HAVOC: Small-scale histomic mapping of biodiversity across entire tumor specimens using deep neural networks

Abstract

SummaryIntra-tumoral heterogeneity can wreak havoc on current precision medicine strategies due to challenges in sufficient sampling of geographically separated areas of biodiversity distributed across centimeter-scale tumor distances. In particular, modern tissue profiling approaches are still largely designed to only interrogate small tumor fragments; which may constitute a minute and non-representative fraction of the overall neoplasm. To address this gap, we developed a pipeline that leverages deep learning to define topographic histomorphologic fingerprints of tissue and create Histomic Atlases of Variation Of Cancers (HAVOC). Importantly, using a number of spatially-resolved readouts, including mass-spectrometry-based proteomics and immunohistochemisy, we demonstrate that these personalized atlases of histomic variation can define regional cancer boundaries with distinct biological programs. Using larger tumor specimens, we show that HAVOC can map spatial organization of cancer biodiversity spanning tissue coordinates separated by multiple centimeters. By applying this tool to guide profiling of 19 distinct geographic partitions from 6 high-grade gliomas, HAVOC revealed that distinct states of differentiation can often co-exist and be regionally distributed across individual tumors. Finally, to highlight generalizability, we further benchmark HAVOC on additional tumor types and experimental models of heterogeneity. Together, we establish HAVOC as a versatile and accessible tool to generate small-scale maps of tissue heterogeneity and guide regional deployment of molecular resources to relevant and biodiverse tumor niches.