Wout Bittremieux

Prof. Dr. Wout Bittremieux is an assistant research professor in the Adrem Data Lab at the University of Antwerp. Specializing in bioinformatics and AI, his research integrates advanced algorithmic solutions and machine learning to address fundamental biological questions through mass spectrometry-based proteomics and metabolomics. 
Dr. Bittremieux has pioneered several innovative tools to extract novel biological insights from vast collections of mass spectra, positioning him at the forefront of bioinformatics, machine learning, and mass spectrometry.

His contributions have been recognized with multiple prestigious awards, including the Postdoctoral Career Development Award from the American Society for Mass Spectrometry (2020), the "Rising Star in Proteomics and Metabolomics" title by the Journal of Proteome Research (2021), the Early Career Researcher Manuscript Competition by the Human Proteome Organization (2022), and the Bioinformatics for Mass Spectrometry Award from the European Proteomics Association and the Metabolites Young Investigator Award (2023).

An active voice in the computational mass spectrometry community, Dr. Bittremieux has published extensively in top-tier scientific journals and is a key member of the European Bioinformatics Community for Mass Spectrometry (EuBIC-MS). He leads the CompMS interest group of the International Society for Computational Biology (ISCB) and has been instrumental in developing mass spectrometry data standards through the Proteomics Standards Initiative (PSI). His contributions to the Global Natural Products Social Molecular Networking (GNPS) platform have impacted tens of thousands of users globally, confirming his reputation as a leader in his field.

Presentation

Learning From Repository-Scale Untargeted Metabolomics Data

Untargeted metabolomics data often face the challenge of limited annotation, with only a minority of mass spectra confidently identified using spectral libraries. I will present a transformative data-driven approach that has led to the creation of a propagated spectral library, known as the "suspect" spectral library, derived from repository-wide molecular networking results on the GNPS platform. Through the reanalysis of over 500 million mass spectra in 1335 publicly available datasets, we compiled a novel spectral library consisting of 87,916 new reference spectra that are structurally related to known reference molecules. I will demonstrate how the suspect library enables the discovery of novel molecules, effectively doubling the annotation rate on average. This advancement provides a powerful tool for researchers to explore previously inaccessible molecular landscapes, fostering novel biological insights.

Additionally, I will discuss recent advancements in the creation of the suspect library. Focusing on improved spectrum clustering techniques, our falcon tool minimizes data redundancy, streamlines data analysis, and enhances the interpretability of molecular networking results. Next, I will introduce our Simba tool, a transformer neural network approach we developed to predict the structural similarity between molecules based on their mass spectra. Unlike traditional modified cosine similarity, which is limited to single modifications, Simba can accurately identify molecules differing by multiple modifications. This significantly increases the number of structural analogs discoverable from untargeted mass spectrometry data.

Together, these innovations mark a significant leap towards repository-scale molecular discovery, vastly amplifying the biological knowledge that can be derived from untargeted metabolomics experiments.