Modeling of signaling crosstalk-mediated drug resistance and its implications on drug combination

MMSyn: A New Multimodal Deep Learning Framework for Enhanced Prediction of Synergistic Drug Combinations

Combination therapy is a promising strategy for the successful treatment of cancer. The large number of possible combinations, however, mean that it is laborious and expensive to screen for synergistic drug combinations in vitro. Nevertheless, because of the availability of high-throughput screening data and advances in computational techniques, deep learning (DL) can be a useful tool for the prediction of synergistic drug combinations. In this study, we proposed a multimodal DL framework, MMSyn, for the prediction of synergistic drug combinations. First, features embedded in the drug molecules were extracted: structure, fingerprint, and string encoding. Then, gene expression data, DNA copy number, and pathway activity were used to describe cancer cell lines. Finally, these processed features were integrated using an attention mechanism and an interaction module and then input into a multilayer perceptron to predict drug synergy. Experimental results showed that our method outperformed five state-of-the-art DL methods and three traditional machine learning models for drug combination prediction. We verified that MMSyn achieved superior performance in stratified cross-validation settings using both the drug combination and cell line data. Moreover, we performed a set of ablation experiments to illustrate the effectiveness of each component and the efficacy of our model. In addition, our visual representation and case studies further confirmed the effectiveness of our model. All results showed that MMSyn can be used as a powerful tool for the prediction of synergistic drug combinations.

Sesquiterpene lactones as emerging biomolecules to cease cancer by targeting apoptosis

Apoptosis is a programmed cell death comprising two signaling cascades including the intrinsic and extrinsic pathways. This process has been shown to be involved in the therapy response of different cancer types, making it an effective target for treating cancer. Cancer has been considered a challenging issue in global health. Cancer cells possess six biological characteristics during their developmental process known as cancer hallmarks. Hallmarks of cancer include continuous growth signals, unlimited proliferation, resistance to proliferation inhibitors, apoptosis escaping, active angiogenesis, and metastasis. Sesquiterpene lactones are one of the large and diverse groups of planet-derived phytochemicals that can be used as sources for a variety of drugs. Some sesquiterpene lactones possess many biological activities such as anti-inflammatory, anti-viral, anti-microbial, anti-malarial, anticancer, anti-diabetic, and analgesic. This review article briefly overviews the intrinsic and extrinsic pathways of apoptosis and the interactions between the modulators of both pathways. Also, the present review summarizes the potential effects of sesquiterpene lactones on different modulators of the intrinsic and extrinsic pathways of apoptosis in a variety of cancer cell lines and animal models. The main purpose of the present review is to give a clear picture of the current knowledge about the pro-apoptotic effects of sesquiterpene lactones on various cancers to provide future direction in cancer therapeutics.

KGANSynergy: knowledge graph attention network for drug synergy prediction

Combination therapy is widely used to treat complex diseases, particularly in patients who respond poorly to monotherapy. For example, compared with the use of a single drug, drug combinations can reduce drug resistance and improve the efficacy of cancer treatment. Thus, it is vital for researchers and society to help develop effective combination therapies through clinical trials. However, high-throughput synergistic drug combination screening remains challenging and expensive in the large combinational space, where an array of compounds are used. To solve this problem, various computational approaches have been proposed to effectively identify drug combinations by utilizing drug-related biomedical information. In this study, considering the implications of various types of neighbor information of drug entities, we propose a novel end-to-end Knowledge Graph Attention Network to predict drug synergy (KGANSynergy), which utilizes neighbor information of known drugs/cell lines effectively. KGANSynergy uses knowledge graph (KG) hierarchical propagation to find multi-source neighbor nodes for drugs and cell lines. The knowledge graph attention network is designed to distinguish the importance of neighbors in a KG through a multi-attention mechanism and then aggregate the entity's neighbor node information to enrich the entity. Finally, the learned drug and cell line embeddings can be utilized to predict the synergy of drug combinations. Experiments demonstrated that our method outperformed several other competing methods, indicating that our method is effective in identifying drug combinations.

DFFNDDS: prediction of synergistic drug combinations with dual feature fusion networks

Drug combination therapies are promising clinical treatments for curing patients. However, efficiently identifying valid drug combinations remains challenging because the number of available drugs has increased rapidly. In this study, we proposed a deep learning model called the Dual Feature Fusion Network for Drug-Drug Synergy prediction (DFFNDDS) that utilizes a fine-tuned pretrained language model and dual feature fusion mechanism to predict synergistic drug combinations. The dual feature fusion mechanism fuses the drug features and cell line features at the bit-wise level and the vector-wise level. We demonstrated that DFFNDDS outperforms competitive methods and can serve as a reliable tool for identifying synergistic drug combinations.

