Computational Biomolecular Mass Spectrometry Group

Our Mission

Modern biology generates vast amounts of data, yet interpreting it remains a bottleneck. We believe that domain knowledge is crucial for making sense of this data. Our group addresses the unique challenges of biological data - noise, sparsity, and complexity - by fusing recent advances in machine learning with practical applications.

We are a bridge between AI Technology for Life (AIT4Life) and Biomolecular Mass Spectrometry and Proteomics (BioMS), connecting expertise across the Information and Computing Sciences and Pharmaceutical Sciences departments.

We aim to develop explainable models that generalize well, helping us better understand and predict stochastic biological processes at the molecular level.

Research Areas

• Computational Mass Spectrometry: Developing statistical tools for shotgun proteomics and Data-Independent Acquisition (DIA).
• Predictive Modeling: forecasting peptide behavior (digestion, fragmentation) to sequence amino acids and study the entire proteome.
• Trustworthy AI: Accurately estimating false discovery rates and defining limits of applicability for AI models.
• Generative Approaches: Exploring reinforcement learning and autoencoders for generating decoy peptides and resolving complex signals.

Community & Collaboration

We are dedicated to building a computational biology community at Utrecht Science Park that connects project ideas, students, and partners from academia and industry. We currently partner with clinicians, instrument vendors, and computer scientists to bridge distinct fields.

Interested in pushing the boundaries of proteomics with us? Get in touch.