Predicting cooperative drug effects through the quantitative cellular profiling of response to individual drugs

Antimalarial Drug Combination Predictions Using the Machine Learning Synergy Predictor (MLSyPred©) tool

PURPOSE

Antimalarial drug resistance is a global public health problem that leads to treatment failure. Synergistic drug combinations can improve treatment outcomes and delay the development of drug resistance. Here, we describe the implementation of a freely available computational tool, Machine Learning Synergy Predictor (MLSyPred©), to predict potential synergy in antimalarial drug combinations.

METHODS

The MLSyPred© synergy prediction method extracts molecular fingerprints from the drugs' biochemical structures to use as features and also cleans and prepares the raw data. Five machine learning algorithms (Logistic Regression, Random Forest, Support vector machine, Ada Boost, and Gradient Boost) were implemented to build prediction models. Implementation and application of the MLSyPred© tool were tested using datasets from 1540 combinations of 79 drugs and compounds biologically evaluated in pairs for three strains of Plasmodium falciparum (3D7, HB3, and Dd2).

RESULTS

The best prediction models were obtained using Logistic Regression for antimalarials with the strains Dd2 and HB3 (0.81 and 0.70 AUC, respectively) and Random Forest for antimalarials with 3D7 (0.69 AUC). The MLSyPred© tool yielded 45% precision for synergistically predicted antimalarial drug combinations that were annotated and biologically validated, thus confirming the functionality and applicability of the tool.

CONCLUSION

 The MLSyPred© tool is freely available and represents a promising strategy for discovering potential synergistic drug combinations for further development as novel antimalarial therapies.

CCSynergy: an integrative deep-learning framework enabling context-aware prediction of anti-cancer drug synergy

Combination therapy is a promising strategy for confronting the complexity of cancer. However, experimental exploration of the vast space of potential drug combinations is costly and unfeasible. Therefore, computational methods for predicting drug synergy are much needed for narrowing down this space, especially when examining new cellular contexts. Here, we thus introduce CCSynergy, a flexible, context aware and integrative deep-learning framework that we have established to unleash the potential of the Chemical Checker extended drug bioactivity profiles for the purpose of drug synergy prediction. We have shown that CCSynergy enables predictions of superior accuracy, remarkable robustness and improved context generalizability as compared to the state-of-the-art methods in the field. Having established the potential of CCSynergy for generating experimentally validated predictions, we next exhaustively explored the untested drug combination space. This resulted in a compendium of potentially synergistic drug combinations on hundreds of cancer cell lines, which can guide future experimental screens.

MatchMaker: A Deep Learning Framework for Drug Synergy Prediction

Drug combination therapies have been a viable strategy for the treatment of complex diseases such as cancer due to increased efficacy and reduced side effects. However, experimentally validating all possible combinations for synergistic interaction even with high-throughout screens is intractable due to vast combinatorial search space. Computational techniques can reduce the number of combinations to be evaluated experimentally by prioritizing promising candidates. We present MatchMaker that predicts drug synergy scores using drug chemical structure information and gene expression profiles of cell lines in a deep learning framework. For the first time, our model utilizes the largest known drug combination dataset to date, DrugComb. We compare the performance of MatchMaker with the state-of-the-art models and observe up to  ∼ 15% correlation and  ∼ 33% mean squared error (MSE) improvements over the next best method. We investigate the cell types and drug pairs that are relatively harder to predict and present novel candidate pairs. MatchMaker is built and available at https://github.com/tastanlab/matchmaker.

Network-based drug sensitivity prediction

Background

Drug sensitivity prediction and drug responsive biomarker selection on high-throughput genomic data is a critical step in drug discovery. Many computational methods have been developed to serve this purpose including several deep neural network models. However, the modular relations among genomic features have been largely ignored in these methods. To overcome this limitation, the role of the gene co-expression network on drug sensitivity prediction is investigated in this study.

