Back

Deep Gaussian Process with Uncertainty Estimation for Microsatellite Instability and Immunotherapy Response Prediction Based on Histology

Park, S.; Pettigrew, M. F.; Cha, Y. J.; Kim, I.-H.; Kim, M.; Banerjee, I.; Barnfather, I.; Clemenceau, J. R.; Jang, I.; Kim, H.; Kim, Y.; Pai, R. K.; Park, J. H.; Samadder, J. J.; Song, K. Y.; Sung, J.-Y.; Cheong, J.-H.; Kang, J.; Lee, S. H.; Wang, S. C.; Hwang, T. H.

2024-11-03 bioinformatics
10.1101/2024.11.01.621561 bioRxiv
Show abstract

Determining tumor microsatellite status has significant clinical value because tumors that are microsatellite instability-high (MSI-H) or mismatch repair deficient (dMMR) respond well to immune check-point inhibitors (ICIs) and oftentimes not to chemotherapeutics. We propose MSI-SEER, a deep Gaussian process-based Bayesian model that analyzes H&E whole-slide images in weakly-supervised-learning to predict microsatellite status in gastric and colorectal cancers. We performed extensive validation using multiple large datasets comprised of patients from diverse racial backgrounds. MSI-SEER achieved state-of-the-art performance with MSI prediction, which was by integrating uncertainty prediction. We achieved high accuracy for predicting ICI responsiveness by combining tumor MSI status with stroma-to-tumor ratio. Finally, MSI-SEERs tile-level predictions revealed novel insights into the role of spatial distribution of MSI-H regions in the tumor microenvironment and ICI response.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.