Recent advances in drug repurposing using machine learning

Urbina, Fabio; Puhl, Ana C.; Ekins, Sean

doi:10.1016/j.cbpa.2021.06.001

Cited by 41 publications

(20 citation statements)

References 98 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This will be expected to return more reliable predictions that when combined with drug discovery expertise can help prioritize compounds in future for in vitro testing. These efforts also complement the increasing number of examples of applying machine learning methods to SARS-CoV-2 drug discovery in order to find new molecules for clinical testing. − …”

Section: Discussionmentioning

confidence: 99%

Machine Learning Models Identify Inhibitors of SARS-CoV-2

Gawriljuk

Zin

Puhl

et al. 2021

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

With the rapidly evolving SARS-CoV-2 variants of concern, there is an urgent need for the discovery of further treatments for the coronavirus disease . Drug repurposing is one of the most rapid strategies for addressing this need, and numerous compounds have already been selected for in vitro testing by several groups. These have led to a growing database of molecules with in vitro activity against the virus. Machine learning models can assist drug discovery through prediction of the best compounds based on previously published data. Herein, we have implemented several machine learning methods to develop predictive models from recent SARS-CoV-2 in vitro inhibition data and used them to prioritize additional FDA-approved compounds for in vitro testing selected from our in-house compound library. From the compounds predicted with a Bayesian machine learning model, lumefantrine, an antimalarial was selected for testing and showed limited antiviral activity in cell-based assays while demonstrating binding (K d 259 nM) to the spike protein using microscale thermophoresis. Several other compounds which we prioritized have since been tested by others and were also found to be active in vitro. This combined machine learning and in vitro testing approach can be expanded to virtually screen available molecules with predicted activity against SARS-CoV-2 reference WIV04 strain and circulating variants of concern. In the process of this work, we have created multiple iterations of machine learning models that can be used as a prioritization tool for SARS-CoV-2 antiviral drug discovery programs. The very latest model for SARS-CoV-2 with over 500 compounds is now freely available at www.assaycentral.org.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine Learning Models Identify Inhibitors of SARS-CoV-2

Gawriljuk

Zin

Puhl

et al. 2021

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In their shadow, drug discovery has been limited to repurposing of very few drugs like remdesivir, − dexamethasone, or combinations of these two drugs, which have shown some utility (in hospital settings and for those that are severely infected patients). In a short period of time, there have been noteworthy efforts to screen large libraries of drugs (either computationally or experimentally) versus individual SARS-CoV-2 targets as well as phenotypic screens in cells infected with this virus in order to repurpose FDA-approved as well as other clinical candidates. , Only limited numbers of molecules have emerged from these screens that have also reached clinical trials. This highlights how drug discovery for this virus is particularly challenging, and efforts to improve our odds of finding molecules that can progress to the clinic and succeed in the future will require an unbiased approach.…”

mentioning

confidence: 99%

Defending Antiviral Cationic Amphiphilic Drugs That May Cause Drug-Induced Phospholipidosis

Lane

Ekins

2021

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

A recent publication in Science has proposed that cationic amphiphilic drugs repurposed for COVID-19 typically use phosholipidosis as their antiviral mechanism of action in cells but will have no in vivo efficacy. On the contrary, our viewpoint, supported by additional experimental data for similar cationic amphiphilic drugs, indicates that many of these molecules have both in vitro and in vivo efficacy with no reported phospholipidosis, and therefore, this class of compounds should not be avoided but further explored, as we continue the search for broad spectrum antivirals.

show abstract

“…Second, by improving screening results of compound libraries, AI methods have already been producing tangible results in the development of new antibiotics for over a decade. 9 As MS neuroprotection is a sorely needed therapeutic area, it is encouraging to read that recently AI methods were used to identify a sirtuin-1 active compound, for which the neuroprotective and pro-regenerative effect was subsequently confirmed in a sciatic nerve crush animal model. 10…”

Section: Ai Drives Novel Drug Developmentmentioning

confidence: 99%