Methods

In this paper, we first introduce a network-based method to identify representative features for drug response prediction by using the gene co-expression network. Then, two graph-based neural network models are proposed and both models integrate gene network information directly into neural network for outcome prediction. Next, we present a large-scale comparative study among the proposed network-based methods, canonical prediction algorithms (i.e., Elastic Net, Random Forest, Partial Least Squares Regression, and Support Vector Regression), and deep neural network models for drug sensitivity prediction. All the source code and processed datasets in this study are available at https://github.com/compbiolabucf/drug-sensitivity-prediction.

Results

In the comparison of different feature selection methods and prediction methods on a non-small cell lung cancer (NSCLC) cell line RNA-seq gene expression dataset with 50 different drug treatments, we found that (1) the network-based feature selection method improves the prediction performance compared to Pearson correlation coefficients; (2) Random Forest outperforms all the other canonical prediction algorithms and deep neural network models; (3) the proposed graph-based neural network models show better prediction performance compared to deep neural network model; (4) the prediction performance is drug dependent and it may relate to the drug’s mechanism of action.

Conclusions

Network-based feature selection method and prediction models improve the performance of the drug response prediction. The relations between the genomic features are more robust and stable compared to the correlation between each individual genomic feature and the drug response in high dimension and low sample size genomic datasets.

DIGREM: an integrated web-based platform for detecting effective multi-drug combinations

MOTIVATION

Synergistic drug combinations are a promising approach to achieve a desirable therapeutic effect in complex diseases through the multi-target mechanism. However, in vivo screening of all possible multi-drug combinations remains cost-prohibitive. An effective and robust computational model to predict drug synergy in silico will greatly facilitate this process.

RESULTS

We developed DIGREM (Drug-Induced Genomic Response models for identification of Effective Multi-drug combinations), an online tool kit that can effectively predict drug synergy. DIGREM integrates DIGRE, IUPUI_CCBB, gene set-based and correlation-based models for users to predict synergistic drug combinations with dose-response information and drug-treated gene expression profiles.

AVAILABILITY AND IMPLEMENTATION

http://lce.biohpc.swmed.edu/drugcombination.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Driver network as a biomarker: systematic integration and network modeling of multi-omics data to derive driver signaling pathways for drug combination prediction

Motivation

Drug combinations that simultaneously suppress multiple cancer driver signaling pathways increase therapeutic options and may reduce drug resistance. We have developed a computational systems biology tool, DrugComboExplorer, to identify driver signaling pathways and predict synergistic drug combinations by integrating the knowledge embedded in vast amounts of available pharmacogenomics and omics data.

Results

This tool generates driver signaling networks by processing DNA sequencing, gene copy number, DNA methylation and RNA-seq data from individual cancer patients using an integrated pipeline of algorithms, including bootstrap aggregating-based Markov random field, weighted co-expression network analysis and supervised regulatory network learning. It uses a systems pharmacology approach to infer the combinatorial drug efficacies and synergy mechanisms through drug functional module-induced regulation of target expression analysis. Application of our tool on diffuse large B-cell lymphoma and prostate cancer demonstrated how synergistic drug combinations can be discovered to inhibit multiple driver signaling pathways. Compared with existing computational approaches, DrugComboExplorer had higher prediction accuracy based on in vitro experimental validation and probability concordance index. These results demonstrate that our network-based drug efficacy screening approach can reliably prioritize synergistic drug combinations for cancer and uncover potential mechanisms of drug synergy, warranting further studies in individual cancer patients to derive personalized treatment plans.

Availability and implementation

DrugComboExplorer is available at https://github.com/Roosevelt-PKU/drugcombinationprediction.

Supplementary information

Supplementary data are available at Bioinformatics online.

