Essentiality and Transcriptome-Enriched Pathway Scores Predict Drug-Combination Synergy

In the prediction of the synergy of drug combinations, systems pharmacology models expand the scope of experiment screening and overcome the limitations of current computational models posed by their lack of mechanical interpretation and integration of gene essentiality. We therefore investigated the synergy of drug combinations for cancer therapies utilizing records in NCI ALMANAC, and we employed logistic regression to test the statistical significance of gene and pathway features in that interaction. We trained our predictive models using 43 NCI-60 cell lines, 165 KEGG pathways, and 114 drug pairs. Scores of drug-combination synergies showed a stronger correlation with pathway than gene features in overall trend analysis and a significant association with both genes and pathways in genome-wide association analyses. However, we observed little overlap of significant gene expressions and essentialities and no significant evidence that associated target and non-target genes and their pathways. We were able to validate four drug-combination pathways between two drug combinations, Nelarabine-Exemestane and Docetaxel-Vermurafenib, and two signaling pathways, PI3K-AKT and AMPK, in 16 cell lines. In conclusion, pathways significantly outperformed genes in predicting drug-combination synergy, and because they have very different mechanisms, gene expression and essentiality should be considered in combination rather than individually to improve this prediction.

Download Full-text

Prediction of Effective Drug Combinations by Chemical Interaction, Protein Interaction and Target Enrichment of KEGG Pathways

BioMed Research International ◽

10.1155/2013/723780 ◽

2013 ◽

Vol 2013 ◽

pp. 1-10 ◽

Cited By ~ 10

Author(s):

Lei Chen ◽

Bi-Qing Li ◽

Ming-Yue Zheng ◽

Jian Zhang ◽

Kai-Yan Feng ◽

...

Keyword(s):

Feature Selection ◽

Protein Interactions ◽

Drug Combination ◽

Molecular Mechanisms ◽

Chemical Interaction ◽

Drug Combinations ◽

Effective Drug ◽

Target Enrichment ◽

Kegg Pathways ◽

Key Features

Drug combinatorial therapy could be more effective in treating some complex diseases than single agents due to better efficacy and reduced side effects. Although some drug combinations are being used, their underlying molecular mechanisms are still poorly understood. Therefore, it is of great interest to deduce a novel drug combination by their molecular mechanisms in a robust and rigorous way. This paper attempts to predict effective drug combinations by a combined consideration of: (1) chemical interaction between drugs, (2) protein interactions between drugs’ targets, and (3) target enrichment of KEGG pathways. A benchmark dataset was constructed, consisting of 121 confirmed effective combinations and 605 random combinations. Each drug combination was represented by 465 features derived from the aforementioned three properties. Some feature selection techniques, including Minimum Redundancy Maximum Relevance and Incremental Feature Selection, were adopted to extract the key features. Random forest model was built with its performance evaluated by 5-fold cross-validation. As a result, 55 key features providing the best prediction result were selected. These important features may help to gain insights into the mechanisms of drug combinations, and the proposed prediction model could become a useful tool for screening possible drug combinations.

Download Full-text

SYNERGxDB: an integrative pharmacogenomic portal to identify synergistic drug combinations for precision oncology

Nucleic Acids Research ◽

10.1093/nar/gkaa421 ◽

2020 ◽

Vol 48 (W1) ◽

pp. W494-W501 ◽

Cited By ~ 2

Author(s):

Heewon Seo ◽

Denis Tkachuk ◽

Chantal Ho ◽

Anthony Mammoliti ◽

Aria Rezaie ◽

...

Keyword(s):

Cell Lines ◽

Cancer Cell ◽

Drug Combination ◽

Predictive Biomarkers ◽

Cancer Cell Lines ◽

Drug Combinations ◽

Drug Synergism ◽

Precision Oncology ◽

Synergistic Drug Combinations ◽

Pharmacological Profiles

Abstract Drug-combination data portals have recently been introduced to mine huge amounts of pharmacological data with the aim of improving current chemotherapy strategies. However, these portals have only been investigated for isolated datasets, and molecular profiles of cancer cell lines are lacking. Here we developed a cloud-based pharmacogenomics portal called SYNERGxDB (http://SYNERGxDB.ca/) that integrates multiple high-throughput drug-combination studies with molecular and pharmacological profiles of a large panel of cancer cell lines. This portal enables the identification of synergistic drug combinations through harmonization and unified computational analysis. We integrated nine of the largest drug combination datasets from both academic groups and pharmaceutical companies, resulting in 22 507 unique drug combinations (1977 unique compounds) screened against 151 cancer cell lines. This data compendium includes metabolomics, gene expression, copy number and mutation profiles of the cancer cell lines. In addition, SYNERGxDB provides analytical tools to discover effective therapeutic combinations and predictive biomarkers across cancer, including specific types. Combining molecular and pharmacological profiles, we systematically explored the large space of univariate predictors of drug synergism. SYNERGxDB constitutes a comprehensive resource that opens new avenues of research for exploring the mechanism of action for drug synergy with the potential of identifying new treatment strategies for cancer patients.

