Feature selection for effective prediction of SARS-COV-2 using machine learning.

Abstract

Background: With rise in variants of SARS-CoV-2, it is necessary to classify the emerging SARS-CoV-2 for early detection and thereby reduce human transmission. Genomic and proteomic information have less frequently been used for classifying in a machine learning (ML) approach for detection of SARS-CoV-2.

Objective: With this aim we used nucleoprotein and viral proteomic evolutionary information of SARS-CoV-2 along with the charge and basicity distribution of amino acids from various strains of SARS-CoV-2 to generate a disease severity model based on ML.

Methods: All sequence and clinical data were obtained from GISAID. Proteomic level calculations were added to comprise the dataset. The training set was used for feature selection. Select K- Best feature selection method was employed which was cross validated with testing set and performance evaluated. Delong's test was also done. We also employed BIRCH clustering on SARS-CoV-2 for clustering the strains.

Results: Out of six ML models four were successful in training and testing. Extra Trees algorithm generated a micro-averaged F1-score of 74.2% and a weighted averaged area under the receiver operating characteristic curve (AUC-ROC) score of 73.7% with multi-class option. The feature selection set to 5, enhanced the ROC AUC from 73.7 to 76.4%. Accuracy of the selected model of 86.9% was achieved.

Conclusion: The unique features identified in the ML approach was able to classify disease severity into classes and had potential for predicting risk in newer variants.