Citation: Amiroch, S.; Irawan, M.I.;
Mukhlash, I.; Al Faroby, M.H.Z.;
Nidom, C.A. Machine Learning for
the Prediction of Antiviral
Compounds Targeting Avian
Influenza A/H9N2 Viral Proteins.
Symmetry 2022, 14, 1114. https://
doi.org/10.3390/sym14061114
Academic Editor: Leyi Wei
Received: 20 April 2022
Accepted: 23 May 2022
Published: 28 May 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
symmetry
S S
Article
Machine Learning for the Prediction of Antiviral Compounds
Targeting Avian Influenza A/H9N2 Viral Proteins
Siti Amiroch
1,2
, Mohammad Isa Irawan
1,
* , Imam Mukhlash
1
, Mohammad Hamim Zajuli Al Faroby
3
and Chairul Anwar Nidom
4,5
1
Department of Mathematics, Faculty of Science and Data Analytics, Institut Teknologi Sepuluh Nopember,
Surabaya 60111, Indonesia; siti.amiroch@unisda.ac.id (S.A.); imamm@matematika.its.ac.id (I.M.)
2
Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Islam Darul ‘Ulum,
Lamongan 62253, Indonesia
3
Department of Data Science, Institut Teknologi Telkom Surabaya, Surabaya 60231, Indonesia;
alfaroby@ittelkom-sby.ac.id
4
Coronavirus and Vaccine Formulation Research Group, Professor Nidom Foundation,
Surabaya 60115, Indonesia; nidomca@pnfinstitute.org
5
Faculty of Veterinary Medicine, Airlangga University, Surabaya 60115, Indonesia
* Correspondence: mii@its.ac.id; Tel.: +62-81233555479; Fax: +62-031-5996506
Abstract: Avian influenza subtype A/H9N2—which infects chickens, reducing egg production by up
to 80%—may be transmissible to humans. In humans, this virus is very harmful since it attacks the
respiratory system and reproductive tract, replicating in both. Previous attempts to find antiviral
candidates capable of inhibiting influenza A/H9N2 transmission were unsuccessful. This study
aims to better characterize A/H9N2 to facilitate the discovery of antiviral compounds capable of
inhibiting its transmission. The Symmetry of this study is to apply several machine learning methods
to perform virtual screening to identify H9N2 antivirus candidates. The parameters used to measure
the machine learning model’s quality included accuracy, sensitivity, specificity, balanced accuracy,
and receiver operating characteristic score. We found that the extreme gradient boosting method
yielded better results in classifying compounds predicted to be suitable antiviral compounds than six
other machine learning methods, including logistic regression, k-nearest neighbor analysis, support
vector machine, multilayer perceptron, random forest, and gradient boosting. Using this algorithm,
we identified 10 candidate synthetic compounds with the highest scores. These high scores predicted
that the molecular fingerprint may involve strong bonding characteristics. Thus, we were able to
find significant candidates for synthetic H9N2 antivirus compounds and identify the best machine
learning method to perform virtual screenings.
Keywords: machine learning; significant compounds; avian influenza A/H9N2; antivirus
1. Introduction
Avian influenza A/H9N2 is a novel bird flu virus first detected in December 2016
in South Sulawesi, Indonesia [1]. Reverse transcription polymerase chain reaction results
suggested that the virus was present in chicken farms from December 2016 to May 2017 [2].
Phylogenetic analysis using the Felsenstein model neighbor-joining algorithm simulated
in MATLAB
®
identified 13 clusters of H9N2 that have spread throughout Indonesia [3].
H9N2 is classified as a low pathogenic avian influenza virus or a “bird flu” and was not
initially thought to infect humans [4]. Nonetheless, H9N2 replicates in the respiratory and
reproductive tracts of chicken hosts, thereby reducing egg production [5] by as much as
80% [1]. Additionally, recent research has shown that the H9N2 virus can also reproduce
in mammalian lungs and reproductive organs (including the ovaries, fallopian tubes,
and uterus), even in humans [6]. These findings can help us understand how potential
pathogens such as the H9N2 virus may threaten human health.
Symmetry 2022, 14, 1114. https://doi.org/10.3390/sym14061114 https://www.mdpi.com/journal/symmetry