Drug-target Interaction Networks Research Articles

Multi-layer graph attention neural networks for accurate drug-target interaction mapping

In the crucial process of drug discovery and repurposing, precise prediction of drug-target interactions (DTIs) is paramount. This study introduces a novel DTI prediction approach—Multi-Layer Graph Attention Neural Network (MLGANN), through a groundbreaking computational framework that effectively harnesses multi-source information to enhance prediction accuracy. MLGANN not only strides forward in constructing a multi-layer DTI network by capturing both direct interactions between drugs and targets as well as their multi-level information but also amalgamates Graph Convolutional Networks (GCN) with a self-attention mechanism to comprehensively integrate diverse data sources. This method exhibited significant performance surpassing existing approaches in comparative experiments, underscoring its immense potential in elevating the efficiency and accuracy of DTI predictions. More importantly, this study accentuates the significance of considering multi-source data information and network heterogeneity in the drug discovery process, offering new perspectives and tools for future pharmaceutical research.

AIGO-DTI: Predicting Drug-Target Interactions Based on Improved Drug Properties Combined with Adaptive Iterative Algorithms.

Artificial intelligence-based methods for predicting drug-target interactions (DTIs) aim to explore reliable drug candidate targets rapidly and cost-effectively to accelerate the drug development process. However, current methods are often limited by the topological regularities of drug molecules, making them difficult to generalize to a broader chemical space. Additionally, the use of similarity to measure DTI network links often introduces noise, leading to false DTI relationships and affecting the prediction accuracy. To address these issues, this study proposes an Adaptive Iterative Graph Optimization (AIGO)-DTI prediction framework. This framework integrates atomic cluster information and enhances molecular features through the design of functional group prompts and graph encoders, optimizing the construction of DTI association networks. Furthermore, the optimization of graph structure is transformed into a node similarity learning problem, utilizing multihead similarity metric functions to iteratively update the network structure to improve the quality of DTI information. Experimental results demonstrate the outstanding performance of AIGO-DTI on multiple public data sets and label reversal data sets. Case studies, molecular docking, and existing research validate its effectiveness and reliability. Overall, the method proposed in this study can construct comprehensive and reliable DTI association network information, providing new graphing and optimization strategies for DTI prediction, which contribute to efficient drug development and reduce target discovery costs.

BindingSiteDTI: differential-scale binding site modelling for drug-target interaction prediction.

Enhanced by contemporary computational advances, the prediction of drug-target interactions (DTIs) has become crucial in developing de novo and effective drugs. Existing deep learning approaches to DTI prediction are frequently beleaguered by a tendency to overfit specific molecular representations, which significantly impedes their predictive reliability and utility in novel drug discovery contexts. Furthermore, existing DTI networks often disregard the molecular size variance between macro molecules (targets) and micro molecules (drugs) by treating them at an equivalent scale that undermines the accurate elucidation of their interaction. We propose a novel DTI network with a differential-scale scheme to model the binding site for enhancing DTI prediction, which is named as BindingSiteDTI. It explicitly extracts multiscale substructures from targets with different scales of molecular size and fixed-scale substructures from drugs, facilitating the identification of structurally similar substructural tokens, and models the concealed relationships at the substructural level to construct interaction feature. Experiments conducted on popular benchmarks, including DUD-E, human, and BindingDB, shown that BindingSiteDTI contains significant improvements compared with recent DTI prediction methods. The source code of BindingSiteDTI can be accessed at https://github.com/MagicPF/BindingSiteDTI.

Network-based drug repurposing identifies small molecule drugs as immune checkpoint inhibitors for endometrial cancer.

