Effective Drug Combinations Research Articles

Activity of amorolfine or ciclopirox in combination with terbinafine against pathogenic fungi in onychomycosis-Results of an invitro investigation.

Onychomycoses are difficult-to-treat fungal infections with high relapse rates. Combining oral and topical antifungal drugs is associated with higher success rates. Additive or synergistic modes of action are expected to enhance treatment success rates. Investigation of the combined effects of antifungal drugs invitro with different modes of action and application on clinical isolates from mycotic nails. Isolates of Trichophyton rubrum, Trichophyton interdigitale and Scopulariopsis brevicaulis were collected from infected toenail specimens of patients with onychomycosis. Susceptibility testing was performed in 96-well polystyrene plates using a standard stepwise microdilution protocol. Additive or synergistic activity at varying concentrations was investigated by the checkerboard method. Combining terbinafine with amorolfine tended to be more effective than terbinafine in conjunction with ciclopirox. In most combinations, additive effects were observed. Synergy was detected in combinations with involving amorolfine in S. brevicaulis. These additive and synergistic interactions indicate that combined therapy with topical amorolfine and oral terbinafine is justified. Sublimation of amorolfine (and terbinafine) may enhance the penetration in and through the nail plate, and support treatment efficacy. These invitro results support the notion that combining oral terbinafine and topical amorolfine is beneficial to patients with onychomycosis, particularly if the pathogen is a non-dermatophyte fungus such as S. brevicaulis.

Boolean modeling of breast cancer signaling pathways uncovers mechanisms of drug synergy.

Breast cancer is one of the most common types of cancer in females. While drug combinations have shown potential in breast cancer treatments, identifying new effective drug pairs is challenging due to the vast number of possible combinations among available compounds. Efforts have been made to accelerate the process with in silico predictions. Here, we developed a Boolean model of signaling pathways in breast cancer. The model was tailored to represent five breast cancer cell lines by integrating information about cell-line specific mutations, gene expression, and drug treatments. The models reproduced cell-line specific protein activities and drug-response behaviors in agreement with experimental data. Next, we proposed a calculation of protein synergy scores (PSSs), determining the effect of drug combinations on individual proteins' activities. The PSSs of selected proteins were used to investigate the synergistic effects of 150 drug combinations across five cancer cell lines. The comparison of the highest single agent (HSA) synergy scores between experiments and model predictions from the MDA-MB-231 cell line achieved the highest Pearson's correlation coefficient of 0.58 with a great balance among the classification metrics (AUC = 0.74, sensitivity = 0.63, and specificity = 0.64). Finally, we clustered drug pairs into groups based on the selected PSSs to gain further insights into the mechanisms underlying the observed synergistic effects of drug pairs. Clustering analysis allowed us to identify distinct patterns in the protein activities that correspond to five different modes of synergy: 1) synergistic activation of FADD and BID (extrinsic apoptosis pathway), 2) synergistic inhibition of BCL2 (intrinsic apoptosis pathway), 3) synergistic inhibition of MTORC1, 4) synergistic inhibition of ESR1, and 5) synergistic inhibition of CYCLIN D. Our approach offers a mechanistic understanding of the efficacy of drug combinations and provides direction for selecting potential drug pairs worthy of further laboratory investigation.

Pharmaceutical preparation, standardization and comparative study of Tinduka Ghanavati and Kulattha Guda Avaleha in context of Shwasa Roga

Ayurveda is the world's oldest medical system, which dates back to the Rigveda period BC. 5000. All the medical systems of the world have received their form of organization and developmental inspiration from this, this is an undisputed proven fact. Ayurveda has been called the science of age. Charak has described Ayurveda as eternal. The medical science of Rasashastra is also included in Ayurveda medical science. Rasashastra has been revolutionary in Ayurveda since the 8th century. This has been said to reflect the results of Rasashastra during this period. The chemical drug manufacturing process was being used in the medical world since the 8th century. Since time immemorial, humans have been engaged in research for various purposes in various areas of their lives. Research in Ayurveda is necessary and mandatory. As the struggle and difficulties in a person's life increase along with progressing on the path of salvation, he is suffering from very painful diseases due to not following the health- protecting diet and practices recommended by the famous people. Among these diseases, respiratory disease also holds an important place. This is seen more in the human community. From the study of various texts, it was found that Tindukaghanvati and Kulathaguda Avaleha are effective drug combinations for respiratory diseases. Therefore, in this research work, the study of the above mentioned Yogas on respiratory diseases was considered. The presented research work is being presented before the scholars to reestablish the principles propounded by the Acharyas. The success of the effort depends on the consent of scholars.

