We investigate protein structure, function, evolution, and interactions to understand biological processes, particularly those linked to disease.
We are deeply committed to developing bioinformatics tools and databases to support the research community, enhancing scientific investigations and fostering open, collaborative advancements in science.
Our work integrates machine learning (ML) approaches, including convolutional neural networks (CNNs) and embeddings, to study amyloid-forming proteins, protein aggregation, and neurodegenerative diseases. We analyze RNA-binding proteins and protein-RNA interactions in gene regulation and employ graph convolutional neural networks (GCNNs) to identify ALS-associated genes and potential biomarkers by integrating gene expression with protein-protein interaction (PPI) networks. Our adaptable methods advance precision medicine across various diseases. Additionally, we investigate protein aggregation and amyloidosis—hallmarks of neurodegenerative disorders—using deep learning and homology-based annotations. Our research extends to intrinsically disordered and liquid-liquid phase separation (LLPS) proteins within membrane-less organelles (MLOs), focusing on disease-related mutations. Using protein language models (pLMs), we generate embeddings for wild-type and mutated sequences to identify novel disease-causing mutations in LLPS proteins.