K. Branson

Buyer Beware: confounding factors and biases abound when predicting omics-based biomarkers from histological images

This paper shows that deep learning models for predicting biomarkers from histology images are confounded by interdependencies among biomarkers, leading to less accurate and less reliable predictions.

Cancer drug sensitivity prediction from routine histology images

This paper demonstrates using deep learning to predict cancer drug sensitivity from histology images and cell line data, identifying histological patterns linked to drug responses.

Data-Driven Modelling of Gene Expression States in Breast Cancer and their Prediction from Routine Whole Slide Images

The paper predicts gene expression states from whole slide images using a graph neural network and identifies co-expressing gene groups with clinical and therapeutic relevance.

Bayesian analysis of isothermal titration calorimetry for binding thermodynamics

This paper introduces a Bayesian framework for analyzing ITC data to better estimate thermodynamic parameters and their uncertainties.