Synergistic Drug Combinations Research Articles

Leveraging Network Target Theory for Efficient Prediction of Drug-Disease Interactions: A Transfer Learning Approach.

Efficient virtual screening methods can expedite drug discovery and facilitate the development of innovative therapeutics. This study presents a novel transfer learning model based on network target theory, integrating deep learning techniques with diverse biological molecular networks to predict drug-disease interactions. By incorporating network techniques that leverage vast existing knowledge, the approach enables the extraction of more precise and informative drug features, resulting in the identification of 88,161 drug-disease interactions involving 7,940 drugs and 2,986 diseases. Furthermore, this model effectively addresses the challenge of balancing large-scale positive and negative samples, leading to improved performance across various evaluation metrics such as an Area under curve (AUC) of 0.9298 and an F1 score of 0.6316. Moreover, the algorithm accurately predicts drug combinations and achieves an F1 score of 0.7746 after fine-tuning. Additionally, it identifies two previously unexplored synergistic drug combinations for distinct cancer types in disease-specific biological network environments. These findings are further validated through in vitro cytotoxicity assays, demonstrating the potential of the model to enhance drug development and identify effective treatment regimens for specific diseases.

A guide for active learning in synergistic drug discovery

Synergistic drug combination screening is a promising strategy in drug discovery, but it involves navigating a costly and complex search space. While AI, particularly deep learning, has advanced synergy predictions, its effectiveness is limited by the low occurrence of synergistic drug pairs. Active learning, which integrates experimental testing into the learning process, has been proposed to address this challenge. In this work, we explore the key components of active learning to provide recommendations for its implementation. We find that molecular encoding has a limited impact on performance, while the cellular environment features significantly enhance predictions. Additionally, active learning can discover 60% of synergistic drug pairs with only exploring 10% of combinatorial space. The synergy yield ratio is observed to be even higher with smaller batch sizes, where dynamic tuning of the exploration-exploitation strategy can further enhance performance. The code can be found at https://github.com/LBiophyEvo/DrugSynergy

Predicting drug combination side effects based on a metapath-based heterogeneous graph neural network

In recent years, combined drug screening has played a very important role in modern drug discovery. Generally, synergistic drug combinations are crucial in treatment for many diseases. However, the toxic side effects of drug combinations are probably increased with the increase of drugs numbers, so the accurate prediction of toxic side effects of drug combinations is equally important. In this paper, we built a Metapath-based Aggregated Embedding Model on Single Drug–Side Effect Heterogeneous Information Network (MAEM-SSHIN), which extracts feature from a heterogeneous information network of single drug side effects, and a Graph Convolutional Network on Combinatorial drugs and Side effect Heterogeneous Information Network (GCN-CSHIN), which transforms the complex task of predicting multiple side effects between drug pairs into the more manageable prediction of relationships between combinatorial drugs and individual side effects. MAEM-SSHIN and GCN-CSHIN provided a united novel framework for predicting potential side effects in combinatorial drug therapies. This integration enhances prediction accuracy, efficiency, and scalability. Our experimental results demonstrate that this combined framework outperforms existing methodologies in predicting side effects, and marks a significant advancement in pharmaceutical research.

Novel combination therapy targeting oncogenic signaling kinase P21 activated Kinase-1 and chemotherapeutic drugs against triple negative breast cancer.