DEML: Drug Synergy and Interaction Prediction Using Ensemble-Based Multi-Task Learning

Synergistic drug combinations have demonstrated effective therapeutic effects in cancer treatment. Deep learning methods accelerate identification of novel drug combinations by reducing the search space. However, potential adverse drug-drug interactions (DDIs), which may increase the risks for combination therapy, cannot be detected by existing computational synergy prediction methods. We propose DEML, an ensemble-based multi-task neural network, for the simultaneous optimization of five synergy regression prediction tasks, synergy classification, and DDI classification tasks. DEML uses chemical and transcriptomics information as inputs. DEML adapts the novel hybrid ensemble layer structure to construct higher order representation using different perspectives. The task-specific fusion layer of DEML joins representations for each task using a gating mechanism. For the Loewe synergy prediction task, DEML overperforms the state-of-the-art synergy prediction method with an improvement of 7.8% and 13.2% for the root mean squared error and the R2 correlation coefficient. Owing to soft parameter sharing and ensemble learning, DEML alleviates the multi-task learning 'seesaw effect' problem and shows no performance loss on other tasks. DEML has a superior ability to predict drug pairs with high confidence and less adverse DDIs. DEML provides a promising way to guideline novel combination therapy strategies for cancer treatment.

A review of deep learning applications in human genomics using next-generation sequencing data

Genomics is advancing towards data-driven science. Through the advent of high-throughput data generating technologies in human genomics, we are overwhelmed with the heap of genomic data. To extract knowledge and pattern out of this genomic data, artificial intelligence especially deep learning methods has been instrumental. In the current review, we address development and application of deep learning methods/models in different subarea of human genomics. We assessed over- and under-charted area of genomics by deep learning techniques. Deep learning algorithms underlying the genomic tools have been discussed briefly in later part of this review. Finally, we discussed briefly about the late application of deep learning tools in genomic. Conclusively, this review is timely for biotechnology or genomic scientists in order to guide them why, when and how to use deep learning methods to analyse human genomic data.

An enhanced cascade-based deep forest model for drug combination prediction

Combination therapy has shown an obvious curative effect on complex diseases, whereas the search space of drug combinations is too large to be validated experimentally even with high-throughput screens. With the increase of the number of drugs, artificial intelligence techniques, especially machine learning methods, have become applicable for the discovery of synergistic drug combinations to significantly reduce the experimental workload. In this study, in order to predict novel synergistic drug combinations in various cancer cell lines, the cell line-specific drug-induced gene expression profile (GP) is added as a new feature type to capture the cellular response of drugs and reveal the biological mechanism of synergistic effect. Then, an enhanced cascade-based deep forest regressor (EC-DFR) is innovatively presented to apply the new small-scale drug combination dataset involving chemical, physical and biological (GP) properties of drugs and cells. Verified by the dataset, EC-DFR outperforms two state-of-the-art deep neural network-based methods and several advanced classical machine learning algorithms. Biological experimental validation performed subsequently on a set of previously untested drug combinations further confirms the performance of EC-DFR. What is more prominent is that EC-DFR can distinguish the most important features, making it more interpretable. By evaluating the contribution of each feature type, GP feature contributes 82.40%, showing the cellular responses of drugs may play crucial roles in synergism prediction. The analysis based on the top contributing genes in GP further demonstrates some potential relationships between the transcriptomic levels of key genes under drug regulation and the synergism of drug combinations.

XDeathDB: a visualization platform for cell death molecular interactions

Lots of cell death initiator and effector molecules, signalling pathways and subcellular sites have been identified as key mediators in both cell death processes in cancer. The XDeathDB visualization platform provides a comprehensive cell death and their crosstalk resource for deciphering the signaling network organization of interactions among different cell death modes associated with 1461 cancer types and COVID-19, with an aim to understand the molecular mechanisms of physiological cell death in disease and facilitate systems-oriented novel drug discovery in inducing cell deaths properly. Apoptosis, autosis, efferocytosis, ferroptosis, immunogenic cell death, intrinsic apoptosis, lysosomal cell death, mitotic cell death, mitochondrial permeability transition, necroptosis, parthanatos, and pyroptosis related to 12 cell deaths and their crosstalk can be observed systematically by the platform. Big data for cell death gene-disease associations, gene-cell death pathway associations, pathway-cell death mode associations, and cell death-cell death associations is collected by literature review articles and public database from iRefIndex, STRING, BioGRID, Reactom, Pathway's commons, DisGeNET, DrugBank, and Therapeutic Target Database (TTD). An interactive webtool, XDeathDB, is built by web applications with R-Shiny, JavaScript (JS) and Shiny Server Iso. With this platform, users can search specific interactions from vast interdependent networks that occur in the realm of cell death. A multilayer spectral graph clustering method that performs convex layer aggregation to identify crosstalk function among cell death modes for a specific cancer. 147 hallmark genes of cell death could be observed in detail in these networks. These potential druggable targets are displayed systematically and tailoring networks to visualize specified relations is available to fulfil user-specific needs. Users can access XDeathDB for free at https://pcm2019.shinyapps.io/XDeathDB/ .

