Steffany A. L. Bennett

The paper introduces iDMS, a neural network that predicts optimal separation and compensation voltages for DMS, improving glycosphingolipid analysis.

The paper introduces iDMS, a deep neural network that predicts optimal ion mobility parameters for resolving monoglycosphingolipid stereoisomers, improving the efficiency of DMS-based assays.

This study benchmarks network inference algorithms for deriving metabolic relationships from lipidomic and metabolomic data, revealing challenges in interpretation despite some ability to distinguish metabolic states.

ImpLiMet is a platform that helps users select the best missing data imputation method by testing eight approaches and evaluating their impact through statistical and visualization tools.

The paper uses statistical and machine learning methods to analyze how sex and age influence antibody responses to SARS-CoV-2 infection and vaccination.

META-BOA provides a web tool to balance metabolomics data using over-sampling algorithms and evaluates their impact through visualization and classification.

BATL is a Bayesian classifier for targeted lipidomics that annotates LC-ESI-MS/MS peaks with high accuracy using eight features, achieving over 95% correct identification in SRM datasets.

The paper investigates the role of monoamine oxidase B in delirium onset during SARS-CoV-2 infection using metabolomic profiling and computational analysis.

RTStaR standardizes and registers lipidomic datasets to match and identify unique lipid species across different matrices and organisms.

The paper identifies human biological processes and protein sequence motifs potentially targeted by SARS-CoV-2 using PPI networks and computational methods.