Immunofluorescence can assess the efficacy of mTOR pathway therapeutic agent Everolimus in breast cancer models

When breast cancer patients start to exhibit resistance to hormonal therapy or chemotherapy, the mTOR inhibitor everolimus can be considered as an alternative therapeutic agent. Everolimus can deregulate the PI3K/AKT/mTOR pathway and affect a range of cellular functions. In some patients, the agent does not exhibit the desired efficacy and, even worse, not without the associated side effects. This study assessed the use of immunofluorescence (IF) as a modality to fill this unmet need of predicting the efficacy of everolimus prior to administration. Cell viability and MTT assays based on IF intensities of pho-4EBP1 Thr37/46 and pho-S6K1 Ser424 on breast cancer cells (Hs578T, MCF7, BT474, MDA-MB-231) and patient-derived cell culture from metastatic sites (ABC-82T and ABC-16TX1) were interrogated. Results show that independent pho-4EBP1 Thr37/46 and pho-S6K1 Ser424 IF expressions can classify data into different groups: everolimus sensitive and resistant. The combined IF baseline intensity of these proteins is predictive of the efficacy of everolimus, and their intensities change dynamically when cells are resistant to everolimus. Furthermore, mTOR resistance is not only consequence of the AKT/mTOR pathway but also through the LKB1 or MAPK/ERK pathway. The LKB1 and pho-GSK3β may also be potential predictive markers for everolimus.

A Comprehensive Survey of Tools and Software for Active Subnetwork Identification

A recent focus of computational biology has been to integrate the complementary information available in molecular profiles as well as in multiple network databases in order to identify connected regions that show significant changes under different conditions. This allows for capturing dynamic and condition-specific mechanisms of the underlying phenomena and disease stages. Here we review 22 such integrative approaches for active module identification published over the last decade. This article only focuses on tools that are currently available for use and are well-maintained. We compare these methods focusing on their primary features, integrative abilities, network structures, mathematical models, and implementations. We also provide real-world scenarios in which these methods have been successfully applied, as well as highlight outstanding challenges in the field that remain to be addressed. The main objective of this review is to help potential users and researchers to choose the best method that is suitable for their data and analysis purpose.

Biomolecular Network-Based Synergistic Drug Combination Discovery

Drug combination is a powerful and promising approach for complex disease therapy such as cancer and cardiovascular disease. However, the number of synergistic drug combinations approved by the Food and Drug Administration is very small. To bridge the gap between urgent need and low yield, researchers have constructed various models to identify synergistic drug combinations. Among these models, biomolecular network-based model is outstanding because of its ability to reflect and illustrate the relationships among drugs, disease-related genes, therapeutic targets, and disease-specific signaling pathways as a system. In this review, we analyzed and classified models for synergistic drug combination prediction in recent decade according to their respective algorithms. Besides, we collected useful resources including databases and analysis tools for synergistic drug combination prediction. It should provide a quick resource for computational biologists who work with network medicine or synergistic drug combination designing.

Computational discovery of transcription factors associated with drug response

This study integrates gene expression, genotype and drug response data in lymphoblastoid cell lines with transcription factor (TF)-binding sites from ENCODE (Encyclopedia of Genomic Elements) in a novel methodology that elucidates regulatory contexts associated with cytotoxicity. The method, GENMi (Gene Expression iN the Middle), postulates that single-nucleotide polymorphisms within TF-binding sites putatively modulate its regulatory activity, and the resulting variation in gene expression leads to variation in drug response. Analysis of 161 TFs and 24 treatments revealed 334 significantly associated TF-treatment pairs. Investigation of 20 selected pairs yielded literature support for 13 of these associations, often from studies where perturbation of the TF expression changes drug response. Experimental validation of significant GENMi associations in taxanes and anthracyclines across two triple-negative breast cancer cell lines corroborates our findings. The method is shown to be more sensitive than an alternative, genome-wide association study-based approach that does not use gene expression. These results demonstrate the utility of GENMi in identifying TFs that influence drug response and provide a number of candidates for further testing.

A simple gene set-based method accurately predicts the synergy of drug pairs

Background

The advance in targeted therapy has greatly increased the effectiveness of clinical cancer therapy and reduced the cytotoxicity of treatments to normal cells. However, patients still suffer from cancer relapse due to the occurrence of drug resistance. It is of great need to explore potential combinatorial drug therapy since individual drug alone may not be sufficient to inhibit continuous activation of cancer-addicted genes or pathways. The DREAM challenge has confirmed the potentiality of computational methods for predicting synergistic drug combinations, while the prediction accuracy can be further improved.

