DIGRE: Drug-Induced Genomic Residual Effect Model for Successful Prediction of Multidrug Effects

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.

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.

From cell lines to cancer patients: personalized drug synergy prediction

MOTIVATION

Combination drug therapies are effective treatments for cancer. However, the genetic heterogeneity of the patients and exponentially large space of drug pairings pose significant challenges for finding the right combination for a specific patient. Current in silico prediction methods can be instrumental in reducing the vast number of candidate drug combinations. However, existing powerful methods are trained with cancer cell line gene expression data, which limits their applicability in clinical settings. While synergy measurements on cell line models are available at large scale, patient-derived samples are too few to train a complex model. On the other hand, patient-specific single-drug response data are relatively more available.

RESULTS

In this work, we propose a deep learning framework, Personalized Deep Synergy Predictor (PDSP), that enables us to use the patient-specific single drug response data for customizing patient drug synergy predictions. PDSP is first trained to learn synergy scores of drug pairs and their single drug responses for a given cell line using drug structures and large scale cell line gene expression data. Then, the model is fine-tuned for patients with their patient gene expression data and associated single drug response measured on the patient ex vivo samples. In this study, we evaluate PDSP on data from three leukemia patients and observe that it improves the prediction accuracy by 27% compared to models trained on cancer cell line data.

AVAILABILITY AND IMPLEMENTATION

PDSP is available at https://github.com/hikuru/PDSP.

Probing Synergistic Targets by Natural Compounds for Hepatocellular Carcinoma

Background

Designing combination drugs for malignant cancers has been restricted due to the scarcity of synergy-medicated targets, while some natural compounds have demonstrated potential to enhance anticancer effects.

Methods

We here explored the feasibility of probing synergy-mediated targets by Berberine (BER) and Evodiamine (EVO) in hepatocellular carcinoma (HCC). Using the genomics-derived HCC signaling networks of compound treatment, NF-κB and c-JUN were inferred as key responding elements with transcriptional activity coinhibited during the synergistic cytotoxicity induction in BEL-7402 cells. Then, selective coinhibitors of NF-κB and c-JUN were tested demonstrating similar synergistic antiproliferation activity.

Results

Consistent with in vivo experiments of zebrafish, coinhibitors were found to significantly reduce tumor growth by 79% and metastasis by 96% compared to blank control, accompanied by anti-angiogenic activity. In an analysis of 365 HCC individuals, the low expression group showed significantly lower malignancies and better prognosis, with the median survival time increased from 67 to 213%, compared to the rest of the groups.

Conclusion

Together, NF-κB and c-JUN were identified as promising synergistic inducers in developing anti-HCC therapies. Also, our method may provide a feasible strategy to explore new targeting space from natural compounds, opening opportunities for the rational design of combinational formulations in combatting malignant cancers.

An In Silico Method for Predicting Drug Synergy Based on Multitask Learning

To make better use of all kinds of knowledge to predict drug synergy, it is crucial to successfully establish a drug synergy prediction model and leverage the reconstruction of sparse known drug targets. Therefore, we present an in silico method that predicts the synergy scores of drug pairs based on multitask learning (DSML) that could fuse drug targets, protein-protein interactions, anatomical therapeutic chemical codes, a priori knowledge of drug combinations. To simultaneously reconstruct drug-target protein interactions and synergistic drug combinations, DSML benefits indirectly from the associations with relation through proteins. In cross-validation experiments, DSML improved the ability to predict drug synergy. Moreover, the reconstruction of drug-target interactions and the incorporation of multisource knowledge significantly improved drug combination predictions by a large margin. The potential drug combinations predicted by DSML demonstrate its ability to predict drug synergy.

Anticancer drug synergy prediction in understudied tissues using transfer learning

OBJECTIVE

Drug combination screening has advantages in identifying cancer treatment options with higher efficacy without degradation in terms of safety. A key challenge is that the accumulated number of observations in in-vitro drug responses varies greatly among different cancer types, where some tissues are more understudied than the others. Thus, we aim to develop a drug synergy prediction model for understudied tissues as a way of overcoming data scarcity problems.

