Mpropred: A machine learning (ML) driven Web-App for bioactivity prediction of SARS-CoV-2 main protease (Mpro) antagonists

Abstract

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic emerged in 2019 and still requiring treatments with fast clinical translatability. Frequent occurrence of mutations in spike glycoprotein of SARS-CoV-2 led the consideration of an alternative therapeutic target to combat the ongoing pandemic. The main protease (Mpro) is such an attractive drug target due to its importance in maturating several polyproteins during the replication process. In the present study, we used a classification structure–activity relationship (CSAR) model to find substructures that leads to to anti-Mpro activities among 758 non-redundant compounds. A set of 12 fingerprints were used to describe Mpro inhibitors, and the random forest approach was used to build prediction models from 100 distinct data splits. The data set’s modelability (MODI index) was found to be robust, with a value of 0.79 above the 0.65 threshold. The accuracy (89%), sensitivity (89%), specificity (73%), and Matthews correlation coefficient (79%) used to calculate the prediction performance, was also found to be statistically robust. An extensive analysis of the top significant descriptors unveiled the significance of methyl side chains, aromatic ring and halogen groups for Mpro inhibition. Finally, the predictive model is made publicly accessible as a web-app named Mpropred in order to allow users to predict the bioactivity of compounds against SARS-CoV-2 Mpro. Later, CMNPD, a marine compound database was screened by our app to predict bioactivity of all the compounds and results revealed significant correlation with their binding affinity to Mpro. Molecular dynamics (MD) simulation and molecular mechanics/Poisson Boltzmann surface area (MM/PBSA) analysis showed improved properties of the complexes. Thus, the knowledge and web-app shown herein can be used to develop more effective and specific inhibitors against the SARS-CoV-2 Mpro. The web-app can be accessed from https://share.streamlit.io/nadimfrds/mpropred/Mpropred_app.py.

Developing a SARS-CoV-2 main protease binding prediction random forest model for drug repurposing for COVID-19 treatment

“…Classification models for predicting SARS-CoV-2 main protease inhibitors have also been developed using a variety of machine learning algorithms, such as random forest, k-nearest neighbors, support vector machine, and Naïve Bayes. [55][56][57][58] Compared to our models, these models were developed based on datasets with much fewer SARS-CoV-2 main protease inhibitors. Moreover, annotations of positives and negatives used to generate the training sets are not consistent.…”

“…Moreover, annotations of positives and negatives used to generate the training sets are not consistent. For example, after collecting compounds with IC 50 values from literature, Ferdous et al 55 discarded compounds with IC 50 of 1-10 µM and assigned compounds with IC 50 < 0.5 µM as positives and compounds with IC 50 > 10 µM as negatives, while Mekni et al 56 excluded compounds with IC 50 > 98 µM as negatives. It is worth noting that the SARS-CoV-2 main protease has multiple binding sites that can bind compounds with distinct structural features.…”

Anti-Dengue: A Machine Learning-Assisted Prediction of Small Molecule Antivirals against Dengue Virus and Implications in Drug Repurposing

“…These MLTs have been employed by various researchers in a multitude of studies [ 40 ]. For example, Mpropred for the prediction of SARS-CoV-2 main protease antagonists [ 41 ], TargIDe for predicting the molecules with antibiofilm activity against Pseudomonas aeruginosa [ 42 ], EBOLApred for predicting cell entry inhibitors against the Ebola virus [ 43 ], and StackHCV for the identification of inhibitors against the NS5 protein of the Hepatitis C virus [ 44 ]. Similarly, we have utilized these techniques to create predictive algorithms such as AVCpred for predicting general effective antiviral compounds [ 15 ]: AVPpred, the first algorithm for predicting antiviral peptides [ 16 ], AVP-IC50 Pred for predicting antiviral peptides activity in terms of the IC 50 , i.e., the half-maximal inhibitory concentration [ 17 ], HIVprotI for predicting and designing inhibitors targeting Human Immunodeficiency Virus (HIV) proteins [ 18 ], and anti-flavi for predicting and designing various novel antiviral compounds, particularly for flaviviruses [ 19 ].…”