Integrative, multimodal analysis of glioblastoma using TCGA molecular data, pathology images, and clinical outcomes

Abstract

Multimodal, multiscale data synthesis is becoming increasingly critical for successful translational biomedical research. In this letter, we present a large-scale investigative initiative on glioblastoma, a high-grade brain tumor, with complementary data types using in silico approaches. We integrate and analyze data from The Cancer Genome Atlas Project on glioblastoma that includes novel nuclear phenotypic data derived from microscopic slides, genotypic signatures described by transcriptional class and genetic alterations, and clinical outcomes defined by response to therapy and patient survival. Our preliminary results demonstrate numerous clinically and biologically significant correlations across multiple data types, revealing the power of in silico multimodal data integration for cancer research.

Fig. 1

The overall architecture for the In Silico brain tumor research is presented. All data sources, i.e. microscopy imaging features, molecular data, and clinical outcomes are captured by PAIS database with which scientific researchers can query for multi-data integration results.

Fig. 2

(a) Features computed from nuclear and “cytoplasm” regions are summarized; (b) A typical image region is overlaid with nuclear (red) and “cytoplasm” (green) boundaries identified by computer algorithms.

Fig. 3

A SQL example is presented to query for mean and covariance nuclear feature vector for each patient in PAIS database.

Fig. 4

Kaplan-Meier plot for patients of three consensus clusters is presented with AUC values and 95% lower and upper confidence bounds.

Fig. 5

Kaplan-Meier plots for patients treated with aggressive (blue) and standard (red) therapy from (a) cluster 1, (b) cluster 2, and (c) cluster 3, are presented with 95% lower and upper confidence bounds.

Fig. 6

The genetic alteration profiles for three consensus clusters of samples are presented. For copy number data (denoted as CNV), light green, dark green, black, dark red, and light red represent homozygous deletion, hemizygous deletion, neutral change, gain, and high-level amplification. For somatic mutation data (denoted as Mut), red represents mutant.