Endometrial cancer (EC) is the 6th most common cancer in women around the world. Alone in the United States (US), 66,200 new cases and 13,030 deaths are expected to occur in 2023 which needs the rapid development of potential therapies against EC. Here, a network-based drug-repurposing strategy is developed which led to the identification of 16 FDA-approved drugs potentially repurposable for EC as potential immune checkpoint inhibitors (ICIs). A network of EC-associated immune checkpoint proteins (ICPs)-induced protein interactions (P-ICP) was constructed. As a result of network analysis of P-ICP, top key target genes closely interacting with ICPs were shortlisted followed by network proximity analysis in drug-target interaction (DTI) network and pathway cross-examination which identified 115 distinct pathways of approved drugs as potential immune checkpoint inhibitors. The presented approach predicted 16 drugs to target EC-associated ICPs-induced pathways, three of which have already been used for EC and six of them possess immunomodulatory properties providing evidence of the validity of the strategy. Classification of the predicted pathways indicated that 15 drugs can be divided into two distinct pathway groups, containing 17 immune pathways and 98 metabolic pathways. In addition, drug-drug correlation analysis provided insight into finding useful drug combinations. This fair and verified analysis creates new opportunities for the quick repurposing of FDA-approved medications in clinical trials.

Machine learning study of the extended drug-target interaction network informed by pain related voltage-gated sodium channels.

Pain is a significant global health issue, and the current treatment options for pain management have limitations in terms of effectiveness, side effects, and potential for addiction. There is a pressing need for improved pain treatments and the development of new drugs. Voltage-gated sodium channels, particularly Nav1.3, Nav1.7, Nav1.8, and Nav1.9, play a crucial role in neuronal excitability and are predominantly expressed in the peripheral nervous system. Targeting these channels may provide a means to treat pain while minimizing central and cardiac adverse effects. In this study, we construct protein-protein interaction (PPI) networks based on pain-related sodium channels and develop a corresponding drug-target interaction network to identify potential lead compounds for pain management. To ensure reliable machine learning predictions, we carefully select 111 inhibitor data sets from a pool of more than 1000 targets in the PPI network. We employ 3 distinct machine learning algorithms combined with advanced natural language processing (NLP)-based embeddings, specifically pretrained transformer and autoencoder representations. Through a systematic screening process, we evaluate the side effects and repurposing potential of more than 150,000 drug candidates targeting Nav1.7 and Nav1.8 sodium channels. In addition, we assess the ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties of these candidates to identify leads with near-optimal characteristics. Our strategy provides an innovative platform for the pharmacological development of pain treatments, offering the potential for improved efficacy and reduced side effects.

MOKPE: drug–target interaction prediction via manifold optimization based kernel preserving embedding

BackgroundIn many applications of bioinformatics, data stem from distinct heterogeneous sources. One of the well-known examples is the identification of drug–target interactions (DTIs), which is of significant importance in drug discovery. In this paper, we propose a novel framework, manifold optimization based kernel preserving embedding (MOKPE), to efficiently solve the problem of modeling heterogeneous data. Our model projects heterogeneous drug and target data into a unified embedding space by preserving drug–target interactions and drug–drug, target–target similarities simultaneously.ResultsWe performed ten replications of ten-fold cross validation on four different drug–target interaction network data sets for predicting DTIs for previously unseen drugs. The classification evaluation metrics showed better or comparable performance compared to previous similarity-based state-of-the-art methods. We also evaluated MOKPE on predicting unknown DTIs of a given network. Our implementation of the proposed algorithm in R together with the scripts that replicate the reported experiments is publicly available at https://github.com/ocbinatli/mokpe.

Investigation of Anti-Alzheimer’s Mechanisms of Sarsasapogenin Derivatives by Network-Based Combining Structure-Based Methods

Alzheimer's disease (AD), a neurodegenerative disease with no cure, affects millions of people worldwide and has become one of the biggest healthcare challenges. Some investigated compounds play anti-AD roles at the cellular or the animal level, but their molecular mechanisms remain unclear. In this study, we designed a strategy combining network-based and structure-based methods together to identify targets for anti-AD sarsasapogenin derivatives (AAs). First, we collected drug-target interactions (DTIs) data from public databases, constructed a global DTI network, and generated drug-substructure associations. After network construction, network-based models were built for DTI prediction. The best bSDTNBI-FCFP_4 model was further used to predict DTIs for AAs. Second, a structure-based molecular docking method was employed for rescreening the prediction results to obtain more credible target proteins. Finally, in vitro experiments were conducted for validation of the predicted targets, and Nrf2 showed significant evidence as the target of anti-AD compound AA13. Moreover, we analyzed the potential mechanisms of AA13 for the treatment of AD. Generally, our combined strategy could be applied to other novel drugs or compounds and become a useful tool in identification of new targets and elucidation of disease mechanisms. Our model was deployed on our NetInfer web server (http://lmmd.ecust.edu.cn/netinfer/).

