DDRE-28. IDENTIFICATION OF SYNERGISTIC DRUG COMBINATIONS FOR THE THERAPY OF IDHmut GLIOMA

OBJECTIVE Isocitrate Dehydrogenase (IDH) mutation in glioma results in a multitude of biological differences with consequences for survival and therapy response. Therefore, IDH mutated (IDHmut) and wildtype (IDHwt) tumors are regarded as separate entities with the need for adjusted therapy like the combination of procarbazine, CCNU and vincristine (PCV). However, as vincristine has often severe side effects like neuropathy new effective therapy options are required. Therefore, we searched for combinations of FDA-approved drugs which effectively inhibit the growth of IDHmut cells in vitro. METHODS We tested different drug combinations of a drug library consisting of 146 FDA-approved drugs on two established IDHmut GSC lines. Based on a previous single agent drug screen, six drugs were selected (Idarubicin, Ixazumib, Ponatinib, Neratinib, Romidepsin) to be combined with all 146 drugs of the library. Cell viability was assessed by the CellTiterGlo 3D assay (Promega) in 96 well plates, while Caspase-Glo 3/7 3D assay was used to measure induction of apoptosis. RESULTS Out of 1460 drug combinations tested altogether 21 synergistic drug combinations could be identified and validated. The combination with the highest blood-brain-barrier permeability score was further investigated. Finally, drug-concentrations elucidating the highest synergistic effect on proliferation was further studied in a 8-point dose-response matrix followed by validation in additional four IDHmut GSC lines. CONCLUSION This work can lay the foundation for future improvements of the therapy of patients suffering from LGGs.

Prediction of synergistic drug combinations using PCA-initialized deep learning

Background Cancer is one of the main causes of death worldwide. Combination drug therapy has been a mainstay of cancer treatment for decades and has been shown to reduce host toxicity and prevent the development of acquired drug resistance. However, the immense number of possible drug combinations and large synergistic space makes it infeasible to screen all effective drug pairs experimentally. Therefore, it is crucial to develop computational approaches to predict drug synergy and guide experimental design for the discovery of rational combinations for therapy. Results We present a new deep learning approach to predict synergistic drug combinations by integrating gene expression profiles from cell lines and chemical structure data. Specifically, we use principal component analysis (PCA) to reduce the dimensionality of the chemical descriptor data and gene expression data. We then propagate the low-dimensional data through a neural network to predict drug synergy values. We apply our method to O’Neil’s high-throughput drug combination screening data as well as a dataset from the AstraZeneca-Sanger Drug Combination Prediction DREAM Challenge. We compare the neural network approach with and without dimension reduction. Additionally, we demonstrate the effectiveness of our deep learning approach and compare its performance with three state-of-the-art machine learning methods: Random Forests, XGBoost, and elastic net, with and without PCA-based dimensionality reduction. Conclusions Our developed approach outperforms other machine learning methods, and the use of dimension reduction dramatically decreases the computation time without sacrificing accuracy.

Deep learning identifies synergistic drug combinations for treating COVID-19

Effective treatments for COVID-19 are urgently needed. However, discovering single-agent therapies with activity against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has been challenging. Combination therapies play an important role in antiviral therapies, due to their improved efficacy and reduced toxicity. Recent approaches have applied deep learning to identify synergistic drug combinations for diseases with vast preexisting datasets, but these are not applicable to new diseases with limited combination data, such as COVID-19. Given that drug synergy often occurs through inhibition of discrete biological targets, here we propose a neural network architecture that jointly learns drug−target interaction and drug−drug synergy. The model consists of two parts: a drug−target interaction module and a target−disease association module. This design enables the model to utilize drug−target interaction data and single-agent antiviral activity data, in addition to available drug−drug combination datasets, which may be small in nature. By incorporating additional biological information, our model performs significantly better in synergy prediction accuracy than previous methods with limited drug combination training data. We empirically validated our model predictions and discovered two drug combinations, remdesivir and reserpine as well as remdesivir and IQ-1S, which display strong antiviral SARS-CoV-2 synergy in vitro. Our approach, which was applied here to address the urgent threat of COVID-19, can be readily extended to other diseases for which a dearth of chemical−chemical combination data exists.

