Format

Send to

Choose Destination
BMC Med Genomics. 2017 Mar 31;10(1):20. doi: 10.1186/s12920-017-0256-3.

Revealing cancer subtypes with higher-order correlations applied to imaging and omics data.

Author information

1
Biomedical Engineering, University of California, Santa Cruz, USA.
2
UC Santa Cruz Genomics Institute, University of California, Santa Cruz, USA.
3
Stanford Center for Biomedical Informatics Research and Biomedical Informatics Training Program, Stanford University School of Medicine, Stanford, USA.
4
Stanford Institute for Neuro-Innovation and Translational Neurosciences, Stanford University School of Medicine, Stanford, USA.
5
Institute for Stem Cell Biology and Regenerative Medicine, Stanford University School of Medicine, Stanford, USA.
6
Departments of Neurosurgery, Stanford University School of Medicine, Stanford, USA.
7
Biomedical Engineering, University of California, Santa Cruz, USA. jstuart@ucsc.edu.
8
UC Santa Cruz Genomics Institute, University of California, Santa Cruz, USA. jstuart@ucsc.edu.

Abstract

BACKGROUND:

Patient stratification to identify subtypes with different disease manifestations, severity, and expected survival time is a critical task in cancer diagnosis and treatment. While stratification approaches using various biomarkers (including high-throughput gene expression measurements) for patient-to-patient comparisons have been successful in elucidating previously unseen subtypes, there remains an untapped potential of incorporating various genotypic and phenotypic data to discover novel or improved groupings.

METHODS:

Here, we present HOCUS, a unified analytical framework for patient stratification that uses a community detection technique to extract subtypes out of sparse patient measurements. HOCUS constructs a patient-to-patient network from similarities in the data and iteratively groups and reconstructs the network into higher order clusters. We investigate the merits of using higher-order correlations to cluster samples of cancer patients in terms of their associations with survival outcomes.

RESULTS:

In an initial test of the method, the approach identifies cancer subtypes in mutation data of glioblastoma, ovarian, breast, prostate, and bladder cancers. In several cases, HOCUS provides an improvement over using the molecular features directly to compare samples. Application of HOCUS to glioblastoma images reveals a size and location classification of tumors that improves over human expert-based stratification.

CONCLUSIONS:

Subtypes based on higher order features can reveal comparable or distinct groupings. The distinct solutions can provide biologically- and treatment-relevant solutions that are just as significant as solutions based on the original data.

KEYWORDS:

Cancer; Clustering; Community detection; MRI; Magnetic resonance imaging; Molecular subtyping; Mutation

PMID:
28359308
PMCID:
PMC5374737
DOI:
10.1186/s12920-017-0256-3
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for BioMed Central Icon for PubMed Central
Loading ...
Support Center