Effective combinations of glucose-lowering drugs in patients with obesity and type 2 diabetes mellitus during the treatment of diabetic foot syndrome

The article provides a brief analysis of the action mechanisms of modern combinations by glucose-lowering drugs for type 2 diabetes mellitus, diabetic foot syndrome and obesity. Using the example of clinical observations, the positive dynamics of reducing body weight and glycated hemoglobin was demonstrated. It also shows how good control of type 2 diabetes makes it possible to effectively treat such a formidable complication as diabetic foot syndrome.

An evaluation of the combination effect of zoledronate and chemotherapeutic agents in canine osteosarcoma cells.

Osteosarcoma (OSA) is an aggressive form of bone cancer in both dogs and humans. The treatment options for metastatic (stage III) OSA are currently limited and the prognosis is poor. Zoledronate, a second generation amino-bisphosphonate, is commonly used for palliation of cancer induced bone pain. Zoledronate has also demonstrated anti-cancer properties and possibly enhances the cytotoxicity of doxorubicin in a canine histiocytosis cell line and human prostatic cancer cell line. The goal of this study was to evaluate the combination effect of zoledronate and various chemotherapeutic drugs in canine OSA cells. Canine OSA cell line (D17), cells from two canine primary OSAs, and MDCK, a canine kidney cell line, were used to evaluate the therapeutic potential of these drugs. Carboplatin, doxorubicin, vinorelbine, toceranib, and isophosphoramide mustard (active metabolite of ifosfamide) were used as chemotherapeutic agents. First, cells were treated with either zoledronate or chemotherapy drug alone for 72 hours. Cell viability was assessed using CellTiter Glo and IC5, IC10, IC20, and IC50 were calculated. Second, cells were treated with a combination of zoledronate and each chemotherapeutic agent at their IC5, IC10, IC20, and IC50 concentrations. After 72 hours, cell viability was assessed by CellTiter Glo. Zoledronate, carboplatin, doxorubicin, vinorelbine, and isophosphoramide mustard showed concentration dependent decrease in cell viability. Toceranib showed decreased cell viability only at higher concentrations. When zoledronate was used in combination with chemotherapy drugs, while it showed potential synergistic effects with toceranib, potential antagonistic effects with vinorelbine and isophosphoramide mustard were observed. However, the results differed by cell line and thus, further evaluation is warranted to understand the exact mechanism of action.

A review on graph neural networks for predicting synergistic drug combinations

Combinational therapies with synergistic effects provide a powerful treatment strategy for tackling complex diseases, particularly malignancies. Discovering these synergistic combinations, often involving various compounds and structures, necessitates exploring a vast array of compound pairings. However, practical constraints such as cost, feasibility, and complexity hinder exhaustive in vivo and in vitro experimentation. In recent years, machine learning methods have made significant inroads in pharmacology. Among these, Graph Neural Networks (GNNs) have gained increasing attention in drug discovery due to their ability to represent complex molecular structures as networks, capture vital structural information, and seamlessly handle diverse data types. This review aims to provide a comprehensive overview of various GNN models developed for predicting effective drug combinations, examining the limitations and strengths of different models, and comparing their predictive performance. Additionally, we discuss the datasets used for drug synergism prediction and the extraction of drug-related information as predictive features. By summarizing the state-of-the-art GNN-driven drug combination prediction, this review aims to offer valuable insights into the promising field of computational pharmacotherapy.

Enhancement of the antitumor effect of cisplatin and ginsenoside Rg3 by encapsulation in polylactic-co-glycolic acid nanoparticles

