Predicting Synergism of Cancer Drug Combinations Using NCI-ALMANAC Data

Using Stochastic Computing for Virtual Screening Acceleration

Stochastic computing is an emerging scientific field pushed by the need for developing high-performance artificial intelligence systems in hardware to quickly solve complex data processing problems. This is the case of virtual screening, a computational task aimed at searching across huge molecular databases for new drug leads. In this work, we show a classification framework in which molecules are described by an energy-based vector. This vector is then processed by an ultra-fast artificial neural network implemented through FPGA by using stochastic computing techniques. Compared to other previously published virtual screening methods, this proposal provides similar or higher accuracy, while it improves processing speed by about two or three orders of magnitude.

Comparative analysis of molecular fingerprints in prediction of drug combination effects

Application of machine and deep learning methods in drug discovery and cancer research has gained a considerable amount of attention in the past years. As the field grows, it becomes crucial to systematically evaluate the performance of novel computational solutions in relation to established techniques. To this end, we compare rule-based and data-driven molecular representations in prediction of drug combination sensitivity and drug synergy scores using standardized results of 14 high-throughput screening studies, comprising 64 200 unique combinations of 4153 molecules tested in 112 cancer cell lines. We evaluate the clustering performance of molecular representations and quantify their similarity by adapting the Centered Kernel Alignment metric. Our work demonstrates that to identify an optimal molecular representation type, it is necessary to supplement quantitative benchmark results with qualitative considerations, such as model interpretability and robustness, which may vary between and throughout preclinical drug development projects.

Artificial intelligence and machine learning methods in predicting anti-cancer drug combination effects

Drug combinations have exhibited promising therapeutic effects in treating cancer patients with less toxicity and adverse side effects. However, it is infeasible to experimentally screen the enormous search space of all possible drug combinations. Therefore, developing computational models to efficiently and accurately identify potential anti-cancer synergistic drug combinations has attracted a lot of attention from the scientific community. Hypothesis-driven explicit mathematical methods or network pharmacology models have been popular in the last decade and have been comprehensively reviewed in previous surveys. With the surge of artificial intelligence and greater availability of large-scale datasets, machine learning especially deep learning methods are gaining popularity in the field of computational models for anti-cancer drug synergy prediction. Machine learning-based methods can be derived without strong assumptions about underlying mechanisms and have achieved state-of-the-art prediction performances, promoting much greater growth of the field. Here, we present a structured overview of available large-scale databases and machine learning especially deep learning methods in computational predictive models for anti-cancer drug synergy prediction. We provide a unified framework for machine learning models and detail existing model architectures as well as their contributions and limitations, shedding light into the future design of computational models. Besides, unbiased experiments are conducted to provide in-depth comparisons between reviewed papers in terms of their prediction performance.

Assessment of elementary derivatives of 1,5-benzodiazepine as anticancer agents with synergy potential

Herein, we designed and synthesized 1,5-benzodiazepines as a lead molecule for anticancer activity and as potent synergistic activity with drug Methotrexate. Working under the framework of green chemistry principles, series of 1,5-benzodiazepine derivatives (3a-3a¹) were synthesized using biocatalyst i.e. thiamine hydrochloride under solvent free neat heat conditions. These compounds were screened for in vitro anti cancer activity against couple of cancer cell lines (HeLa and HEPG2) and normal human cell line HEK-293 via MTT assay. The IC₅₀ values for the compounds were in the range 0.067 to 0.35 µM, better than Paclitaxel and compatible with the drug Methotrexate. Compound 3x was found to be influential against both the cell lines with IC₅₀ values of 0.067 ± 0.002 µM against HeLa and 0.087 ± 0.003 µM against HEPG2 cell line, having activity as compatible to the standard drug Methotrexate. Bioinformatic analysis showed that these compounds are good tyrosine kinase inhibitors which was then proved using enzyme inhibition assay. The studies of apoptosis revealed late apoptotic mode of cell death for the compounds against HEPG2 cancer cell line using flow cytometry method. Synergistic studies of compound 3x and drug Methotrexate showed that the combination was highly active against cancer HeLa and HEPG2 cell line with IC50 value 0.046 ± 0.002 µM and 0.057 ± 0.002 µM respectively, which was well supported by apoptosis pathway. Further the compounds proved its scope as DNA intercalating agents, as its molecular docking and DNA binding studies revealed that the compounds would fit well into the DNA strands.