Prediction of synergistic drug combinations using PCA-initialized deep learning

Background

Cancer is one of the main causes of death worldwide. Combination drug therapy has been a mainstay of cancer treatment for decades and has been shown to reduce host toxicity and prevent the development of acquired drug resistance. However, the immense number of possible drug combinations and large synergistic space makes it infeasible to screen all effective drug pairs experimentally. Therefore, it is crucial to develop computational approaches to predict drug synergy and guide experimental design for the discovery of rational combinations for therapy.

Results

We present a new deep learning approach to predict synergistic drug combinations by integrating gene expression profiles from cell lines and chemical structure data. Specifically, we use principal component analysis (PCA) to reduce the dimensionality of the chemical descriptor data and gene expression data. We then propagate the low-dimensional data through a neural network to predict drug synergy values. We apply our method to O’Neil’s high-throughput drug combination screening data as well as a dataset from the AstraZeneca-Sanger Drug Combination Prediction DREAM Challenge. We compare the neural network approach with and without dimension reduction. Additionally, we demonstrate the effectiveness of our deep learning approach and compare its performance with three state-of-the-art machine learning methods: Random Forests, XGBoost, and elastic net, with and without PCA-based dimensionality reduction.

Conclusions

Our developed approach outperforms other machine learning methods, and the use of dimension reduction dramatically decreases the computation time without sacrificing accuracy.

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.

Co-Targeting Plk1 and DNMT3a in Advanced Prostate Cancer

Because there is no effective treatment for late-stage prostate cancer (PCa) at this moment, identifying novel targets for therapy of advanced PCa is urgently needed. A new network-based systems biology approach, XDeath, is developed to detect crosstalk of signaling pathways associated with PCa progression. This unique integrated network merges gene causal regulation networks and protein-protein interactions to identify novel co-targets for PCa treatment. The results show that polo-like kinase 1 (Plk1) and DNA methyltransferase 3A (DNMT3a)-related signaling pathways are robustly enhanced during PCa progression and together they regulate autophagy as a common death mode. Mechanistically, it is shown that Plk1 phosphorylation of DNMT3a leads to its degradation in mitosis and that DNMT3a represses Plk1 transcription to inhibit autophagy in interphase, suggesting a negative feedback loop between these two proteins. Finally, a combination of the DNMT inhibitor 5-Aza-2'-deoxycytidine (5-Aza) with inhibition of Plk1 suppresses PCa synergistically.

GLI1 reduces drug sensitivity by regulating cell cycle through PI3K/AKT/GSK3/CDK pathway in acute myeloid leukemia

Acute myeloid leukemia (AML) is a hematological malignancy with high incidence and recurrence rates. Gene expression profiling has revealed that transcriptional overexpression of glioma-associated oncogene 1 (GLI1), a vital gene in the Hedgehog (Hh) signaling pathway, occurs in poor-prognosis AML, and high levels of phosphoinositide-3-kinase, regulatory subunit 1 (PIK3R1) and AKT3 predict shorter overall survival in AML patients. In this study, we discovered that GLI1 overexpression promotes cell proliferation and reduces chemotherapy sensitivity in AML cells while knocking down GLI1 has the opposite effect. Moreover, GLI1 promoted cell cycle progression and led to elevated protein levels of cyclins and cyclin-dependent kinases (CDKs) in AML cells. By luciferase assays and co-immunoprecipitation, we demonstrated that the PI3K/AKT pathway is directly activated by GLI1. GLI1 overexpression significantly accelerates tumor growth and upregulated p-AKT, CDK4, and cyclinD3 in vivo. Notably, the GLI1 inhibitor GANT61 and the CDK4/6 inhibitor PD 0332991 had synergistic effects in promoting Ara-c sensitivity in AML cell lines and patient samples. Collectively, our data demonstrate that GLI1 reduces drug sensitivity by regulating cell cycle through the PI3K/AKT/GSK3/CDK pathway, providing a new perspective for involving GLI1 and CDK4/6 inhibitors in relapsed/refractory (RR) patient treatment.

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.