Download Full-text

Drug Combinations targeting multiple cellular mechanisms enable axonal regeneration from crushed optic nerve into the brain

10.1101/157099 ◽

2017 ◽

Cited By ~ 1

Author(s):

Mustafa M. Siddiq ◽

Yana Zorina ◽

Arjun Yadaw ◽

Jens Hansen ◽

Vera Rabinovich ◽

...

Keyword(s):

Optic Nerve ◽

Drug Treatment ◽

Cell Body ◽

Drug Combination ◽

Axonal Regeneration ◽

Computational Models ◽

Drug Combinations ◽

Systems Pharmacology ◽

Injury Site ◽

The Brain

Injured central nervous system (CNS) axons do not regenerate, due to lack of intrinsic capacity of the neurons and the inhibitory environment at the injury site. Currently, there are no drugs or drug combinations to promote axonal regeneration in the injured spinal cord or optic nerve. We used a systems pharmacology approach to develop a four-drug combination with the potential to increase neuronal capacity by regulating multiple subcellular processes at the cell body to trigger long neurites in inhibitory environments. Dynamical computational models of neurite outgrowth showed that the transcriptional effects of drugs applied at the cell body when combined with drugs that work locally near the site of the injured axons could produce extensive synergistic growth. We used the optic nerve crush in rats to test the drug combinations. We intravitreally injected two drugs, HU-210 (cannabinoid receptor-1 agonist) and IL-6 (interleukin 6 receptor agonist) to stimulate retinal ganglion cells (RGCs) whose axons had been crushed, and applied two drugs in gel foam, taxol to stabilize microtubules and activated protein C (APC) to potentially clear the injury site debris field. Morphology experiments using the injured optic nerve show that the four-drug combination promotes robust axonal regeneration from the RGC to the chiasm. Electrophysiologically the four-drug treatment restored pattern electroretinograms (pERG), and about 25% of the animals had detectable visual evoked potentials (VEP) in the brain. We conclude that systems pharmacology-based drug treatment can promote functional axonal regeneration after nerve injury.

Download Full-text

A high-throughput drug combination screen of targeted small molecule inhibitors in cancer cell lines

Scientific Data ◽

10.1038/s41597-019-0255-7 ◽

2019 ◽

Vol 6 (1) ◽

Cited By ~ 5

Author(s):

Åsmund Flobak ◽

Barbara Niederdorfer ◽

Vu To Nakstad ◽

Liv Thommesen ◽

Geir Klinkenberg ◽

...

Keyword(s):

Signal Transduction ◽

Cell Viability ◽

Cell Lines ◽

Cancer Cell ◽

Drug Combination ◽

Cancer Cell Lines ◽

Drug Combinations ◽

Clinical Investigations ◽

Transduction Mechanisms ◽

Targeting Signal

Abstract While there is a high interest in drug combinations in cancer therapy, openly accessible datasets for drug combination responses are sparse. Here we present a dataset comprising 171 pairwise combinations of 19 individual drugs targeting signal transduction mechanisms across eight cancer cell lines, where the effect of each drug and drug combination is reported as cell viability assessed by metabolic activity. Drugs are chosen by their capacity to specifically interfere with well-known signal transduction mechanisms. Signalling processes targeted by the drugs include PI3K/AKT, NFkB, JAK/STAT, CTNNB1/TCF, and MAPK pathways. Drug combinations are classified as synergistic based on the Bliss independence synergy metrics. The data identifies combinations that synergistically reduce cancer cell viability and that can be of interest for further pre-clinical investigations.

