Using random forests to uncover the predictive power of distance-varying cell interactions in tumor microenvironments

• Published in: PLoS computational biology Vol. 20; no. 6; p. e1011361
• Main Authors: VanderDoes, Jeremy, Marceaux, Claire, Yokote, Kenta, Asselin-Labat, Marie-Liesse, Rice, Gregory, Hywood, Jack D
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 14.06.2024; Public Library of Science (PLoS)
• Subjects: Biology and Life Sciences; Breast cancer; Cancer; Cancer therapies; Care and treatment; Cell culture; Cell interaction; Cell interactions; Data analysis; Datasets; Development and progression; Expected values; Functionals; Geospatial data; Immune system; Immunotherapy; Information management; Ion beams; Lung cancer; Machine learning; Medical research; Medicine and Health Sciences; Medicine, Experimental; Methods; Microenvironments; Neutrophils; Physical Sciences; Predictions; Prognosis; Research and Analysis Methods; Scholarships & fellowships; Spatial data; Spatial distribution; Statistics; Tumor cells; Tumor microenvironment; Tumors; Canada
• ISSN: 1553-7358; 1553-734X; 1553-7358
• DOI: 10.1371/journal.pcbi.1011361

Tumor microenvironments (TMEs) contain vast amounts of information on patient's cancer through their cellular composition and the spatial distribution of tumor cells and immune cell populations. Exploring variations in TMEs between patient groups, as well as determining the extent to which this information can predict outcomes such as patient survival or treatment success with emerging immunotherapies, is of great interest. Moreover, in the face of a large number of cell interactions to consider, we often wish to identify specific interactions that are useful in making such predictions. We present an approach to achieve these goals based on summarizing spatial relationships in the TME using spatial K functions, and then applying functional data analysis and random forest models to both predict outcomes of interest and identify important spatial relationships. This approach is shown to be effective in simulation experiments at both identifying important spatial interactions while also controlling the false discovery rate. We further used the proposed approach to interrogate two real data sets of Multiplexed Ion Beam Images of TMEs in triple negative breast cancer and lung cancer patients. The methods proposed are publicly available in a companion R package funkycells.