Purpose: To develop dual-loaded polylactic-co-glycolic acid (PLGA) nanoparticles (NPs) with two chemotherapeutic agents, i.e., cisplatin (DDP) and 20(R)-ginsenoside Rg3(Rg3), and to evaluate the drug release profiles and synergistic inhibitory effects of the nanoparticles on lung cancer A549 cells.Methods: The dual-laden PLGA NPs were synthesized using modified emulsion and solvent vaporization procedures. Drug loading (DL) and efficacy of co-encapsulation (EE) were determined with a modification of column elution technique. The cytotoxic and inhibitory effects of individual and combined drugs on A549 lung cancer cells were evaluated using MTT assay.Results: A sustained pattern of drug release was shown by PLGA/DDP, PLGA/Rg3, and PLGA/DDP+Rg3. The formulated PLGA and unbound drugs exerted dose- and time-reliant cytotoxic effects on A549 cells. At all concentrations tested, drugs encapsulated in PLGA nanoparticles were more effective in killing the cells than the free drugs (p < 0.05). In particular, PLGA/DDP + Rg3 formulation produced a synergistic inhibitory effect on the proliferation of A549 cells.Conclusion: Single- and dual-load PLGA groups display variabilities in profiles of drug release and in vitro cytotoxic effect. Furthermore, dual-load PLGA group produces significantly enhanced treatment effect. These results suggest that PLGA formulations hold great potential for future drug delivery.

Salmonella-mediated methionine deprivation drives immune activation and enhances immune checkpoint blockade therapy in melanoma

BackgroundAlthough immune checkpoint inhibitor (ICI)-based therapy is advantageous for patients with advanced melanoma, resistance and relapse are frequent. Thus, it is crucial to identify effective drug combinations and develop new...

SN-38, an active metabolite of irinotecan, inhibits transcription of nuclear factor erythroid 2-related factor 2 and enhances drug sensitivity of colorectal cancer cells.

Nuclear factor erythroid 2-related factor 2 (Nrf2) significantly contributes to drug resistance of cancer cells, and Nrf2 inhibitors have been vigorously pursued. Repurposing of existing drugs, especially anticancer drugs, is a straightforward and promising strategy to find clinically available Nrf2 inhibitors and effective drug combinations. Topoisomerase inhibitors SN-38 (an active metabolite of irinotecan), topotecan, mitoxantrone, and epirubicin were found to significantly suppress Nrf2 transcriptional activity in cancer cells. SN-38, the most potent one among them, significantly inhibited the transcription of Nrf2, as indicated by decreased mRNA level and binding of RNA polymerase II to NFE2L2 gene, while no impact on Nrf2 protein or mRNA degradation was observed. SN-38 synergized with Nrf2-sensitive anticancer drugs such as mitomycin C in killing colorectal cancer cells, and irinotecan and mitomycin C synergistically inhibited the growth of SW480 xenografts in nude mice. Our study identified SN-38 and three other topoisomerase inhibitors as Nrf2 inhibitors, revealed the Nrf2-inhibitory mechanism of SN-38, and indicate that clinically feasible drug combinations could be designed based on their interactions with Nrf2 signaling.

In Vitro Combinatorial Activity of Direct Acting Antivirals and Monoclonal Antibodies against the Ancestral B.1 and BQ.1.1 SARS-CoV-2 Viral Variants.

Combination antiviral therapy may be helpful in the treatment of SARS-CoV-2 infection; however, no clinical trial data are available, and combined use of direct-acting antivirals (DAA) and monoclonal antibodies (mAb) has been reported only anecdotally. To assess the cooperative effects of dual drug combinations in vitro, we used a VERO E6 cell-based in vitro system with the ancestral B.1 or the highly divergent BQ.1.1 virus to test pairwise combinations of the licensed DAA, including nirmatrelvir (NRM), remdesivir (RDV) and the active metabolite of molnupiravir (EIDD-1931) as well the combination of RDV with four licensed mAbs (sotrovimab, bebtelovimab, cilgavimab, tixagevimab; tested only with the susceptible B.1 virus). According to SynergyFinder 3.0 summary and weighted scores, all the combinations had an additive effect. Within DAA/DAA combinations, paired scores with the B.1 and BQ.1.1 variants were comparable. In the post hoc analysis weighting synergy by concentrations, several cases of highly synergistic scores were detected at specific drug concentrations, both for DAA/DAA and for RDV/mAb combinations. This was supported by in vitro confirmation experiments showing a more than a linear shift of a drug-effective concentration (IC50) at increasing concentrations of the companion drug, although the effect was prominent with DAA/DAA combinations and minimal or null with RDV/mAb combinations. These results support the cooperative effects of dual drug combinations in vitro, which should be further investigated in animal models before introduction into the clinic.

SynergyX: a multi-modality mutual attention network for interpretable drug synergy prediction.

