Goeva Lab

Computational biology at the interface of statistics, machine learning, and genomics.

The Goeva Lab develops statistical and machine learning methods for high-dimensional biological data, with a focus on single-cell and spatial genomics. We design principled and interpretable approaches to uncover subtle and heterogeneous biological signals that are often obscured by noise, cell state variation, and complex experimental structure.

We focus on making biological discovery both statistically rigorous and scientifically interpretable.

Our work sits at the intersection of statistics, machine learning, and molecular biology. We are particularly interested in problems where standard analyses either miss biologically meaningful signals or produce patterns that are difficult to interpret reliably. By combining mathematical rigor with close collaboration with experimental researchers, we aim to build computational frameworks that improve how we detect, quantify, and understand cellular behavior in health and disease.