CV #

Education and work #

• 2025 - Current : Postdoc, University of Antwerp
• 2020 - 2025 : PhD in Bioscience Engineering, Ghent University
  • Dissertation title: Self-supervised Transformers for Biological Data Modalities
• 2018 - 2020 : MSc in Bioinformatics (Bioscience Engineering), Ghent University
• 2015 - 2018 : BSc in Bioscience Engineering: Cell and Gene Biotechnology, Ghent University
• 2009 - 2015 : Science-Mathematics, Leiepoort Campus Sint-Hendrik Deinze

Additional courses:

• 2023: ACDL (Advanced Course on Data Science & Machine Learning), 5-day course, Castiglione della Pescaia, Italy
• 2023: Causal Machine Learning, semester course at Ghent University
• 2022: Research to Market, 2-day course at Ghent University

Academic output #

• Publications:
  • De Waele, Gaetan, Jim Clauwaert, Gerben Menschaert, and Willem Waegeman. “CpG Transformer for imputation of single-cell methylomes.” Bioinformatics 38, no. 3 (2022): 597-603.
  • De Waele, Gaetan, Gerben Menschaert, and Willem Waegeman.“An antimicrobial drug recommender system using MALDI-TOF MS and dual-branch neural networks” eLife 13:RP93242 (2024).
  • Mey, Friederike*, Gaetan De Waele*, Wouter Demeester, Chiara Guidi, Dries Duchi, Tomek Diederen, Hanne Kochuyt et al. “Machine learning reveals novel compound for the improved production of chitooligosaccharides in Escherichia coli.” New Biotechnology (2025).
  • De Waele, Gaetan, Gerben Menschaert, Peter Vandamme, and Willem Waegeman. “Pre-trained Maldi Transformers improve MALDI-TOF MS-based prediction.” Computers in Biology and Medicine (2025).

• Preprints:
  • De Waele, Gaetan, Gerben Menschaert, and Willem Waegeman. “A systematic assessment of single-cell language model configurations.” bioRxiv (2025): 2025-04.
  • Vergauwe, Fauve, Gaetan De Waele, Andrea Sass, Callum Highmore, Niall Hanrahan, Yoshiki Cook, Mads Lichtenberg et al. “Harnessing machine learning to predict antibiotic susceptibility in Pseudomonas aeruginosa biofilms.” bioRxiv (2025): 2025-04.

(*: shared first author)

• Conference contributions:
  • Oral at ISMB22, Madison, USA. “CpG Transformer for imputation of single-cell methylomes”
  • Oral at AAAI24 LLMs4Bio workshop, Vancouver, Canada. “Pre-trained Maldi Transformers improve MALDI-TOF MS-based prediction”
  • Poster at ABLS24, Leuven, Belgium. “Transformers for MALDI-TOF MS-based antimicrobial drug recommendation”
  • Oral at ISMB24, Montreal, Canada. “Transformers for MALDI-TOF MS-based antimicrobial drug recommendation”
  • Poster at VIB.AI Symposium 24, Mechelen, Belgium, “Benchmarking single-cell Language Model building blocks”

• Software:
  • cpg-transformer, code supporting my work on methylation (CpG) data imputation.
  • h5torch, a simple utility that allows PyTorch Dataloading from HDF5 files.
  • bio-attention, definitions for transformers adapted to the work in my PhD.
  • maldi-nn, code supporting my work on MALDI-TOF mass spectrometry.
  • bento-sc, code supporting my work on single-cell transcriptomic language models.
  • cut2min-bucket, a small dataloading utility to use flash-attn with variable length inputs.

Teaching #

• 2020 - 2025 : Teaching assistance for “Machine learning for the Life Sciences” course
• 2024 - 2025 : Tutor for Master thesis “End-to-end de novo metabolomics” by Wout Welvaert
• 2024 - 2025 : Tutor for Master thesis “Variational inference for DTI” by Robbe Claeys
• 2023 - 2024 : Tutor for Master thesis “Novel neural networks for bacterial species prediction from MALDI-TOF data” by Jorge Isaac Cueva Villavicencio
• 2022 - 2023 : Tutor for Master thesis “Two-Branch Neural Networks for Predicting Protein-DNA Interaction” by Natan Tourne
• 2022 - 2023 : Tutor for Master thesis “Designing novel protein sequences using advanced generative models” by Scout Van den Bergh
• 2021 - 2022 : Tutor for Master thesis “Detection of 5mC modification in Nanopore sequencing data using deep learning” by Yari Van Laere
• 2021 - 2022 : Teaching assistance for “UGain Machine Learning” course
• 2021 - 2022 : Tutor for MSc Bioinformatics Design Project “Automated benchmarking of optimized general purpose machine learning classifiers for single cell transcriptomics” by Ruben Allaert, Seoyeon Oh, Natan Tourne, and Christopher Van Hessche
• 2020 - 2021 : Tutor for MSc Bioinformatics Design Project “Benchmarking study of ML methods for bacterial species identification from MALDI-TOF MS data” by Kobe De Temmerman, Triana Forment, Ju Hyung Lee, Natalie Thomas, and Elien Martens