Most of the triple negative phenotype or basal-like molecular subtypes of breast cancers are associated with aggressive clinical behaviour and show poor disease prognosis. Current treatment options are constrained, emphasizing the need for novel combinatorial therapies for this particular tumor subtype. Our group has demonstrated that functionally active p21 activated kinase 1 (PAK1) exhibits significantly higher expression levels in clinical triple negative breast cancer (TNBC) samples compared to other subtypes, as well as adjacent normal tissues. Low PAK1 expression in TNBC was significantly linked to better prognosis, with improved overall survival (OS, p=0.00236) and relapse-free survival (RFS, p=0.0314), as shown by GOBO analysis. To confirm the role of PAK1 as a therapeutic target and to discover novel synergistic chemotherapy drug combinations, we conducted a drug combination screen using triple negative breast cancer cell lines and a mouse metastatic tumor cell line. We identified the combined inhibition of PAK1 inhibitor, NVS-PAK1 with doxorubicin/paclitaxel/methotrexate as a synergistic novel therapeutic approach for treating metastatic TNBC to improve overall survival. This study also indicated a reduction in the effective dosage of the chemotherapeutic drug when combined with NVS-PAK1. Our study demonstrates that combining NVS-PAK1 with each of the chemotherapeutic drugs' doxorubicin, paclitaxel, and methotrexate resulted in decreased colony formation, reduced wound healing capability, and diminished migratory and invasive potential in both TNBC cell lines and 4T1 in vitro. These findings were further validated in orthotopic mouse mammary tumors, confirming that simultaneous PAK1 inhibition alongside chemotherapy significantly enhanced anti-tumor efficacy and reduced metastasis.

TransferBAN-Syn: a transfer learning-based algorithm for predicting synergistic drug combinations against echinococcosis.

Echinococcosis is a zoonotic parasitic disease caused by the larvae of echinococcus tapeworms infesting the human body. Drug combination therapy is highly valued for the treatment of echinococcosis because of its potential to overcome resistance and enhance the response to existing drugs. Traditional methods of identifying drug combinations via biological experimentation is costly and time-consuming. Besides, the scarcity of existing drug combinations for echinococcosis hinders the development of computational methods. In this study, we propose a transfer learning-based model, namely TransferBAN-Syn, to identify synergistic drug combinations against echinococcosis based on abundant information of drug combinations against parasitic diseases. To the best of our knowledge, this is the first work that leverages transfer learning to improve prediction accuracy with limited drug combination data in echinococcosis treatment. Specifically, TransferBAN-Syn contains a drug interaction feature representation module, a disease feature representation module, and a prediction module, where the bilinear attention network is employed in the drug interaction feature representation module to deeply extract the fusion feature of drug combinations. Besides, we construct a special dataset with multi-source information and drug combinations for parasitic diseases, including 21 parasitic diseases and echinococcosis. TransferBAN-Syn is designed and initially trained on the abundant data from the 21 parasitic diseases, which serves as the source domain. The parameters in the feature representation modules of drug interactions and diseases are preserved from this source domain, and those in the prediction module are then fine-tuned to specifically identify the synergistic drug combinations for echinococcosis in the target domain. Comparison experiments have shown that TransferBAN-Syn not only improves the accuracy of predicting echinococcosis drug combinations but also enhances generalizability. Furthermore, TransferBAN-Syn identifies potential drug combinations that hold promise in the treatment of echinococcosis. TransferBAN-Syn not only offers new synergistic drug combinations for echinococcosis but also provides a novel approach for predicting potential drug pairs for diseases with limited combination data.

Systematic prediction of synergistic drug combinations through network-based deep learning framework

Systematic prediction of synergistic drug combinations through network-based deep learning framework

Leveraging artificial intelligence and machine learning to accelerate discovery of disease-modifying therapies in type 1 diabetes.

Progress in developing therapies for the maintenance of endogenous insulin secretion in, or the prevention of, type 1 diabetes has been hindered by limited animal models, the length and cost of clinical trials, difficulties in identifying individuals who will progress faster to a clinical diagnosis of type 1 diabetes, and heterogeneous clinical responses in intervention trials. Classic placebo-controlled intervention trials often include monotherapies, broad participant populations and extended follow-up periods focused on clinical endpoints. While this approach remains the 'gold standard' of clinical research, efforts are underway to implement new approaches harnessing the power of artificial intelligence and machine learning to accelerate drug discovery and efficacy testing. Here, we review emerging approaches for repurposing agents used to treat diseases that share pathogenic pathways with type 1 diabetes and selecting synergistic combinations of drugs to maximise therapeutic efficacy. We discuss how emerging multi-omics technologies, including analysis of antigen processing and presentation to adaptive immune cells, may lead to the discovery of novel biomarkers and subsequent translation into antigen-specific immunotherapies. We also discuss the potential for using artificial intelligence to create 'digital twin' models that enable rapid in silico testing of personalised agents as well as dose determination. To conclude, we discuss some limitations of artificial intelligence and machine learning, including issues pertaining to model interpretability and bias, as well as the continued need for validation studies via confirmatory intervention trials.

