A cancer pharmacogenomic screen powering crowd-sourced advancement of drug combination prediction

Abstract

In the last decade advances in genomics, uptake of targeted therapies, and the advent of personalized treatments have fueled a dramatic change in cancer care. However, the effectiveness of most targeted therapies is short lived, as tumors evolve and develop resistance. Combinations of drugs offer the potential to overcome resistance. The space of possible combinations is vast, and significant advances are required to effectively find optimal treatment regimens tailored to a patient's tumor. DREAM and AstraZeneca hosted a Challenge open to the scientific community aimed at computational prediction of synergistic drug combinations and predictive biomarkers associated to these combinations. We released a data set comprising ~11,500 experimentally tested drug combinations, coupled to deep molecular characterization of the respective 85 cancer cell lines. Among 150 submitted approaches, those that incorporated prior knowledge of putative drug targets showed superior performance predicting drug synergy across independent data. Genomic features of best-performing models revealed putative mechanisms of drug synergy for multiple drugs in combination with PI3K/AKT pathway inhibitors.All rights reserved. No reuse allowed without permission.(which was not peer-reviewed) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity.

The transcriptomic response of cells to a drug combination is more than the sum of the responses to the monotherapies

“…While previous research has indicated that synergy is context-specific (Held et al, 2013;Holbeck et al, 2017) , our finding that monotherapy correlation is associated with EOB in the independent DREAM dataset suggest that these mechanisms may constitute general features of synergy ( Figure 7A). Machine learning methods on cell line characteristics and drug combination features can also be effective in predicting synergy (Menden et al, 2018) . However to our knowledge, only the DREAM dataset we used has matched post-treatment expression and viability data, limiting our ability to validate our findings regarding the gene expression patterns associated with synergy in other contexts.…”

Stratification and prediction of drug synergy based on target functional similarity

“…The average synergy is computed for each target pair, as the mean of the top three synergistic drug-cell line pairs. We chose a threshold of 20 as synergistic effect, and a score lower than -20 as antagonistic effect, as in Menden et al (10).…”

“…However, gene mutation information, arguably the most actionable information in the clinic, was not used. In the recent Dialogue on Reverse-Engineering Assessment and Methods (DREAM) drug combination challenge (10), the best performing team used a protein-protein interaction network to augment the genomic features based on their network distance from drug targets. Whilst the best performer achieved outstanding predictability comparable to the level of experimental replicates, synergy was predicted based on supervised machine learning algorithms.…”

Defining subpopulations of differential drug response to reveal novel target populations

“…We next examined the drug pairs as combination therapies in cell lines 25 and patientderived tumor xenograft models (PDXs) 26 to investigate whether the drug pairs with divergent response and subpopulations with preferential sensitivity to one drug would be associated with efficacy of their combination treatment ( Figure 3C). SEABED first compared the single drug responses of BRAF, MEK and PI3K inhibitors as before to identify BRAF mutant subpopulations with differential response.…”

“…The discovery pharmacology dataset was extracted from the The Genomics of Drug Sensitivity in Cancer (GDSC) database 3,4 , while leads from the analysis were validated with the Cancer Cell Line Encyclopedia (CCLE) 5 and the Cancer Therapeutics Response Portal (CTRP) [6][7][8] . Furthermore, suggested drug combinations were validated with cell line responses from the AstraZeneca-DREAM challenge dataset 25 and patient derived xenograft (PDX) models from Gao et al 26 .…”