In this master's thesis, we will develop and utilize a novel sparse deep learning framework designed to perform simultaneous prediction and modality selection applied to microbiome and metabolite datasets. You can read the full proposal here
.

This project aims to develop predictive models that can assess a compound's impact on the human gut microbiome. You can read the full proposal here
.

By reducing embedding redundancy and incorporating supervised fine-tuning, we aim to produce efficient protein representations for a better microbial representation to enhance downstream analyses. You can read the full proposal here
.

Here we will extend the DGrowthR package by integrating penalized spline models as an alternative to Gaussian processes for growth curve analysis. You can read the full proposal here
.

Here we will develop analytical methods for characterizing and predicting divergent growth outcomes in B. subtilis cultures based on their initial cell densities. You can read the full proposal here
.

The purpose of this M.Sc. thesis project is to extend DGrowthR into a more general curve analysis package called DCurveR that can handle luminescence curves and thermal proteome profiling data.. You can read the full proposal here
.

We aim to enhance bacterial single-cell analysis by developing a proteome-based representation. You can read the full proposal here
.

“Biomedical Statistics and Data Science”