The Crosstalk between FAK and Wnt Signaling Pathways in Cancer and Its Therapeutic Implication

Focal adhesion kinase (FAK) and Wnt signaling pathways are important contributors to tumorigenesis in several cancers. While most results come from studies investigating these pathways individually, there is increasing evidence of a functional crosstalk between both signaling pathways during development and tumor progression. A number of FAK-Wnt interactions are described, suggesting an intricate, context-specific, and cell type-dependent relationship. During development for instance, FAK acts mainly upstream of Wnt signaling; and although in intestinal homeostasis and mucosal regeneration Wnt seems to function upstream of FAK signaling, FAK activates the Wnt/β-catenin signaling pathway during APC-driven intestinal tumorigenesis. In breast, lung, and pancreatic cancers, FAK is reported to modulate the Wnt signaling pathway, while in prostate cancer, FAK is downstream of Wnt. In malignant mesothelioma, FAK and Wnt show an antagonistic relationship: Inhibiting FAK signaling activates the Wnt pathway and vice versa. As the identification of effective Wnt inhibitors to translate in the clinical setting remains an outstanding challenge, further understanding of the functional interaction between Wnt and FAK could reveal new therapeutic opportunities and approaches greatly needed in clinical oncology. In this review, we summarize some of the most relevant interactions between FAK and Wnt in different cancers, address the current landscape of Wnt- and FAK-targeted therapies in different clinical trials, and discuss the rationale for targeting the FAK-Wnt crosstalk, along with the possible translational implications.

Parallel Tempering with Lasso for model reduction in systems biology

Systems Biology models reveal relationships between signaling inputs and observable molecular or cellular behaviors. The complexity of these models, however, often obscures key elements that regulate emergent properties. We use a Bayesian model reduction approach that combines Parallel Tempering with Lasso regularization to identify minimal subsets of reactions in a signaling network that are sufficient to reproduce experimentally observed data. The Bayesian approach finds distinct reduced models that fit data equivalently. A variant of this approach that uses Lasso to perform selection at the level of reaction modules is applied to the NF-κB signaling network to test the necessity of feedback loops for responses to pulsatile and continuous pathway stimulation. Taken together, our results demonstrate that Bayesian parameter estimation combined with regularization can isolate and reveal core motifs sufficient to explain data from complex signaling systems.

Cells respond to diverse environmental cues using complex networks of interacting proteins and other biomolecules. Mathematical and computational models have become invaluable tools to understand these networks and make informed predictions to rationally perturb cell behavior. However, the complexity of detailed models that try to capture all known biochemical elements of signaling networks often makes it difficult to determine the key regulatory elements that are responsible for specific cell behaviors. Here, we present a Bayesian computational approach, PTLasso, to automatically extract minimal subsets of detailed models that are sufficient to explain experimental data. The method simultaneously calibrates and reduces models, and the Bayesian approach samples globally, allowing us to find alternate mechanistic explanations for the data if present. We demonstrate the method on both synthetic and real biological data and show that PTLasso is an effective method to isolate distinct parts of a larger signaling model that are sufficient for specific data.

A Proteomic Connectivity Map for Characterizing the Tumor Adaptive Response to Small Molecule Chemical Perturbagens

A powerful means to understand the cellular function of corrupt oncogenic signaling programs requires perturbing the system and monitoring the downstream consequences. Here, using a unique pair of non-small cell lung cancer (NSCLC)/normal lung epithelial patient-derived cell lines (HCC4017/HBEC30KT), we systematically interrogated the remodeling of the NSCLC proteome upon treatment with 35 chemical perturbagens targeting a diverse array of mechanistic classes. HCC4017 and HBEC30KT cells differ significantly in their proteomic response to the same compound treatment. Using protein covariance analyses, we identified a large number of functional protein networks. For example, we found that a poorly studied protein, C5orf22, is a novel component of the WBP11/PQBP1 splicing complex. Depletion of C5orf22 leads to the aberrant splicing and expression of genes involved in cell growth and immunomodulation. In summary, we show that by systematically measuring the tumor adaptive responses at the proteomic level, an understanding could be generated that provides critical circuit-level biological insights for these pharmacologic perturbagens.

PTPRS drives adaptive resistance to MEK/ERK inhibitors through SRC

PTPRS is the most commonly mutated receptor tyrosine phosphatase in colorectal cancer (CRC). PTPRS has been shown to directly affect ERK and regulate its activation and nuclear localization. Here we identify that PTPRS may play a significant role in developing adaptive resistance to MEK/ERK inhibitors (MEKi/ERKi) through SRC activation. Moreover, we demonstrate a new clinical approach to averting adaptive resistance through the use of the SRC inhibitor, dasatinib. Our data suggest the potential for dasatinib to enhance the efficacy of MEKi and ERKi by preventing adaptive resistance pathways operating through SRC.

Differential regulatory network-based quantification and prioritization of key genes underlying cancer drug resistance based on time-course RNA-seq data

Drug resistance is a major cause for the failure of cancer chemotherapy or targeted therapy. However, the molecular regulatory mechanisms controlling the dynamic evolvement of drug resistance remain poorly understood. Thus, it is important to develop methods for identifying key gene regulatory mechanisms of the resistance to specific drugs. In this study, we developed a data-driven computational framework, DryNetMC, using a differential regulatory network-based modeling and characterization strategy to quantify and prioritize key genes underlying cancer drug resistance. The DryNetMC does not only infer gene regulatory networks (GRNs) via an integrated approach, but also characterizes and quantifies dynamical network properties for measuring node importance. We used time-course RNA-seq data from glioma cells treated with dbcAMP (a cAMP activator) as a realistic case to reconstruct the GRNs for sensitive and resistant cells. Based on a novel node importance index that comprehensively quantifies network topology, network entropy and expression dynamics, the top ranked genes were verified to be predictive of the drug sensitivities of different glioma cell lines, in comparison with other existing methods. The proposed method provides a quantitative approach to gain insights into the dynamic adaptation and regulatory mechanisms of cancer drug resistance and sheds light on the design of novel biomarkers or targets for predicting or overcoming drug resistance.