Methods

Based on previous reports, we hypothesized the similarity in biological functions or genes perturbed by two drugs can determine their synergistic effects. To test the feasibility of the hypothesis, we proposed three scoring systems: co-gene score, co-GS score, and co-gene/GS score, measuring the similarities in genes with significant expressional changes, enriched gene sets, and significantly changed genes within an enriched gene sets between a pair of drugs, respectively. Performances of these scoring systems were evaluated by the probabilistic c-index (PC-index) devised by the DREAM consortium. We also applied the proposed method to the Connectivity Map dataset to explore more potential synergistic drug combinations.

Results

Using a gold standard derived by the DREAM consortium, we confirmed the prediction power of the three scoring systems (all P-values < 0.05). The co-gene/GS score achieved the best prediction of drug synergy (PC-index = 0.663, P-value < 0.0001), outperforming all methods proposed during DREAM challenge. Furthermore, a binary classification test showed that co-gene/GS scoring was highly accurate and specific. Since our method is constructed on a gene set-based analysis, in addition to synergy prediction, it provides insights into the functional relevance of drug combinations and the underlying mechanisms by which drugs achieve synergy.

Conclusions

Here we proposed a novel and simple method to predict and investigate drug synergy, and validated its efficacy to accurately predict synergistic drug combinations and to comprehensively explore their underlying mechanisms. The method is widely applicable to expression profiles of other drug treatments and is expected to accelerate the realization of precision cancer treatment.

Electronic supplementary material

The online version of this article (doi:10.1186/s12918-016-0310-3) contains supplementary material, which is available to authorized users.

Polypharmacology Shakes Hands with Complex Aetiopathology

Chronic diseases are due to deviations of fundamental physiological systems, with different pathologies being characterised by similar malfunctioning biological networks. The ensuing compensatory mechanisms may weaken the body's dynamic ability to respond to further insults and reduce the efficacy of conventional single target treatments. The multitarget, systemic, and prohomeostatic actions emerging for plant cannabinoids exemplify what might be needed for future medicines. Indeed, two combined cannabis extracts were approved as a single medicine (Sativex(®)), while pure cannabidiol, a multitarget cannabinoid, is emerging as a treatment for paediatric drug-resistant epilepsy. Using emerging cannabinoid medicines as an example, we revisit the concept of polypharmacology and describe a new empirical model, the 'therapeutic handshake', to predict efficacy/safety of compound combinations of either natural or synthetic origin.

Combining genomic and network characteristics for extended capability in predicting synergistic drugs for cancer

The identification of synergistic chemotherapeutic agents from a large pool of candidates is highly challenging. Here, we present a Ranking-system of Anti-Cancer Synergy (RACS) that combines features of targeting networks and transcriptomic profiles, and validate it on three types of cancer. Using data on human β-cell lymphoma from the Dialogue for Reverse Engineering Assessments and Methods consortium we show a probability concordance of 0.78 compared with 0.61 obtained with the previous best algorithm. We confirm 63.6% of our breast cancer predictions through experiment and literature, including four strong synergistic pairs. Further in vivo screening in a zebrafish MCF7 xenograft model confirms one prediction with strong synergy and low toxicity. Validation using A549 lung cancer cells shows similar results. Thus, RACS can significantly improve drug synergy prediction and markedly reduce the experimental prescreening of existing drugs for repurposing to cancer treatment, although the molecular mechanism underlying particular interactions remains unknown.

Predicting combinations of chemotherapeutic drugs that act synergistically is challenging. Here the authors take a computational approach to predict synergistic pairs, validate novel pairs using several cancer cell lines, and assess toxicity in a zebrafish xenograft model.

Systematic synergy modeling: understanding drug synergy from a systems biology perspective

Owing to drug synergy effects, drug combinations have become a new trend in combating complex diseases like cancer, HIV and cardiovascular diseases. However, conventional synergy quantification methods often depend on experimental dose–response data which are quite resource-demanding. In addition, these methods are unable to interpret the explicit synergy mechanism. In this review, we give representative examples of how systems biology modeling offers strategies toward better understanding of drug synergy, including the protein-protein interaction (PPI) network-based methods, pathway dynamic simulations, synergy network motif recognitions, integrative drug feature calculations, and “omic”-supported analyses. Although partially successful in drug synergy exploration and interpretation, more efforts should be put on a holistic understanding of drug-disease interactions, considering integrative pharmacology and toxicology factors. With a comprehensive and deep insight into the mechanism of drug synergy, systems biology opens a novel avenue for rational design of effective drug combinations.

