Synergy from gene expression and network mining (SynGeNet) method predicts synergistic drug combinations for diverse melanoma genomic subtypes

Abstract

Systems biology perspectives are crucial for understanding the pathophysiology of complex diseases, and therefore hold great promise for the discovery of novel treatment strategies. Drug combinations have been shown to improve durability and reduce resistance to available first-line therapies in a variety of cancers; however, traditional drug discovery approaches are prohibitively cost and labor-intensive to evaluate large-scale matrices of potential drug combinations. Computational methods are needed to efficiently model complex interactions of drug target pathways and identify mechanisms underlying drug combination synergy. In this study, we employ a computational approach, SynGeNet (Synergy from Gene expression and Network mining), which integrates transcriptomics-based connectivity mapping and network centrality analysis to analyze disease networks and predict drug combinations. As an exemplar of a disease in which combination therapies demonstrate efficacy in genomic-specific contexts, we investigate malignant melanoma. We employed SynGeNet to generate drug combination predictions for each of the four major genomic subtypes of melanoma (BRAF, NRAS, NF1, and triple wild type) using publicly available gene expression and mutation data. We validated synergistic drug combinations predicted by our method across all genomic subtypes using results from a high-throughput drug screening study across. Finally, we prospectively validated the drug combination for BRAF -mutant melanoma that was top ranked by our approach, vemurafenib (BRAF inhibitor) + tretinoin (retinoic acid receptor agonist), using both in vitro and in vivo models of BRAF -mutant melanoma and RNA-sequencing analysis of drug-treated melanoma cells to validate the predicted mechanisms. Our approach is applicable to a wide range of disease domains, and, importantly, can model disease-relevant protein subnetworks in precision medicine contexts.

High dimensional model representation of log-likelihood ratio: binary classification with expression data

“…MTM efficiently takes advantage of information in the data and is computationally fast. This is in contrast to several recent pipelines proposed for analyzing gene-pairs that are rather computationally intensive or may rely on large datasets (see [4,5,[7][8][9][10] for examples).…”

“…for some w 0 , w f , w f ,f ∈ R. In case of dependent features, we still assume the second order HDMR expansion follows a structure similar to (4), except that the coefficients w f , w f ,f are different than the independent case. Now, consider a binary classification problem with class labels y = 0, 1 and feature index set F. Let X be a random unlabeled observation with true label y x .…”

“…However, two general themes of the recent method developments are leveraging big data, such as the cancer genome atlas (TCGA), or taking advantage of side information such as sets of co-mutated genes or disease protein subnetworks, e.g. [4,5]. Such information may not be readily available or may not be easily applicable to the current dataset, as cancer gene interactions are highly context dependent [6].…”

A systems pharmacology approach to determine the mechanisms of action of pleiotropic natural products in breast cancer from transcriptome data

“…Additionally, given the poly-pharmacologic properties found here, simulations on the effect of different combinations to determine synergistic and antagonistic combinations and side-effects would provide more information. Regan-Fendt et al 66 recently developed a computational drug combination analysis using transcriptome data and disease specific root genes for malignant melanoma and successfully predicted vemurafenib and tretinoin as synergistic therapeutic combinations. Variants of this approach, for instance, modelling the active drug subnetworks using deep learning, could be applied to systematically predict combinations and side-effects for precision medicine applications in complex diseases 40, 45 .…”

Exploring the druggable space around the Fanconi anemia pathway using machine learning and mechanistic models

“…However, training the system with expression in normal tissue is a quite general approach than could be complemented with other potentially interesting data. For example, the Connectivity Map [91] contains 1 million profiles of cell liens treated with different drugs and has been successfully used for drug repurposing using network analysis [92].…”