Network-based drug repurposing for HPV-associated cervical cancer

In women, cervical cancer (CC) is the fourth most common cancer around the world with average cases of 604,000 and 342,000 deaths per year. Approximately 50% of high-grade CC are attributed to human papillomavirus (HPV) types 16 and 18. Chances of CC in HPV-positive patients are 6 times more than HPV-negative patients which demands timely and effective treatment. Repurposing of drugs is considered a viable approach to drug discovery which makes use of existing drugs, thus potentially reducing the time and costs associated with de-novo drug discovery. In this study, we present an integrative drug repurposing framework based on a systems biology-enabled network medicine platform. First, we built an HPV-induced CC protein interaction network named HPV2C following the CC signatures defined by the omics dataset, obtained from GEO database. Second, the drug target interaction (DTI) data obtained from DrugBank, and related databases was used to model the DTI network followed by drug target network proximity analysis of HPV-host associated key targets and DTIs in the human protein interactome. This analysis identified 142 potential anti-HPV repurposable drugs to target HPV induced CC pathways. Third, as per the literature survey 51 of the predicted drugs are already used for CC and 33 of the remaining drugs have anti-viral activity. Gene set enrichment analysis of potential drugs in drug-gene signatures and in HPV-induced CC-specific transcriptomic data in human cell lines additionally validated the predictions. Finally, 13 drug combinations were found using a network based on overlapping exposure. To summarize, the study provides effective network-based technique to quickly identify suitable repurposable drugs and drug combinations that target HPV-associated CC.

Predicting Drug-Target Interactions Over Heterogeneous Information Network.

Identifying Drug-Target Interactions (DTIs) is a critical step in studying pathogenesis and drug development. Due to the fact that conventional experimental methods usually suffer from high costs and low efficiency, various computational methods have been proposed to detect potential DTIs by extracting features from the biological information of drugs and their target proteins. Though effective, most of them fall short of considering the topological structure of the DTI network, which provides a global view to discover novel DTIs. In this paper, a network-based computational method, namely LG-DTI, is proposed to accurately predict DTIs over a heterogeneous information network. For drugs and target proteins, LG-DTI first learns not only their local representations from drug molecular structures and protein sequences, but also their global representations by using a semi-supervised heterogeneous network embedding method. These two kinds of representations consist of the final representations of drugs and target proteins, which are then incorporated into a Random Forest classifier to complete the task of DTI prediction. The performance of LG-DTI has been evaluated on two independent datasets and also compared with several state-of-the-art methods. Experimental results show the superior performance of LG-DTI. Moreover, our case study indicates that LG-DTI can be a valuable tool for identifying novel DTIs.

The curse and blessing of abundance-the evolution of drug interaction databases and their impact on drug network analysis.

Widespread bioinformatics applications such as drug repositioning or drug-drug interaction prediction rely on the recent advances in machine learning, complex network science, and comprehensive drug datasets comprising the latest research results in molecular biology, biochemistry, or pharmacology. The problem is that there is much uncertainty in these drug datasets-we know the drug-drug or drug-target interactions reported in the research papers, but we cannot know if the not reported interactions are absent or yet to be discovered. This uncertainty hampers the accuracy of such bioinformatics applications. We use complex network statistics tools and simulations of randomly inserted previously unaccounted interactions in drug-drug and drug-target interaction networks-built with data from DrugBank versions released over the plast decade-to investigate whether the abundance of new research data (included in the latest dataset versions) mitigates the uncertainty issue. Our results show that the drug-drug interaction networks built with the latest dataset versions become very dense and, therefore, almost impossible to analyze with conventional complex network methods. On the other hand, for the latest drug database versions, drug-target networks still include much uncertainty; however, the robustness of complex network analysis methods slightly improves. Our big data analysis results pinpoint future research directions to improve the quality and practicality of drug databases for bioinformatics applications: benchmarking for drug-target interaction prediction and drug-drug interaction severity standardization.

