Recent advances in deep generative modeling have enabled breakthroughs in realistic image, voice and text synthesis. Similar breakthroughs in chromatogram, mass spectra and metabolomics data generation are on the near horizon.
In this webinar, we’ll discuss recent work in the development of deep generative modeling algorithms to enable chromatogram cleaning, de novo compound identification and metabolomics data synthesis and disentanglement.
- Learn about the actively investigated machine learning paradigm of deep generative modeling
- Understand the impact of deep generative modeling in computational mass spectrometry including in de novo compound identification
- Discover how deep generative modeling can facilitate better understanding and biological interpretation of metabolomics data
