Muhammad Saqib Sohail

This paper introduces a method to infer fitness effects from short-read time-series genomic data while accounting for genetic linkage, validated on HIV and SARS-CoV-2 datasets.

This study introduces a back-projection model to improve inference from sparse genomic surveillance data by estimating infection times and accounting for sampling biases in SARS-CoV-2 variants.

IFNBoost is a machine learning model that predicts IFNγ-inducing peptides with high accuracy, outperforming existing models and using both peptide sequences and metadata features.