Mathematical modeling and computational prediction of cancer drug resistance

Diverse forms of resistance to anticancer drugs can lead to the failure of chemotherapy. Drug resistance is one of the most intractable issues for successfully treating cancer in current clinical practice. Effective clinical approaches that could counter drug resistance by restoring the sensitivity of tumors to the targeted agents are urgently needed. As numerous experimental results on resistance mechanisms have been obtained and a mass of high-throughput data has been accumulated, mathematical modeling and computational predictions using systematic and quantitative approaches have become increasingly important, as they can potentially provide deeper insights into resistance mechanisms, generate novel hypotheses or suggest promising treatment strategies for future testing. In this review, we first briefly summarize the current progress of experimentally revealed resistance mechanisms of targeted therapy, including genetic mechanisms, epigenetic mechanisms, posttranslational mechanisms, cellular mechanisms, microenvironmental mechanisms and pharmacokinetic mechanisms. Subsequently, we list several currently available databases and Web-based tools related to drug sensitivity and resistance. Then, we focus primarily on introducing some state-of-the-art computational methods used in drug resistance studies, including mechanism-based mathematical modeling approaches (e.g. molecular dynamics simulation, kinetic model of molecular networks, ordinary differential equation model of cellular dynamics, stochastic model, partial differential equation model, agent-based model, pharmacokinetic–pharmacodynamic model, etc.) and data-driven prediction methods (e.g. omics data-based conventional screening approach for node biomarkers, static network approach for edge biomarkers and module biomarkers, dynamic network approach for dynamic network biomarkers and dynamic module network biomarkers, etc.). Finally, we discuss several further questions and future directions for the use of computational methods for studying drug resistance, including inferring drug-induced signaling networks, multiscale modeling, drug combinations and precision medicine.

Computational Approaches in Theranostics: Mining and Predicting Cancer Data

The ability to understand the complexity of cancer-related data has been prompted by the applications of (1) computer and data sciences, including data mining, predictive analytics, machine learning, and artificial intelligence, and (2) advances in imaging technology and probe development. Computational modelling and simulation are systematic and cost-effective tools able to identify important temporal/spatial patterns (and relationships), characterize distinct molecular features of cancer states, and address other relevant aspects, including tumor detection and heterogeneity, progression and metastasis, and drug resistance. These approaches have provided invaluable insights for improving the experimental design of therapeutic delivery systems and for increasing the translational value of the results obtained from early and preclinical studies. The big question is: Could cancer theranostics be determined and controlled in silico? This review describes the recent progress in the development of computational models and methods used to facilitate research on the molecular basis of cancer and on the respective diagnosis and optimized treatment, with particular emphasis on the design and optimization of theranostic systems. The current role of computational approaches is providing innovative, incremental, and complementary data-driven solutions for the prediction, simplification, and characterization of cancer and intrinsic mechanisms, and to promote new data-intensive, accurate diagnostics and therapeutics.

GLI1 overexpression promotes gastric cancer cell proliferation and migration and induces drug resistance by combining with the AKT-mTOR pathway

Hedgehog (HH) pathway significantly affected the pathogenesis of Gastric cancer (GC), but the multiple uncanonical HH pathways that are mediated by Zinc Finger protein GLI1 (GLI1) are still unclear. In the present work, we evaluated GLI1 and p-AKT expression in GC using immunohistochemistry (IHC) analysis. GLI1 and AKT specific shRNA was transfected into GC cell lines to investigate the cross-regulation between HH pathway and AKT-mTOR pathway. The effect of GLI1 and p-AKT on proliferation, migration, and drug resistance were examined. Moreover, a mouse xenograft model of GC was established to verify the role of GLI1 and p-AKT in promoting drug sensitivity in vivo. Our results suggested the clinicopathological factors and prognosis by the differential expression of GLI1 and p-AKT in GC patients. GLI1 was activated by the AKT-mTOR pathway. Co-expression of GLI1 and p-AKT was associated with cell viability, migration, and drug resistance and indicated a poor prognosis in GC patients. Agents targeted against both GLI1 and p-AKT may reverse drug-resistance and achieve better inhibition than agents targeted against a single molecule. There was a significant correlation between the high expression of GLI1 and p-AKT in GC. Additionally, our study confirmed the activity of the AKT-mTOR-GLI1 axis, which provided a new viable field for GC treatment.