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.

Representation of molecules for drug response prediction

The rapid development of machine learning and deep learning algorithms in the recent decade has spurred an outburst of their applications in many research fields. In the chemistry domain, machine learning has been widely used to aid in drug screening, drug toxicity prediction, quantitative structure-activity relationship prediction, anti-cancer synergy score prediction, etc. This review is dedicated to the application of machine learning in drug response prediction. Specifically, we focus on molecular representations, which is a crucial element to the success of drug response prediction and other chemistry-related prediction tasks. We introduce three types of commonly used molecular representation methods, together with their implementation and application examples. This review will serve as a brief introduction of the broad field of molecular representations.

Machine learning methods, databases and tools for drug combination prediction

Combination therapy has shown an obvious efficacy on complex diseases and can greatly reduce the development of drug resistance. However, even with high-throughput screens, experimental methods are insufficient to explore novel drug combinations. In order to reduce the search space of drug combinations, there is an urgent need to develop more efficient computational methods to predict novel drug combinations. In recent decades, more and more machine learning (ML) algorithms have been applied to improve the predictive performance. The object of this study is to introduce and discuss the recent applications of ML methods and the widely used databases in drug combination prediction. In this study, we first describe the concept and controversy of synergism between drug combinations. Then, we investigate various publicly available data resources and tools for prediction tasks. Next, ML methods including classic ML and deep learning methods applied in drug combination prediction are introduced. Finally, we summarize the challenges to ML methods in prediction tasks and provide a discussion on future work.

A gentle introduction to understanding preclinical data for cancer pharmaco-omic modeling

A central goal of precision oncology is to administer an optimal drug treatment to each cancer patient. A common preclinical approach to tackle this problem has been to characterize the tumors of patients at the molecular and drug response levels, and employ the resulting datasets for predictive in silico modeling (mostly using machine learning). Understanding how and why the different variants of these datasets are generated is an important component of this process. This review focuses on providing such introduction aimed at scientists with little previous exposure to this research area.

Modeling drug combination effects via latent tensor reconstruction

Motivation

Combination therapies have emerged as a powerful treatment modality to overcome drug resistance and improve treatment efficacy. However, the number of possible drug combinations increases very rapidly with the number of individual drugs in consideration, which makes the comprehensive experimental screening infeasible in practice. Machine-learning models offer time- and cost-efficient means to aid this process by prioritizing the most effective drug combinations for further pre-clinical and clinical validation. However, the complexity of the underlying interaction patterns across multiple drug doses and in different cellular contexts poses challenges to the predictive modeling of drug combination effects.

Results

We introduce comboLTR, highly time-efficient method for learning complex, non-linear target functions for describing the responses of therapeutic agent combinations in various doses and cancer cell-contexts. The method is based on a polynomial regression via powerful latent tensor reconstruction. It uses a combination of recommender system-style features indexing the data tensor of response values in different contexts, and chemical and multi-omics features as inputs. We demonstrate that comboLTR outperforms state-of-the-art methods in terms of predictive performance and running time, and produces highly accurate results even in the challenging and practical inference scenario where full dose–response matrices are predicted for completely new drug combinations with no available combination and monotherapy response measurements in any training cell line.

Availability and implementation

comboLTR code is available at https://github.com/aalto-ics-kepaco/ComboLTR.

Supplementary information

Supplementary data are available at Bioinformatics online.

Current Development of Glioblastoma Therapeutic Agents

Glioblastoma multiforme (GBM) is the most common and aggressive malignant primary brain tumor in humans. Over the past several decades, despite improvements in neurosurgical techniques, development of powerful chemotherapeutic agents, advances in radiotherapy, and comprehensive genomic profiling and molecular characterization, treatment of GBM has achieved very limited success in increasing overall survival. Thus, identifying and understanding the key molecules and barriers responsible for the malignant phenotypes and treatment resistance of GBM will yield new potential therapeutic targets. We review the most recent development of receptor tyrosine kinase targeted therapy for GBM and discuss the current status of several novel strategies with the emphasis on blood-brain barrier penetration as a major obstacle for small-molecule drugs to achieve their therapeutic goals. Likewise, a major opportunity for the treatment of GBM lies in the use of biomarkers for the discovery and development of new receptor tyrosine kinase targeted therapy.

