Current computer-aided drug design最新文献

{"title":"Graph-DTI: A New Model for Drug-target Interaction Prediction Based on Heterogenous Network Graph Embedding.","authors":"Xiaohan Qu, Guoxia Du, Jing Hu, Yongming Cai","doi":"10.2174/1573409919666230713142255","DOIUrl":"10.2174/1573409919666230713142255","url":null,"abstract":"<p><strong>Background: </strong>In this study, we aimed to develop a new end-to-end learning model called Graph-Drug-Target Interaction (DTI), which integrates various types of information in the heterogeneous network data, and to explore automatic learning of the topology-maintaining representations of drugs and targets, thereby effectively contributing to the prediction of DTI. Precise predictions of DTI can guide drug discovery and development. Most machine learning algorithms integrate multiple data sources and combine them with common embedding methods. However, the relationship between the drugs and target proteins is not well reported. Although some existing studies have used heterogeneous network graphs for DTI prediction, there are many limitations in the neighborhood information between the nodes in the heterogeneous network graphs. We studied the drug-drug interaction (DDI) and DTI from DrugBank Version 3.0, protein-protein interaction (PPI) from the human protein reference database Release 9, drug structure similarity from Morgan fingerprints of radius 2 and calculated by RDKit, and protein sequence similarity from Smith-Waterman score.</p><p><strong>Methods: </strong>Our study consists of three major components. First, various drugs and target proteins were integrated, and a heterogeneous network was established based on a series of data sets. Second, the graph neural networks-inspired graph auto-encoding method was used to extract high-order structural information from the heterogeneous networks, thereby revealing the description of nodes (drugs and proteins) and their topological neighbors. Finally, potential DTI prediction was made, and the obtained samples were sent to the classifier for secondary classification.</p><p><strong>Results: </strong>The performance of Graph-DTI and all baseline methods was evaluated using the sums of the area under the precision-recall curve (AUPR) and the area under the receiver operating characteristic curve (AUC). The results indicated that Graph-DTI outperformed the baseline methods in both performance results.</p><p><strong>Conclusion: </strong>Compared with other baseline DTI prediction methods, the results showed that Graph-DTI had better prediction performance. Additionally, in this study, we effectively classified drugs corresponding to different targets and vice versa. The above findings showed that Graph-DTI provided a powerful tool for drug research, development, and repositioning. Graph- DTI can serve as a drug development and repositioning tool more effectively than previous studies that did not use heterogeneous network graph embedding.</p>","PeriodicalId":10886,"journal":{"name":"Current computer-aided drug design","volume":" ","pages":"1013-1024"},"PeriodicalIF":1.5,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9779531","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deciphering the Underlying Mechanisms of Sanleng-Ezhu for the Treatment of Idiopathic Pulmonary Fibrosis Based on Network Pharmacology and Single-cell RNA Sequencing Data.","authors":"Xianqiang Zhou, Fang Tan, Suxian Zhang, Tiansong Zhang","doi":"10.2174/1573409920666230808120504","DOIUrl":"10.2174/1573409920666230808120504","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Aims: &lt;/strong&gt;To decipher the underlying mechanisms of Sanleng-Ezhu for the treatment of idiopathic pulmonary fibrosis based on network pharmacology and single-cell RNA sequencing data.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Idiopathic Pulmonary Fibrosis (IPF) is the most common type of interstitial lung disease. Although the combination of herbs Sanleng (SL) and Ezhu (EZ) has shown reliable efficacy in the management of IPF, its underlying mechanisms remain unknown.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;Based on LC-MS/MS analysis and the Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform (TCMSP) database, we identified the bioactive components of SL-EZ. After obtaining the IPF-related dataset GSE53845 from the Gene Expression Omnibus (GEO) database, we performed the differential expression analysis and the weighted gene co-expression network analysis (WGCNA), respectively. We obtained lowly and highly expressed IPF subtype gene sets by comparing Differentially Expressed Genes (DEGs) with the most significantly negatively and positively related IPF modules in WGCNA. Subsequently, we performed Gene Ontology (GO), and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses on IPF subtype gene sets. The low- and highexpression MCODE subgroup feature genes were identified by the MCODE plug-in and were adopted for Disease Ontology (DO), GO, and KEGG enrichment analyses. Next, we performed the immune cell infiltration analysis of the MCODE subgroup feature genes. Single-cell RNA sequencing analysis demonstrated the cell types which expressed different MCODE subgroup feature genes. Molecular docking and animal experiments validated the effectiveness of SL-EZ in delaying the progression of pulmonary fibrosis.