Hybrid Machine Learning and Experimental Studies of Antiviral Potential of Ionic Liquids against P100, MS2, and Phi6

Viruses are a group of widespread organisms that are
often responsible
for very dangerous diseases, as most of them follow a mechanism to
multiply and infect their hosts as quickly as possible. Pathogen viruses
also mutate regularly, with the result that measures to prevent virus
transmission and recover from the disease caused are often limited.
The development of new substances is very time-consuming and highly
budgeted and requires the sacrifice of many living organisms. Computational
chemistry methods allow faster analysis at a much lower cost and,
most importantly, reduce the number of living organisms sacrificed
experimentally to a minimum. Ionic liquids (ILs) are a group of chemical
compounds that could potentially find a wide range of applications
due to their potential virucidal activity. In our study, we conducted
a complex computational analysis to predict the antiviral activity
of ionic liquids against three surrogate viruses: two nonenveloped
viruses, Listeria monocytogenes phage P100 and Escherichia coli phage MS2, and one enveloped virus, Pseudomonas syringae phage Phi6. Based on experimental data
of toxic activity (logEC90), we assigned activity classes
to 154 ILs. Prediction models were created and validated according
to the Organization for Economic Co-operation and Development (OECD)
recommendations using the Classification Tree method. Further, we
performed an external validation of our models through virtual screening
on a set of 1277 theoretically generated ionic liquids and then selected
10 active ionic liquids, which were synthesized to verify their activity
against the analyzed viruses. Our study proved the effectiveness and
efficiency of computational methods to predict the antiviral activity
of ionic liquids. Thus, computational models are a cost-effective
alternative approach compared with time-consuming experimental studies
where live animals are involved.