MATERIALS AND METHODS

We collected a comprehensive set of genetic, molecular, phenotypic features for cancer cell lines. We developed a drug synergy prediction model based on multitask deep neural networks to integrate multimodal input and multiple output. We also utilized transfer learning from data-rich tissues to data-poor tissues.

RESULTS

We showed improved accuracy in predicting synergy in both data-rich tissues and understudied tissues. In data-rich tissue, the prediction model accuracy was 0.9577 AUROC for binarized classification task and 174.3 mean squared error for regression task. We observed that an adequate transfer learning strategy significantly increases accuracy in the understudied tissues.

CONCLUSIONS

Our synergy prediction model can be used to rank synergistic drug combinations in understudied tissues and thus help to prioritize future in-vitro experiments. Code is available at https://github.com/yejinjkim/synergy-transfer.

Capitalizing on Synthetic Lethality of MYC to Treat Cancer in the Digital Age

Deregulation of MYC is among the most frequent oncogenic drivers of cancer. Developing targeted therapies against MYC is, therefore, one of the most critical unmet needs of cancer therapy. Unfortunately, MYC has been labelled as undruggable due to the lack of success in developing clinically relevant MYC-targeted therapies. Synthetic lethality is a promising approach that targets MYC-dependent vulnerabilities in cancer. However, translating the synthetic lethality targets to the clinics is still challenging due to the complex nature of cancers. This review highlights the most promising mechanisms of MYC synthetic lethality and how these discoveries are currently translated into the clinic. Finally, we discuss how in silico computational platforms can improve clinical success of synthetic lethality-based therapy.

H-RACS: a handy tool to rank anti-cancer synergistic drugs

Though promising, identifying synergistic combinations from a large pool of candidate drugs remains challenging for cancer treatment. Due to unclear mechanism and limited confirmed cases, only a few computational algorithms are able to predict drug synergy. Yet they normally require the drug-cell treatment results as an essential input, thus exclude the possibility to pre-screen those unexplored drugs without cell treatment profiling. Based on the largest dataset of 33,574 combinational scenarios, we proposed a handy webserver, H-RACS, to overcome the above problems. Being loaded with chemical structures and target information, H-RACS can recommend potential synergistic pairs between candidate drugs on 928 cell lines of 24 prevalent cancer types. A high model performance was achieved with AUC of 0.89 on independent combinational scenarios. On the second independent validation of DREAM dataset, H-RACS obtained precision of 67% among its top 5% ranking list. When being tested on new combinations and new cell lines, H-RACS showed strong extendibility with AUC of 0.84 and 0.81 respectively. As the first online server freely accessible at http://www.badd-cao.net/h-racs, H-RACS may promote the pre-screening of synergistic combinations for new chemical drugs on unexplored cancers.

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

Our ability to discover effective drug combinations is limited, in part by insufficient understanding of how the transcriptional response of two monotherapies results in that of their combination. We analyzed matched time course RNAseq profiling of cells treated with single drugs and their combinations and found that the transcriptional signature of the synergistic combination was unique relative to that of either constituent monotherapy. The sequential activation of transcription factors in time in the gene regulatory network was implicated. The nature of this transcriptional cascade suggests that drug synergy may ensue when the transcriptional responses elicited by two unrelated individual drugs are correlated. We used these results as the basis of a simple prediction algorithm attaining an AUROC of 0.77 in the prediction of synergistic drug combinations in an independent dataset.

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.

Predicting drug synergy for precision medicine using network biology and machine learning

Identification of effective drug combinations for patients is an expensive and time-consuming procedure, especially for in vitro experiments. To accelerate the synergistic drug discovery process, we present a new classification model to identify more effective anti-cancer drug pairs using in silico network biology approach. Based on the hypotheses that the drug synergy comes from the collective effects on the biological network, therefore, we developed six network biology features, including overlap and distance of drug perturbation network, that were derived by using individual drug-perturbed transcriptome profiles and the relevant biological network analysis. Using publicly available drug synergy databases and three machine-learning (ML) methods, the model was trained to discriminate the positive (synergistic) and negative (nonsynergistic) drug combinations. The proposed models were evaluated on the test cases to predict the most promising network biology feature, which is the network degree activity, i.e. the synergistic effect between drug pairs is mainly accounted by the complementary signaling pathways or molecular networks from two drugs.