A novel method for drug-target interaction prediction based on graph transformers model

BackgroundDrug-target interactions (DTIs) prediction becomes more and more important for accelerating drug research and drug repositioning. Drug-target interaction network is a typical model for DTIs prediction. As many different types of relationships exist between drug and target, drug-target interaction network can be used for modeling drug-target interaction relationship. Recent works on drug-target interaction network are mostly concentrate on drug node or target node and neglecting the relationships between drug-target.ResultsWe propose a novel prediction method for modeling the relationship between drug and target independently. Firstly, we use different level relationships of drugs and targets to construct feature of drug-target interaction. Then, we use line graph to model drug-target interaction. After that, we introduce graph transformer network to predict drug-target interaction.ConclusionsThis method introduces a line graph to model the relationship between drug and target. After transforming drug-target interactions from links to nodes, a graph transformer network is used to accomplish the task of predicting drug-target interactions.

β-Carboline dimers inhibit the tumor proliferation by the cell cycle arrest of sarcoma through intercalating to Cyclin-A2.

β-Carbolines are potentially strong alkaloids with a wide range of bioactivities, and their dimers exhibit stronger antitumor activity other than the monomers. However, the detailed mechanisms of the β-carboline dimers in inhibiting sarcoma (SARC) remain unclear. The results showed that β-carboline-3-carboxylic acid dimers Comp1 and Comp2, which were synthesized in our lab and modified at the N9 position and linked at the C3 position, exhibited effective inhibition activity on MG-63 proliferation (IC50 = 4.6μM). Meanwhile, the large scale transcriptome profiles of SARC from The Cancer Genome Atlas (TCGA) were analyzed, and found that abnormal expression of genes relevant to apoptosis, cell cycle, and signaling pathways of Hedgehog, HIF, Ras involved in the SARC pathogenesis. Interestingly, both dimers could promote the apoptosis and arrest the cell cycle in S phase to inhibit proliferation of MG-63. Moreover, Comp1 and Comp2 inhibited the expression CDK2, CCNA2, DBF4, and PLK1 associated with various immune cells and cell cycle in MG-63. Remarkably, drug-target interaction network analysis showed that numerous proteins involved in cell cycle were the potential targets of Comp1 and Comp2, especially CCNA2. Further molecular docking, isothermal titration calorimetry (ITC) and Cellular Thermal Shift Assay (CETSA) confirmed that both dimers could directly interact with CCNA2, which is significantly correlated with CD4+ T cells, by strong hydrophobic interactions (Kd=5.821 ×106 N). Meanwhile, the levels of CCNA2 and CDK2 were inhibited to decrease in MG-63 by both dimer treatments at transcription and protein levels, implying that Comp1 and Comp2 blocked the interaction between CCNA2 and CDK2 through competitive binding with CCNA2 to arrest the cell cycle of MG-63 cells in the S phase. Additionally, the transcriptome profiles of β-carboline-treated mice from Gene Expression Omnibus (GEO) were obtained, and found that similar antitumor mechanism was shared among β-carboline derivatives. Overall, our results elucidated the antitumor mechanisms of Comp1 and Comp2 through dual-suppressing the function of CCNA2 to profoundly arrest cell cycle of MG-63, then effectively inhibited cell proliferation of MG-63. These results provide new insights into the antitumor mechanism of β-carboline dimers and new routes of various novel cancer-related drug targets for future possible cancer therapy.

Meta-analysis of active tuberculosis gene expression ascertains host directed drug targets.