Modelling of compound combination effects and applications to efficacy and toxicity: state-of-the-art, challenges and perspectives

The development of treatments involving combinations of drugs is a promising approach towards combating complex or multifactorial disorders. However, the large number of compound combinations that can be generated, even from small compound collections, means that exhaustive experimental testing is infeasible. The ability to predict the behaviour of compound combinations in biological systems, whittling down the number of combinations to be tested, is therefore crucial. Here, we review the current state-of-the-art in the field of compound combination modelling, with the aim to support the development of approaches that, as we hope, will finally lead to an integration of chemical with systems-level biological information for predicting the effect of chemical mixtures.

Systems medicine: evolution of systems biology from bench to bedside

High-throughput experimental techniques for generating genomes, transcriptomes, proteomes, metabolomes, and interactomes have provided unprecedented opportunities to interrogate biological systems and human diseases on a global level. Systems biology integrates the mass of heterogeneous high-throughput data and predictive computational modeling to understand biological functions as system-level properties. Most human diseases are biological states caused by multiple components of perturbed pathways and regulatory networks rather than individual failing components. Systems biology not only facilitates basic biological research but also provides new avenues through which to understand human diseases, identify diagnostic biomarkers, and develop disease treatments. At the same time, systems biology seeks to assist in drug discovery, drug optimization, drug combinations, and drug repositioning by investigating the molecular mechanisms of action of drugs at a system's level. Indeed, systems biology is evolving to systems medicine as a new discipline that aims to offer new approaches for addressing the diagnosis and treatment of major human diseases uniquely, effectively, and with personalized precision.

TIMMA-R: an R package for predicting synergistic multi-targeted drug combinations in cancer cell lines or patient-derived samples

Summary: Network pharmacology-based prediction of multi-targeted drug combinations is becoming a promising strategy to improve anticancer efficacy and safety. We developed a logic-based network algorithm, called Target Inhibition Interaction using Maximization and Minimization Averaging (TIMMA), which predicts the effects of drug combinations based on their binary drug-target interactions and single-drug sensitivity profiles in a given cancer sample. Here, we report the R implementation of the algorithm (TIMMA-R), which is much faster than the original MATLAB code. The major extensions include modeling of multiclass drug-target profiles and network visualization. We also show that the TIMMA-R predictions are robust to the intrinsic noise in the experimental data, thus making it a promising high-throughput tool to prioritize drug combinations in various cancer types for follow-up experimentation or clinical applications.

Availability and implementation: TIMMA-R source code is freely available at http://cran.r-project.org/web/packages/timma/.

Contact:jing.tang@helsinki.fi

Supplementary information:Supplementary data are available at Bioinformatics online.

Drug-repurposing identified the combination of Trolox C and Cytisine for the treatment of type 2 diabetes

Background

Drug-induced gene expression dataset (for example Connectivity Map, CMap) represent a valuable resource for drug-repurposing, a class of methods for identifying novel indications for approved drugs. Recently, CMap-based methods have successfully applied to identifying drugs for a number of diseases. However, currently few gene expression based methods are available for the repurposing of combined drugs. Increasing evidence has shown that the combination of drugs may valid for novel indications.

Method

Here, for this purpose, we presented a simple CMap-based scoring system to predict novel indications for the combination of two drugs. We then confirmed the effectiveness of the predicted drug combination in an animal model of type 2 diabetes.

Results

We applied the presented scoring system to type 2 diabetes and identified a candidate combination of two drugs, Trolox C and Cytisine. Finally, we confirmed that the predicted combined drugs are effective for the treatment of type 2 diabetes.

Conclusion

The presented scoring system represents one novel method for drug repurposing, which would provide helps for greatly extended the space of drugs.