Prediction of drug combination effects with a minimal set of experiments

Antiviral activity of Vigna radiata extract against feline coronavirus in vitro

Feline infectious peritonitis (FIP) is a fatal illness caused by a mutated feline coronavirus (FCoV). This disease is characterized by its complexity, resulting from systemic infection, antibody-dependent enhancement (ADE), and challenges in accessing effective therapeutics. Extract derived from Vigna radiata (L.) R. Wilczek (VRE) exhibits various pharmacological effects, including antiviral activity. This study aimed to investigate the antiviral potential of VRE against FCoV, addressing the urgent need to advance the treatment of FIP. We explored the anti-FCoV activity, antiviral mechanism, and combinational application of VRE by means of in vitro antiviral assays. Our findings reveal that VRE effectively inhibited the cytopathic effect induced by FCoV, reduced viral proliferation, and downregulated spike protein expression. Moreover, VRE blocked FCoV in the early and late infection stages and was effective under in vitro ADE infection. Notably, when combined with VRE, the polymerase inhibitor GS-441524 or protease inhibitor GC376 suppressed FCoV more effectively than monotherapy. In conclusion, this study characterizes the antiviral property of VRE against FCoV in vitro, and VRE possesses therapeutic potential for FCoV treatment.

Tailored Viral-like Particles as Drivers of Medical Breakthroughs

Despite the recognized potential of nanoparticles, only a few formulations have progressed to clinical trials, and an even smaller number have been approved by the regulatory authorities and marketed. Virus-like particles (VLPs) have emerged as promising alternatives to conventional nanoparticles due to their safety, biocompatibility, immunogenicity, structural stability, scalability, and versatility. Furthermore, VLPs can be surface-functionalized with small molecules to improve circulation half-life and target specificity. Through the functionalization and coating of VLPs, it is possible to optimize the response properties to a given stimulus, such as heat, pH, an alternating magnetic field, or even enzymes. Surface functionalization can also modulate other properties, such as biocompatibility, stability, and specificity, deeming VLPs as potential vaccine candidates or delivery systems. This review aims to address the different types of surface functionalization of VLPs, highlighting the more recent cutting-edge technologies that have been explored for the design of tailored VLPs, their importance, and their consequent applicability in the medical field.

Data-driven learning of structure augments quantitative prediction of biological responses

Multi-factor screenings are commonly used in diverse applications in medicine and bioengineering, including optimizing combination drug treatments and microbiome engineering. Despite the advances in high-throughput technologies, large-scale experiments typically remain prohibitively expensive. Here we introduce a machine learning platform, structure-augmented regression (SAR), that exploits the intrinsic structure of each biological system to learn a high-accuracy model with minimal data requirement. Under different environmental perturbations, each biological system exhibits a unique, structured phenotypic response. This structure can be learned based on limited data and once learned, can constrain subsequent quantitative predictions. We demonstrate that SAR requires significantly fewer data comparing to other existing machine-learning methods to achieve a high prediction accuracy, first on simulated data, then on experimental data of various systems and input dimensions. We then show how a learned structure can guide effective design of new experiments. Our approach has implications for predictive control of biological systems and an integration of machine learning prediction and experimental design.

Integrated drug profiling and CRISPR screening identify BCR::ABL1-independent vulnerabilities in chronic myeloid leukemia

BCR::ABL1-independent pathways contribute to primary resistance to tyrosine kinase inhibitor (TKI) treatment in chronic myeloid leukemia (CML) and play a role in leukemic stem cell persistence. Here, we perform ex vivo drug screening of CML CD34+ leukemic stem/progenitor cells using 100 single drugs and TKI-drug combinations and identify sensitivities to Wee1, MDM2, and BCL2 inhibitors. These agents effectively inhibit primitive CD34+CD38- CML cells and demonstrate potent synergies when combined with TKIs. Flow-cytometry-based drug screening identifies mepacrine to induce differentiation of CD34+CD38- cells. We employ genome-wide CRISPR-Cas9 screening for six drugs, and mediator complex, apoptosis, and erythroid-lineage-related genes are identified as key resistance hits for TKIs, whereas the Wee1 inhibitor AZD1775 and mepacrine exhibit distinct resistance profiles. KCTD5, a consistent TKI-resistance-conferring gene, is found to mediate TKI-induced BCR::ABL1 ubiquitination. In summary, we delineate potential mechanisms for primary TKI resistance and non-BCR::ABL1-targeting drugs, offering insights for optimizing CML treatment.

Large-scale Pan-cancer Cell Line Screening Identifies Actionable and Effective Drug Combinations

Oncology drug combinations can improve therapeutic responses and increase treatment options for patients. The number of possible combinations is vast and responses can be context-specific. Systematic screens can identify clinically relevant, actionable combinations in defined patient subtypes. We present data for 109 anticancer drug combinations from AstraZeneca's oncology small molecule portfolio screened in 755 pan-cancer cell lines. Combinations were screened in a 7 × 7 concentration matrix, with more than 4 million measurements of sensitivity, producing an exceptionally data-rich resource. We implement a new approach using combination Emax (viability effect) and highest single agent (HSA) to assess combination benefit. We designed a clinical translatability workflow to identify combinations with clearly defined patient populations, rationale for tolerability based on tumor type and combination-specific "emergent" biomarkers, and exposures relevant to clinical doses. We describe three actionable combinations in defined cancer types, confirmed in vitro and in vivo, with a focus on hematologic cancers and apoptotic targets.

SIGNIFICANCE

We present the largest cancer drug combination screen published to date with 7 × 7 concentration response matrices for 109 combinations in more than 750 cell lines, complemented by multi-omics predictors of response and identification of "emergent" combination biomarkers. We prioritize hits to optimize clinical translatability, and experimentally validate novel combination hypotheses. This article is featured in Selected Articles from This Issue, p. 695.

Engineering CRISPR/Cas9 therapeutics for cancer precision medicine

The discovery of Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR) and CRISPR-associated protein 9 (Cas9) technology has revolutionized field of cancer treatment. This review explores usage of CRISPR/Cas9 for editing and investigating genes involved in human carcinogenesis. It provides insights into the development of CRISPR as a genetic tool. Also, it explores recent developments and tools available in designing CRISPR/Cas9 systems for targeting oncogenic genes for cancer treatment. Further, we delve into an overview of cancer biology, highlighting key genetic alterations and signaling pathways whose deletion prevents malignancies. This fundamental knowledge enables a deeper understanding of how CRISPR/Cas9 can be tailored to address specific genetic aberrations and offer personalized therapeutic approaches. In this review, we showcase studies and preclinical trials that show the utility of CRISPR/Cas9 in disrupting oncogenic targets, modulating tumor microenvironment and increasing the efficiency of available anti treatments. It also provides insight into the use of CRISPR high throughput screens for cancer biomarker identifications and CRISPR based screening for drug discovery. In conclusion, this review offers an overview of exciting developments in engineering CRISPR/Cas9 therapeutics for cancer treatment and highlights the transformative potential of CRISPR for innovation and effective cancer treatments.