Discovering effective anti-tumor drug combinations is crucial for advancing cancer therapy. Taking full account of intricate biological interactions is highly important in accurately predicting drug synergy. However, the extremely limited prior knowledge poses great challenges in developing current computational methods. To address this, we introduce SynergyX, a multi-modality mutual attention network to improve anti-tumor drug synergy prediction. It dynamically captures cross-modal interactions, allowing for the modeling of complex biological networks and drug interactions. A convolution-augmented attention structure is adopted to integrate multi-omic data in this framework effectively. Compared with other state-of-the-art models, SynergyX demonstrates superior predictive accuracy in both the General Test and Blind Test and cross-dataset validation. By exhaustively screening combinations of approved drugs, SynergyX reveals its ability to identify promising drug combination candidates for potential lung cancer treatment. Another notable advantage lies in its multidimensional interpretability. Taking Sorafenib and Vorinostat as an example, SynergyX serves as a powerful tool for uncovering drug-gene interactions and deciphering cell selectivity mechanisms. In summary, SynergyX provides an illuminating and interpretable framework, poised to catalyze the expedition of drug synergy discovery and deepen our comprehension of rational combination therapy.

Augmented drug combination dataset to improve the performance of machine learning models predicting synergistic anticancer effects

Combination therapy has gained popularity in cancer treatment as it enhances the treatment efficacy and overcomes drug resistance. Although machine learning (ML) techniques have become an indispensable tool for discovering new drug combinations, the data on drug combination therapy currently available may be insufficient to build high-precision models. We developed a data augmentation protocol to unbiasedly scale up the existing anti-cancer drug synergy dataset. Using a new drug similarity metric, we augmented the synergy data by substituting a compound in a drug combination instance with another molecule that exhibits highly similar pharmacological effects. Using this protocol, we were able to upscale the AZ-DREAM Challenges dataset from 8798 to 6,016,697 drug combinations. Comprehensive performance evaluations show that ML models trained on the augmented data consistently achieve higher accuracy than those trained solely on the original dataset. Our data augmentation protocol provides a systematic and unbiased approach to generating more diverse and larger-scale drug combination datasets, enabling the development of more precise and effective ML models. The protocol presented in this study could serve as a foundation for future research aimed at discovering novel and effective drug combinations for cancer treatment.

Optimizing drug combination and mechanism analysis based on risk pathway crosstalk in pan cancer

Combination therapy can greatly improve the efficacy of cancer treatment, so identifying the most effective drug combination and interaction can accelerate the development of combination therapy. Here we developed a computational network biological approach to identify the effective drug which inhibition risk pathway crosstalk of cancer, and then filtrated and optimized the drug combination for cancer treatment. We integrated high-throughput data concerning pan-cancer and drugs to construct miRNA-mediated crosstalk networks among cancer pathways and further construct networks for therapeutic drug. Screening by drug combination method, we obtained 687 optimized drug combinations of 83 first-line anticancer drugs in pan-cancer. Next, we analyzed drug combination mechanism, and confirmed that the targets of cancer-specific crosstalk network in drug combination were closely related to cancer prognosis by survival analysis. Finally, we save all the results to a webpage for query (http://bio-bigdata.hrbmu.edu.cn/oDrugCP/). In conclusion, our study provided an effective method for screening precise drug combinations for various cancer treatments, which may have important scientific significance and clinical application value for tumor treatment.

Inhibitory effect of galantamine and donepezil combination against cholinesterase: An in silico and in vitro study.

This study aimed to evaluate the in silico and in vitro inhibitory effect of the combined use of galantamine (GAL) and donepezil (DON) against acetylcholinesterase and butyrylcholinesterase (BuChE) enzymes. In silico and in vitro cholinesterase analysis were carried out for GAL and DON alone and combined. Molecular modeling studies were carried out (docking analysis, molecular dynamics simulation, and quantum theory of atoms in molecules). Cholinesterase's inhibitory activities by modified Ellman's method and the drug combination effect using the Chou-Talalay method were assayed. GAL/DON combination showed the co-occupancy of the ligands in both enzymes through in silico studies. Regarding in vitro BuChE inhibition analyses, three of five combinations showed an interaction between GAL and DON at the threshold of additive affect (0.9 < CI < 1.1), with a tendency toward a synergistic effect for higher concentrations. This is the first report showing the efficacy of the GAL/DON combinations inhibiting BuChE, showing the importance of analyzing the behavior of different ligands when co-occupancy into the active site is possible. These combinations might be a possible therapy to improved efficacy, reduced doses, minor side effects, and high levels of the neurotransmitter in the synaptic space for Alzheimer's disease.