Cancer Cell's Achilles Heels: Considerations for Design of Anti-Cancer Drug Combinations.

Loss of function screens using shRNA (short hairpin RNA) and CRISPR (clustered regularly interspaced short palindromic repeats) are routinely used to identify genes that modulate responses of tumor cells to anti-cancer drugs. Here, by integrating GSEA (Gene Set Enrichment Analysis) and CMAP (Connectivity Map) analyses of multiple published shRNA screens, we identified a core set of pathways that affect responses to multiple drugs with diverse mechanisms of action. This suggests that these pathways represent "weak points" or "Achilles heels", whose mild disturbance should make cancer cells vulnerable to a variety of treatments. These "weak points" include proteasome, protein synthesis, RNA splicing, RNA synthesis, cell cycle, Akt-mTOR, and tight junction-related pathways. Therefore, inhibitors of these pathways are expected to sensitize cancer cells to a variety of drugs. This hypothesis was tested by analyzing the diversity of drugs that synergize with FDA-approved inhibitors of the proteasome, RNA synthesis, and Akt-mTOR pathways. Indeed, the quantitative evaluation indicates that inhibitors of any of these signaling pathways can synergize with a more diverse set of pharmaceuticals, compared to compounds inhibiting targets distinct from the "weak points" pathways. Our findings described here imply that inhibitors of the "weak points" pathways should be considered as primary candidates in a search for synergistic drug combinations.

Synergistic combinations of Angelica sinensis for myocardial infarction treatment: network pharmacology and quadratic optimization approach

Background and aimAngelica sinensis (Oliv.) Diels (Danggui, DG), exhibits potential in myocardial infarction (MI) treatment. However, research on its synergistic combinations for cardioprotective effects has been limited owing to inadequate approaches.Experimental procedureWe identified certain phenolic acids and phthalein compounds in DG. Network pharmacology analysis and experimental validation revealed the components that protected H9c2 cells and reduced lactate dehydrogenase levels. Subsequently, a combination of computational experimental strategies and a secondary phenotypic optimization platform was employed to identify effective component combinations with synergistic interactions. The Chou-Talalay and Zero Interaction Potency (ZIP) models were utilized to quantify the synergistic relationships. The optimal combination identified, Z-Ligustide and Chlorogenic acid (Z-LIG/CGA), was evaluated for its protective effects on cardiac function and cardiomyocytes apoptosis induced by inflammatory in a mouse model of induced by left anterior descending coronary artery ligation. Flow cytometry was further utilized to detect the polarization ratio of M1/M2 macrophages and the expression of inflammatory cytokines in serum was measured, assessing the inhibition of inflammatory responses and pro-inflammatory signaling factors by Z-LIG/CGA.Key resultsQuadratic surface analysis revealed that the Z-LIG/CGA combination displayed synergistic cardioprotective effects (combination index value <1; ZIP value >10). In vivo, Z-LIG/CGA significantly improved cardiac function and reduced the fibrotic area in mice post-MI, surpassing the results in groups treated with Z-LIG or CGA alone. Compared to the MI group, the Z-LIG/CGA group exhibited decreased ratios of the myocardial cell apoptosis-related proteins BAX/Bcl-2 and Cleaved Caspase-3/Caspase-3 in mice. Further research revealed that Z-LIG/CGA treatment significantly increased IL-1R2 levels, significantly decreased IL-17RA levels, and inhibited the activation of p-STAT1, thereby alleviating cell apoptosis after MI. Additionally, the Z-LIG/CGA combination significantly inhibited the ratio of M1/M2 macrophages and suppressed the expression levels of pro-inflammatory cytokines IL-1β, IL-6, IL-17, and TNF-α in the serum.Conclusion and implicationsWe successfully identified a synergistic drug combination, Z-LIG/CGA, which improves MI outcomes by inhibiting cardiomyocyte apoptosis and inflammatory damage through modulating macrophage polarization and regulating the IL-1R2/IL-17RA/STAT1 signaling pathway. This study provides a charming paradigm to explore effective drug combinations in traditional Chinese medicine and a promising treatment for MI.