Multi-omics and immunogenomics analysis revealed PFKFB3 as a targetable hallmark and mediates sunitinib resistance in papillary renal cell carcinoma: in silico study with laboratory verification

Glycolysis-related metabolic reprogramming is a central hallmark of human cancers, especially in renal cell carcinoma. However, the regulatory function of glycolytic signature in papillary RCC has not been well elucidated. In the present study, the glycolysis-immune predictive signature was constructed and validated using WGCNA, glycolysis-immune clustering analysis. PPI network of DEGs was constructed and visualized. Functional enrichments and patients' overall survival were analyzed. QRT-PCR experiments were performed to detect hub genes' expression and distribution, siRNA technology was used to silence targeted genes; cell proliferation and migration assays were applied to evaluate the biological function. Glucose concentration, lactate secretion, and ATP production were measured. Glycolysis-Immune Related Prognostic Index (GIRPI) was constructed and combined analyzed with single-cell RNA-seq. High-GIRPI signature predicted significantly poorer outcomes and relevant clinical features of pRCC patients. Moreover, GIRPI also participated in several pathways, which affected tumor immune microenvironment and provided potential therapeutic strategy. As a key glycolysis regulator, PFKFB3 could promote renal cancer cell proliferation and migration in vitro. Blocking of PFKFB3 by selective inhibitor PFK-015 or glycolytic inhibitor 2-DG significantly restrained renal cancer cells' neoplastic potential. PFK-015 and sunitinib could synergistically inhibit pRCC cells proliferation. Glycolysis-Immune Risk Signature is closely associated with pRCC prognosis, progression, immune infiltration, and therapeutic response. PFKFB3 may serve as a pivotal glycolysis regulator and mediates Sunitinib resistance in pRCC patients.

Inhibitory Efficacy of Main Components of Scutellaria baicalensis on the Interaction between Spike Protein of SARS-CoV-2 and Human Angiotensin-Converting Enzyme II

Blocking the interaction between the SARS-CoV-2 spike protein and the human angiotensin-converting enzyme II (hACE2) protein serves as a therapeutic strategy for treating COVID-19. Traditional Chinese medicine (TCM) treatments containing bioactive products could alleviate the symptoms of severe COVID-19. However, the emergence of SARS-CoV-2 variants has complicated the process of developing broad-spectrum drugs. As such, the aim of this study was to explore the efficacy of TCM treatments against SARS-CoV-2 variants through targeting the interaction of the viral spike protein with the hACE2 receptor. Antiviral activity was systematically evaluated using a pseudovirus system. Scutellaria baicalensis (S. baicalensis) was found to be effective against SARS-CoV-2 infection, as it mediated the interaction between the viral spike protein and the hACE2 protein. Moreover, the active molecules of S. baicalensis were identified and analyzed. Baicalein and baicalin, a flavone and a flavone glycoside found in S. baicalensis, respectively, exhibited strong inhibitory activities targeting the viral spike protein and the hACE2 protein, respectively. Under optimized conditions, virus infection was inhibited by 98% via baicalein-treated pseudovirus and baicalin-treated hACE2. In summary, we identified the potential SARS-CoV-2 inhibitors from S. baicalensis that mediate the interaction between the Omicron spike protein and the hACE2 receptor. Future studies on the therapeutic application of baicalein and baicalin against SARS-CoV-2 variants are needed.

Harnessing machine learning to find synergistic combinations for FDA-approved cancer drugs

Combination therapy is a fundamental strategy in cancer chemotherapy. It involves administering two or more anti-cancer agents to increase efficacy and overcome multidrug resistance compared to monotherapy. However, drug combinations can exhibit synergy, additivity, or antagonism. This study presents a machine learning framework to classify and predict cancer drug combinations. The framework utilizes several key steps including data collection and annotation from the O'Neil drug interaction dataset, data preprocessing, stratified splitting into training and test sets, construction and evaluation of classification models to categorize combinations as synergistic, additive, or antagonistic, application of regression models to predict combination sensitivity scores for enhanced predictions compared to prior work, and the last step is examination of drug features and mechanisms of action to understand synergy behaviors for optimal combinations. The models identified combination pairs most likely to synergize against different cancers. Kinase inhibitors combined with mTOR inhibitors, DNA damage-inducing drugs or HDAC inhibitors showed benefit, particularly for ovarian, melanoma, prostate, lung and colorectal carcinomas. Analysis highlighted Gemcitabine, MK-8776 and AZD1775 as frequently synergizing across cancer types. This machine learning framework provides a valuable approach to uncover more effective multi-drug regimens.

TCR-transgenic T cells and YB-1-based oncolytic virotherapy improve survival in a preclinical Ewing sarcoma xenograft mouse model

Background

Ewing sarcoma (EwS) is an aggressive and highly metastatic bone and soft tissue tumor in pediatric patients and young adults. Cure rates are low when patients present with metastatic or relapsed disease. Therefore, innovative therapy approaches are urgently needed. Cellular- and oncolytic virus-based immunotherapies are on the rise for solid cancers.

Methods

Here, we assess the combination of EwS tumor-associated antigen CHM1319-specific TCR-transgenic CD8+ T cells and the YB-1-driven (i.e. E1A13S-deleted) oncolytic adenovirus XVir-N-31 in vitro and in a xenograft mouse model for antitumor activity and immunostimulatory properties.

Results

In vitro both approaches specifically kill EwS cell lines in a synergistic manner over controls. This effect was confirmed in vivo, with increased survival using the combination therapy. Further in vitro analyses of immunogenic cell death and antigen presentation confirmed immunostimulatory properties of virus-infected EwS tumor cells. As dendritic cell maturation was also increased by XVir-N-31, we observed superior proliferation of CHM1319-specific TCR-transgenic CD8+ T cells only in virus-tested conditions, emphasizing the superior immune-activating potential of XVir-N-31.

Conclusion

Our data prove synergistic antitumor effects in vitro and superior tumor control in a preclinical xenograft setting. Combination strategies of EwS-redirected T cells and YB-1-driven virotherapy are a highly promising immunotherapeutic approach for EwS and warrant further evaluation in a clinical setting.

AlphaML: A clear, legible, explainable, transparent, and elucidative binary classification platform for tabular data

Leveraging the potential of machine learning and recognizing the broad applications of binary classification, it becomes essential to develop platforms that are not only powerful but also transparent, interpretable, and user friendly. We introduce alphaML, a user-friendly platform that provides clear, legible, explainable, transparent, and elucidative (CLETE) binary classification models with comprehensive customization options. AlphaML offers feature selection, hyperparameter search, sampling, and normalization methods, along with 15 machine learning algorithms with global and local interpretation. We have integrated a custom metric for hyperparameter search that considers both training and validation scores, safeguarding against under- or overfitting. Additionally, we employ the NegLog2RMSL scoring method, which uses both training and test scores for a thorough model evaluation. The platform has been tested using datasets from multiple domains and offers a graphical interface, removing the need for programming expertise. Consequently, alphaML exhibits versatility, demonstrating promising applicability across a broad spectrum of tabular data configurations.

Drug combinations screening using a Bayesian ranking approach based on dose-response models

Drug combinations have been of increasing interest in recent years for the treatment of complex diseases such as cancer, as they could reduce the risk of drug resistance. Moreover, in oncology, combining drugs may allow tackling tumor heterogeneity. Identifying potent combinations can be an arduous task since exploring the full dose-response matrix of candidate combinations over a large number of drugs is costly and sometimes unfeasible, as the quantity of available biological material is limited and may vary across patients. Our objective was to develop a rank-based screening approach for drug combinations in the setting of limited biological resources. A hierarchical Bayesian 4-parameter log-logistic (4PLL) model was used to estimate dose-response curves of dose-candidate combinations based on a parsimonious experimental design. We computed various activity ranking metrics, such as the area under the dose-response curve and Bliss synergy score, and we used the posterior distributions of ranks and the surface under the cumulative ranking curve to obtain a comprehensive final ranking of combinations. Based on simulations, our proposed method achieved good operating characteristics to identifying the most promising treatments in various scenarios with limited sample sizes and interpatient variability. We illustrate the proposed approach on real data from a combination screening experiment in acute myeloid leukemia.