Fetal drug exposure after maternally administered CFTR modulators Elexacaftor/Tezacaftor/Ivacaftor in a rat model

BackgroundThe potential effects of the very effective cystic fibrosis triple combination drug, Elexacaftor/Tezacaftor/Ivacaftor (ETI) in pregnancy on prenatal development of offspring remain largely unknown. Research questionWe aimed to investigate the fetal tissue distribution pattern of maternally administered ETI by placental transfer in the rat fetuses. Study design and methodsSprague Dawley pregnant rats were administered ETI (6.7 mg/kg/d elexacaftor + 3.5 mg/kg/d tezacaftor + 25 mg/kg/d ivacaftor) traced with [3 H]-ivacaftor in single dose acute experiments (intraperitoneal injection) or treated orally with ETI (the same dose) for 7 days in sub-chronic experiments. Fetal tissue samples were collected at embryonic day (E) 19 and analyzed using liquid scintillation counting for acute experiments or liquid chromatography-mass spectrometry for sub-chronic experiments. ResultsOn day E19, after acute exposure, the entry of ivacaftor into fetal brain (brain/plasma concentration ratios <50%) was significantly lower than to other tissues (>100%). However, after sub-chronic exposure, the entry of all 3 components into the developing brain was comparably extensive as into other tissues (tissue/plasma ratios, 260 – 1000%). Each component of ETI accumulated in different fetal tissues to approximately equal extent. Inter-litter differences on fetal drug distribution were found in cortex for ivacaftor, muscle for tezacaftor and cortex and mid/hindbrain for elexacaftor. Fetal plasma concentrations of ETI (ng/mL) were variable between litters. The entry of ivacaftor and tezacaftor into adult brain appeared to be restricted (<100%). InterpretationFetal rats are exposed to maternally ingested ETI after sub-chronic exposure, potentially impacting fetal development. The brain entry data highlights the need for attention be paid to any long-term potential effects ETI exposure could have on normal brain development.

Romidepsin and Afatinib Abrogate Jak–Signal Transducer and Activator of Transcription Signaling and Elicit Synergistic Antitumor Effects in Cutaneous T-Cell Lymphoma

Cutaneous T-cell lymphomas (CTCL) are mature lymphoid neoplasias resulting from the malignant transformation of skin-resident T cells. A distinctive clinical feature of CTCL is their sensitivity to treatment with histone deacetylase (HDAC) inhibitors. However, responses to HDAC inhibitor therapy are universally transient and non-curative, highlighting the need for effective and durable drug combinations. Here we demonstrate that the combination of romidepsin, a selective class I HDAC inhibitor, with afatinib, an epidermal growth factor receptor (EGFR) family inhibitor, induces strongly synergistic antitumor effects in CTCL models in vitro and in vivo via abrogation of JAK-STAT signalling. These results support a previously unrecognized potential role for HDAC inhibitor plus afatinib combination in the treatment of CTCL.

Ex vivo platform en route to functional precision medicine: clinical relevance in gynecological cancers.

A scientific interrogation-driven approach to the clinical management of cancer patients is based on molecular profiling of the tumor. Empowered by the knowledge of oncogenic drivers and biomarkers, oncologists chart an optimal treatment path toward increasing the mathematical probability of a positive outcome. In this entire chain of events, an experimental proof of logical interrogation has never been incorporated before. Here, we provide the first evidence that the result of ex vivo testing of a drug matched to the genomic profiling of an N-of-1 tumor can deliver meaningful insight connecting scientific interrogation and a clinical event. Using resected tissues from endometrial (EC) and ovarian (OC) cancer patients, we designed a personalized ex vivo platform to test combinations of drugs in the default histological architecture of the individual tumors. Following the CART-T cells' principle, we co-cultured with autologous T-cells to test targeted drugs and immune checkpoint inhibitors. The study was designed with a limited clinical information window from patient registration/consent to obtaining the tumor tissues, and adjuvant treatment/post-surgery event (PSE) data were accessed retrospectively. Using a checkerboard analysis, we found that PSE-free survival time was longer in patients whose therapy "matched" the effective drug combination in ex vivo culture/co-cultures compared to those with no effect. Specifically, out of 32 EC patients in the "test & treatment-matched" category whose tumor cells failed to respond to ex vivo drug testing, none achieved > 4 and > 3 years of PSE-free survival. In contrast, out of 38 EC patients in the "test & treatment-matched" category, 4 and 6 patients, whose tumor cells responded to drugs in ex vivo culture, achieved > 4 and > 3 years of PSE-free survival, respectively. Cases with genomically-guided ex vivo testing showed that a "match" between an effective ex vivo drug combination and therapy resulted in late PSE, whereas a "match" between prescribed treatment and an ineffective drug combination in ex vivo testing led to early PSE. Our study demonstrates that integrating genomic data with personalized drug testing on an ex vivo culture/co-culture platform is an effective tool for modeling functional precision medicine in gynecological cancers. This approach bridges the gap between next-generation drug testing in translational research and patient care, providing insight for improved treatment outcomes.

