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

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.

Emergence of Novel SARS-CoV-2 variants in India: second wave.

Introduction: Globally South-East Asia reported 40% of SARS-CoV-2 infected cases in the fourth week of April 2021. It continued to show an increase with India accounting for 50% of cases worldwide and 30% of global deaths. Genomic surveillance should continue at a rapid pace because of the continuously evolving nature of the virus.

Benchmarking Datasets from Malaria Cytotoxic T-cell Epitopes Using Machine Learning Approach.

Background: Epitope prediction remains a major challenge in malaria due to the unique parasite biology, in addition to rapidly evolving parasite sequence variation in Plasmodium species. Although several models for epitope prediction exist, they are not useful in Plasmodium specific epitope development. Hence, it was proposed to use machine learning based methods to develop a peptide sequence based epitope predictor specific for malaria.

Phylogenetic analysis of the NS5 gene of Zika virus.

ZIKV infection has become a global threat spreading across 31 countries in Central America, South America, and the Caribbean. However, little information is available about the molecular epidemiology of ZIKV. Shared mutation of a threonine residue to alanine at the same position in the C terminal of NS5 sequences was observed in sequences from Colombia, Mexico, Panama, and Martinique.