Standardized assays to monitor drug sensitivity in hematologic cancers

The principle of drug sensitivity testing is to expose cancer cells to a library of different drugs and measure its effects on cell viability. Recent technological advances, continuous approval of targeted therapies, and improved cell culture protocols have enhanced the precision and clinical relevance of such screens. Indeed, drug sensitivity testing has proven diagnostically valuable for patients with advanced hematologic cancers. However, different cell types behave differently in culture and therefore require optimized drug screening protocols to ensure that their ex vivo drug sensitivity accurately reflects in vivo drug responses. For example, primary chronic lymphocytic leukemia (CLL) and multiple myeloma (MM) cells require unique microenvironmental stimuli to survive in culture, while this is less the case for acute myeloid leukemia (AML) cells. Here, we present our optimized and validated protocols for culturing and drug screening of primary cells from AML, CLL, and MM patients, and a generic protocol for cell line models. We also discuss drug library designs, reproducibility, and quality controls. We envision that these protocols may serve as community guidelines for the use and interpretation of assays to monitor drug sensitivity in hematologic cancers and thus contribute to standardization. The read-outs may provide insight into tumor biology, identify or confirm treatment resistance and sensitivity in real time, and ultimately guide clinical decision-making.

A granularity-level information fusion strategy on hypergraph transformer for predicting synergistic effects of anticancer drugs

Combination therapy has exhibited substantial potential compared to monotherapy. However, due to the explosive growth in the number of cancer drugs, the screening of synergistic drug combinations has become both expensive and time-consuming. Synergistic drug combinations refer to the concurrent use of two or more drugs to enhance treatment efficacy. Currently, numerous computational methods have been developed to predict the synergistic effects of anticancer drugs. However, there has been insufficient exploration of how to mine drug and cell line data at different granularity levels for predicting synergistic anticancer drug combinations. Therefore, this study proposes a granularity-level information fusion strategy based on the hypergraph transformer, named HypertranSynergy, to predict synergistic effects of anticancer drugs. HypertranSynergy introduces synergistic connections between cancer cell lines and drug combinations using hypergraph. Then, the Coarse-grained Information Extraction (CIE) module merges the hypergraph with a transformer for node embeddings. In the CIE module, Contranorm is a normalization layer that mitigates over-smoothing, while Gaussian noise addresses local information gaps. Additionally, the Fine-grained Information Extraction (FIE) module assesses fine-grained information's impact on predictions by employing similarity-aware matrices from drug/cell line features. Both CIE and FIE modules are integrated into HypertranSynergy. In addition, HypertranSynergy achieved the AUC of 0.93${\pm }$0.01 and the AUPR of 0.69${\pm }$0.02 in 5-fold cross-validation of classification task, and the RMSE of 13.77${\pm }$0.07 and the PCC of 0.81${\pm }$0.02 in 5-fold cross-validation of regression task. These results are better than most of the state-of-the-art models.

RECOVER identifies synergistic drug combinations in vitro through sequential model optimization

For large libraries of small molecules, exhaustive combinatorial chemical screens become infeasible to perform when considering a range of disease models, assay conditions, and dose ranges. Deep learning models have achieved state-of-the-art results in silico for the prediction of synergy scores. However, databases of drug combinations are biased toward synergistic agents and results do not generalize out of distribution. During 5 rounds of experimentation, we employ sequential model optimization with a deep learning model to select drug combinations increasingly enriched for synergism and active against a cancer cell line-evaluating only ∼5% of the total search space. Moreover, we find that learned drug embeddings (using structural information) begin to reflect biological mechanisms. In silico benchmarking suggests search queries are ∼5-10× enriched for highly synergistic drug combinations by using sequential rounds of evaluation when compared with random selection or ∼3× when using a pretrained model.

Cooperative regulation of coupled oncoprotein synthesis and stability in triple-negative breast cancer by EGFR and CDK12/13

Evidence has long suggested that epidermal growth factor receptor (EGFR) may play a prominent role in triple-negative breast cancer (TNBC) pathogenesis, but clinical trials of EGFR inhibitors have yielded disappointing results. Using a candidate drug screen, we identified that inhibition of cyclin-dependent kinases 12 and 13 (CDK12/13) dramatically sensitizes diverse models of TNBC to EGFR blockade. This combination therapy drives cell death through the 4E-BP1-dependent suppression of the translation and translation-linked turnover of driver oncoproteins, including MYC. A genome-wide CRISPR/Cas9 screen identified the CCR4-NOT complex as a major determinant of sensitivity to the combination therapy whose loss renders 4E-BP1 unresponsive to drug-induced dephosphorylation, thereby rescuing MYC translational suppression and promoting MYC stability. The central roles of CCR4-NOT and 4E-BP1 in response to the combination therapy were further underscored by the observation of CNOT1 loss and rescue of 4E-BP1 phosphorylation in TNBC cells that naturally evolved therapy resistance. Thus, pharmacological inhibition of CDK12/13 reveals a long-proposed EGFR dependence in TNBC that functions through the cooperative regulation of translation-coupled oncoprotein stability.

Computational Advancements in Cancer Combination Therapy Prediction

Given the high attrition rate of de novo drug discovery and limited efficacy of single-agent therapies in cancer treatment, combination therapy prediction through in silico drug repurposing has risen as a time- and cost-effective alternative for identifying novel and potentially efficacious therapies for cancer. The purpose of this review is to provide an introduction to computational methods for cancer combination therapy prediction and to summarize recent studies that implement each of these methods. A systematic search of the PubMed database was performed, focusing on studies published within the past 10 years. Our search included reviews and articles of ongoing and retrospective studies. We prioritized articles with findings that suggest considerations for improving combination therapy prediction methods over providing a meta-analysis of all currently available cancer combination therapy prediction methods. Computational methods used for drug combination therapy prediction in cancer research include networks, regression-based machine learning, classifier machine learning models, and deep learning approaches. Each method class has its own advantages and disadvantages, so careful consideration is needed to determine the most suitable class when designing a combination therapy prediction method. Future directions to improve current combination therapy prediction technology include incorporation of disease pathobiology, drug characteristics, patient multiomics data, and drug-drug interactions to determine maximally efficacious and tolerable drug regimens for cancer. As computational methods improve in their capability to integrate patient, drug, and disease data, more comprehensive models can be developed to more accurately predict safe and efficacious combination drug therapies for cancer and other complex diseases.

The Development of Immunotherapy for the Treatment of Recurrent Glioblastoma

Recurrent glioblastoma (rGBM) is a highly aggressive form of brain cancer that poses a significant challenge for treatment in neuro-oncology, and the survival status of patients after relapse usually means rapid deterioration, thus becoming the leading cause of death among patients. In recent years, immunotherapy has emerged as a promising strategy for the treatment of recurrent glioblastoma by stimulating the body's immune system to recognize and attack cancer cells, which could be used in combination with other treatments such as surgery, radiation, and chemotherapy to improve outcomes for patients with recurrent glioblastoma. This therapy combines several key methods such as the use of monoclonal antibodies, chimeric antigen receptor T cell (CAR-T) therapy, checkpoint inhibitors, oncolytic viral therapy cancer vaccines, and combination strategies. In this review, we mainly document the latest immunotherapies for the treatment of glioblastoma and especially focus on rGBM.

Targeting metabolism by B-raf inhibitors and diclofenac restrains the viability of BRAF-mutated thyroid carcinomas with Hif-1α-mediated glycolytic phenotype

BACKGROUND

B-raf inhibitors (BRAFi) are effective for BRAF-mutated papillary (PTC) and anaplastic (ATC) thyroid carcinomas, although acquired resistance impairs tumour cells' sensitivity and/or limits drug efficacy. Targeting metabolic vulnerabilities is emerging as powerful approach in cancer.

METHODS

In silico analyses identified metabolic gene signatures and Hif-1α as glycolysis regulator in PTC. BRAF-mutated PTC, ATC and control thyroid cell lines were exposed to HIF1A siRNAs or chemical/drug treatments (CoCl2, EGF, HGF, BRAFi, MEKi and diclofenac). Genes/proteins expression, glucose uptake, lactate quantification and viability assays were used to investigate the metabolic vulnerability of BRAF-mutated cells.