Simplex representation of molecular structure as universal QSAR/QSPR tool

We review the development and application of the Simplex approach for the solution of various QSAR/QSPR problems. The general concept of the simplex method and its varieties are described. The advantages of utilizing this methodology, especially for the interpretation of QSAR/QSPR models, are presented in comparison to other fragmentary methods of molecular structure representation. The utility of SiRMS is demonstrated not only in the standard QSAR/QSPR applications, but also for mixtures, polymers, materials, and other complex systems. In addition to many different types of biological activity (antiviral, antimicrobial, antitumor, psychotropic, analgesic, etc.), toxicity and bioavailability, the review examines the simulation of important properties, such as water solubility, lipophilicity, as well as luminescence, and thermodynamic properties (melting and boiling temperatures, critical parameters, etc.). This review focuses on the stereochemical description of molecules within the simplex approach and details the possibilities of universal molecular stereo-analysis and stereochemical configuration description, along with stereo-isomerization mechanism and molecular fragment "topography" identification.

Drug combination therapy for emerging viral diseases

Effective therapeutics to combat emerging viral infections are an unmet need. Historically, treatments for chronic viral infections with single drugs have not been successful, as exemplified by human immunodeficiency virus (HIV) and hepatitis C virus (HCV) infections. Combination therapy for these diseases has led to improved clinical outcomes with dramatic reductions in viral load, morbidity, and mortality. Drug combinations can enhance therapeutic efficacy through additive, and ideally synergistic, effects for emerging and re-emerging viruses, such as influenza, severe acute respiratory syndrome-coronavirus (SARS-CoV), Middle East respiratory syndrome (MERS)-CoV, Ebola, Zika, and SARS-coronavirus 2 (CoV-2). Although novel drug development through traditional pipelines remains a priority, in the interim, effective synergistic drug candidates could be rapidly identified by drug-repurposing screens, facilitating accelerated paths to clinical testing and potential emergency use authorizations.

Current Advances and Limitations of Deep Learning in Anticancer Drug Sensitivity Prediction

Anticancer drug screening can accelerate drug discovery to save the lives of cancer patients, but cancer heterogeneity makes this screening challenging. The prediction of anticancer drug sensitivity is useful for anticancer drug development and the identification of biomarkers of drug sensitivity. Deep learning, as a branch of machine learning, is an important aspect of in silico research. Its outstanding computational performance means that it has been used for many biomedical purposes, such as medical image interpretation, biological sequence analysis, and drug discovery. Several studies have predicted anticancer drug sensitivity based on deep learning algorithms. The field of deep learning has made progress regarding model performance and multi-omics data integration. However, deep learning is limited by the number of studies performed and data sources available, so it is not perfect as a pre-clinical approach for use in the anticancer drug screening process. Improving the performance of deep learning models is a pressing issue for researchers. In this review, we introduce the research of anticancer drug sensitivity prediction and the use of deep learning in this research area. To provide a reference for future research, we also review some common data sources and machine learning methods. Lastly, we discuss the advantages and disadvantages of deep learning, as well as the limitations and future perspectives regarding this approach.

Artificial intelligence and machine learning-aided drug discovery in central nervous system diseases: State-of-the-arts and future directions

Neurological disorders significantly outnumber diseases in other therapeutic areas. However, developing drugs for central nervous system (CNS) disorders remains the most challenging area in drug discovery, accompanied with the long timelines and high attrition rates. With the rapid growth of biomedical data enabled by advanced experimental technologies, artificial intelligence (AI) and machine learning (ML) have emerged as an indispensable tool to draw meaningful insights and improve decision making in drug discovery. Thanks to the advancements in AI and ML algorithms, now the AI/ML-driven solutions have an unprecedented potential to accelerate the process of CNS drug discovery with better success rate. In this review, we comprehensively summarize AI/ML-powered pharmaceutical discovery efforts and their implementations in the CNS area. After introducing the AI/ML models as well as the conceptualization and data preparation, we outline the applications of AI/ML technologies to several key procedures in drug discovery, including target identification, compound screening, hit/lead generation and optimization, drug response and synergy prediction, de novo drug design, and drug repurposing. We review the current state-of-the-art of AI/ML-guided CNS drug discovery, focusing on blood-brain barrier permeability prediction and implementation into therapeutic discovery for neurological diseases. Finally, we discuss the major challenges and limitations of current approaches and possible future directions that may provide resolutions to these difficulties.