Pathway crosstalk perturbation network modeling for identification of connectivity changes induced by diabetic neuropathy and pioglitazone

BACKGROUND

Aggregation of high-throughput biological data using pathway-based approaches is useful to associate molecular results to functional features related to the studied phenomenon. Biological pathways communicate with one another through the crosstalk phenomenon, forming large networks of interacting processes.

RESULTS

In this work, we present the pathway crosstalk perturbation network (PXPN) model, a novel model used to analyze and integrate pathway perturbation data based on graph theory. With this model, the changes in activity and communication between pathways observed in transitions between physiological states are represented as networks. The model presented here is agnostic to the type of biological data and pathway definition used and can be implemented to analyze any type of high-throughput perturbation experiments. We present a case study in which we use our proposed model to analyze a gene expression dataset derived from experiments in a BKS-db/db mouse model of type 2 diabetes mellitus-associated neuropathy (DN) and the effects of the drug pioglitazone in this condition. The networks generated describe the profile of pathway perturbation involved in the transitions between the healthy and the pathological state and the pharmacologically treated pathology. We identify changes in the connectivity of perturbed pathways associated to each biological transition, such as rewiring between extracellular matrix, neuronal system, and G-protein coupled receptor signaling pathways.

CONCLUSION

The PXPN model is a novel, flexible method used to integrate high-throughput data derived from perturbation experiments; it is agnostic to the type of data and enrichment function used, and it is applicable to a wide range of biological phenomena of interest.

Personalized Prediction of Acquired Resistance to EGFR-Targeted Inhibitors Using a Pathway-Based Machine Learning Approach

Epidermal growth factor receptor (EGFR) inhibitors have benefitted cancer patients worldwide, but resistance inevitably develops over time, resulting in treatment failures. An accurate prediction model for acquired resistance (AR) to EGFR inhibitors is critical for early diagnosis and according intervention, but is not yet available due to personal variations and the complex mechanisms of AR. Here, we have developed a novel pipeline to build a meta-analysis-based, multivariate model for personalized pathways in AR to EGFR inhibitors, using sophisticated machine learning algorithms. Surprisingly, the model achieved excellent predictive performance, with a cross-study validation area under curve (AUC) of over 0.9, and generalization performance on independent cohorts of samples, with a perfect AUC score of 1. Furthermore, the model showed excellent transferability across different cancer cell lines and EGFR inhibitors, including gefitinib, erlotinib, afatinib, and cetuximab. In conclusion, our model achieved high predictive accuracy through robust cross study validation, and enabled individualized prediction on newly introduced data. We also discovered common pathway alteration signatures for AR to EGFR inhibitors, which can provide directions for other follow-up studies.

A novel integrated action crossing method for drug-drug interaction prediction in non-communicable diseases

BACKGROUND AND OBJECTIVE

Drug-drug interaction (DDI) is one of the main causes of toxicity and treatment inefficacy. This work focuses on non-communicable diseases (NCDs), the non-transmissible and long-lasting diseases since they are the leading cause of death globally. Drugs that are used in NCDs increase the probability of DDIs as a result of long time usage. This work proposes an Integrated Action Crossing (IAC) method that is effective in predicting the NCDs DDIs based on pharmacokinetic (PK) mechanism.

METHODS

Drug-Enzyme (CYP450) and Drug-Transporter actions including substrate, inhibitor and inducer affect the PK mechanism of other drugs. Hence, this paper proposes an enzyme and transporter protein integrated action crossing method for DDIs prediction in NCDs. The NCDs Drugs information was retrieved from the DrugBank database and the actions of enzymes and transporter proteins that were crossed and integrated. The datasets were generated for machine training.

RESULTS

Three machine learning approaches: Support Vector Machine, k-Nearest Neighbors, and Neural Networks were used for the assessment of the method. Performance evaluation was performed through five-fold cross validation and the different datasets and learning methods were compared. Two layers NNs achieved the best performance at the accuracy of 83.15% (F-Measure 85.23% and AUC 0.901).

CONCLUSIONS

The IAC method delivers better performance compared to the conventional method for the identification of NCDs DDIs.

Drug-based perturbation screen uncovers synergistic drug combinations in Burkitt lymphoma

Burkitt lymphoma (BL) is a highly aggressive B-cell lymphoma associated with MYC translocation. Here, we describe drug response profiling of 42 blood cancer cell lines including 17 BL to 32 drugs targeting key cancer pathways and provide a systematic study of drug combinations in BL cell lines. Based on drug response, we identified cell line specific sensitivities, i.e. to venetoclax driven by BCL2 overexpression and partitioned subsets of BL driven by response to kinase inhibitors. In the combination screen, including BET, BTK and PI3K inhibitors, we identified synergistic combinations of PI3K and BTK inhibition with drugs targeting Akt, mTOR, BET and doxorubicin. A detailed comparison of PI3K and BTKi combinations identified subtle differences, in line with convergent pathway activity. Most synergistic combinations were identified for the BET inhibitor OTX015, which showed synergistic effects for 41% of combinations including inhibitors of PI3K/AKT/mTOR signalling. The strongest synergy was observed for the combination of the CDK 2/7/9 inhibitor SNS032 and OTX015. Our data provide a landscape of drug combination effects in BL and suggest that targeting CDK and BET could provide a novel vulnerability of BL.