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;We obtained 5 bioactive components of SL-EZ as well as their corresponding 66 candidate targets. After normalizing the samples of the GSE53845 dataset from the GEO database source, we obtained 1907 DEGs of IPF. Next, we performed a WGCNA analysis on the dataset and got 11 modules. Notably, we obtained 2 IPF subgroups by contrasting the most significantly up- and down-regulated modular genes in IPF with DEGs, respectively. The different IPF subgroups were compared with drugcandidate targets to obtain direct targets of action. After constructing the protein interaction networks between IPF subgroup genes and drug candidate targets, we applied the MCODE plug-in to filter the highest-scoring MCODE components. DO, GO, and KEGG enrichment analyses were applied to drug targets, IPF subgroup genes, and MCODE component signature genes. In addition, we downloaded the single-cell dataset GSE157376 from the GEO database. By performing quality control and dimensionality reduction, we clustered the scattered primary sample cells into 11 clusters and annotated them into 2 cell subtypes. Drug sensitivity analysis suggested that SL-EZ acts on different cell subtypes in IPF subgroups. Molecula","PeriodicalId":10886,"journal":{"name":"Current computer-aided drug design","volume":" ","pages":"888-910"},"PeriodicalIF":1.5,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9969800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unearthing Insights into Metabolic Syndrome by Linking Drugs, Targets, and Gene Expressions Using Similarity Measures and Graph Theory.","authors":"Alwaz Zafar, Bilal Wajid, Ans Shabbir, Fahim Gohar Awan, Momina Ahsan, Sarfraz Ahmad, Imran Wajid, Faria Anwar, Fazeelat Mazhar","doi":"10.2174/1573409920666230817101913","DOIUrl":"10.2174/1573409920666230817101913","url":null,"abstract":"<p><strong>Aims and objectives: </strong>Metabolic syndrome (MetS) is a group of metabolic disorders that includes obesity in combination with at least any two of the following conditions, i.e., insulin resistance, high blood pressure, low HDL cholesterol, and high triglycerides level. Treatment of this syndrome is challenging because of the multiple interlinked factors that lead to increased risks of type-2 diabetes and cardiovascular diseases. This study aims to conduct extensive <i>in silico</i> analysis to (i) find central genes that play a pivotal role in MetS and (ii) propose suitable drugs for therapy. Our objective is to first create a drug-disease network and then identify novel genes in the drug-disease network with strong associations to drug targets, which can help in increasing the therapeutical effects of different drugs. In the future, these novel genes can be used to calculate drug synergy and propose new drugs for the effective treatment of MetS.</p><p><strong>Methods: </strong>For this purpose, we (i) investigated associated drugs and pathways for MetS, (ii) employed eight different similarity measures to construct eight gene regulatory networks, (iii) chose an optimal network, where a maximum number of drug targets were central, (iv) determined central genes exhibiting strong associations with these drug targets and associated disease-causing pathways, and lastly (v) employed these candidate genes to propose suitable drugs.</p><p><strong>Results: </strong>Our results indicated (i) a novel drug-disease network complex, with (ii) novel genes associated with MetS.</p><p><strong>Conclusion: </strong>Our developed drug-disease network complex closely represents MetS with associated novel findings and markers for an improved understanding of the disease and suggested therapy.</p>","PeriodicalId":10886,"journal":{"name":"Current computer-aided drug design","volume":" ","pages":"773-783"},"PeriodicalIF":1.5,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10024102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Docking, Synthesis, and I<i>n vitro</i> Anti-depressant Activity of Certain Isatin Derivatives.","authors":"Thulasingam Muthukumaran, K Asok Kumar, M Saleshier Francis","doi":"10.2174/1573409919666230523114134","DOIUrl":"10.2174/1573409919666230523114134","url":null,"abstract":"<p><strong>Background: </strong><i>In vitro</i>, the molecular docking method has been suggested for estimating the biological affinity of the pharmacophores with physiologically active compounds. It is the latter stage in molecular docking, and the docking scores are examined using the AutoDock 4.2 tool program. The chosen compounds can be evaluated for <i>in vitro</i> activity based on the binding scores, and the IC₅₀ values can be computed.