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.

Incorporating Multisource Knowledge To Predict Drug Synergy Based on Graph Co-regularization

Drug combinations may reduce toxicity and increase therapeutic efficacy, offering a promising strategy to conquer multiple complex diseases. However, due to large-scale combinatorial space, it remains challenging to identify effective combinations. Although many computational methods have focused on predicting drug synergy to reduce combinatorial space, they fail to effectively consider multiple sources of important knowledge. Thus, it is necessary to propose a computational method that can exploit useful information to predict drug synergy. Here, we developed a computational method to predict drug synergy based on graph co-regularization, named DSGCR. By incorporating drug-target network patterns, pharmacological patterns, and prior knowledge of drug combinations, DSGCR performs predictions of synergistic drug combinations. Compared to several existing methods, DSGCR achieves superior performance in predicting drug synergy in terms of various metrics via cross-validation. Additionally, we analyzed the importance of various sources of drug knowledge concerning three DSGCR's scenarios. Finally, the potential of DSGCR to score drug synergy was confirmed by three predicted synergistic drug combinations.

Rethinking Drug Repositioning and Development with Artificial Intelligence, Machine Learning, and Omics

Pharmaceutical industry and the art and science of drug development are sorely in need of novel transformative technologies in the current age of digital health and artificial intelligence (AI). Often described as game-changing technologies, AI and machine learning algorithms have slowly but surely begun to revolutionize pharmaceutical industry and drug development over the past 5 years. In this expert review, we describe the most frequently used machine learning algorithms in drug development pipelines and the -omics databases well poised to support machine learning and drug discovery. Subsequently, we analyze the emerging new computational approaches to drug discovery and the in silico pipelines for drug repositioning and the synergies among -omics system sciences, AI and machine learning. As with system sciences, AI and machine learning embody a system scale and Big Data driven vision for drug discovery and development. We conclude with a future outlook on the ways in which machine learning approaches can be implemented to buttress and expedite drug discovery and precision medicine. As AI and machine learning are rapidly entering pharmaceutical industry and the art and science of drug development, we need to critically examine the attendant prospects and challenges to benefit patients and public health.

Advances in computational approaches in identifying synergistic drug combinations

Accumulated empirical clinical experience, supported by animal or cell line models, has initiated efforts of predicting synergistic combinatorial drugs with more-than-additive effect compared with the sum of the individual agents. Aiming to construct better computational models, this review started from the latest updated data resources of combinatorial drugs, then summarized the reported mechanism of the known synergistic combinations from aspects of drug molecular and pharmacological patterns, target network properties and compound functional annotation. Based on above, we focused on the main in silico strategies recently published, covering methods of molecular modeling, mathematical simulation, optimization of combinatorial targets and pattern-based statistical/learning model. Future thoughts are also discussed related to the role of natural compounds, drug combination with immunotherapy and management of adverse effects. Overall, with particular emphasis on mechanism of action of drug synergy, this review may serve as a rapid reference to design improved models for combinational drugs.

Advancement of multi-target drug discoveries and promising applications in the field of Alzheimer's disease

Complex diseases (e.g., Alzheimer's disease) or infectious diseases are usually caused by complicated and varied factors, including environmental and genetic factors. Multi-target (polypharmacology) drugs have been suggested and have emerged as powerful and promising alternative paradigms in modern medicinal chemistry for the development of versatile chemotherapeutic agents to solve these medical challenges. The multifunctional agents capable of modulating multiple biological targets simultaneously display great advantages of higher efficacy, improved safety profile, and simpler administration compared to single-targeted agents. Therefore, multifunctional agents would certainly open novel avenues to rationally design the next generation of more effective but less toxic therapeutic agents. Herein, the authors review the recent progress made in the discovery and design processes of selective multi-targeted agents, especially the successful application of multi-target drugs for the treatment of Alzheimer's disease.