Improving the therapeutic ratio of radiotherapy against radioresistant cancers: Leveraging on novel artificial intelligence-based approaches for drug combination discovery

Despite numerous advances in cancer radiotherapy, tumor radioresistance remain one of the major challenges limiting treatment efficacy of radiotherapy. Conventional strategies to overcome radioresistance involve understanding the underpinning molecular mechanisms, and subsequently using combinatorial treatment strategies involving radiation and targeted drug combinations against these radioresistant tumors. These strategies exploit and target the molecular fingerprint and vulnerability of the radioresistant clones to achieve improved efficacy in tumor eradication. However, conventional drug-screening approaches for the discovery of new drug combinations have been proven to be inefficient, limited and laborious. With the increasing availability of computational resources in recent years, novel approaches such as Quadratic Phenotypic Optimization Platform (QPOP), CURATE.AI and Drug Combination and Prediction and Testing (DCPT) platform have emerged to aid in drug combination discovery and the longitudinally optimized modulation of combination therapy dosing. These platforms could overcome the limitations of conventional screening approaches, thereby facilitating the discovery of more optimal drug combinations to improve the therapeutic ratio of combinatorial treatment. The use of better and more accurate models and methods with rapid turnover can thus facilitate a rapid translation in the clinic, hence, resulting in a better patient outcome. Here, we reviewed the clinical observations, molecular mechanisms and proposed treatment strategies for tumor radioresistance and discussed how novel approaches may be applied to enhance drug combination discovery, with the aim to further improve the therapeutic ratio and treatment efficacy of radiotherapy against radioresistant cancers.

Structural Bases for the Synergistic Inhibition of Human Thymidylate Synthase and Ovarian Cancer Cell Growth by Drug Combinations

Simple Summary

Drug combinations may help overcome drug resistance, a relevant cause of failure of ovarian cancer therapy. However, designing successful combinations requires a lengthy preclinical validation process. We have analyzed combinations of 5-fluorouracil and raltitrexed, two anticancer drugs that target thymidylate synthase, a key enzyme for the nucleotide synthesis. We have observed administration sequence specific and synergistic combined effects of the two drugs against cisplatin sensitive and resistant ovarian cancer cells. However, the focus of this work was to show that a high stability of the complex of the enzyme with the two drugs, as highlighted by X-ray crystallography, and synergistic inhibition of the enzyme represent indicators, if not prerequisites, for this drug combination to be synergistically active against sensitive and resistant ovarian cancer cells. We thus propose that structural and mechanistic information acquired during the preclinical research can help predict a successful therapeutic application of a drug combination.

Abstract

Combining drugs represent an approach to efficiently prevent and overcome drug resistance and to reduce toxicity; yet it is a highly challenging task, particularly if combinations of inhibitors of the same enzyme target are considered. To show that crystallographic and inhibition kinetic information can provide indicators of cancer cell growth inhibition by combinations of two anti-human thymidylate synthase (hTS) drugs, we obtained the X-ray crystal structure of the hTS:raltitrexed:5-fluorodeoxyuridine monophosphate (FdUMP) complex. Its analysis showed a ternary complex with both molecules strongly bound inside the enzyme catalytic cavity. The synergistic inhibition of hTS and its mechanistic rationale were consistent with the structural analysis. When administered in combination to A2780 and A2780/CP ovarian cancer cells, the two drugs inhibited ovarian cancer cell growth additively/synergistically. Together, these results support the idea that X-ray crystallography can provide structural indicators for designing combinations of hTS (or any other target)-directed drugs to accelerate preclinical research for therapeutic application.

