Repurposing Therapeutics for COVID-19: Rapid Prediction of Commercially available drugs through Machine Learning and Docking

Sovesh Mahapatra; Prathul Nath; Manisha Chatterjee; Neeladrisingha Das; Deepjyoti Kalita; Partha Roy; Soumitra Satapathi

There are various methods for the validation of the binary classifiers. The True Positive Rate is the ratio of the actual actives to the predicted positives and this can be obtained as (TP/TP+FN). The False Positive Rate is the ratio of the predicted false actives to actual inactives and this can be obtained as (FP/TN+FP). Accuracy shows the model's performance relative to the real values and this can be calculated as (TN+TP/TN+TP+FP+FN). The Sensitivity shows the model's ability to identify the positive results and this is calculated as (TP/FN+TP) and the Specificity shows the model's ability to identify the negative results and this is calculated as (TN/TN+FP). A model with high specificity and sensitivity has a low error rate. The Balanced Classification Rate (BCR) is the mean of the sensitivity and specificity, which provides the accuracy of the model applied on the imbalanced dataset. This BCR can be calculated as 0.5*(specificity+sensitivity). All rights reserved. No reuse allowed without permission. the author/funder, who has granted medRxiv a license to display the preprint in perpetuity.