Patrick G. A. Pedrioli

MOAgent discovers biomarker candidates in multi-omics data using gradient-boosted decision trees, addressing data challenges and providing accessible analysis tools.

This study shows PRAMEL7 interacts with CUL2 to destabilize NuRD complex, promoting ground-state pluripotency in ESCs by reducing repressive chromatin regulation.

scROSHI identifies cell types without training data by using pre-existing gene sets and hierarchical relationships, outperforming methods in low-data and high-diversity scenarios.

The paper compares the proteome of remyelination and developmental myelination in mice, finding distinct protein compositions and identifying potential therapeutic targets.

PCfun annotates protein complex function using natural language processing and machine learning, integrating word embeddings from PubMed Central articles with supervised and unsupervised methods.

The paper analyzes surfaceome dynamics during neuronal development and synaptic plasticity, revealing surface protein reorganization independent of global proteostasis.

SCIM matches single-cell measurements across technologies by learning a technology-invariant latent space and applying bipartite matching, achieving high accuracy in real-world datasets.

The paper develops a DIA-based proteotyping strategy for HDL particles, revealing significant proteotype differences between healthy individuals and those with T2DM or CHD.