Improved Treatment Outcomes by Using Patient Specific Drug Combinations in Mammalian Target of Rapamycin Activated Advanced Metastatic Cancers

Background: Activation of the mTOR signaling pathway is ubiquitous in cancers and a favourable therapeutic target. However, presently approved mTOR inhibitor monotherapies have modest benefits in labeled indications while poor outcomes have been reported for mTOR inhibitor monotherapy when administered in a label-agnostic setting based on univariate molecular indications. The present study aimed to determine whether patient-specific combination regimens with mTOR inhibitors and other anticancer agents selected based on multi-analyte molecular and functional tumor interrogation (ETA: Encyclopedic Tumor Analysis) yields significant treatment response and survival benefits in advanced or refractory solid organ cancers. Methods: We evaluated treatment outcomes in 49 patients diagnosed with unresectable or metastatic solid organ cancers, of whom 3 were therapy naïve and 46 were pre-treated in whom the cancer had progressed on 2 or more prior systemic lines. All patients received mTOR inhibitor in combination with other targeted, endocrine or cytotoxic agents as guided by ETA. Patients were followed-up to determine Objective Response Rate (ORR), Progression Free Survival (PFS) and Overall Survival (OS). Results: The Objective Response Rate (ORR) was 57.1%, the disease Control rate (DCR) was 91.8%, median Progression Free Survival (mPFS) was 4.9 months and median Overall Survival (mOS) was 9.4 months. There were no Grade IV treatment related adverse events (AEs) or any treatment related deaths. Conclusion: Patient-specific combination regimens with mTOR inhibition and other anti-neoplastic agents, when selected based on multi-analyte molecular and functional profiling of the tumor can yield meaningful outcomes in advanced or refractory solid organ cancers. Trial Registration: Details of all trials are available at WHO-ICTRP: https://apps.who.int/trialsearch/. RESILIENT ID CTRI/2018/02/011808. ACTPRO ID CTRI/2018/05/014178. LIQUID IMPACT ID CTRI/2019/02/017548.

Efficacy of combination treatment using YHO-1701, an orally active STAT3 inhibitor, with molecular-targeted agents on cancer cell lines

Signal transducer and activator of transcription 3 (STAT3) plays a critical role in regulating cell growth, survival, and metastasis. STAT3 signaling is constitutively activated in various types of hematologic or solid malignancies. YHO-1701 has been developed as an orally available STAT3 inhibitor. Herein, YHO-1701 in combination with molecular-targeted agents was evaluated. Additive or synergistic effects were observed in a broad spectrum of “combination treatment + cell line” pairs. Of particular interest was the synergistic effect observed when YHO-1701 was combined with imatinib or dasatinib [breakpoint cluster region-abelson (BCR-ABL) inhibitors], osimertinib [epidermal growth factor receptor (EGFR) inhibitor], crizotinib, alectinib, or ceritinib [anaplastic lymphoma kinase (ALK) inhibitors]. The results further showed a close relationship between these synergistic effects and the cellular levels of the key molecules involved in the target pathways for YHO-1701 and each combination drug. The combination of YHO-1701 with alectinib resulted in significantly greater antitumor activity without exhibiting body weight loss in an NCI-H2228 [echinoderm microtubule-associated protein-like 4 (EML4)-ALK fusion] xenograft mouse model. Our results strongly suggest that the logical strategy in combination with the novel STAT3 inhibitor YHO-1701 and other mechanistically different targeted agents, could be a promising approach in future clinical settings.

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.

Pathway-Based Drug-Repurposing Schemes in Cancer: The Role of Translational Bioinformatics

Cancer is a set of complex pathologies that has been recognized as a major public health problem worldwide for decades. A myriad of therapeutic strategies is indeed available. However, the wide variability in tumor physiology, response to therapy, added to multi-drug resistance poses enormous challenges in clinical oncology. The last years have witnessed a fast-paced development of novel experimental and translational approaches to therapeutics, that supplemented with computational and theoretical advances are opening promising avenues to cope with cancer defiances. At the core of these advances, there is a strong conceptual shift from gene-centric emphasis on driver mutations in specific oncogenes and tumor suppressors-let us call that the silver bullet approach to cancer therapeutics-to a systemic, semi-mechanistic approach based on pathway perturbations and global molecular and physiological regulatory patterns-we will call this the shrapnel approach. The silver bullet approach is still the best one to follow when clonal mutations in driver genes are present in the patient, and when there are targeted therapies to tackle those. Unfortunately, due to the heterogeneous nature of tumors this is not the common case. The wide molecular variability in the mutational level often is reduced to a much smaller set of pathway-based dysfunctions as evidenced by the well-known hallmarks of cancer. In such cases "shrapnel gunshots" may become more effective than "silver bullets". Here, we will briefly present both approaches and will abound on the discussion on the state of the art of pathway-based therapeutic designs from a translational bioinformatics and computational oncology perspective. Further development of these approaches depends on building collaborative, multidisciplinary teams to resort to the expertise of clinical oncologists, oncological surgeons, and molecular oncologists, but also of cancer cell biologists and pharmacologists, as well as bioinformaticians, computational biologists and data scientists. These teams will be capable of engaging on a cycle of analyzing high-throughput experiments, mining databases, researching on clinical data, validating the findings, and improving clinical outcomes for the benefits of the oncological patients.

