of the candidates generated for the SARS-CoV-2 Main protease},
doi = {10.11578/dc.20230110.2},
url = {https://doi.org/10.11578/dc.20230110.2},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20230110.2}},
year = {2023},
month = {jan}
}