Cargando…

Memory augmented recurrent neural networks for de-novo drug design

A recurrent neural network (RNN) is a machine learning model that learns the relationship between elements of an input series, in addition to inferring a relationship between the data input to the model and target output. Memory augmentation allows the RNN to learn the interrelationships between ele...

Descripción completa

Detalles Bibliográficos
Autores principales: Suresh, Naveen, Chinnakonda Ashok Kumar, Neelesh, Subramanian, Srikumar, Srinivasa, Gowri
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9223405/
https://www.ncbi.nlm.nih.gov/pubmed/35737661
http://dx.doi.org/10.1371/journal.pone.0269461
_version_ 1784733118043783168
author Suresh, Naveen
Chinnakonda Ashok Kumar, Neelesh
Subramanian, Srikumar
Srinivasa, Gowri
author_facet Suresh, Naveen
Chinnakonda Ashok Kumar, Neelesh
Subramanian, Srikumar
Srinivasa, Gowri
author_sort Suresh, Naveen
collection PubMed
description A recurrent neural network (RNN) is a machine learning model that learns the relationship between elements of an input series, in addition to inferring a relationship between the data input to the model and target output. Memory augmentation allows the RNN to learn the interrelationships between elements of the input over a protracted length of the input series. Inspired by the success of stack augmented RNN (StackRNN) to generate strings for various applications, we present two memory augmented RNN-based architectures: the Neural Turing Machine (NTM) and the Differentiable Neural Computer (DNC) for the de-novo generation of small molecules. We trained a character-level convolutional neural network (CNN) to predict the properties of a generated string and compute a reward or loss in a deep reinforcement learning setup to bias the Generator to produce molecules with the desired property. Further, we compare the performance of these architectures to gain insight to their relative merits in terms of the validity and novelty of the generated molecules and the degree of property bias towards the computational generation of de-novo drugs. We also compare the performance of these architectures with simpler recurrent neural networks (Vanilla RNN, LSTM, and GRU) without an external memory component to explore the impact of augmented memory in the task of de-novo generation of small molecules.
format Online
Article
Text
id pubmed-9223405
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-92234052022-06-24 Memory augmented recurrent neural networks for de-novo drug design Suresh, Naveen Chinnakonda Ashok Kumar, Neelesh Subramanian, Srikumar Srinivasa, Gowri PLoS One Research Article A recurrent neural network (RNN) is a machine learning model that learns the relationship between elements of an input series, in addition to inferring a relationship between the data input to the model and target output. Memory augmentation allows the RNN to learn the interrelationships between elements of the input over a protracted length of the input series. Inspired by the success of stack augmented RNN (StackRNN) to generate strings for various applications, we present two memory augmented RNN-based architectures: the Neural Turing Machine (NTM) and the Differentiable Neural Computer (DNC) for the de-novo generation of small molecules. We trained a character-level convolutional neural network (CNN) to predict the properties of a generated string and compute a reward or loss in a deep reinforcement learning setup to bias the Generator to produce molecules with the desired property. Further, we compare the performance of these architectures to gain insight to their relative merits in terms of the validity and novelty of the generated molecules and the degree of property bias towards the computational generation of de-novo drugs. We also compare the performance of these architectures with simpler recurrent neural networks (Vanilla RNN, LSTM, and GRU) without an external memory component to explore the impact of augmented memory in the task of de-novo generation of small molecules. Public Library of Science 2022-06-23 /pmc/articles/PMC9223405/ /pubmed/35737661 http://dx.doi.org/10.1371/journal.pone.0269461 Text en © 2022 Suresh et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Suresh, Naveen
Chinnakonda Ashok Kumar, Neelesh
Subramanian, Srikumar
Srinivasa, Gowri
Memory augmented recurrent neural networks for de-novo drug design
title Memory augmented recurrent neural networks for de-novo drug design
title_full Memory augmented recurrent neural networks for de-novo drug design
title_fullStr Memory augmented recurrent neural networks for de-novo drug design
title_full_unstemmed Memory augmented recurrent neural networks for de-novo drug design
title_short Memory augmented recurrent neural networks for de-novo drug design
title_sort memory augmented recurrent neural networks for de-novo drug design
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9223405/
https://www.ncbi.nlm.nih.gov/pubmed/35737661
http://dx.doi.org/10.1371/journal.pone.0269461
work_keys_str_mv AT sureshnaveen memoryaugmentedrecurrentneuralnetworksfordenovodrugdesign
AT chinnakondaashokkumarneelesh memoryaugmentedrecurrentneuralnetworksfordenovodrugdesign
AT subramaniansrikumar memoryaugmentedrecurrentneuralnetworksfordenovodrugdesign
AT srinivasagowri memoryaugmentedrecurrentneuralnetworksfordenovodrugdesign