CellMiner Cross-Database (CellMinerCDB) version 1.2: Exploration of patient-derived cancer cell line pharmacogenomics

CellMiner Cross-Database (CellMinerCDB, discover.nci.nih.gov/cellminercdb) allows integration and analysis of molecular and pharmacological data within and across cancer cell line datasets from the National Cancer Institute (NCI), Broad Institute, Sanger/MGH and MD Anderson Cancer Center (MDACC). We present CellMinerCDB 1.2 with updates to datasets from NCI-60, Broad Cancer Cell Line Encyclopedia and Sanger/MGH, and the addition of new datasets, including NCI-ALMANAC drug combination, MDACC Cell Line Project proteomic, NCI-SCLC DNA copy number and methylation data, and Broad methylation, genetic dependency and metabolomic datasets. CellMinerCDB (v1.2) includes several improvements over the previously published version: (i) new and updated datasets; (ii) support for pattern comparisons and multivariate analyses across data sources; (iii) updated annotations with drug mechanism of action information and biologically relevant multigene signatures; (iv) analysis speedups via caching; (v) a new dataset download feature; (vi) improved visualization of subsets of multiple tissue types; (vii) breakdown of univariate associations by tissue type; and (viii) enhanced help information. The curation and common annotations (e.g. tissues of origin and identifiers) provided here across pharmacogenomic datasets increase the utility of the individual datasets to address multiple researcher question types, including data reproducibility, biomarker discovery and multivariate analysis of drug activity.

Leveraging multi-way interactions for systematic prediction of pre-clinical drug combination effects

We present comboFM, a machine learning framework for predicting the responses of drug combinations in pre-clinical studies, such as those based on cell lines or patient-derived cells. comboFM models the cell context-specific drug interactions through higher-order tensors, and efficiently learns latent factors of the tensor using powerful factorization machines. The approach enables comboFM to leverage information from previous experiments performed on similar drugs and cells when predicting responses of new combinations in so far untested cells; thereby, it achieves highly accurate predictions despite sparsely populated data tensors. We demonstrate high predictive performance of comboFM in various prediction scenarios using data from cancer cell line pharmacogenomic screens. Subsequent experimental validation of a set of previously untested drug combinations further supports the practical and robust applicability of comboFM. For instance, we confirm a novel synergy between anaplastic lymphoma kinase (ALK) inhibitor crizotinib and proteasome inhibitor bortezomib in lymphoma cells. Overall, our results demonstrate that comboFM provides an effective means for systematic pre-screening of drug combinations to support precision oncology applications.

Combinatorial treatments have become a standard of care for various complex diseases including cancers. Here, the authors show that combinatorial responses of two anticancer drugs can be accurately predicted using factorization machines trained on large-scale pharmacogenomic data for guiding precision oncology studies.

A Middle-Out Modeling Strategy to Extend a Colon Cancer Logical Model Improves Drug Synergy Predictions in Epithelial-Derived Cancer Cell Lines

Cancer is a heterogeneous and complex disease and one of the leading causes of death worldwide. The high tumor heterogeneity between individuals affected by the same cancer type is accompanied by distinct molecular and phenotypic tumor profiles and variation in drug treatment response. In silico modeling of cancer as an aberrantly regulated system of interacting signaling molecules provides a basis to enhance our biological understanding of disease progression, and it offers the means to use computer simulations to test and optimize drug therapy designs on particular cancer types and subtypes. This sets the stage for precision medicine: the design of treatments tailored to individuals or groups of patients based on their tumor-specific molecular cancer profiles. Here, we show how a relatively large manually curated logical model can be efficiently enhanced further by including components highlighted by a multi-omics data analysis of data from Consensus Molecular Subtypes covering colorectal cancer. The model expansion was performed in a pathway-centric manner, following a partitioning of the model into functional subsystems, named modules. The resulting approach constitutes a middle-out modeling strategy enabling a data-driven expansion of a model from a generic and intermediate level of molecular detail to a model better covering relevant processes that are affected in specific cancer subtypes, comprising 183 biological entities and 603 interactions between them, partitioned in 25 functional modules of varying size and structure. We tested this model for its ability to correctly predict drug combination synergies, against a dataset of experimentally determined cell growth responses with 18 drugs in all combinations, on eight cancer cell lines. The results indicate that the extended model had an improved accuracy for drug synergy prediction for the majority of the experimentally tested cancer cell lines, although significant improvements of the model's predictive performance are still needed. Our study demonstrates how a tumor-data driven middle-out approach toward refining a logical model of a biological system can further customize a computer model to represent specific cancer cell lines and provide a basis for identifying synergistic effects of drugs targeting specific regulatory proteins. This approach bridges between preclinical cancer model data and clinical patient data and may thereby ultimately be of help to develop patient-specific in silico models that can steer treatment decisions in the clinic.

