Maria K. Jaakkola

The paper introduces a new pathway analysis method for longitudinal data, demonstrating its application in early type 1 diabetes studies with subtle biological signals.

The paper evaluates deconvolution methods for inferring immune infiltration from bulk gene expression using a DREAM Challenge, finding that some community-contributed methods, especially deep learning-based ones, perform well.

This study evaluates unsupervised clustering methods for segmenting dynamic total-body PET images at the organ level, finding that k-means with PCA performs best but still has limited accuracy.