About me
As a computational biologist, I study how cellular systems respond to genetic and environmental perturbations and how these responses contribute to the emergence of complex diseases. My research integrates probabilistic modeling, generative learning, and causal inference to characterize cellular dynamics and heterogeneity from single-cell and multimodal data. I develop machine learning frameworks grounded in statistical and geometric principles, including flow matching, variational inference, and representation learning, to model the underlying structure of biological processes and predict the effects of perturbations. A key goal of my work is to design models that not only achieve accurate predictions but also provide mechanistic and interpretable insights, ultimately enabling more efficient experimental design and informed therapeutic strategies.
-
Computational Biology
-
Coding
-
Machine Learning
-
Perturbation Modeling
Supervisors
-
Prof Pietro Lio
The aim of Professor Pietro Liò's research programme is developing computational models that bridge machine learning, systems biology, and medicine to understand complex biological processes and human diseases. His group focuses on graph-based deep learning, generative models, and multi-scale simulations to study molecular interactions, cellular dynamics, and clinical outcomes in health and disease. Liò Group
-
Dr Mo Loftollahi
My team and I seek to leverage artificial intelligence (AI) and machine learning (ML) models to capture the real-world behaviour of all the cells within individual human organs. Loftollahi's Group
-
Prof Manolis Kellis
Our group at MIT aims to further our understanding of the human genome by computational integration of large-scale functional and comparative genomics datasets. Kellis' Group
-
Dr Miguel Martins
The aim of Miguel's research programme is understanding the cellular and molecular mechanisms that mitochondria use, as signaling hubs, for coping with toxic insults. Martins' Group