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.

Efficient prediction of drug-drug interaction using deep learning models

A drug-drug interaction or drug synergy is extensively utilised for cancer treatment. However, prediction of drug-drug interaction is defined as an ill-posed problem, because manual testing is only implementable on small group of drugs. Predicting the drug-drug interaction score has been a popular research topic recently. Recently many machine learning models have proposed in the literature to predict the drug-drug interaction score efficiently. However, these models suffer from the over-fitting issue. Therefore, these models are not so-effective for predicting the drug-drug interaction score. In this work, an integrated convolutional mixture density recurrent neural network is proposed and implemented. The proposed model integrates convolutional neural networks, recurrent neural networks and mixture density networks. Extensive comparative analysis reveals that the proposed model significantly outperforms the competitive models.

Repositioning of 8565 Existing Drugs for COVID-19

The coronavirus disease 2019 (COVID-19) pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has infected over 7.1 million people and led to over 0.4 million deaths. Currently, there is no specific anti-SARS-CoV-2 medication. New drug discovery typically takes more than 10 years. Drug repositioning becomes one of the most feasible approaches for combating COVID-19. This work curates the largest available experimental data set for SARS-CoV-2 or SARS-CoV 3CL (main) protease inhibitors. On the basis of this data set, we develop validated machine learning models with relatively low root-mean-square error to screen 1553 FDA-approved drugs as well as another 7012 investigational or off-market drugs in DrugBank. We found that many existing drugs might be potentially potent to SARS-CoV-2. The druggability of many potent SARS-CoV-2 3CL protease inhibitors is analyzed. This work offers a foundation for further experimental studies of COVID-19 drug repositioning.

Concise Polygenic Models for Cancer-Specific Identification of Drug-Sensitive Tumors from Their Multi-Omics Profiles

In silico models to predict which tumors will respond to a given drug are necessary for Precision Oncology. However, predictive models are only available for a handful of cases (each case being a given drug acting on tumors of a specific cancer type). A way to generate predictive models for the remaining cases is with suitable machine learning algorithms that are yet to be applied to existing in vitro pharmacogenomics datasets. Here, we apply XGBoost integrated with a stringent feature selection approach, which is an algorithm that is advantageous for these high-dimensional problems. Thus, we identified and validated 118 predictive models for 62 drugs across five cancer types by exploiting four molecular profiles (sequence mutations, copy-number alterations, gene expression, and DNA methylation). Predictive models were found in each cancer type and with every molecular profile. On average, no omics profile or cancer type obtained models with higher predictive accuracy than the rest. However, within a given cancer type, some molecular profiles were overrepresented among predictive models. For instance, CNA profiles were predictive in breast invasive carcinoma (BRCA) cell lines, but not in small cell lung cancer (SCLC) cell lines where gene expression (GEX) and DNA methylation profiles were the most predictive. Lastly, we identified the best XGBoost model per cancer type and analyzed their selected features. For each model, some of the genes in the selected list had already been found to be individually linked to the response to that drug, providing additional evidence of the usefulness of these models and the merits of the feature selection scheme.