Pairwise combinations of chemical compounds that delay yeast chronological aging through different signaling pathways display synergistic effects on the extent of aging delay

We have recently discovered six plant extracts that delay yeast chronological aging. Most of them affect different nodes, edges and modules of an evolutionarily conserved network of longevity regulation that integrates certain signaling pathways and protein kinases; this network is also under control of such aging-delaying chemical compounds as spermidine and resveratrol. We have previously shown that, if a strain carrying an aging-delaying single-gene mutation affecting a certain node, edge or module of the network is exposed to some of the six plant extracts, the mutation and the plant extract enhance aging-delaying efficiencies of each other so that their combination has a synergistic effect on the extent of aging delay. We therefore hypothesized that a pairwise combination of two aging-delaying plant extracts or a combination of one of these plant extracts and spermidine or resveratrol may have a synergistic effect on the extent of aging delay only if each component of this combination targets a different element of the network. To test our hypothesis, we assessed longevity-extending efficiencies of all possible pairwise combinations of the six plant extracts or of one of them and spermidine or resveratrol in chronologically aging yeast. In support of our hypothesis, we show that only pairwise combinations of naturally-occurring chemical compounds that slow aging through different nodes, edges and modules of the network delay aging in a synergistic manner.

Oncobox Bioinformatical Platform for Selecting Potentially Effective Combinations of Target Cancer Drugs Using High-Throughput Gene Expression Data

Sequential courses of anticancer target therapy lead to selection of drug-resistant cells, which results in continuous decrease of clinical response. Here we present a new approach for predicting effective combinations of target drugs, which act in a synergistic manner. Synergistic combinations of drugs may prevent or postpone acquired resistance, thus increasing treatment efficiency. We cultured human ovarian carcinoma SKOV-3 and neuroblastoma NGP-127 cancer cell lines in the presence of Tyrosine Kinase Inhibitors (Pazopanib, Sorafenib, and Sunitinib) and Rapalogues (Temsirolimus and Everolimus) for four months and obtained cell lines demonstrating increased drug resistance. We investigated gene expression profiles of intact and resistant cells by microarrays and analyzed alterations in 378 cancer-related signaling pathways using the bioinformatical platform Oncobox. This revealed numerous pathways linked with development of drug resistant phenotypes. Our approach is based on targeting proteins involved in as many as possible signaling pathways upregulated in resistant cells. We tested 13 combinations of drugs and/or selective inhibitors predicted by Oncobox and 10 random combinations. Synergy scores for Oncobox predictions were significantly higher than for randomly selected drug combinations. Thus, the proposed approach significantly outperforms random selection of drugs and can be adopted to enhance discovery of new synergistic combinations of anticancer target drugs.

DeepSynergy: predicting anti-cancer drug synergy with Deep Learning

Motivation

While drug combination therapies are a well-established concept in cancer treatment, identifying novel synergistic combinations is challenging due to the size of combinatorial space. However, computational approaches have emerged as a time- and cost-efficient way to prioritize combinations to test, based on recently available large-scale combination screening data. Recently, Deep Learning has had an impact in many research areas by achieving new state-of-the-art model performance. However, Deep Learning has not yet been applied to drug synergy prediction, which is the approach we present here, termed DeepSynergy. DeepSynergy uses chemical and genomic information as input information, a normalization strategy to account for input data heterogeneity, and conical layers to model drug synergies.

Results

DeepSynergy was compared to other machine learning methods such as Gradient Boosting Machines, Random Forests, Support Vector Machines and Elastic Nets on the largest publicly available synergy dataset with respect to mean squared error. DeepSynergy significantly outperformed the other methods with an improvement of 7.2% over the second best method at the prediction of novel drug combinations within the space of explored drugs and cell lines. At this task, the mean Pearson correlation coefficient between the measured and the predicted values of DeepSynergy was 0.73. Applying DeepSynergy for classification of these novel drug combinations resulted in a high predictive performance of an AUC of 0.90. Furthermore, we found that all compared methods exhibit low predictive performance when extrapolating to unexplored drugs or cell lines, which we suggest is due to limitations in the size and diversity of the dataset. We envision that DeepSynergy could be a valuable tool for selecting novel synergistic drug combinations.

Availability and implementation

DeepSynergy is available via www.bioinf.jku.at/software/DeepSynergy.