MHCLSyn: Multi-View Hypergraph Contrastive Learning for Synergistic Drug Combination Prediction

MHCLSyn: Multi-View Hypergraph Contrastive Learning for Synergistic Drug Combination Prediction

Multi-Component, Time-Course screening to develop combination cancer therapies based on synergistic toxicity

Clinical trials in cancer are ideally built on a foundation of sound mechanistic rationale and well-validated drug activity in relevant disease models. The screening of approved and investigational drugs in cell-based phenotypic assays can provide evidence of drug activity, but alternative screening paradigms are needed to develop and optimize multidrug combination regimens. Here, we utilize in vitro screening outcomes across a panel of lymphoma cell lines to dissect the activity of four small-molecule drugs (Venetoclax, Ibrutinib, Prednisolone, and Lenalidomide) currently under investigation within ongoing clinical trials in lymphoma. Data from multiple concentration ranges and time points show that synergistic drug combinations promote apoptosis and cytotoxicity responses at concentrations and time points that are consistent with in vivo drug exposures. To fully map the interaction landscape of these agents in relevant cell models, we developed an in vitro assay format that facilitated time-course evaluations involving concurrent multidrug exposure which further highlighted rapid, synergistic apoptosis induction as a central engine for the activity of this multicomponent targeted therapy. In addition to several instances of exceptional drug+drug synergy, the genetically similar diffuse large B cell lymphoma models also displayed substantial heterogeneity in the degree of synergism between drug pairs. A parallel survey of chemotherapies exhibited limited combination benefit, supporting recent findings that multicomponent chemotherapy outcomes are driven by individual drug activity. Collectively, these data demonstrate how in vitro drug screening data can identify multidrug combinations that exploit drug synergy to overcome the functional diversity of human malignancies.

DD-PRiSM: a deep learning framework for decomposition and prediction of synergistic drug combinations.

Combination therapies have emerged as a promising approach for treating complex diseases, particularly cancer. However, predicting the efficacy and safety profiles of these therapies remains a significant challenge, primarily because of the complex interactions among drugs and their wide-ranging effects. To address this issue, we introduce DD-PRiSM (Decomposition of Drug-Pair Response into Synergy and Monotherapy effect), a deep-learning pipeline that predicts the effects of combination therapy. DD-PRiSM consists of two predictive models. The first is the Monotherapy model, which predicts parameters of the drug response curve based on drug structure and cell line gene expression. This reconstructed curve is then used to predict cell viability at the given drug dosage. The second is the Combination therapy model, which predicts the efficacy of drug combinations by analyzing individual drug effects and their synergistic interactions with a specific dosage level of individual drugs. The efficacy of DD-PRiSM is demonstrated through its performance metrics, achieving a root mean square error of 0.0854, a Pearson correlation coefficient of 0.9063, and an R2 of 0.8209 for unseen pairs. Furthermore, DD-PRiSM distinguishes itself by its capability to decompose combination therapy efficacy, successfully identifying synergistic drug pairs. We demonstrated synergistic responses vary across cancer types and identified hub drugs that trigger synergistic effects. Finally, we suggested a promising drug pair through our case study.