Download Full-text

GraphSynergy: Network Inspired Deep Learning Model for Anti–Cancer Drug Combination Prediction

10.21203/rs.3.rs-315189/v1 ◽

2021 ◽

Author(s):

Jiannan Yang ◽

Zhongzhi Xu ◽

William Wu ◽

Qian Chu ◽

Qingpeng Zhang

Keyword(s):

Deep Learning ◽

Cell Lines ◽

Cancer Cell ◽

Drug Combination ◽

Drug Combinations ◽

Cancer Drug ◽

Ppi Network ◽

Convolutional Network ◽

Anti Cancer ◽

Protein Modules

Abstract Compared with monotherapy, anti-cancer drug combination can provide effective therapy with less toxicity in cancer treatment. Recent studies found that the topological positions of protein modules related to the drugs and the cancer cell lines in the protein-protein interaction (PPI) network may reveal the effects of drugs. However, due to the size of the combinatorial space, identifying synergistic combinations of drugs from PPI network is computationally difficult. To address this challenge, we propose an end-to-end deep learning framework, namely Graph Convolutional Network for Drug Synergy (GraphSynergy), to make synergistic drug combination predictions. GraphSynergy adapts a spatial-based Graph Convolutional Network component to encode the high-order structure information of protein modules targeted by a pair of drugs, as well as the protein modules associated with a specific cancer cell line in the PPI network. The pharmacological effects of drug combinations are explicitly evaluated by their therapy and toxic scores. By introducing an attention component to automatically allocate contribution weights to the proteins, we show the ability of GraphSynergy to capture the pivotal proteins that play a part in both PPI network and biomolecular interactions between drug combinations and cancer cell lines. Experiments on two latest drug combination datasets demonstrate that GraphSynergy outperforms the state-of-the-art in predicting synergistic drug combinations. This study sheds light on using machine learning to discover effective combination therapies for cancer and other complex diseases.

Download Full-text

DSCN: double-target selection guided by CRISPR screening and network

10.1101/2021.09.06.459081 ◽

2021 ◽

Author(s):

Enze Liu ◽

Xue Wu ◽

Lei Wang ◽

Yang Huo ◽

Huanmei Wu ◽

...

Keyword(s):

Cell Lines ◽

Drug Combinations ◽

Superior Performance ◽

Cancer Therapies ◽

Omics Data ◽

Ppi Network ◽

Pancreatic Cell ◽

Single Target ◽

Target Combination ◽

Selection Of

AbstractCancer is a complex disease with usually multiple disease mechanisms. Target combination is a better strategy than a single target in developing cancer therapies. However, target combinations are generally more difficult to be predicted. Current CRISPR-cas9 technology enables genome-wide screening for potential targets, but only a handful of genes have been screend as target combinations. Thus, an effective computational approach for selecting candidate target combinations is highly desirable. Selected target combinations also need to be translational between cell lines and cancer patients.We have therefore developed DSCN (double-target selection guided by CRISPR screening and network), a method that matches expression levels in patients and gene essentialities in cell lines through spectral-clustered protein-protein interaction (PPI) network. In DSCN, a sub-sampling approach is developed to model first-target knockdown and its impact on the PPI network, and it also facilitates the selection of a second target. Our analysis first demonstrated high correlation of the DSCN sub-sampling-based gene knockdown model and its predicted differential gene expressions using observed gene expression in 22 pancreatic cell lines before and after MAP2K1 and MAP2K2 inhibition (R2 = 0.75). In our DSCN algorithm, various scoring schemes were evaluated. The ‘diffusion-path’ method showed the most significant statistical power of differentialting known synthetic lethal (SL) versus non-SL gene pairs (P = 0.001) in pancreatic cancer. The superior performance of DSCN over existing network-based algorithms, such as OptiCon[1] and VIPER[2], in the selection of target combinations is attributable to its ability to calculate combinations for any gene pairs, whereas other approaches focus on the combinations among optimized regulators in the network. DSCN’s computational speed is also at least ten times faster than that of other methods. Finally, in applying DSCN to predict target combinations and drug combinations for individual samples (DSCNi), we showed high correlation of DSCNi predicted target combinations with synergistic drug combinations (P = 1e-5) in pancreatic cell lines. In summary, DSCN is a highly effective computational method for the selection of target combinations.Author SummaryCancer therapies require targets to function. Compared to single target, target combination is a better strategy for developing cancer therapies. However, predicting target combination is much complicated than predicting single target. Current CRISPR technology enables whole genome screening of potential targets. But most of the experiments have been conducted on single target (gene) level. To facilitate the prediction of target combinations, we developed DSCN (double-target selection guided by CRISPR screening and network) that utilize single target-level CRISPR screening data and expression profiles for predicting target combinations by connecting cell-line omics-data with tissue omics-data. DSCN showed great accuracy on different cancer types and superior performance compared to existing network-based prediction tools. We also introduced DSCNi derived from DSCN and designed specific for predicting target combinations for single-paitent. We showed synergistic target combinations predicted by DSCNi accurately reflected synergies on drug combination levels. Thus, DSCN and DSCNi have the potential be further applied in personalized medicine field.