An Integrated Local Classification Model of Predicting Drug-Drug Interactions via Dempster-Shafer Theory of Evidence

Drug-drug interactions (DDIs) may trigger adverse drug reactions, which endanger the patients. DDI identification before making clinical medications is critical but bears a high cost in clinics. Computational approaches, including global model-based and local model based, are able to screen DDI candidates among a large number of drug pairs by utilizing preliminary characteristics of drugs (e.g. drug chemical structure). However, global model-based approaches are usually slow and don't consider the topological structure of DDI network, while local model-based approaches have the degree-induced bias that a new drug tends to link to the drug having many DDI. All of them lack an effective ensemble method to combine results from multiple predictors. To address the first two issues, we propose a local classification-based model (LCM), which considers the topology of DDI network and has the relaxation of the degree-induced bias. Furthermore, we design a novel supervised fusion rule based on the Dempster-Shafer theory of evidence (LCM-DS), which aggregates the results from multiple LCMs. To make the final prediction, LCM-DS integrates three aspects from multiple classifiers, including the posterior probabilities output by individual classifiers, the proximity between their instance decision profiles and their reference profiles, as well as the quality of their reference profiles. Last, the substantial comparison with three state-of-the-art approaches demonstrates the effectiveness of our LCM, and the comparison with both individual LCM implementations and classical fusion algorithms exhibits the superiority of our LCM-DS.

Analysis of the Literature and Patents on Solid Dispersions from 1980 to 2015

Background: Solid dispersions are an effective formulation technique to improve the solubility, dissolution rate, and bioavailability of water-insoluble drugs for oral delivery. In the last 15 years, increased attention was focused on this technology. There were 23 marketed drugs prepared by solid dispersion techniques. Objective: This study aimed to report the big picture of solid dispersion research from 1980 to 2015. Method: Scientific knowledge mapping tools were used for the qualitative and the quantitative analysis of patents and literature from the time and space dimensions. Results: Western Europe and North America were the major research areas in this field with frequent international cooperation. Moreover, there was a close collaboration between universities and industries, while research collaboration in Asia mainly existed between universities. The model drugs, main excipients, preparation technologies, characterization approaches and the mechanism involved in the formulation of solid dispersions were analyzed via the keyword burst and co-citation cluster techniques. Integrated experimental, theoretical and computational tools were useful techniques for in silico formulation design of the solid dispersions. Conclusions: Our research provided the qualitative and the quantitative analysis of patents and literature of solid dispersions in the last three decades.

Ensemble Prediction of Synergistic Drug Combinations Incorporating Biological, Chemical, Pharmacological, and Network Knowledge

Combinatorial therapy may reduce drug side effects and improve drug efficacy, making combination therapy a promising strategy to treat complex diseases. However, in the existing computational methods, the natural properties and network knowledge of drugs have not been adequately and simultaneously considered, making it difficult to identify effective drug combinations. Computational methods that incorporate multiple sources of information (biological, chemical, pharmacological, and network knowledge) offer more opportunities to screen synergistic drug combinations. Therefore, we developed a novel Ensemble Prediction framework of Synergistic Drug Combinations (EPSDC) to accurately and efficiently predict drug combinations by integrating information from multiple-sources. EPSDC constructs feature vector of drug pair by concatenating different types of drug similarities, and then uses these groups in a feature-based base predictor. Next, transductive learning is applied on heterogeneous drug-target networks to achieve a network-based score for the drug pair. Finally, two types of ensemble rules are introduced to combine the feature-based score and the network-based score, and then potential drug combinations are prioritized. To demonstrate the effect of the ensemble rule, comprehensive experiments were conducted to compare single models and ensemble models. The experimental results indicated that our method outperformed the state-of-the-art method in five-fold cross validation and de novo prediction tests on the two benchmark datasets. We further analyzed the effect of maximum length of the meta-path and the impacts of different types of features. Moreover, the practical usefulness of our method was confirmed in the predicted novel drug combinations. The source code of EPSDC is available at https://github.com/KDDing/EPSDC.

