Prediction of individualized therapeutic vulnerabilities in cancer from genomic profiles

Abstract

Motivation: Somatic homozygous deletions of chromosomal regions in cancer, while not necessarily oncogenic, may lead to therapeutic vulnerabilities specific to cancer cells compared with normal cells. A recently reported example is the loss of one of the two isoenzymes in glioblastoma cancer cells such that the use of a specific inhibitor selectively inhibited growth of the cancer cells, which had become fully dependent on the second isoenzyme. We have now made use of the unprecedented conjunction of large-scale cancer genomics profiling of tumor samples in The Cancer Genome Atlas (TCGA) and of tumor-derived cell lines in the Cancer Cell Line Encyclopedia, as well as the availability of integrated pathway information systems, such as Pathway Commons, to systematically search for a comprehensive set of such epistatic vulnerabilities.

Results: Based on homozygous deletions affecting metabolic enzymes in 16 TCGA cancer studies and 972 cancer cell lines, we identified 4104 candidate metabolic vulnerabilities present in 1019 tumor samples and 482 cell lines. Up to 44% of these vulnerabilities can be targeted with at least one Food and Drug Administration-approved drug. We suggest focused experiments to test these vulnerabilities and clinical trials based on personalized genomic profiles of those that pass preclinical filters. We conclude that genomic profiling will in the future provide a promising basis for network pharmacology of epistatic vulnerabilities as a promising therapeutic strategy.

Availability and implementation: A web-based tool for exploring all vulnerabilities and their details is available at http://cbio.mskcc.org/cancergenomics/statius/ along with supplemental data files.

Fig. 1.

Deletions often result in the loss of a locus (horizontal bars) that often contains multiple genes. These deletions can sometimes cause loss of a metabolic gene as a passenger event. This type of alterations are not lethal to a cell if another gene can sufficiently carry the load of the deleted metabolic gene, but the loss of these passenger genes may create therapeutic vulnerabilities in tumors

Fig. 2.

Overall process of identification of therapeutic vulnerabilities. Statius imports cancer genomics data provided by the cBioPortal (Cerami et al., 2012; Gao et al., 2013), along with pathway and drug annotations from a customizable list of external resources. It then produces a list of sample-specific vulnerabilities categorized by the cancer study as output. These potential vulnerabilities can be further tested in cell lines bearing the vulnerability of interest

Fig. 3.

Systematic screening of cancer samples revealed metabolic vulnerabilities that are of therapeutic interest in a uniform way across different cancer types. (a) Across 16 cancer studies, we identified 4101 vulnerabilities. (b) We screened 5971 samples (972 cell lines and 4999 tumor samples) and found 1019 tumor samples and 482 cancer cell lines to have possible metabolic vulnerabilities (red). (c) All vulnerabilities were attributable to 263 distinct homozygous deletion events; 156 (60%) of these deletions were shared between at least one cell line and one tumor sample. (d) Forty-four percent of all identified vulnerabilities can potentially be targeted with an FDA-approved drug (green) and furthermore 8% with an FDA-approved drug that is currently known to be used in cancer therapy (orange)

Fig. 4.

Four vulnerabilities, with different contexts, identified in the ovarian serous cystadenocarcinoma (TCGA) cancer study. Each vulnerability is associated with a sample and a metabolic context. Furthermore, for each vulnerability, the gene sets are annotated to provide information whether a gene is homozygously deleted (red; HomDel), essential (black; E/G), not expressed (orange; N/E), shows tissue-specific expression (green; TS/E) or is known to be selectively targeted by a drug (gray; drugs: N). For gene sets extracted from Pathway Commons, the metabolic reaction of interest is visualized as an image that was produced by ChiBE (Babur et al., 2010)

Fig. 5.

Potential applications to personalized and/or precision cancer therapy. Our method can easily be extended to identify vulnerabilities from the genomic profile of a recently diagnosed cancer patient. The candidate vulnerabilities for this patient can then be tested on primary cell cultures or xenograft models (established from patient’s tumor sample) with drugs of interest as suggested by our analysis. Once the vulnerability is verified, ‘basket’ clinical trials can be designed to test the efficacy of the drug on patients who are predicted to have this particular vulnerability