RESULTS

A specific metabolic gene signature was identified as a hallmark of BRAF-mutated tumours, which display a glycolytic phenotype, characterised by enhanced glucose uptake, lactate efflux and increased expression of Hif-1α-modulated glycolytic genes. Indeed, Hif-1α stabilisation counteracts the inhibitory effects of BRAFi on these genes and on cell viability. Interestingly, targeting metabolic routes with BRAFi and diclofenac combination we could restrain the glycolytic phenotype and synergistically reduce tumour cells' viability.

CONCLUSION

The identification of a metabolic vulnerability of BRAF-mutated carcinomas and the capacity BRAFi and diclofenac combination to target metabolism open new therapeutic perspectives in maximising drug efficacy and reducing the onset of secondary resistance and drug-related toxicity.

Mitophagy Promotes Resistance to BH3 Mimetics in Acute Myeloid Leukemia

BH3 mimetics are used as an efficient strategy to induce cell death in several blood malignancies, including acute myeloid leukemia (AML). Venetoclax, a potent BCL-2 antagonist, is used clinically in combination with hypomethylating agents for the treatment of AML. Moreover, MCL1 or dual BCL-2/BCL-xL antagonists are under investigation. Yet, resistance to single or combinatorial BH3-mimetic therapies eventually ensues. Integration of multiple genome-wide CRISPR/Cas9 screens revealed that loss of mitophagy modulators sensitizes AML cells to various BH3 mimetics targeting different BCL-2 family members. One such regulator is MFN2, whose protein levels positively correlate with drug resistance in patients with AML. MFN2 overexpression is sufficient to drive resistance to BH3 mimetics in AML. Insensitivity to BH3 mimetics is accompanied by enhanced mitochondria-endoplasmic reticulum interactions and augmented mitophagy flux, which acts as a prosurvival mechanism to eliminate mitochondrial damage. Genetic or pharmacologic MFN2 targeting synergizes with BH3 mimetics by impairing mitochondrial clearance and enhancing apoptosis in AML.

SIGNIFICANCE

AML remains one of the most difficult-to-treat blood cancers. BH3 mimetics represent a promising therapeutic approach to eliminate AML blasts by activating the apoptotic pathway. Enhanced mitochondrial clearance drives resistance to BH3 mimetics and predicts poor prognosis. Reverting excessive mitophagy can halt BH3-mimetic resistance in AML. This article is highlighted in the In This Issue feature, p. 1501.

Caffeine Supplementation and FOXM1 Inhibition Enhance the Antitumor Effect of Statins in Neuroblastoma

High-risk neuroblastoma exhibits transcriptional activation of the mevalonate pathway that produces cholesterol and nonsterol isoprenoids. A better understanding of how this metabolic reprogramming contributes to neuroblastoma development could help identify potential prevention and treatment strategies. Here, we report that both the cholesterol and nonsterol geranylgeranyl-pyrophosphate branches of the mevalonate pathway are critical to sustain neuroblastoma cell growth. Blocking the mevalonate pathway by simvastatin, a cholesterol-lowering drug, impeded neuroblastoma growth in neuroblastoma cell line xenograft, patient-derived xenograft (PDX), and TH-MYCN transgenic mouse models. Transcriptional profiling revealed that the mevalonate pathway was required to maintain the FOXM1-mediated transcriptional program that drives mitosis. High FOXM1 expression contributed to statin resistance and led to a therapeutic vulnerability to the combination of simvastatin and FOXM1 inhibition. Furthermore, caffeine synergized with simvastatin to inhibit the growth of neuroblastoma cells and PDX tumors by blocking statin-induced feedback activation of the mevalonate pathway. This function of caffeine depended on its activity as an adenosine receptor antagonist, and the A2A adenosine receptor antagonist istradefylline, an add-on drug for Parkinson's disease, could recapitulate the synergistic effect of caffeine with simvastatin. This study reveals that the FOXM1-mediated mitotic program is a molecular statin target in cancer and identifies classes of agents for maximizing the therapeutic efficacy of statins, with implications for treatment of high-risk neuroblastoma.

SIGNIFICANCE

Caffeine treatment and FOXM1 inhibition can both enhance the antitumor effect of statins by blocking the molecular and metabolic processes that confer statin resistance, indicating potential combination therapeutic strategies for neuroblastoma. See related commentary by Stouth et al., p. 2091.

Cholesterol-Lowering Drugs as Potential Antivirals: A Repurposing Approach against Flavivirus Infections

Flaviviruses, including Dengue (DENV), Zika (ZIKV), and Yellow Fever (YFV) viruses, represent a significant global health burden. The development of effective antiviral therapies against these viruses is crucial to mitigate their impact. This study investigated the antiviral potential of the cholesterol-lowering drugs atorvastatin and ezetimibe in monotherapy and combination against DENV, ZIKV, and YFV. In vitro results demonstrated a dose-dependent reduction in the percentage of infected cells for both drugs. The combination of atorvastatin and ezetimibe showed a synergistic effect against DENV 2, an additive effect against DENV 4 and ZIKV, and an antagonistic effect against YFV. In AG129 mice infected with DENV 2, monotherapy with atorvastatin or ezetimibe significantly reduced clinical signs and increased survival. However, the combination of both drugs did not significantly affect survival. This study provides valuable insights into the potential of atorvastatin and ezetimibe as antiviral agents against flaviviruses and highlights the need for further investigations into their combined therapeutic effects.

A hybrid deep forest-based method for predicting synergistic drug combinations

Combination therapy is a promising approach in treating multiple complex diseases. However, the large search space of available drug combinations exacerbates challenge for experimental screening. To predict synergistic drug combinations in different cancer cell lines, we propose an improved deep forest-based method, ForSyn, and design two forest types embedded in ForSyn. ForSyn handles imbalanced and high-dimensional data in medium-/small-scale datasets, which are inherent characteristics of drug combination datasets. Compared with 12 state-of-the-art methods, ForSyn ranks first on four metrics for eight datasets with different feature combinations. We conduct a systematic analysis to identify the most appropriate configuration parameters. We validate the predictive value of ForSyn with cell-based experiments on several previously unexplored drug combinations. Finally, a systematic analysis of feature importance is performed on the top contributing features extracted by ForSyn. The resulting key genes may play key roles on corresponding cancers.

Glioblastoma and the search for non-hypothesis driven combination therapeutics in academia

Glioblastoma (GBM) remains a cancer of high unmet clinical need. Current standard of care for GBM, consisting of maximal surgical resection, followed by ionisation radiation (IR) plus concomitant and adjuvant temozolomide (TMZ), provides less than 15-month survival benefit. Efforts by conventional drug discovery to improve overall survival have failed to overcome challenges presented by inherent tumor heterogeneity, therapeutic resistance attributed to GBM stem cells, and tumor niches supporting self-renewal. In this review we describe the steps academic researchers are taking to address these limitations in high throughput screening programs to identify novel GBM combinatorial targets. We detail how they are implementing more physiologically relevant phenotypic assays which better recapitulate key areas of disease biology coupled with more focussed libraries of small compounds, such as drug repurposing, target discovery, pharmacologically active and novel, more comprehensive anti-cancer target-annotated compound libraries. Herein, we discuss the rationale for current GBM combination trials and the need for more systematic and transparent strategies for identification, validation and prioritisation of combinations that lead to clinical trials. Finally, we make specific recommendations to the preclinical, small compound screening paradigm that could increase the likelihood of identifying tractable, combinatorial, small molecule inhibitors and better drug targets specific to GBM.

