Subclonal reconstruction of tumors using machine learning and population genetics

The majority of cancer genomic data are generated from bulk samples composed of mixtures of cancer subpopulations, as well as normal cells. Subclonal reconstruction approaches based on machine learning aim to separate those subpopulations in a sample and reconstruct their evolutionary history. However, current approaches are entirely data-driven and agnostic to evolutionary theory. We demonstrate that systematic errors occur in the analysis if evolution is not accounted for, and this is exacerbated by multi-sampling of the same tumor. We present a novel approach for model-based tumor subclonal reconstruction (MOBSTER) that combines machine learning with theoretical population genetics. Using public whole-genome sequencing data from 2,606 samples from different cohorts, new data and synthetic validation, we show this method is more robust and accurate than current techniques in single sample, multi-region and longitudinal data. This approach minimizes the confounding factors of non-evolutionary methods, leading to more accurate recovery of the evolutionary history of human cancers.