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

Abstract

Intra-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.

Competing Interest Statement

The authors have declared no competing interest.

Funding Statement

The Diamandis Lab is supported by the Terry Fox New Investigator Award program, the Canadian Institute of Health Research and the Brain Tumor Foundation of Canada. A.O. S.L., P.D, and P.P also received research grant support from the Princess Margaret Cancer Foundation and the Ontario Institute for Cancer Research.

Author Declarations

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

The University Health Network Research Ethics Board approved the study: REB #17-6193.

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines and uploaded the relevant EQUATOR Network research reporting checklist(s) and other pertinent material as supplementary files, if applicable.

Yes

Data Availability

The mass spectrometry proteomics data of all HAVOC derived regions presented in this manuscript have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD037548 (username: reviewer_pxd037548@ebi.ac.uk; password: fy4uPFAi). The data can also be examined directly through our interactive data portal (Brain Protein Atlas29; https://www.brainproteinatlas.org/dash/apps/ad). Labeling legend for mass spectrometry proteomics data can be found at https://bitbucket.org/diamandislabii/havoc. As described, some of the data used in this publication derived from The Cancer Genome Atlas Program (TCGA) and deposited at the Data Coordinating Center (DCC) for public access [http://cancergenome.nih.gov/]. The RNA-Seq IvyGAP data used are publicly available at Gene Expression Omnibus through GEO series accession number GSE107560. The single-cell are publicly available through the Broad Institute Single-Cell Portal (https://singlecell.broadinstitute.org/single_cell/study/SCP503) and CReSCENT60 (https://crescent.cloud; study ID CRES-P23). Additional proteomic data from different glioblastoma regions were also derived from Lam et al are also publicly available through the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD019381. The H&E slide and ground truth annotations for the metastatic lung carcinoma mouse model was provided directly from the authors and the relevant study.

留言 (0)

沒有登入
gif