Differential Expression and Pathway Analysis in Drug-Resistant Triple-Negative Breast Cancer Cell Lines Using RNASeq Analysis

Triple-negative breast cancer (TNBC) is among the most notorious types of breast cancer, the treatment of which does not give consistent results due to the absence of the three receptors (estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) as well as high amount of molecular variability. Drug resistance also contributes to treatment unresponsiveness. We studied differentially expressed genes, their biological roles, as well as pathways from RNA-Seq datasets of two different TNBC drug-resistant cell lines of Basal B subtype SUM159 and MDA-MB-231 treated with drugs JQ1 and Dexamethasone, respectively, to elucidate the mechanism of drug resistance. RNA sequencing(RNA-Seq) data analysis was done using edgeR which is an efficient program for determining the most significant Differentially Expressed Genes (DEGs), Gene Ontology (GO) terms, and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways. iPathway analysis was further used to obtain validated results using analysis that takes into consideration type, function, and interactions of genes in the pathway. The significant similarities and differences throw light into the molecular heterogeneity of TNBC, giving clues into the aspects that can be focused to overcome drug resistance. From this study, cytokine-cytokine receptor interaction pathway appeared to be a key factor in TNBC drug resistance.

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.

Predicting the impact of combined therapies on myeloma cell growth using a hybrid multi-scale agent-based model

Multiple myeloma is a malignant still incurable plasma cell disorder. This is due to refractory disease relapse, immune impairment, and development of multi-drug resistance. The growth of malignant plasma cells is dependent on the bone marrow (BM) microenvironment and evasion of the host's anti-tumor immune response. Hence, we hypothesized that targeting tumor-stromal cell interaction and endogenous immune system in BM will potentially improve the response of multiple myeloma (MM). Therefore, we proposed a computational simulation of the myeloma development in the complicated microenvironment which includes immune cell components and bone marrow stromal cells and predicted the effects of combined treatment with multi-drugs on myeloma cell growth. We constructed a hybrid multi-scale agent-based model (HABM) that combines an ODE system and Agent-based model (ABM). The ODEs was used for modeling the dynamic changes of intracellular signal transductions and ABM for modeling the cell-cell interactions between stromal cells, tumor, and immune components in the BM. This model simulated myeloma growth in the bone marrow microenvironment and revealed the important role of immune system in this process. The predicted outcomes were consistent with the experimental observations from previous studies. Moreover, we applied this model to predict the treatment effects of three key therapeutic drugs used for MM, and found that the combination of these three drugs potentially suppress the growth of myeloma cells and reactivate the immune response. In summary, the proposed model may serve as a novel computational platform for simulating the formation of MM and evaluating the treatment response of MM to multiple drugs.

A Computational-Based Method for Predicting Drug-Target Interactions by Using Stacked Autoencoder Deep Neural Network

Identifying the interaction between drugs and target proteins is an important area of drug research, which provides a broad prospect for low-risk and faster drug development. However, due to the limitations of traditional experiments when revealing drug-protein interactions (DTIs), the screening of targets not only takes a lot of time and money but also has high false-positive and false-negative rates. Therefore, it is imperative to develop effective automatic computational methods to accurately predict DTIs in the postgenome era. In this article, we propose a new computational method for predicting DTIs from drug molecular structure and protein sequence by using the stacked autoencoder of deep learning, which can adequately extract the raw data information. The proposed method has the advantage that it can automatically mine the hidden information from protein sequences and generate highly representative features through iterations of multiple layers. The feature descriptors are then constructed by combining the molecular substructure fingerprint information, and fed into the rotation forest for accurate prediction. The experimental results of fivefold cross-validation indicate that the proposed method achieves superior performance on gold standard data sets (enzymes, ion channels, GPCRs [G-protein-coupled receptors], and nuclear receptors) with accuracy of 0.9414, 0.9116, 0.8669, and 0.8056, respectively. We further comprehensively explore the performance of the proposed method by comparing it with other feature extraction algorithms, state-of-the-art classifiers, and other excellent methods on the same data set. The excellent comparison results demonstrate that the proposed method is highly competitive when predicting drug-target interactions.

Systems pharmacology exploration of botanic drug pairs reveals the mechanism for treating different diseases

Multi-herb therapy has been widely used in Traditional Chinese medicine and tailored to meet the specific needs of each individual. However, the potential molecular or systems mechanisms of them to treat various diseases have not been fully elucidated. To address this question, a systems pharmacology approach, integrating pharmacokinetics, pharmacology and systems biology, is used to comprehensively identify the drug-target and drug-disease networks, exemplified by three representative Radix Salviae Miltiorrhizae herb pairs for treating various diseases (coronary heart disease, dysmenorrheal and nephrotic syndrome). First, the compounds evaluation and the multiple targeting technology screen the active ingredients and identify the specific targets for each herb of three pairs. Second, the herb feature mapping reveals the differences in chemistry and pharmacological synergy between pairs. Third, the constructed compound-target-disease network explains the mechanisms of treatment for various diseases from a systematic level. Finally, experimental verification is taken to confirm our strategy. Our work provides an integrated strategy for revealing the mechanism of synergistic herb pairs, and also a rational way for developing novel drug combinations for treatments of complex diseases.