Download Full-text

Predicting Tumor Cell Response to Synergistic Drug Combinations Using a Novel Simplified Deep Learning Model

10.1101/2020.04.10.036491 ◽

2020 ◽

Author(s):

Heming Zhang ◽

Jiarui Feng ◽

Amanda Zeng ◽

Philip Payne ◽

Fuhai Li

Keyword(s):

Deep Learning ◽

Signaling Pathways ◽

Drug Combination ◽

Computational Models ◽

Learning Model ◽

Drug Combinations ◽

Small Set ◽

Novel Drug ◽

Deep Learning Model ◽

Synergistic Drug Combinations

AbstractDrug combinations targeting multiple targets/pathways are believed to be able to reduce drug resistance. Computational models are essential for novel drug combination discovery. In this study, we proposed a new simplified deep learning model, DeepSignalingSynergy, for drug combination prediction. Compared with existing models that use a large number of chemical-structure and genomics features in densely connected layers, we built the model on a small set of cancer signaling pathways, which can mimic the integration of multi-omics data and drug target/mechanism in a more biological meaningful and explainable manner. The evaluation results of the model using the NCI ALMANAC drug combination screening data indicated the feasibility of drug combination prediction using a small set of signaling pathways. Interestingly, the model analysis suggested the importance of heterogeneity of the 46 signaling pathways, which indicates that some new signaling pathways should be targeted to discover novel synergistic drug combinations.

Download Full-text

Secdrug: A Computational Method for Discovering Novel Secondary Drug Combinations Using Large-Scale Pharmacogenomics Databases

Blood ◽

10.1182/blood-2018-99-117653 ◽

2018 ◽

Vol 132 (Supplement 1) ◽

pp. 4473-4473

Author(s):

Li Chen ◽

Ujjal Kumar Mukherjee ◽

Emily Rankine ◽

Brian G. Van Ness ◽

Amit Kumar Mitra

Keyword(s):

Drug Resistance ◽

B Cell ◽

Cell Lines ◽

Cancer Cell ◽

Cancer Chemotherapy ◽

Drug Combination ◽

Large Scale ◽

Drug Sensitivity ◽

Drug Combinations ◽

Test Drug

Abstract Drug resistance is a major obstacle in achieving complete and sustained therapeutic effect in cancer chemotherapy. Chemo-resistance may also lead to over-dosing and unwanted exposure to ineffective anti-tumor agents thereby increasing the risk of negative side-effects and the cost of drug development. Therefore, our goal is to utilize a large-scale pharmacogenomics database (Genomics of Drug Sensitivity in Cancer or GDSC, the largest public resource of drug-sensitivity data on over 250 drugs in more than 1000 human cancer cell lines of common and rare types of adult and childhood cancers of diverse origin) and develop a prediction method to identify novel secondary drug combination regimens that may effectively reverse drug resistance. We utilized a greedy algorithm-based set-covering computational optimization method followed by a regularization technique to seek all secondary drugs that could kill maximum number of cell lines of the test disease (B-Cell cancers) resistant to the test drug (the Proteasome inhibitor/PI drug Bortezomib/Bz/Velcade) in a sequential manner ordered by the number of cell lines killed. The predicted top secondary drug combinations in PI-resistant B-cell cancers are shown in Figure 1. To validate our prediction results, we treated human multiple myeloma cell lines (HMCLs) highly resistant to the proteasome inhibitors Bortezomib, Carfilzomob, Oprozomib and Ixazomib with the predicted best secondary drugs. Figure 2 depicts In vitro chemo-sensitivity profiles of PI-resistant HMCLs and other B-cell cancer cell lines showing percent survival compared to untreated control at increasing concentrations of secondary drugs, as single agents or in combination. Furthermore, for each drug in the predicted drug combination, we identified differentially expressed (DE) genes by comparing the expression profiles between extraordinary- sensitive and resistant cell lines. These significantly regulated DE genes were used to identify pathways associated with the successful drug combinations. Finally, we developed an R software package secDrug based on this computational pipeline for predicting novel secondary therapies in chemotherapy-resistant cancers. secDrug takes a query of any cancer type and any test drug, and outputs a list of the top secondary drug combinations with confidence score and biological pathway visualization. Thus, secDrug has potential application in clinical decision-making for discovering resistance-reversing cancer chemotherapy regimens. Disclosures No relevant conflicts of interest to declare.