Multi-drug resistant tuberculosis still remains a major public health crisis globally. With the emergence of newer active tuberculosis disease, the requirement of prolonged treatment time and adherence to therapy till its completion necessitates the search of newer therapeutics, targeting human host factors. The current work utilized statistical meta-analysis of human gene transcriptomes of active pulmonary tuberculosis disease obtained from six public datasets. The meta-analysis resulted in the identification of 2038 significantly differentially expressed genes (DEGs) in the active tuberculosis disease. The gene ontology (GO) analysis revealed that these genes were major contributors in immune responses. The pathway enrichment analyses identified from various human canonical pathways are related to other infectious diseases. In addition, the comparison of the DEGs with the tuberculosis genome wide association study (GWAS) datasets revealed the presence of few genetic variants in their proximity. The analysis of protein interaction networks (human and Mycobacterium tuberculosis) and host directed drug-target interaction network led to new candidate drug targets for drug repurposing studies. The current work sheds light on host genes and pathways enriched in active tuberculosis disease and suggest potential drug repurposing targets for host-directed therapies.

Identification of the Mechanism of Matrine Combined with Glycyrrhizin for Hepatocellular Carcinoma Treatment through Network Pharmacology and Bioinformatics Analysis.

Matrine and glycyrrhizin are representative active ingredients of traditional Chinese medicine (TCM) used in clinical practice. Studies have demonstrated that matrine has antitumor pharmacological effects and that glycyrrhizin protects liver function. However, the potential bioactive compounds and mechanisms remain unknown, as well as whether they have synergistic effects in killing cancer cells and protecting liver cells. To investigate the synergistic effects and mechanism of matrine combined with glycyrrhizin in hepatocellular carcinoma (HCC) treatment, we used both network pharmacology and bioinformatics analyses. First, the chemical gene interaction information of matrine and glycyrrhizin was obtained from the PubChem database. The pathogenic genes of HCC were accessed from five public databases. The RNA sequencing data and clinical information of HCC patients were downloaded from The Cancer Genome Atlas (TCGA). Next, the overlapping genes among the potential targets of matrine and glycyrrhizin and HCC-related targets were determined using bioinformatics analysis. We constructed the drug-target interaction network. Prognosis-associated genes were acquired through the univariate Cox regression model and Lasso-Cox regression model. The results were verified by the International Cancer Genome Consortium (ICGC) database. Finally, we predicted the immune function of the samples. The drug-target interaction network consisted of 10 matrine and glycyrrhizin targets. We selected a Lasso-Cox regression model consisting of 3 differentially expressed genes (DEGs) to predict the efficacy of the combination in HCC. Subsequently, we successfully predicted the overall survival of HCC patients using the constructed prognostic model and investigated the correlation of the immune response. Matrine and glycyrrhizin have synergistic effects on HCC. The model we obtained consisted of three drug-target genes by Lasso-Cox regression analysis. The model independently predicted the combined effect of matrine and glycyrrhizin in HCC treatment and OS, which will be helpful for guiding clinical treatment. The prognostic model was correlated with the immune cells and immune checkpoints of patients, which had an adjuvant effect on HCC immunotherapy. Matrine and glycyrrhizin can have therapeutic effects on HCC by promoting the production or enhancing the core gene activity in the drug network and improving the immune system function of patients.

Network-based Drug Repurposing: A Critical Review.

New drug development for a disease is a tedious, time-consuming, complex, and expensive process. Even if it is done, the chances for success of newly developed drugs are still very low. Modern reports state that repurposing the pre-existing drugs will have more efficient functioning than newly developed drugs. This repurposing process will save time, reduce expenses and provide more success rate. The only limitation for this repurposing is getting a desired pharmacological and characteristic parameter of various drugs from vast data about medications, their effects, and target mechanisms. This drawback can be avoided by introducing computational methods of analysis. This includes various network analysis types that use various biological processes and relationships with various drugs to simplify data interpretation. Some of the data sets now available in standard, and simplified forms include gene expression, drug-target interactions, protein networks, electronic health records, clinical trial results, and drug adverse event reports. Integrating various data sets and interpretation methods allows a more efficient and easy way to repurpose an exact drug for the desired target and effect. In this review, we are going to discuss briefly various computational biological network analysis methods like gene regulatory networks, metabolic networks, protein-protein interaction networks, drug-target interaction networks, drugdisease association networks, drug-drug interaction networks, drug-side effects networks, integrated network-based methods, semantic link networks, and isoform-isoform networks. Along with this, we briefly discussed the drug's limitations, prediction methodologies, and data sets utilised in various biological networks for drug repurposing.