Autoencoder-based drug synergy framework for malignant diseases

Drug combination emerges as a viable option for the treatment of malignant diseases. Drug combination outperforms monotherapy by improving therapeutic efficacy, reducing toxicity, and overcoming drug resistance. To find viable drug combinations it is difficult to traverse empirically because of enormous combinational space. Machine learning and deep learning approaches are used to uncover novel synergistic drug combinations in enormous combinational space. Here, AESyn, a novel autoencoder-based drug synergy framework for malignant diseases using a bag of words encoding is proposed. The bag of word encoding technique is used to extract drug-targeted genes. The framework utilized screening data from NCI-ALMANAC, and O’Neil datasets. Autoencoders take drug embeddings with drug-targeted genes as input for processing. The autoencoder in the proposed framework is used to extract drug features. The proposed framework is evaluated on classification and regression metrics. The performance of the proposed framework is compared with existing methods of drug synergy. According to the findings, the proposed framework achieved high performance with an accuracy of 95%, AUROC of 94.2%, and MAPE of 7.2. The autoencoder-based framework for malignant diseases using an encoding technique provides a stable, order-independent drug synergy prediction.

PAIRWISE: Deep Learning-based Prediction of Effective Personalized Drug Combinations in Cancer.

Combination therapies offer promise for improving cancer treatment efficacy and preventing recurrence. However, identifying optimal drug combinations tailored to specific cancer subtypes and individual patients is extremely challenging due to the vast number of possible combinations and tumor heterogeneity. To address this gap, we take a machine learning approach combining deep learning with transfer learning to incorporate prior scientific knowledge and predict drug synergy based on tumor-specific transcriptome profiles. This approach, called PAIRWISE, explicitly modeled synergistic effects of drug combinations in cancer cell lines or individual tumor samples based on drug chemical structures, drug targets, and transcriptomes of inferred samples. PAIRWISE outperformed competing models with an area under the receiver operating characteristic curve (AUROC) of 0.85 on held-out cancer cell lines. When applied to an independent dataset of combinations with Bruton Tyrosine Kinase inhibitors (BTKi) in Diffuse Large B Cell Lymphoma (DLBCL) cell lines, PAIRWISE accurately predicted synergistic drug combinations with an AUROC of 0.72. To further confirm the robustness of PAIRWISE predictions, we performed an in silico, patient profile-directed screen for other compounds that would synergize with BTKi in DLBCL patients, and confirmed the synergy of the predictions using a panel of eight non-Hodgkin lymphoma cell lines. These findings demonstrate the ability of PAIRWISE to nominate effective personalized drug combinations, accelerating the development of precision oncology.

Repurposing Drugs and Synergistic Combinations as Potential Therapies for Inhibiting SARS-CoV-2 and Coronavirus Replication.

Drug repurposing can serve an important role in rapidly discovering medicament options for emerging microbial pandemics. In this study, a pragmatic approach is demonstrated for screening and testing drug combinations as potential broad-spectrum therapies against SARS-CoV-2 and other betacoronaviruses. Rapid cell-based phenotypic small molecule screens were executed using related common-cold-causing HCoV-OC43 betacoronavirus to identify replication inhibitors from a library of drugs approved by regulatory agencies for other indications. Given the best inhibitors, an expedient checkerboard strategy then served to identify synergistic drug combinations. These combinations were then validated using more challenging assays involving SARS-CoV-2 and variants. Promising drug combinations against multiple viral variants were discovered and involved Tilorone with Nelfinavir or Molnupiravir.

Zidovudine in synergistic combination with nitrofurantoin or omadacycline: in vitro and in murine urinary tract or lung infection evaluation against multidrug-resistant Klebsiella pneumoniae.