QSAR-derived affinity fingerprints (part 2): modeling performance for potency prediction

Affinity fingerprints report the activity of small molecules across a set of assays, and thus permit to gather information about the bioactivities of structurally dissimilar compounds, where models based on chemical structure alone are often limited, and model complex biological endpoints, such as human toxicity and in vitro cancer cell line sensitivity. Here, we propose to model in vitro compound activity using computationally predicted bioactivity profiles as compound descriptors. To this aim, we apply and validate a framework for the calculation of QSAR-derived affinity fingerprints (QAFFP) using a set of 1360 QSAR models generated using K_i, K_d, IC₅₀ and EC₅₀ data from ChEMBL database. QAFFP thus represent a method to encode and relate compounds on the basis of their similarity in bioactivity space. To benchmark the predictive power of QAFFP we assembled IC₅₀ data from ChEMBL database for 18 diverse cancer cell lines widely used in preclinical drug discovery, and 25 diverse protein target data sets. This study complements part 1 where the performance of QAFFP in similarity searching, scaffold hopping, and bioactivity classification is evaluated. Despite being inherently noisy, we show that using QAFFP as descriptors leads to errors in prediction on the test set in the ~ 0.65-0.95 pIC₅₀ units range, which are comparable to the estimated uncertainty of bioactivity data in ChEMBL (0.76-1.00 pIC₅₀ units). We find that the predictive power of QAFFP is slightly worse than that of Morgan2 fingerprints and 1D and 2D physicochemical descriptors, with an effect size in the 0.02-0.08 pIC₅₀ units range. Including QSAR models with low predictive power in the generation of QAFFP does not lead to improved predictive power. Given that the QSAR models we used to compute the QAFFP were selected on the basis of data availability alone, we anticipate better modeling results for QAFFP generated using more diverse and biologically meaningful targets. Data sets and Python code are publicly available at https://github.com/isidroc/QAFFP_regression .

DTF: Deep Tensor Factorization for predicting anticancer drug synergy

Motivation

Combination therapies have been widely used to treat cancers. However, it is cost and time consuming to experimentally screen synergistic drug pairs due to the enormous number of possible drug combinations. Thus, computational methods have become an important way to predict and prioritize synergistic drug pairs.

Results

We proposed a Deep Tensor Factorization (DTF) model, which integrated a tensor factorization method and a deep neural network (DNN), to predict drug synergy. The former extracts latent features from drug synergy information while the latter constructs a binary classifier to predict the drug synergy status. Compared to the tensor-based method, the DTF model performed better in predicting drug synergy. The area under precision-recall curve (PR AUC) was 0.58 for DTF and 0.24 for the tensor method. We also compared the DTF model with DeepSynergy and logistic regression models, and found that the DTF outperformed the logistic regression model and achieved similar performance as DeepSynergy using several performance metrics for classification task. Applying the DTF model to predict missing entries in our drug–cell-line tensor, we identified novel synergistic drug combinations for 10 cell lines from the 5 cancer types. A literature survey showed that some of these predicted drug synergies have been identified in vivo or in vitro. Thus, the DTF model could be a valuable in silico tool for prioritizing novel synergistic drug combinations.

Availability and implementation

Source code and data are available at https://github.com/ZexuanSun/DTF-Drug-Synergy.

Supplementary information

Supplementary data are available at Bioinformatics online.

Deep graph embedding for prioritizing synergistic anticancer drug combinations

Drug combinations are frequently used for the treatment of cancer patients in order to increase efficacy, decrease adverse side effects, or overcome drug resistance. Given the enormous number of drug combinations, it is cost- and time-consuming to screen all possible drug pairs experimentally. Currently, it has not been fully explored to integrate multiple networks to predict synergistic drug combinations using recently developed deep learning technologies. In this study, we proposed a Graph Convolutional Network (GCN) model to predict synergistic drug combinations in particular cancer cell lines. Specifically, the GCN method used a convolutional neural network model to do heterogeneous graph embedding, and thus solved a link prediction task. The graph in this study was a multimodal graph, which was constructed by integrating the drug-drug combination, drug-protein interaction, and protein-protein interaction networks. We found that the GCN model was able to correctly predict cell line-specific synergistic drug combinations from a large heterogonous network. The majority (30) of the 39 cell line-specific models show an area under the receiver operational characteristic curve (AUC) larger than 0.80, resulting in a mean AUC of 0.84. Moreover, we conducted an in-depth literature survey to investigate the top predicted drug combinations in specific cancer cell lines and found that many of them have been found to show synergistic antitumor activity against the same or other cancers in vitro or in vivo. Taken together, the results indicate that our study provides a promising way to better predict and optimize synergistic drug pairs in silico.