A deep tabular data learning model predicting cisplatin sensitivity identifies BCL2L1 dependency in cancer

Cisplatin, a platinum-based chemotherapeutic agent, is widely used as a front-line treatment for several malignancies. However, treatment outcomes vary widely due to intrinsic and acquired resistance. In this study, cisplatin-perturbed gene expression and pathway enrichment were used to define a gene signature, which was further utilized to develop a cisplatin sensitivity prediction model using the TabNet algorithm. The TabNet model performed better (>80 % accuracy) than all other machine learning models when compared to a wide range of machine learning algorithms. Moreover, by using feature importance and comparing predicted ovarian cancer patient samples, BCL2L1 was identified as an important gene contributing to cisplatin resistance. Furthermore, the pharmacological inhibition of BCL2L1 was found to synergistically increase cisplatin efficacy. Collectively, this study developed a tool to predict cisplatin sensitivity using cisplatin-perturbed gene expression and pathway enrichment knowledge and identified BCL2L1 as an important gene in this setting.

The Antineoplastic Effect of Carboplatin Is Potentiated by Combination with Pitavastatin or Metformin in a Chemoresistant High-Grade Serous Carcinoma Cell Line

The combination of Carboplatin with Paclitaxel is the mainstay treatment for high-grade serous carcinoma; however, many patients with advanced disease undergo relapse due to chemoresistance. Drug repurposing coupled with a combination of two or more compounds with independent mechanisms of action has the potential to increase the success rate of the antineoplastic treatment. The purpose of this study was to explore whether the combination of Carboplatin with repurposed drugs led to a therapeutic benefit. Hence, we assessed the cytotoxic effects of Carboplatin alone and in combination with several repurposed drugs (Pitavastatin, Metformin, Ivermectin, Itraconazole and Alendronate) in two tumoral models, i.e., Carboplatin (OVCAR8) and Carboplatin-Paclitaxel (OVCAR8 PTX R P) chemoresistant cell lines and in a non-tumoral (HOSE6.3) cell line. Cellular viability was measured using the Presto Blue assay, and the synergistic interactions were evaluated using the Chou-Talalay, Bliss Independence and Highest Single Agent reference models. Combining Carboplatin with Pitavastatin or Metformin displayed the highest cytotoxic effect and the strongest synergism among all combinations for OVCAR8 PTX R P cells, resulting in a chemotherapeutic effect superior to Carboplatin as a single agent. Concerning HOSE6.3 cells, combining Carboplatin with almost all the repurposed drugs demonstrated a safe pharmacological profile. Overall, we propose that Pitavastatin or Metformin could act synergistically in combination with Carboplatin for the management of high-grade serous carcinoma patients with a Carboplatin plus Paclitaxel resistance profile.

Predicting cell line-specific synergistic drug combinations through a relational graph convolutional network with attention mechanism

Identifying synergistic drug combinations (SDCs) is a great challenge due to the combinatorial complexity and the fact that SDC is cell line specific. The existing computational methods either did not consider the cell line specificity of SDC, or did not perform well by building model for each cell line independently. In this paper, we present a novel encoder-decoder network named SDCNet for predicting cell line-specific SDCs. SDCNet learns common patterns across different cell lines as well as cell line-specific features in one model for drug combinations. This is realized by considering the SDC graphs of different cell lines as a relational graph, and constructing a relational graph convolutional network (R-GCN) as the encoder to learn and fuse the deep representations of drugs for different cell lines. An attention mechanism is devised to integrate the drug features from different layers of the R-GCN according to their relative importance so that representation learning is further enhanced. The common patterns are exploited through partial parameter sharing in cell line-specific decoders, which not only reconstruct the known SDCs but also predict new ones for each cell line. Experiments on various datasets demonstrate that SDCNet is superior to state-of-the-art methods and is also robust when generalized to new cell lines that are different from the training ones. Finally, the case study again confirms the effectiveness of our method in predicting novel reliable cell line-specific SDCs.

Functional Testing to Characterize and Stratify PI3K Inhibitor Responses in Chronic Lymphocytic Leukemia

PURPOSE

PI3K inhibitors (PI3Ki) are approved for relapsed chronic lymphocytic leukemia (CLL). Although patients may show an initial response to these therapies, development of treatment intolerance or resistance remain clinical challenges. To overcome these, prediction of individual treatment responses based on actionable biomarkers is needed. Here, we characterized the activity and cellular effects of 10 PI3Ki and investigated whether functional analyses can identify treatment vulnerabilities in PI3Ki-refractory/intolerant CLL and stratify responders to PI3Ki.

EXPERIMENTAL DESIGN

Peripheral blood mononuclear cell samples (n = 51 in total) from treatment-naïve and PI3Ki-treated patients with CLL were studied. Cells were profiled against 10 PI3Ki and the Bcl-2 antagonist venetoclax. Cell signaling and immune phenotypes were analyzed by flow cytometry. Cell viability was monitored by detection of cleaved caspase-3 and the CellTiter-Glo assay.

RESULTS

pan-PI3Kis were most effective at inhibiting PI3K signaling and cell viability, and showed activity in CLL cells from both treatment-naïve and idelalisib-refractory/intolerant patients. CLL cells from idelalisib-refractory/intolerant patients showed overall reduced protein phosphorylation levels. The pan-PI3Ki copanlisib, but not the p110δ inhibitor idelalisib, inhibited PI3K signaling in CD4+ and CD8+ T cells in addition to CD19+ B cells, but did not significantly affect T-cell numbers. Combination treatment with a PI3Ki and venetoclax resulted in synergistic induction of apoptosis. Analysis of drug sensitivities to 73 drug combinations and profiling of 31 proteins stratified responders to idelalisib and umbralisib, respectively.

CONCLUSIONS

Our findings suggest novel treatment vulnerabilities in idelalisib-refractory/intolerant CLL, and indicate that ex vivo functional profiling may stratify PI3Ki responders.

SYNPRED: prediction of drug combination effects in cancer using different synergy metrics and ensemble learning

Background

In cancer research, high-throughput screening technologies produce large amounts of multiomics data from different populations and cell types. However, analysis of such data encounters difficulties due to disease heterogeneity, further exacerbated by human biological complexity and genomic variability. The specific profile of cancer as a disease (or, more realistically, a set of diseases) urges the development of approaches that maximize the effect while minimizing the dosage of drugs. Now is the time to redefine the approach to drug discovery, bringing an artificial intelligence (AI)–powered informational view that integrates the relevant scientific fields and explores new territories.

Results

Here, we show SYNPRED, an interdisciplinary approach that leverages specifically designed ensembles of AI algorithms, as well as links omics and biophysical traits to predict anticancer drug synergy. It uses 5 reference models (Bliss, Highest Single Agent, Loewe, Zero Interaction Potency, and Combination Sensitivity Score), which, coupled with AI algorithms, allowed us to attain the ones with the best predictive performance and pinpoint the most appropriate reference model for synergy prediction, often overlooked in similar studies. By using an independent test set, SYNPRED exhibits state-of-the-art performance metrics either in the classification (accuracy, 0.85; precision, 0.91; recall, 0.90; area under the receiver operating characteristic, 0.80; and F1-score, 0.91) or in the regression models, mainly when using the Combination Sensitivity Score synergy reference model (root mean square error, 11.07; mean squared error, 122.61; Pearson, 0.86; mean absolute error, 7.43; Spearman, 0.87). Moreover, data interpretability was achieved by deploying the most current and robust feature importance approaches. A simple web-based application was constructed, allowing easy access by nonexpert researchers.

Conclusions

The performance of SYNPRED rivals that of the existing methods that tackle the same problem, yielding unbiased results trained with one of the most comprehensive datasets available (NCI ALMANAC). The leveraging of different reference models allowed deeper insights into which of them can be more appropriately used for synergy prediction. The Combination Sensitivity Score clearly stood out with improved performance among the full scope of surveyed approaches and synergy reference models. Furthermore, SYNPRED takes a particular focus on data interpretability, which has been in the spotlight lately when using the most advanced AI techniques.

