Integrative analysis of complex cancer genomics and clinical profiles using the cBioPortal

Abstract

The cBioPortal for Cancer Genomics (http://cbioportal.org) provides a Web resource for exploring, visualizing, and analyzing multidimensional cancer genomics data. The portal reduces molecular profiling data from cancer tissues and cell lines into readily understandable genetic, epigenetic, gene expression, and proteomic events. The query interface combined with customized data storage enables researchers to interactively explore genetic alterations across samples, genes, and pathways and, when available in the underlying data, to link these to clinical outcomes. The portal provides graphical summaries of gene-level data from multiple platforms, network visualization and analysis, survival analysis, patient-centric queries, and software programmatic access. The intuitive Web interface of the portal makes complex cancer genomics profiles accessible to researchers and clinicians without requiring bioinformatics expertise, thus facilitating biological discoveries. Here, we provide a practical guide to the analysis and visualization features of the cBioPortal for Cancer Genomics.

Fig. 1. Performing a query of a single cancer study

The four steps to query genomic data in the cBioPortal for Cancer Genomics for a single cancer study. The query page is accessed from the site's home page. All queries must include at least one gene. The query shown is the one used to generate the results shown in Figs. 2 and 3.

Fig. 2. The OncoPrint tab

The example shows a visual summary of the different mechanisms of RB pathway alteration across a set of glioblastoma samples based on a query of the three genes CDKN2A, CDK4, and RB1. The OncoPrint tab summarizes genomic alterations in all queried genes across a sample set. Each row represents a gene, and each column represents a tumor sample. Red bars indicate gene amplifications, blue bars are homozygous deletions, and green squares are nonsynonymous mutations.

Fig. 3. The Mutual Exclusivity tab

The example shows that genes that alter RB signaling in glioblastoma have a tendency toward mutual exclusivity. This tab provides summary statistics on mutual exclusivity and co-occurrence of genomic alterations in each pair of query genes. In this example, all three pairs have a tendency toward mutual exclusivity. Although the CDK4-RB1 pair has the strongest tendency toward mutual exclusivity (dark blue background), the relationship is not statistically significant (P = 0.11). The mutual exclusivity is significant for the other two gene pairs (P < 0.05, red outline). The P values are determined by a Fisher's exact test with the null hypothesis that the frequency of occurrence of a pair of alterations in two genes is proportional to their uncorrelated occurrence in each gene.

Fig. 4. The Plots tab

The example shows ERBB2 mRNA expression is increased in samples with DNA amplification, and ERBB2 protein abundance is higher in samples with increased mRNA. (A) A plot showing the relationship between ERBB2 mRNA abundance and CNA in the ERBB2 gene in tumors from the selected cancer study. The “x”s indicate individual tumors, and the circles indicate tumors with missense mutations. (B) A plot showing the relationship between the abudance of the ERBB2 protein and mRNA in samples from the selected cancer study. Homdel, homozygously deleted; Hetloss, heterozygously deleted; Diploid, two alleles present; Gain, low-level gene amplification event; Amp, high-level gene amplification event; Mutated, nonsynonymous mutation; Normal, no mutation or CNA present.

Fig. 5. The Mutations tab

To generate these results, the query was limited to mutations for ERBB2 in the indicated cancer study. Four of the 10 ERBB2 mutations in colorectal cancer occur in a hotspot in the kinase domain. (A) The graphical view shows the Pfam protein domains and the positions of specific mutations. The length of the line connecting the mutation annotation to the protein is indicative of the number of samples that have the mutation. The most recurrent mutations are labeled in the graphical view. (B) The tabular view provides additional information about all mutations in each query gene.

Fig. 6. The Protein Changes tab

When available in the cancer study selected, results related to protein or phosphoprotein abundance are provided through this tab. In this example, glioblastoma (GBM) samples with alterations in PTEN have increased phosphorylated AKT. (A) Phosphoproteins with different amounts when comparing PTEN-altered samples and PTEN-wild-type samples. The list is sorted by P values from a two-sample t-test. (B) Boxplot representation of the relative amount of AKT pT308 in PTEN-altered and PTEN-wild-type samples. This plot is generated by clicking the icon in the Plot column of the tabulated data.

Fig. 7. The Survival tab

The example shows the overall survival (A) and the disease-free survival (B) of ovarian cancer patients with or without BRCA1 or BRCA2 mutations. The red curves in the Kaplan-Meier plots includes all tumors with a BRCA1 or BRCA2 germline or somatic mutation, the blue curves includes all samples without a BRCA1 or BRCA2 mutation.

Fig. 8. The Network tab

The example shows network analysis of EGFR networks in serous ovarian cancer. (A) Network view of the EGFR and ERBB2 neighborhood in serous ovarian cancer (TCGA data set) rendered with Cytoscape Web (34).The query genes, EGFR and ERBB2, are outlined with a thick border, and nearest neighbor genes are color-coded by their alteration frequency in ovarian cancer. One can display drugs that target EGFR or ERBB2 (hexagons; orange indicates FDA-approved), as well as details about genomic alterations and links to external resources for any gene in the network (bottom left, example MYC). (B) The “Gene Legend” accessed from the “Legend” button. Mousing over any gene in the network or single-clicking the gene displays multidimensional genomic data (copy number, mutation, and mRNA expression) onto all nodes in the network. (C) The “Interaction Legend” accessed from the “Legend” button. Double-clicking the edge displays additional details about the interaction between the two nodes. Edges can represent different interaction types (color-coded, such as “reacts with”). (D) Options for filtering, cropping, and searching the network are shown.

Fig. 9. Cross-cancer queries

(A) Users initiate a query against all cancer studies in three steps. (B) The results are displayed as a histogram of the alteration frequencies of the query gene (or genes) across cancer studies. The example shows that TP53 mutation frequencies are the highest in squamous cell carcinomas of ovary, lung, and head and neck.

Fig. 10. The cancer study summary view

The example shows an overview of clinical attributes and a scatter plot of mutation count versus fraction of genome altered for each case in the TCGA endometrial cancer study.

Fig. 11. The cBioPortal patient view

The example shows the relevant genomic alterations and clinical data of an endometrial cancer sample with mixed histology from the TCGA study.