Machine learning reveals genetic modifiers of the immune microenvironment of cancer

Bridget Riley-Gillis; Shirng-Wern Tsaih; Emily King; Sabrina Wollenhaupt; Jonas Reeb; Amy R Peck; Kelsey Wackman; Angela Lemke; Hallgeir Rui; Zoltan Dezso; Michael J Flister

doi:10.1016/j.isci.2023.107576

Machine learning reveals genetic modifiers of the immune microenvironment of cancer

iScience. 2023 Aug 9;26(9):107576. doi: 10.1016/j.isci.2023.107576. eCollection 2023 Sep 15.

Authors

Bridget Riley-Gillis¹, Shirng-Wern Tsaih², Emily King¹, Sabrina Wollenhaupt³, Jonas Reeb³, Amy R Peck², Kelsey Wackman^{2

4

5}, Angela Lemke^{2

4

5}, Hallgeir Rui^{4

6}, Zoltan Dezso⁷, Michael J Flister^{1

2

5

6}

Affiliations

¹ Genomics Research Center, AbbVie Inc, 1 North Waukegan Road, North Chicago, IL 60064, USA.
² Genomic Sciences and Precision Medicine Center, Medical College of Wisconsin, Milwaukee, WI, USA.
³ Information Research, AbbVie Deutschland GmbH & Co. KG, 67061, Knollstrasse, Ludwigshafen, Germany.
⁴ Department of Pathology, Medical College of Wisconsin, Milwaukee, WI 53226, USA.
⁵ Department of Physiology, Medical College of Wisconsin, Milwaukee, WI 53226, USA.
⁶ Cancer Center, Medical College of Wisconsin, Milwaukee, WI 53226, USA.
⁷ Genomics Research Center, AbbVie Bay Area, 1000 Gateway Boulevard, South San Francisco, CA 94080, USA.

Abstract

Heritability in the immune tumor microenvironment (iTME) has been widely observed yet remains largely uncharacterized. Here, we developed a machine learning approach to map iTME modifiers within loci from genome-wide association studies (GWASs) for breast cancer (BrCa) incidence. A random forest model was trained on a positive set of immune-oncology (I-O) targets, and then used to assign I-O target probability scores to 1,362 candidate genes in linkage disequilibrium with 155 BrCa GWAS loci. Cluster analysis of the most probable candidates revealed two subfamilies of genes related to effector functions and adaptive immune responses, suggesting that iTME modifiers impact multiple aspects of anticancer immunity. Two of the top ranking BrCa candidates, LSP1 and TLR1, were orthogonally validated as iTME modifiers using BrCa patient biopsies and comparative mapping studies, respectively. Collectively, these data demonstrate a robust and flexible framework for functionally fine-mapping GWAS risk loci to identify translatable therapeutic targets.

Keywords: Cancer systems biology; Microenvironment; Quantitative genetics.