Predicting novel drugs for SARS-CoV-2 using machine learning from a >10 million chemical space

Predicting novel drugs for SARS-CoV-2 using machine learning from a >10 million chemical space

There is an urgent need for the identification of effective therapeutics for COVID-19 and we have developed a machine learning drug discovery pipeline to identify several drug candidates. First, we collect assay data for 65 target human proteins known to interact with the SARS-CoV-2 proteins, includ...

Full description

Bibliographic Details
Main Authors: Joel Kowalewski, Anandasankar Ray
Format: Article
Language:English
Published: Elsevier 2020-08-01
Series:Heliyon
Subjects:
Microbiology
Virology
Toxicology
Computer-aided drug design
Viruses
Viral disease
Online Access:http://www.sciencedirect.com/science/article/pii/S2405844020314833
id doaj-7a41ee2dd407418b856481f90992e487
record_format Article
spelling doaj-7a41ee2dd407418b856481f90992e4872020-11-25T03:54:05ZengElsevierHeliyon2405-84402020-08-0168e04639Predicting novel drugs for SARS-CoV-2 using machine learning from a >10 million chemical spaceJoel Kowalewski0Anandasankar Ray1Interdepartmental Neuroscience Program, University of California, Riverside, CA 92521, USAInterdepartmental Neuroscience Program, University of California, Riverside, CA 92521, USA; Department of Molecular, Cell and Systems Biology, University of California, Riverside, CA 92521, USA; Corresponding author.There is an urgent need for the identification of effective therapeutics for COVID-19 and we have developed a machine learning drug discovery pipeline to identify several drug candidates. First, we collect assay data for 65 target human proteins known to interact with the SARS-CoV-2 proteins, including the ACE2 receptor. Next, we train machine learning models to predict inhibitory activity and use them to screen FDA registered chemicals and approved drugs (~100,000) and ~14 million purchasable chemicals. We filter predictions according to estimated mammalian toxicity and vapor pressure. Prospective volatile candidates are proposed as novel inhaled therapeutics since the nasal cavity and respiratory tracts are early bottlenecks for infection. We also identify candidates that act across multiple targets as promising for future analyses. We anticipate that this theoretical study can accelerate testing of two categories of therapeutics: repurposed drugs suited for short-term approval, and novel efficacious drugs suitable for a long-term follow up.http://www.sciencedirect.com/science/article/pii/S2405844020314833MicrobiologyVirologyToxicologyComputer-aided drug designVirusesViral disease
collection DOAJ
language English
format Article
sources DOAJ
author Joel Kowalewski
Anandasankar Ray
spellingShingle Joel Kowalewski
Anandasankar Ray
Predicting novel drugs for SARS-CoV-2 using machine learning from a >10 million chemical space
Heliyon
Microbiology
Virology
Toxicology
Computer-aided drug design
Viruses
Viral disease
author_facet Joel Kowalewski
Anandasankar Ray
author_sort Joel Kowalewski
title Predicting novel drugs for SARS-CoV-2 using machine learning from a >10 million chemical space
title_short Predicting novel drugs for SARS-CoV-2 using machine learning from a >10 million chemical space
title_full Predicting novel drugs for SARS-CoV-2 using machine learning from a >10 million chemical space
title_fullStr Predicting novel drugs for SARS-CoV-2 using machine learning from a >10 million chemical space
title_full_unstemmed Predicting novel drugs for SARS-CoV-2 using machine learning from a >10 million chemical space
title_sort predicting novel drugs for sars-cov-2 using machine learning from a >10 million chemical space
publisher Elsevier
series Heliyon
issn 2405-8440
publishDate 2020-08-01
description There is an urgent need for the identification of effective therapeutics for COVID-19 and we have developed a machine learning drug discovery pipeline to identify several drug candidates. First, we collect assay data for 65 target human proteins known to interact with the SARS-CoV-2 proteins, including the ACE2 receptor. Next, we train machine learning models to predict inhibitory activity and use them to screen FDA registered chemicals and approved drugs (~100,000) and ~14 million purchasable chemicals. We filter predictions according to estimated mammalian toxicity and vapor pressure. Prospective volatile candidates are proposed as novel inhaled therapeutics since the nasal cavity and respiratory tracts are early bottlenecks for infection. We also identify candidates that act across multiple targets as promising for future analyses. We anticipate that this theoretical study can accelerate testing of two categories of therapeutics: repurposed drugs suited for short-term approval, and novel efficacious drugs suitable for a long-term follow up.
topic Microbiology
Virology
Toxicology
Computer-aided drug design
Viruses
Viral disease
url http://www.sciencedirect.com/science/article/pii/S2405844020314833
work_keys_str_mv AT joelkowalewski predictingnoveldrugsforsarscov2usingmachinelearningfroma10millionchemicalspace
AT anandasankarray predictingnoveldrugsforsarscov2usingmachinelearningfroma10millionchemicalspace
_version_ 1724474920374632448

Similar Items