Limited treatment options and multidrug-resistant (MDR) Klebsiella pneumoniae present a significant therapeutic challenge, underscoring the need for novel approaches. Drug repurposing is a promising tool for augmenting the activity of many antibiotics. This study aimed to identify novel synergistic drug combinations against K. pneumoniae based on drug repurposing. We used the clinically isolated GN 172867 MDR strain of K. pneumoniae to determine the reversal resistance activity of zidovudine (AZT). The combined effects of AZT and various antibiotics, including nitrofurantoin (NIT) and omadacycline (OMC), were examined using the checkerboard method, growth curves, and crystal violet assays to assess biofilms. An in vitro combination activity testing was carried out in 12 isolates of K. pneumoniae. In vivo murine urinary tract and lung infection models were used to evaluate the therapeutic effects of AZT + NIT and AZT + OMC, respectively. The fractional inhibitory concentration index and growth curve demonstrated that AZT synergized with NIT or OMC against K. pneumoniae strains. In addition, AZT + NIT inhibited biofilm formation and cleared mature biofilms. In vivo, compared with untreated GN 172867-infected mice, AZT + NIT and AZT + OMC treatment decreased colony counts in multiple tissues (P < 0.05) and pathological scores in the bladder and kidneys (P < 0.05) and increased the survival rate by 60% (P < 0.05). This study evaluated the combination of AZT and antibiotics to treat drug-resistant K. pneumoniae infections and found novel drug combinations for the treatment of acute urinary tract infections. These findings suggest that AZT may exert significant anti-resistance activity.

Synergistic invitro antimicrobial activity of polyherbal combination of Morinda lucida fruit and Pterocarpus santalinoides seed against multi-drug resistant clinical bacterial isolates

Background: Synergistic drug combination has been shown to be a way of bypassing drug resistance and reducing the amounts of antimicrobials consumed. As infections caused by multi-drug resistant organisms (MDROs) continue to pose global threat, it is important to search for new antimicrobial combinations of plant origin that are safe and readily available. The objective of this study is to evaluate the synergistic antimicrobial activity of extracts of Morinda lucida fruit and Pterocarpus santalinoides seed against multi-drug resistant (MDR) bacterial isolates Methodology: Morinda lucida and P. santalinoides fruits were plucked and washed clean, and the fruits of P. santalinoides were deseeded to remove the seeds. They were cut into smaller pieces and dried under shade before being milled into smooth powder and extracted with methanol. The clinical bacterial isolates used were MDR Escherichia coli, Proteus mirabilis, Klebsiella pneumoniae, Pseudomonas aeruginosa, and Staphylococcus aureus. The phytochemical constituents of the extracts were determined using the standard method. The invitro antimicrobial assay of the extracts was done at a concentration of 50 to 400 mg/ml using the agar well diffusion technique. The minimum inhibitory concentration (MIC) and fractional inhibitory concentration (FIC) of each extract were determined using the Checker-board micro-titration method, and the FIC result obtained for each isolate was used to calculate the fractional inhibitory concentration index (FICI) of the combined extracts. The time kill assay was performed to confirm the synergistic and bactericidal activities from the MIC values obtained. Results: The phytochemical analysis revealed that the extracts of both herbal plants contained alkaloids, phenol, tannin, saponin, glycosides, and terpenoids. The antimicrobial assay results showed that the polyherbal combination of the extracts was active against all the MDR bacterial isolates tested with varying zones of inhibition. The mean inhibition zone diameters of individual M. lucida and P. santalinoides ranged from 18.0±0.9mm to 26.0±1.4mm and 17.0±0.1mm to 24.0±0.2mm respectively, while the MIC ranged from 6.25mg/ml to 12.5mg/ml for M. lucida and 12.5 mg/ml for P. santalinoides. The mean inhibition zone diameter of the polyherbal combination of the two plant extracts ranged from 25.00±00mm to 34.0±0.4mm, which compared favorably with that of levofloxacin control (28.0±0.0mm to 32.00±0.0mm), while their MIC ranged from 0.39mg/ml to 1.56mg/ml. The FIC of M. lucida extract ranged from 0.06mg/ml to 0.25mg/ml while that of P. santalinoides ranged from 0.03mg/ml to 0.13mg/ml. The FICI of combined extracts ranged from 0.09mg/ml to 0.38 mg/ml for all the MDR isolates, which is less than 0.5mg/ml, indicating synergism against all the isolates. The time of kill assay confirmed the synergistic and bactericidal activities with a 3log10 CFU/ml decrease in the number of viable cells within 6 hours of incubation.Conclusion: Our findings showed synergistic antibacterial actions of extracts of M. lucida fruit and P. santalinoides seed against MDR clinical bacterial isolates, comparable to levofloxacin. Combination of these herbal plants may serve as alternative sources of antimicrobial agents for the treatment of infections caused by MDR bacterial pathogens.

