Protein-Protein Interactions (PPIs) and Post-Translational Modifications (PTMs) play a central role in the regulation of biological processes. However, not much in known about the interplay of these two regulatory mechanisms. For this reason, I aim to develop MoDPA, a computational method to identify co-occurring PTMs from the reanalysis of a large MS-based proteomics dataset. I will implement a Variational AutoEncoder (VAE), a deep-learning model to project the data to a low-dimension latent space and calculate correlations between PTMs. I will then visualize the results as a network where nodes, representing PTMs, are connected by edges representing co-occurrence. I will analyse the network to identify relevant clusters of biologically related (modified) proteins and annotate known interactions based on the information already present in the literature (i.e., Tabloid Proteome). A first, preliminary analysis already identified a cluster of strongly interconnected modification sites on proteins related to immune response and metabolism, as well as clusters of phosphorylated proteins and kinases. To validate this approach, I plan to study how PTMs affect the interactions between chaperones and their client proteins, with a focus on spontaneous modifications connected to molecular ageing.