Rachel J. Dutton

Enabling predictive modeling of molecular connections between fermented foods and human inflammation through a paired dataset of cell-based models and multi-omics approaches

The paper creates a paired dataset of fermented foods and human cell responses to enable predictive models of their anti-inflammatory effects through multi-omics approaches.

Leveraging publicly available datasets and machine learning approaches for predicting the health benefits of fermented foods

The paper uses machine learning on fermented food datasets to predict bioactive peptides and their health benefits, providing publicly available tools and resources for further research.

Algorithmic Learning for Auto-deconvolution of GC-MS Data to Enable Molecular Networking within GNPS.

The paper develops a machine learning workflow for auto-deconvolution of GC-MS data within GNPS, enabling molecular networking and applications in breathomics and volatilome mapping.

Reference data based insights expand understanding of human metabolomes

This paper expands the interpretability of human metabolomes by using food-based annotations, increasing the fraction of molecular features understood 7-fold.