Dual-view jointly learning improves personalized drug synergy prediction.

Accurate and robust estimation of the synergistic drug combination is important for medicine precision. Although some computational methods have been developed, some predictions are still unreliable especially for the cross-dataset predictions, due to the complex mechanism of drug combinations and heterogeneity of cancer samples. We have proposed JointSyn that utilizes dual-view jointly learning to predict sample-specific effects of drug combination from drug and cell features. JointSyn outperforms existing state-of-the-art methods in predictive accuracy and robustness across various benchmarks. Each view of JointSyn captures drug synergy-related characteristics and makes complementary contributes to the final prediction of the drug combination. Moreover, JointSyn with fine-tuning improves its generalization ability to predict a novel drug combination or cancer sample using a small number of experimental measurements. We also used JointSyn to generate an estimated atlas of drug synergy for pan-cancer and explored the differential pattern among cancers. These results demonstrate the potential of JointSyn to predict drug synergy, supporting the development of personalized combinatorial therapies. Source code and data are available at https://github.com/LiHongCSBLab/JointSyn.

A multi-view feature representation for predicting drugs combination synergy based on ensemble and multi-task attention models

This paper proposes a novel multi-view ensemble predictor model that is designed to address the challenge of determining synergistic drug combinations by predicting both the synergy score value values and synergy class label of drug combinations with cancer cell lines. The proposed methodology involves representing drug features through four distinct views: Simplified Molecular-Input Line-Entry System (SMILES) features, molecular graph features, fingerprint features, and drug-target features. On the other hand, cell line features are captured through four views: gene expression features, copy number features, mutation features, and proteomics features. To prevent overfitting of the model, two techniques are employed. First, each view feature of a drug is paired with each corresponding cell line view and input into a multi-task attention deep learning model. This multi-task model is trained to simultaneously predict both the synergy score value and synergy class label. This process results in sixteen input view features being fed into the multi-task model, producing sixteen prediction values. Subsequently, these prediction values are utilized as inputs for an ensemble model, which outputs the final prediction value. The ‘MVME’ model is assessed using the O’Neil dataset, which includes 38 distinct drugs combined across 39 distinct cancer cell lines to output 22,737 drug combination pairs. For the synergy score value, the proposed model scores a mean square error (MSE) of 206.57, a root mean square error (RMSE) of 14.30, and a Pearson score of 0.76. For the synergy class label, the model scores 0.90 for accuracy, 0.96 for precision, 0.57 for kappa, 0.96 for the area under the ROC curve (ROC-AUC), and 0.88 for the area under the precision-recall curve (PR-AUC).

Anticancer role of flubendazole: Effects and molecular mechanisms (Review).

Flubendazole, an anthelmintic agent with a well-established safety profile, has emerged as a promising anticancer drug that has demonstrated efficacy against a spectrum of cancer types over the past decade. Its anticancer properties encompass a multifaceted mechanism of action, including the inhibition of cancer cell proliferation, disruption of microtubule dynamics, regulation of cell cycle, autophagy, apoptosis, suppression of cancer stem cell characteristics, promotion of ferroptosis and inhibition of angiogenesis. The present review aimed to provide a comprehensive overview of the molecular underpinnings of the anticancer activity of flubendazole, highlighting key molecules and regulatory pathways. Given the breadth of the potential of flubendazole, further research is imperative to identify additional cancer types sensitive to flubendazole, refine experimental methodologies for enhancing its reliability, uncover synergistic drug combinations, improve its bioavailability and explore innovative administration methods. The present review provided a foundation for future studies on the role of flubendazole in oncology and described its molecular mechanisms of action.