FURI | Fall 2021
Inference of Brain Morphology From Spatial Gene Expression
The Allen Brain Atlas offers an atlas of gene expression across the whole mouse brain, but spatial transcriptomic datasets are beyond direct interpretation. Reducing dimensionality with principal component analysis (PCA) and partitioning with k-means clustering yields labels that reflect classical anatomy, albeit imperfectly and at the cost of gene information. We perform supervised classification with logistic regression as a supervised baseline, gradient-boosted trees as a maximally nonlinear model, and factorization machines as a model with constrained nonlinearity. We find that the addition of nonlinearity fails to meaningfully improve performance, suggesting that experimentally described nonlinear relationships between gene expression levels do not make a significant difference in classification of anatomical regions of the brain.
Hometown: Anchorage, Alaska, United States
Graduation date: Spring 2023