Trifluridine for treatment of mpox infection in drug combinations in ophthalmic cell models.

The Mpox virus can cause severe disease in the susceptible population with dermatologic and systemic manifestations. Furthermore, ophthalmic manifestations of mpox infection are well documented. Topical trifluridine (TFT) eye drops have been used for therapy of ophthalmic mpox infection in patients, however, its efficacy against mpox virus infection in this scenario has not been previously shown. In the present study, we have established ophthalmic cell models suitable for the infection with mpox virus. We show, that TFT is effective against a broad range of mpox isolates in conjunctival epithelial cells and keratocytes. Further, TFT remained effective against a tecovirimat-resistant virus strain. In the context of drug combinations, a nearly additive effect was observed for TFT combinations with brincidofovir and tecovirimat in conjunctival epithelial cells, while a slight antagonism was observed for both combinations in keratocytes. Altogether, our findings demonstrate TFT as a promising drug for treatment of ophthalmic mpox infection able to overcome tecovirimat resistance. However, conflicting results regarding the effect of drug combinations with approved compounds warrant close monitoring of such use in patients.

"I Would Rather Die Drinking than take the Medicine": Role of Alcohol Use Disorder in Loss-to-follow-up of Tuberculosis Treatment in a Rural Area of Ballabgarh, Haryana.

Alcohol use disorder (AUD) is a significant risk factor for tuberculosis (TB) treatment loss-to-follow-up (LTFU). This field-based study was undertaken to understand the role of AUD and TB treatment LTFU and the reasons behind this association in a rural area of Ballabgarh, Haryana. TB patients who had completed their treatment and who had been LTFU were included in the study, along with the National TB Elimination Program (NTEP) staff, healthcare providers, family, and community members from Ballabgarh block of the north Indian state of Haryana. In-depth interviews (IDIs) and focused group discussions (FGDs) were conducted to gauge the perceptions of stakeholders regarding reasons for LTFU, especially in the context of alcohol use. Inductive analysis of the transcripts was done in keeping with the grounded theory, and themes with their sub-themes were identified. A conceptual framework of TB-AUD was constructed, and potential areas for intervention were determined. Fifty-eight IDIs and four FGDs were conducted in mid-2018. Almost all key informants and many patient participants believed that alcohol use makes TB patients highly susceptible to treatment LTFU. Key themes identified were shared personality traits and attitudes, combined side effects of anti-tubercular drugs and alcohol use, lack of family support, and an adverse financial situation. These findings call for a change in NTEP's approach to AUD-TB. Interventions may include collecting alcohol use information at patient enrolment and closure, integrating brief interventions for alcohol cessation in NTEP, and linking patients to deaddiction centers with the provision of appropriate dietary and financial support.

Deep Drug Synergy Prediction Network Using Modified Triangular Mutation-Based Differential Evolution.

Drug combination therapy is crucial in cancer treatment, but accurately predicting drug synergy remains a challenge due to the complexity of drug combinations. Machine learning and deep learning models have shown promise in drug combination prediction, but they suffer from issues such as gradient vanishing, overfitting, and parameter tuning. To address these problems, the deep drug synergy prediction network, named as EDNet is proposed that leverages a modified triangular mutation-based differential evolution algorithm. This algorithm evolves the initial connection weights and architecture-related attributes of the deep bidirectional mixture density network, improving its performance and addressing the aforementioned issues. EDNet automatically extracts relevant features and provides conditional probability distributions of output attributes. The performance of EDNet is evaluated over two well-known drug synergy datasets, NCI-ALMANAC and deep-synergy. The results demonstrate that EDNet outperforms the competing models. EDNet facilitates efficient drug interactions, enhancing the overall effectiveness of drug combinations for improved cancer treatment outcomes.