Pitavastatin and Ivermectin Enhance the Efficacy of Paclitaxel in Chemoresistant High-Grade Serous Carcinoma

Simple Summary

The main challenge in high-grade serous carcinoma management is to unveil therapeutic approaches to overcome chemoresistance. Drug combinations and repurposing of non-oncological agents are attractive strategies that allow for higher efficacy, decreased toxicity, and the overcoming of chemoresistance. Several non-oncological drugs display an effective anti-cancer activity and have been studied to be repurposed in multi-drug resistant neoplasms. The purpose of our study was to explore whether combining Paclitaxel with repurposed drugs (Pitavastatin, Metformin, Ivermectin, Itraconazole and Alendronate) led to a therapeutic benefit. Our results showed that the combination of Paclitaxel with Pitavastatin or Ivermectin demonstrates the highest cytotoxic effect and the strongest synergism among all combinations for two chemoresistant cell lines. Thus, the combination of these repurposed drugs with Paclitaxel could be a particularly valuable strategy to treat ovarian cancer patients with intrinsic or acquired chemoresistance.

Abstract

Chemotherapy is a hallmark in high-grade serous carcinoma management; however, chemoresistance and side effects lead to therapeutic interruption. Combining repurposed drugs with chemotherapy has the potential to improve antineoplastic efficacy, since drugs can have independent mechanisms of action and suppress different pathways simultaneously. This study aimed to explore whether the combination of Paclitaxel with repurposed drugs led to a therapeutic benefit. Thus, we evaluated the cytotoxic effects of Paclitaxel alone and in combination with several repurposed drugs (Pitavastatin, Metformin, Ivermectin, Itraconazole and Alendronate) in two tumor chemoresistant (OVCAR8 and OVCAR8 PTX R P) and a non-tumoral (HOSE6.3) cell lines. Cellular viability was assessed using Presto Blue assay, and the synergistic interactions were evaluated using Chou–Talalay, Bliss Independence and Highest Single Agent reference models. The combination of Paclitaxel with Pitavastatin or Ivermectin showed the highest cytotoxic effect and the strongest synergism among all combinations for both chemoresistant cell lines, resulting in a chemotherapeutic effect superior to both drugs alone. Almost all the repurposed drugs in combination with Paclitaxel presented a safe pharmacological profile in non-tumoral cells. Overall, we suggest that Pitavastatin and Ivermectin could act synergistically in combination with Paclitaxel, being promising two-drug combinations for high-grade serous carcinoma management.

Prediction and evaluation of combination pharmacotherapy using natural language processing, machine learning and patient electronic health records

Combination pharmacotherapy targets key disease pathways in a synergistic or additive manner and has high potential in treating complex diseases. Computational methods have been developed to identifying combination pharmacotherapy by analyzing large amounts of biomedical data. Existing computational approaches are often underpowered due to their reliance on our limited understanding of disease mechanisms. On the other hand, observable phenotypic inter-relationships among thousands of diseases often reflect their underlying shared genetic and molecular underpinnings, therefore can offer unique opportunities to design computational models to discover novel combinational therapies by automatically transferring knowledge among phenotypically related diseases. We developed a novel phenome-driven drug discovery system, named TuSDC, which leverages knowledge of existing drug combinations, disease comorbidities, and disease treatments of thousands of disease and drug entities extracted from over 31.5 million biomedical research articles using natural language processing techniques. TuSDC predicts combination pharmacotherapy by extracting representations of diseases and drugs using tensor factorization approaches. In external validation, TuSDC achieved an average precision of 0.77 for top ranked candidates, outperforming a state of art mechanism-based method for discovering drug combinations in treating hypertension. We evaluated top ranked anti-hypertension drug combinations using electronic health records of 84.7 million unique patients and showed that a novel drug combination hydrochlorothiazide-digoxin was associated with significantly lower hazards of subsequent hypertension as compared to the monotherapy hydrochlorothiazide alone (HR: 0.769, 95% CI [0.732, 0.807]) and digoxin alone (0.857, 95% CI [0.785, 0.936]). Data-driven informatics analyses reveal that the renin-angiotensin system is involved in the synergistical interactions of hydrochlorothiazide and digoxin on regulating hypertension. The prediction model's code with PyTorch version 1.5 is available at http://nlp.case.edu/public/data/TuSDC/.

A benchmark study of deep learning-based multi-omics data fusion methods for cancer

BACKGROUND

A fused method using a combination of multi-omics data enables a comprehensive study of complex biological processes and highlights the interrelationship of relevant biomolecules and their functions. Driven by high-throughput sequencing technologies, several promising deep learning methods have been proposed for fusing multi-omics data generated from a large number of samples.

RESULTS

In this study, 16 representative deep learning methods are comprehensively evaluated on simulated, single-cell, and cancer multi-omics datasets. For each of the datasets, two tasks are designed: classification and clustering. The classification performance is evaluated by using three benchmarking metrics including accuracy, F1 macro, and F1 weighted. Meanwhile, the clustering performance is evaluated by using four benchmarking metrics including the Jaccard index (JI), C-index, silhouette score, and Davies Bouldin score. For the cancer multi-omics datasets, the methods' strength in capturing the association of multi-omics dimensionality reduction results with survival and clinical annotations is further evaluated. The benchmarking results indicate that moGAT achieves the best classification performance. Meanwhile, efmmdVAE, efVAE, and lfmmdVAE show the most promising performance across all complementary contexts in clustering tasks.

CONCLUSIONS

Our benchmarking results not only provide a reference for biomedical researchers to choose appropriate deep learning-based multi-omics data fusion methods, but also suggest the future directions for the development of more effective multi-omics data fusion methods. The deep learning frameworks are available at https://github.com/zhenglinyi/DL-mo .

Computational models, databases and tools for antibiotic combinations

Antibiotic combination is a promising strategy to extend the lifetime of antibiotics and thereby combat antimicrobial resistance. However, screening for new antibiotic combinations is both time-consuming and labor-intensive. In recent years, an increasing number of researchers have used computational models to predict effective antibiotic combinations. In this review, we summarized existing computational models for antibiotic combinations and discussed the limitations and challenges of these models in detail. In addition, we also collected and summarized available data resources and tools for antibiotic combinations. This study aims to help computational biologists design more accurate and interpretable computational models.

Elevated NF-κB/SHh/GLI1 Signature Denotes a Worse Prognosis and Represent a Novel Potential Therapeutic Target in Advanced Prostate Cancer

Prostate cancer (PCa) is the second most frequent cancer in men worldwide. NF-κB seems to play a key role in cell survival, proliferation and invasion, sustaining the heterogeneous multifocal nature of PCa. In recent years, the Hedgehog (Hh) signaling pathway has attracted attention as a therapeutic target due to its implication in tumorigenesis and metastasis in several types of cancer, including PCa. Although it is well-known that Sonic Hedgehog (SHh) is a transcriptional target of NF-κB(p65), and that GLI1 is the effector of this crosstalk, the precise role played by this axis in PCa is still not completely clear. Here, we set out to explore the correlation between NF-κB activation and SHh pathways in PCa, investigating if the interplay between NF-κB(p65) and SHh-GLI1 in advanced PCa could be a prospective therapeutic target. Our findings demonstrate that a NF-κB-SHh-GLI1 gene signature is enriched in PCa patients featuring a higher Gleason score. Moreover, elevated levels of this signature are associated with worse prognosis, thus suggesting that this axis could provide a route to treat aggressive PCa.

A scalable, open-source implementation of a large-scale mechanistic model for single cell proliferation and death signaling

Mechanistic models of how single cells respond to different perturbations can help integrate disparate big data sets or predict response to varied drug combinations. However, the construction and simulation of such models have proved challenging. Here, we developed a python-based model creation and simulation pipeline that converts a few structured text files into an SBML standard and is high-performance- and cloud-computing ready. We applied this pipeline to our large-scale, mechanistic pan-cancer signaling model (named SPARCED) and demonstrate it by adding an IFNγ pathway submodel. We then investigated whether a putative crosstalk mechanism could be consistent with experimental observations from the LINCS MCF10A Data Cube that IFNγ acts as an anti-proliferative factor. The analyses suggested this observation can be explained by IFNγ-induced SOCS1 sequestering activated EGF receptors. This work forms a foundational recipe for increased mechanistic model-based data integration on a single-cell level, an important building block for clinically-predictive mechanistic models.