Download Full-text

Identifying biomarkers of anti-cancer drug synergy using multi-task learning

10.1101/243568 ◽

2018 ◽

Cited By ~ 2

Author(s):

Nanne Aben ◽

Julian R. de Ruiter ◽

Evert Bosdriesz ◽

Yongsoo Kim ◽

Gergana Bounova ◽

...

Keyword(s):

Breast Cancer ◽

Sample Size ◽

Cell Lines ◽

Drug Combination ◽

Pi3k Pathway ◽

Drug Combinations ◽

Task Learning ◽

Main Challenge ◽

Anti Cancer ◽

Dual Inhibitors

AbstractCombining anti-cancer drugs has the potential to increase treatment efficacy. Because patient responses to drug combinations are highly variable, predictive biomarkers of synergy are required to identify which patients are likely to benefit from a drug combination. To aid biomarker identification, the DREAM challenge consortium has recently released data from a screen containing 85 cell lines and 167 drug combinations. The main challenge of these data is the low sample size: per drug combination, a median of 14 cell lines have been screened. We found that widely used methods in single drug response prediction, such as Elastic Net regression per drug, are not predictive in this setting. Instead, we propose to use multi-task learning: training a single model simultaneously on all drug combinations, which we show results in increased predictive performance. In contrast to other multi-task learning approaches, our approach allows for the identification of biomarkers, by using a modified random forest variable importance score, which we illustrate using artificial data and the DREAM challenge data. Notably, we find that mutations in MYO15A are associated with synergy between ALK / IGFR dual inhibitors and PI3K pathway inhibitors in triple-negative breast cancer.Author summaryCombining drugs is a promising strategy for cancer treatment. However, it is often not known which patients will benefit from a particular drug combination. To identify patients that are likely to benefit, we need to identify biomarkers, such as mutations in the tumor’s DNA, that are associated with favorable response to the drug combination. In this work, we identified such biomarkers using the drug combination data released by the DREAM challenge consortium, which contain 85 tumor cell lines and 167 drug combinations. The main challenge of these data is the extremely low sample size: a median of 14 cell lines have been screened per drug combination. We found that traditional methods to identify biomarkers for monotherapy response, which analyze each drug separately, are not suitable in this low sample size setting. Instead, we used a technique called multi-task learning to jointly analyze all drug combinations in a single statistical model. In contrast to existing multi-task learning algorithms, which are black-box methods, our method allows for the identification of biomarkers. Notably, we find that, in a subset of breast cancer cell lines, MYO15A mutations associate with response to the combination of ALK / IGFR dual inhibitors and PI3K pathway inhibitors.

Download Full-text

Discovering Synergistic Drug Combination from a Computational Perspective

Current Topics in Medicinal Chemistry ◽

10.2174/1568026618666180330141804 ◽

2018 ◽

Vol 18 (12) ◽

pp. 965-974 ◽

Cited By ~ 3

Author(s):

Pingjian Ding ◽

Jiawei Luo ◽

Cheng Liang ◽

Qiu Xiao ◽

Buwen Cao ◽

...

Keyword(s):

Computational Methods ◽

Drug Combination ◽

Computational Models ◽

Rapid Development ◽

Drug Combinations ◽

Effective Drug ◽

In Vitro Method ◽

Feature Based ◽

Synergistic Drug Combinations

Synergistic drug combinations play an important role in the treatment of complex diseases. The identification of effective drug combination is vital to further reduce the side effects and improve therapeutic efficiency. In previous years, in vitro method has been the main route to discover synergistic drug combinations. However, many limitations of time and resource consumption lie within the in vitro method. Therefore, with the rapid development of computational models and the explosive growth of large and phenotypic data, computational methods for discovering synergistic drug combinations are an efficient and promising tool and contribute to precision medicine. It is the key of computational methods how to construct the computational model. Different computational strategies generate different performance. In this review, the recent advancements in computational methods for predicting effective drug combination are concluded from multiple aspects. First, various datasets utilized to discover synergistic drug combinations are summarized. Second, we discussed feature-based approaches and partitioned these methods into two classes including feature-based methods in terms of similarity measure, and feature-based methods in terms of machine learning. Third, we discussed network-based approaches for uncovering synergistic drug combinations. Finally, we analyzed and prospected computational methods for predicting effective drug combinations.

Download Full-text