Integrated multi-similarity fusion and heterogeneous graph inference for drug-target interaction prediction

Drug-target interaction (DTI) prediction performs a crucial part in drug discovery and design. Although many computational approaches for such prediction have been proposed, current researches still generally adopt chemical similarities of drugs or the sequence similarities of targets. However, the valuable information of known interactions has not been noticed, and the existing noise and useless information reduce the accuracy of DTI prediction. In addition, many existing computational approaches ignore the behavior information between nodes of the DTI network. In this paper, we develop an ensemble computational approach called integrated multi-similarity fusion and heterogeneous graph inference. First, based on the known DTI network, the degree distribution of drug and target similarities are analyzed and the noise and useless information are removed to improve prediction accuracy. Second, based on drug and target similarities and known DTIs, a strategy of multi-similarity fusion is proposed to capture potential useful information from known interactions that is used for enhancing drug and target similarities. Third, the heterogeneous graph inference is used to predict the DTIs to capture the edge weight (closeness) and behavior information (diffusion) between nodes of a heterogeneous network. To assist the reproducibility of our work and its comparison to published results, we perform experiments on four benchmark datasets. Results show that our approach outperforms some existing approaches and can contribute to predicting potential DTIs.

Celastrol Alleviates Autoimmune Hepatitis Through the PI3K/AKT Signaling Pathway Based on Network Pharmacology and Experiments.

Objective: This work aims to explore the potential targets and underlying therapeutic mechanisms of celastrol in autoimmune hepatitis (AIH) through network pharmacology and experiments on Laboratory Animals. Methods: A drug-target interaction network was constructed to predict the possible targets of celastrol and their potential relationship with the drug; docking studies were also performed for validation. This study used both acute and chronic rodent models of autoimmune hepatitis. Gross appearance of liver and spleen were obtained from murine models, hematoxylin-eosin staining and Sirius red staining were performed to examine hepatic inflammation and fibrosis respectively. By combining molecular docking and enrichment analysis results, the most prominent signaling pathway was selected and further confirmed by Western blot in AIH models administered with celastrol. Results: In total, 82 common targets of celastrol and AIH were obtained from databases, identified by network pharmacology, and adequately enriched. Among them, PIK3R1, SRC, MAPK1, AKT1, and HRAS were selected as the top 5 closely related targets to celastrol. They all performed effectively in molecular docking, with AKT1 and PIK3R1 exhibiting more-prominent binding energy. Subsequently, celastrol administration significantly ameliorated hepatitis and liver fibrosis by reducing AKT1 and PI3K phosphorylation in both acute liver injury and chronic models of autoimmune hepatitis. Conclusion: In summary, celastrol significantly attenuates autoimmune hepatitis by suppressing the PI3K/AKT signaling pathway, confirmed by validated animal models. These findings may help identify the mechanism involved in the anti-inflammatory action of celastrol in autoimmune hepatitis and provide ideas for future comprehensive studies.

Comprehensive Network Analysis Identified SIRT7, NTRK2, and CHI3L1 as New Potential Markers for Intervertebral Disc Degeneration.