SynergyFinder 3.0: an interactive analysis and consensus interpretation of multi-drug synergies across multiple samples

SynergyFinder (https://synergyfinder.fimm.fi) is a free web-application for interactive analysis and visualization of multi-drug combination response data. Since its first release in 2017, SynergyFinder has become a popular tool for multi-dose combination data analytics, partly because the development of its functionality and graphical interface has been driven by a diverse user community, including both chemical biologists and computational scientists. Here, we describe the latest upgrade of this community-effort, SynergyFinder release 3.0, introducing a number of novel features that support interactive multi-sample analysis of combination synergy, a novel consensus synergy score that combines multiple synergy scoring models, and an improved outlier detection functionality that eliminates false positive results, along with many other post-analysis options such as weighting of synergy by drug concentrations and distinguishing between different modes of synergy (potency and efficacy). Based on user requests, several additional improvements were also implemented, including new data visualizations and export options for multi-drug combinations. With these improvements, SynergyFinder 3.0 supports robust identification of consistent combinatorial synergies for multi-drug combinatorial discovery and clinical translation.

A novel network based linear model for prioritization of synergistic drug combinations

Drug combination therapies can improve drug efficacy, reduce drug dosage, and overcome drug resistance in cancer treatments. Current research strategies to determine which drug combinations have a synergistic effect rely mainly on clinical or empirical experience and screening predefined pools of drugs. Given the number of possible drug combinations, the speed, and scope to find new drug combinations are very limited using these methods. Due to the exponential growth in the number of drug combinations, it is difficult to test all possible combinations in the lab. There are several large-scale public genomic and phenotypic resources that provide data from single drug-treated cells as well as data from small molecule treated cells. These databases provide a wealth of information regarding cellular responses to drugs and offer an opportunity to overcome the limitations of the current methods. Developing a new advanced data processing and analysis strategy is imperative and a computational prediction algorithm is highly desirable. In this paper, we developed a computational algorithm for the enrichment of synergistic drug combinations using gene regulatory network knowledge and an operational module unit (OMU) system which we generate from single drug genomic and phenotypic data. As a proof of principle, we applied the pipeline to a group of anticancer drugs and demonstrate how the algorithm could help researchers efficiently find possible synergistic drug combinations using single drug data to evaluate all possible drug pairs.

Circadian and Immunity Cycle Talk in Cancer Destination: From Biological Aspects to In Silico Analysis

Simple Summary

The circadian cycle is a natural cycle of the body repeated every 24 h, based on a day and night rhythm, and it affects many body processes. The present article reviews the importance and role of the circadian cycle in cancer and its association with the immune system and immunotherapy drugs at the cellular and molecular levels. It also examines the genes and cellular pathways involved in both circadian and immune systems. It offers possible computational solutions to increase the effectiveness of cancer treatment concerning the circadian cycle.

Abstract

Cancer is the leading cause of death and a major problem to increasing life expectancy worldwide. In recent years, various approaches such as surgery, chemotherapy, radiation, targeted therapies, and the newest pillar, immunotherapy, have been developed to treat cancer. Among key factors impacting the effectiveness of treatment, the administration of drugs based on the circadian rhythm in a person and within individuals can significantly elevate drug efficacy, reduce adverse effects, and prevent drug resistance. Circadian clocks also affect various physiological processes such as the sleep cycle, body temperature cycle, digestive and cardiovascular processes, and endocrine and immune systems. In recent years, to achieve precision patterns for drug administration using computational methods, the interaction of the effects of drugs and their cellular pathways has been considered more seriously. Integrated data-derived pathological images and genomics, transcriptomics, and proteomics analyses have provided an understanding of the molecular basis of cancer and dramatically revealed interactions between circadian and immunity cycles. Here, we describe crosstalk between the circadian cycle signaling pathway and immunity cycle in cancer and discuss how tumor microenvironment affects the influence on treatment process based on individuals’ genetic differences. Moreover, we highlight recent advances in computational modeling that pave the way for personalized immune chronotherapy.

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.

Computational Pipeline for Rational Drug Combination Screening in Patient-Derived Cells

In many complex diseases, such as cancers, resistance to monotherapies easily occurs, and longer-term treatment responses often require combinatorial therapies as next-line regimens. However, due to a massive number of possible drug combinations to test, there is a need for systematic and rational approaches to finding safe and effective drug combinations for each individual patient. This protocol describes an ecosystem of computational methods to guide high-throughput combinatorial screening that help experimental researchers to identify optimal drug combinations in terms of synergy, efficacy, and/or selectivity for further preclinical and clinical investigation. The methods are demonstrated in the context of combinatorial screening in primary cells of leukemia patients, where the translational aim is to identify drug combinations that show not only high synergy but also maximal cancer-selectivity. The mechanism-agnostic and cost-effective computational methods are widely applicable to various cancer types, which are amenable to drug testing, as the computational methods take as input only the phenotypic measurements of a subset of drug combinations, without requiring target information or genomic profiles of the patient samples.

Systematic review of computational methods for drug combination prediction

Synergistic effects between drugs are rare and highly context-dependent and patient-specific. Hence, there is a need to develop novel approaches to stratify patients for optimal therapy regimens, especially in the context of personalized design of combinatorial treatments. Computational methods enable systematic in-silico screening of combination effects, and can thereby prioritize most potent combinations for further testing, among the massive number of potential combinations. To help researchers to choose a prediction method that best fits for various real-world applications, we carried out a systematic literature review of 117 computational methods developed to date for drug combination prediction, and classified the methods in terms of their combination prediction tasks and input data requirements. Most current methods focus on prediction or classification of combination synergy, and only a few methods consider the efficacy and potential toxicity of the combinations, which are the key determinants of therapeutic success of drug treatments. Furthermore, there is a need to further develop methods that enable dose-specific predictions of combination effects across multiple doses, which is important for clinical translation of the predictions, as well as model-based identification of biomarkers predictive of heterogeneous drug combination responses. Even if most of the computational methods reviewed focus on anticancer applications, many of the modelling approaches are also applicable to antiviral and other diseases or indications.

Model-based computational precision medicine to develop combination therapies for autoimmune diseases

INTRODUCTION

The complex pathophysiology of autoimmune diseases (AIDs) is being progressively deciphered, providing evidence for a multiplicity of pro-inflammatory pathways underlying heterogeneous clinical phenotypes and disease evolution.

AREAS COVERED

Treatment strategies involving drug combinations are emerging as a preferred option to achieve remission in a vast majority of patients affected by systemic AIDs. The design of appropriate drug combinations can benefit from AID modeling following a comprehensive multi-omics molecular profiling of patients combined with Artificial Intelligence (AI)-powered computational analyses. Such disease models support patient stratification in homogeneous subgroups, shed light on dysregulated pro-inflammatory pathways and yield hypotheses regarding potential therapeutic targets and candidate biomarkers to stratify and monitor patients during treatment. AID models inform the rational design of combination therapies interfering with independent pro-inflammatory pathways related to either one of five prominent immune compartments contributing to the pathophysiology of AIDs, i.e. pro-inflammatory signals originating from tissues, innate immune mechanisms, T lymphocyte activation, autoantibodies and B cell activation, as well as soluble mediators involved in immune cross-talk.

EXPERT OPINION

The optimal management of AIDs in the future will rely upon rationally designed combination therapies, as a modality of a model-based Computational Precision Medicine taking into account the patients' biological and clinical specificities.