Contact

klambauer@bioinf.jku.at.

Supplementary information

Supplementary data are available at Bioinformatics online.

The Prediction of Drug-Disease Correlation Based on Gene Expression Data

The explosive growth of high-throughput experimental methods and resulting data yields both opportunity and challenge for selecting the correct drug to treat both a specific patient and their individual disease. Ideally, it would be useful and efficient if computational approaches could be applied to help achieve optimal drug-patient-disease matching but current efforts have met with limited success. Current approaches have primarily utilized the measureable effect of a specific drug on target tissue or cell lines to identify the potential biological effect of such treatment. While these efforts have met with some level of success, there exists much opportunity for improvement. This specifically follows the observation that, for many diseases in light of actual patient response, there is increasing need for treatment with combinations of drugs rather than single drug therapies. Only a few previous studies have yielded computational approaches for predicting the synergy of drug combinations by analyzing high-throughput molecular datasets. However, these computational approaches focused on the characteristics of the drug itself, without fully accounting for disease factors. Here, we propose an algorithm to specifically predict synergistic effects of drug combinations on various diseases, by integrating the data characteristics of disease-related gene expression profiles with drug-treated gene expression profiles. We have demonstrated utility through its application to transcriptome data, including microarray and RNASeq data, and the drug-disease prediction results were validated using existing publications and drug databases. It is also applicable to other quantitative profiling data such as proteomics data. We also provide an interactive web interface to allow our Prediction of Drug-Disease method to be readily applied to user data. While our studies represent a preliminary exploration of this critical problem, we believe that the algorithm can provide the basis for further refinement towards addressing a large clinical need.

Computational models for predicting drug responses in cancer research

The computational prediction of drug responses based on the analysis of multiple types of genome-wide molecular data is vital for accomplishing the promise of precision medicine in oncology. This will benefit cancer patients by matching their tumor characteristics to the most effective therapy available. As larger and more diverse layers of patient-related data become available, further demands for new bioinformatics approaches and expertise will arise. This article reviews key strategies, resources and techniques for the prediction of drug sensitivity in cell lines and patient-derived samples. It discusses major advances and challenges associated with the different model development steps. This review highlights major trends in this area, and will assist researchers in the assessment of recent progress and in the selection of approaches to emerging applications in oncology.

Informatics Approaches for Predicting, Understanding, and Testing Cancer Drug Combinations

Making cancer treatment more effective is one of the grand challenges in our health care system. However, many drugs have entered clinical trials but so far showed limited efficacy or induced rapid development of resistance. We urgently need multi-targeted drug combinations, which shall selectively inhibit the cancer cells and block the emergence of drug resistance. The book chapter focuses on mathematical and computational tools to facilitate the discovery of the most promising drug combinations to improve efficacy and prevent resistance. Data integration approaches that leverage drug-target interactions, cancer molecular features, and signaling pathways for predicting, understanding, and testing drug combinations are critically reviewed.

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.

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.

Predicting synergistic effects between compounds through their structural similarity and effects on transcriptomes

MOTIVATION

Combinatorial therapies have been under intensive research for cancer treatment. However, due to the large number of possible combinations among candidate compounds, exhaustive screening is prohibitive. Hence, it is important to develop computational tools that can predict compound combination effects, prioritize combinations and limit the search space to facilitate and accelerate the development of combinatorial therapies.

RESULTS

In this manuscript we consider the NCI-DREAM Drug Synergy Prediction Challenge dataset to identify features informative about combination effects. Through systematic exploration of differential expression profiles after single compound treatments and comparison of molecular structures of compounds, we found that synergistic levels of combinations are statistically significantly associated with compounds' dissimilarity in structure and similarity in induced gene expression changes. These two types of features offer complementary information in predicting experimentally measured combination effects of compound pairs. Our findings offer insights on the mechanisms underlying different combination effects and may help prioritize promising combinations in the very large search space.

AVAILABILITY AND IMPLEMENTATION

The R code for the analysis is available on https://github.com/YiyiLiu1/DrugCombination CONTACT: hongyu.zhao@yale.eduSupplementary information: Supplementary data are available at Bioinformatics online.