Intervertebral disc degeneration (IDD) is considered the basis of serious clinical symptoms, especially for low back pain (LBP). Therefore, it is essential to explore the regulatory role and diagnostic performance of dysregulated genes and potential drugs in IDD. Through WGCNA co-expression analysis, 36 co-expression modules were obtained. Among them, MidnightBlue and Red modules were the most related to IDD. Functional enrichment analysis showed that the Red module was mainly related to neutrophil activation and regulation of cytokine-mediated signaling pathway and apoptosis, whereas the MidnightBlue module was mainly related to extracellular matrix organization, bone development, extracellular matrix, extracellular matrix component, and other extracellular matrices. Furthermore, 356 genes highly related to the module were screened to construct a protein interaction network. Network degree distribution analysis showed that the known IDD-related genes had a higher degree of distribution. Enrichment analysis demonstrated that these genes were enriched in MAPK_SIGNALING_PATHWAY (FDR = 0.012), CHEMOKINE_SIGNALING_PATHWAY, and some other pathways. By constructing a disease-gene interaction network, three disease-specific genes were finally identified. Through combining with the drug-target gene interaction network, two potential therapeutic drugs, entrectinib and larotrectinib, were determined. Finally, based on these genes, the diagnostic model in the training dataset, test dataset, and verification dataset all showed a high diagnostic performance. The findings of this study contributed to the diagnosis of IDD and personalized treatment of IDD.

Comparative analysis of network-based approaches and machine learning algorithms for predicting drug-target interactions.

Computational prediction of drug-target interactions (DTIs) is of particular importance in the process of drug repositioning because of its efficiency in selecting potential candidates for DTIs. A variety of computational methods for predicting DTIs have been proposed over the past decade. Our interest is which methods or techniques are the most advantageous for increasing prediction accuracy. This article provides a comprehensive overview of network-based, machine learning, and integrated DTI prediction methods. The network-based methods handle a DTI network along with drug and target similarities in a matrix form and apply graph-theoretic algorithms to identify new DTIs. Machine learning methods use known DTIs and the features of drugs and target proteins as training data to build a predictive model. Integrated methods combine these two techniques. We assessed the prediction performance of the selected state-of-the-art methods using two different benchmark datasets. Our experimental results demonstrate that the integrated methods outperform the others in general. Some previous methods showed low accuracy on predicting interactions of unknown drugs which do not exist in the training dataset. Combining similarity matrices from multiple features by data fusion was not beneficial in increasing prediction accuracy. Finally, we analyzed future directions for further improvements in DTI predictions.

A New Prospect for the Treatment of Nephrotic Syndrome Based on Network Pharmacology Analysis.

Network pharmacology is an emerging field which is currently capturing interest in drug discovery and development. Chronic kidney conditions have become a threat globally due to its associated lifelong therapies. Nephrotic syndrome (NS) is a common glomerular disease that is seen in paediatric and adult population with characteristic manifestation of proteinuria, oedema, hypoalbuminemia, and hyperlipidemia. It involves podocyte damage with tubulointerstitial fibrosis and glomerulosclerosis. Till date there has been no specific treatment available for this condition that provides complete remission. Repurposing of drugs can thus be a potential strategy for the treatment of NS. Recently, epigenetic mechanisms were identified that promote progression of many renal diseases. Therefore, in the present study, we investigated two epigenetic drugs valproic acid (VPA) and all-trans retinoic acid (ATRA). Epigenetic drugs act by binging about changes in gene expression without altering the DNA sequence. The changes include DNA methylation or histone modifications. The targets for the two drugs ATRA and VPA were collated from ChEMBL and Binding DB. All the genes associated with NS were collected from DisGeNET and KEGG database. Interacting proteins for the target genes were acquired from STRING database. The genes were then subjected to gene ontology and pathway enrichment analysis using a functional enrichment software tool. A drug-target and drug-potential target-protein interaction network was constructed using the Cytoscape software. Our results revealed that the two drugs VPA and ATRA had 65 common targets that contributed to kidney diseases. Out of which, 25 targets were specifically NS associated. Further, our work exhibited that ATRA and VPA were synergistically involved in pathways of inflammation, renal fibrosis, glomerulosclerosis and possibly mitochondrial biogenesis and endoplasmic reticulum stress. We thus propose a synergistic potential of the two drugs for treating chronic kidney diseases, specifically NS. The outcomes will undoubtedly invigorate further preclinical and clinical explorative studies. We identify network pharmacology as an initial inherent approach in identifying drug candidates for repurposing and synergism.