Mcl-1 and Bcl-xL levels predict responsiveness to dual MEK/Bcl-2 inhibition in B-cell malignancies

Most patients with chronic lymphocytic leukemia (CLL) initially respond to targeted therapies, but eventually relapse and develop resistance. Novel treatment strategies are therefore needed to improve patient outcomes. Here, we performed direct drug testing on primary CLL cells and identified synergy between eight different mitogen-activated protein kinase kinase (MEK) inhibitors and the B-cell lymphoma 2 (Bcl-2) antagonist venetoclax. Drug sensitivity was independent of immunoglobulin heavy-chain gene variable region (IGVH) and tumor protein p53 (TP53) mutational status, and CLL cells from idelalisib-resistant patients remained sensitive to the treatment. This suggests that combined MEK/Bcl-2 inhibition may be an option for high-risk CLL. To test whether sensitivity could be detected in other B-cell malignancies, we performed drug testing on cell line models of CLL (n = 4), multiple myeloma (MM; n = 8), and mantle cell lymphoma (MCL; n = 7). Like CLL, MM cells were sensitive to the MEK inhibitor trametinib, and synergy was observed with venetoclax. In contrast, MCL cells were unresponsive to MEK inhibition. To investigate the underlying mechanisms of the disease-specific drug sensitivities, we performed flow cytometry-based high-throughput profiling of 31 signaling proteins and regulators of apoptosis in the 19 cell lines. We found that high expression of the antiapoptotic proteins myeloid cell leukemia-1 (Mcl-1) or B-cell lymphoma-extra large (Bcl-xL) predicted low sensitivity to trametinib + venetoclax. The low sensitivity could be overcome by combined treatment with an Mcl-1 or Bcl-xL inhibitor. Our findings suggest that MEK/Bcl-2 inhibition has therapeutic potential in leukemia and myeloma, and demonstrate that protein expression levels can serve as predictive biomarkers for treatment sensitivities.

iTReX: Interactive exploration of mono- and combination therapy dose response profiling data

High throughput screening methods, measuring the sensitivity and resistance of tumor cells to drug treatments have been rapidly evolving. Not only do these screens allow correlating response profiles to tumor genomic features for developing novel predictors of treatment response, but they can also add evidence for therapy decision making in precision oncology. Recent analysis methods developed for either assessing single agents or combination drug efficacies enable quantification of dose-response curves with restricted symmetric fit settings. Here, we introduce iTReX, a user-friendly and interactive Shiny/R application, for both the analysis of mono- and combination therapy responses. The application features an extended version of the drug sensitivity score (DSS) based on the integral of an advanced five-parameter dose-response curve model and a differential DSS for combination therapy profiling. Additionally, iTReX includes modules that visualize drug target interaction networks and support the detection of matches between top therapy hits and the sample omics features to enable the identification of druggable targets and biomarkers. iTReX enables the analysis of various quantitative drug or therapy response readouts (e.g. luminescence, fluorescence microscopy) and multiple treatment strategies (drug treatments, radiation). Using iTReX we validate a cost-effective drug combination screening approach and reveal the application's ability to identify potential sample-specific biomarkers based on drug target interaction networks. The iTReX web application is accessible at https://itrex.kitz-heidelberg.de.

High-throughput screening for drug discovery targeting the cancer cell-microenvironment interactions in hematological cancers

INTRODUCTION

The interactions between leukemic blasts and cells within the bone marrow environment affect oncogenesis, cancer stem cell survival, as well as drug resistance in hematological cancers. The importance of this interaction is increasingly being recognized as a potentially important target for future drug discoveries and developments. Recent innovations in the high throughput drug screening-related technologies, novel ex-vivo disease-models, and freely available machine-learning algorithms are advancing the drug discovery process by targeting earlier undruggable proteins, complex pathways, as well as physical interactions (e.g. leukemic cell-bone microenvironment interaction).

AREA COVERED

In this review, the authors discuss the recent methodological advancements and existing challenges to target specialized hematopoietic niches within the bone marrow during leukemia and suggest how such methods can be used to identify drugs targeting leukemic cell-bone microenvironment interactions.

EXPERT OPINION

The recent development in cell-cell communication scoring technology and culture conditions can speed up the drug discovery by targeting the cell-microenvironment interaction. However, to accelerate this process, collecting clinical-relevant patient tissues, developing culture model systems, and implementing computational algorithms, especially trained to predict drugs and their combination targeting the cancer cell-bone microenvironment interaction are needed.

bayesynergy: flexible Bayesian modelling of synergistic interaction effects in in vitro drug combination experiments

The effect of cancer therapies is often tested pre-clinically via in vitro experiments, where the post-treatment viability of the cancer cell population is measured through assays estimating the number of viable cells. In this way, large libraries of compounds can be tested, comparing the efficacy of each treatment. Drug interaction studies focus on the quantification of the additional effect encountered when two drugs are combined, as opposed to using the treatments separately. In the bayesynergy R package, we implement a probabilistic approach for the description of the drug combination experiment, where the observed dose response curve is modelled as a sum of the expected response under a zero-interaction model and an additional interaction effect (synergistic or antagonistic). Although the model formulation makes use of the Bliss independence assumption, we note that the posterior estimates of the dose-response surface can also be used to extract synergy scores based on other reference models, which we illustrate for the Highest Single Agent model. The interaction is modelled in a flexible manner, using a Gaussian process formulation. Since the proposed approach is based on a statistical model, it allows the natural inclusion of replicates, handles missing data and uneven concentration grids, and provides uncertainty quantification around the results. The model is implemented in the open-source Stan programming language providing a computationally efficient sampler, a fast approximation of the posterior through variational inference, and features parallel processing for working with large drug combination screens.

Machine learning approaches for drug combination therapies

Drug combination therapy is a promising strategy to treat complex diseases such as cancer and infectious diseases. However, current knowledge of drug combination therapies, especially in cancer patients, is limited because of adverse drug effects, toxicity and cell line heterogeneity. Screening new drug combinations requires substantial efforts since considering all possible combinations between drugs is infeasible and expensive. Therefore, building computational approaches, particularly machine learning methods, could provide an effective strategy to overcome drug resistance and improve therapeutic efficacy. In this review, we group the state-of-the-art machine learning approaches to analyze personalized drug combination therapies into three categories and discuss each method in each category. We also present a short description of relevant databases used as a benchmark in drug combination therapies and provide a list of well-known, publicly available interactive data analysis portals. We highlight the importance of data integration on the identification of drug combinations. Finally, we address the advantages of combining multiple data sources on drug combination analysis by showing an experimental comparison.

Network-guided identification of cancer-selective combinatorial therapies in ovarian cancer

Each patient's cancer consists of multiple cell subpopulations that are inherently heterogeneous and may develop differing phenotypes such as drug sensitivity or resistance. A personalized treatment regimen should therefore target multiple oncoproteins in the cancer cell populations that are driving the treatment resistance or disease progression in a given patient to provide maximal therapeutic effect, while avoiding severe co-inhibition of non-malignant cells that would lead to toxic side effects. To address the intra- and inter-tumoral heterogeneity when designing combinatorial treatment regimens for cancer patients, we have implemented a machine learning-based platform to guide identification of safe and effective combinatorial treatments that selectively inhibit cancer-related dysfunctions or resistance mechanisms in individual patients. In this case study, we show how the platform enables prediction of cancer-selective drug combinations for patients with high-grade serous ovarian cancer using single-cell imaging cytometry drug response assay, combined with genome-wide transcriptomic and genetic profiles. The platform makes use of drug-target interaction networks to prioritize those combinations that warrant further preclinical testing in scarce patient-derived primary cells. During the case study in ovarian cancer patients, we investigated (i) the relative performance of various ensemble learning algorithms for drug response prediction, (ii) the use of matched single-cell RNA-sequencing data to deconvolute cell population-specific transcriptome profiles from bulk RNA-seq data, (iii) and whether multi-patient or patient-specific predictive models lead to better predictive accuracy. The general platform and the comparison results are expected to become useful for future studies that use similar predictive approaches also in other cancer types.