EMBR-11. SYNERGISTIC DRUG COMBINATIONS FOR THE TREATMENT OF MYC AMPLIFIED GROUP 3 MEDULLOBLASTOMA

Background Medulloblastoma (MB) is a highly aggressive brain tumour in children. Patients with Group 3 MB harbouring a MYC-amplification (subtype II) show a particularly poor outcome despite high-intensity multimodal therapy. We and others have previously shown that MYC amplified Group 3 MB cells are highly susceptible towards treatment with class I histone deacetylase (HDAC) inhibitors such as entinostat. However, in clinical trials HDACi as a monotherapy show only modest efficacy in solid tumours. We propose to increase the efficacy of class I HDACi by drug combinations. Methods To identify synergistic drug combinations (entinostat + X) for the treatment of MYC amplified MB we performed a drug screen with a library of n=75 clinically available compounds as single agents and in combination with entinostat in n=3 MYC amplified vs. n=1 MYC-non amplified cell lines. Synergistic behaviour of the six most promising drug combinations was validated by metabolic activity assays, cell count experiments and gene expression profiling. Synergy was assessed by the Loewe additivity model using a combination of ray design and checkerboard matrix. Results The drug screen revealed n=20/75 drugs that were particularly effective (drug sensitivity score ≥10) in combination with entinostat treatment in all three MYC amplified cell lines. Synergy assessment of the top n=6 drugs confirmed strong synergistic activity with entinostat for n=2 drugs (navitoclax, irinotecan). The BCL-2 family inhibitor navitoclax showed the most robust synergy with entinostat in subsequent validation experiments. Conclusion Several drugs either clinically available or currently in clinical trials, including the BCL-2/Xl/w inhibitor navitoclax, show promising effects in a combination therapy with entinostat for the treatment of MYC amplified Group 3 MB.

DeepDDS: deep graph neural network with attention mechanism to predict synergistic drug combinations

Drug combination therapy becomes promising method in the treatment of cancer. However, the number of possible drug combinations toward cancer cell lines is too large, and it is challenging to screen synergistic drug combinations through wet-lab experiments. Therefore, the computational screening has become an important way to prioritize drug combinations. Graph attention network has recently shown strong performance in screening of compound-protein interactions, but it has not been applied to the screening of drug combinations. In this paper, we proposed a deep learning model (DeepDDS) based on graph neural networks and attention mechanism to identify drug combinations that can effectively inhibit the viability of specific cancer cell line. The graph representation of drug molecule structure and gene expression profiles is taken as input to predict the synergistic effects of drug combinations. We compare DeepDDS with traditional machine learning methods (random forest, support vector machine) and other deep learning methods (DeepSynergy, DTF) on the same data set. Our experimental results show that DeepDDS achieved best performance by the AUC value 0.93. Also, on an independent test set released by AstraZeneca, DeepDDS is superior to other comparative methods by 12.2% higher than the suboptimal method. We believe that DeepDDS is a effective tool that can prioritize synergistic drug combinations.

Matrix Drug Screen Identifies Synergistic Drug Combinations to Augment SMAC Mimetic Activity in Ovarian Cancer

Inhibitor of apoptosis (IAP) proteins are frequently upregulated in ovarian cancer, resulting in the evasion of apoptosis and enhanced cellular survival. Birinapant, a synthetic second mitochondrial activator of caspases (SMAC) mimetic, suppresses the functions of IAP proteins in order to enhance apoptotic pathways and facilitate tumor death. Despite on-target activity, however, pre-clinical trials of single-agent birinapant have exhibited minimal activity in the recurrent ovarian cancer setting. To augment the therapeutic potential of birinapant, we utilized a high-throughput screening matrix to identify synergistic drug combinations. Of those combinations identified, birinapant plus docetaxel was selected for further evaluation, given its remarkable synergy both in vitro and in vivo. We showed that this synergy results from multiple convergent pathways to include increased caspase activation, docetaxel-mediated TNF-α upregulation, alternative NF-kB signaling, and birinapant-induced microtubule stabilization. These findings provide a rationale for the integration of birinapant and docetaxel in a phase 2 clinical trial for recurrent ovarian cancer where treatment options are often limited and minimally effective.

The repurposed drugs suramin and quinacrine inhibit cooperatively in vitro SARS-CoV-2 3CLpro

Since the first report of a new pneumonia disease in December 2019 (Wuhan, China) up to now WHO reported more than 50 million confirmed cases and more than one million losses, globally. The causative agent of COVID-19 (SARS-CoV-2) has spread worldwide resulting in a pandemic of unprecedented magnitude. To date, no clinically safe drug or vaccine is available and the development of molecules to combat SARS-CoV-2 infections is imminent. A well-known strategy to identify molecules with inhibitory potential against SARS-CoV-2 proteins is the repurposing of clinically developed drugs, e.g., anti-parasitic drugs. The results described in this study demonstrate the inhibitory potential of quinacrine and suramin against SARS-CoV-2 main protease (3CLpro). Quinacrine and suramin molecules present a competitive and non-competitive mode of inhibition, respectively, with IC50 and KD values in low μM range. Using docking and molecular dynamics simulations we identified a possible binding mode and the amino acids involved in these interactions. Our results suggested that suramin in combination with quinacrine showed promising synergistic efficacy to inhibit SARS-CoV-2 3CLpro. The identification of effective, synergistic drug combinations could lead to the design of better treatments for the COVID-19 disease. Drug repositioning offers hope to the SARS-CoV-2 control.