</p><p><strong>Objective: </strong>The purpose of this work was to create methyl isatin compounds as potential antidepressants, compute physicochemical characteristics, and carry out docking analysis.</p><p><strong>Methods: </strong>The protein data bank of the RCSB (Research Collaboratory for Structural Bioinformatics) was used to download the PDB structures of monoamine oxidase (PDB ID: 2BXR) and indoleamine 2,3-dioxygenase (PDB ID: 6E35). Based on the literature, methyl isatin derivatives were chosen as the lead chemicals. By determining their IC₅₀ values, the chosen compounds were tested for <i>in vitro</i> anti-depressant activity.</p><p><strong>Results: </strong>The binding scores for the interactions of SDI 1 and SD 2 with indoleamine 2,3 dioxygenase were found to be -10.55 kcal/mol and -11.08 kcal/mol, respectively, while the scores for their interactions with monoamine oxidase were found to be -8.76 kcal/mol and -9.28 kcal/mol, respectively, using AutoDock 4.2. The relationship between biological affinity and pharmacophore electrical structure was examined using the docking technique. The chosen compounds were tested for their ability to inhibit MAO, and the IC₅₀ values for each were found to be 51.20 and 56, respectively.</p><p><strong>Conclusion: </strong>This investigation has identified many novel and effective MAO-A inhibitors from the family of chemicals known as methyl isatin derivatives. Lead optimization was applied to the SDI 1 and SDI 2 derivatives. The superior bioactivity, pharmacokinetic profile, BBB penetration, pre-ADMET profiles, such as HIA (human intestinal absorption) and MDCK (Madin-Darby canine kidney), plasma protein binding, toxicity assessment, and docking outcomes, have been obtained. According to the study, synthesised isatin 1 and SDI 2 derivatives exhibited a stronger MAO inhibitory activity and effective binding energy, which may help prevent stress-induced depression and other neurodegenerative disorders caused by a monoamine imbalance.</p>","PeriodicalId":10886,"journal":{"name":"Current computer-aided drug design","volume":" ","pages":"431-440"},"PeriodicalIF":1.7,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9514650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine Learning Algorithms Identify Target Genes and the Molecular Mechanism of Matrine against Diffuse Large B-cell Lymphoma.","authors":"Yidong Zhu, Zhongping Ning, Ximing Li, Zhikang Lin","doi":"10.2174/1573409920666230821102806","DOIUrl":"10.2174/1573409920666230821102806","url":null,"abstract":"<p><strong>Background: </strong>Diffuse large B-cell lymphoma (DLBCL) is the most common type of non-Hodgkin's lymphoma worldwide. Novel treatment strategies are still needed for this disease.</p><p><strong>Objective: </strong>The present study aimed to systematically explore the potential targets and molecular mechanisms of matrine in the treatment of DLBCL.</p><p><strong>Methods: </strong>Potential matrine targets were collected from multiple platforms. Microarray data and clinical characteristics of DLBCL were downloaded from publicly available database. Differential expression analysis and weighted gene co-expression network analysis (WGCNA) were applied to identify the hub genes of DLBCL using R software. Then, the shared target genes between matrine and DLBCL were identified as the potential targets of matrine against DLBCL. The least absolute shrinkage and selection operator (LASSO) algorithm was used to determine the final core target genes, which were further verified by molecular docking simulation and receiver operating characteristic (ROC) curve analysis. Functional analysis was also performed to elucidate the potential mechanisms.</p><p><strong>Results: </strong>A total of 222 matrine target genes and 1269 DLBCL hub genes were obtained through multiple databases and machine learning algorithms. From the nine shared target genes of matrine and DLBCL, five final core target genes, including <i>CTSL, NR1H2, PDPK1, MDM2, and JAK3</i>, were identified. Molecular docking showed that the binding of matrine to the core genes was stable. ROC curves also suggested close associations between the core genes and DLBCL. Additionally, functional analysis showed that the therapeutic effect of matrine against DLBCL may be related to the PI3K-Akt signaling pathway.</p><p><strong>Conclusion: </strong>Matrine may target five genes and the PI3K-Akt signaling pathway in DLBCL treatment.</p>","PeriodicalId":10886,"journal":{"name":"Current computer-aided drug design","volume":" ","pages":"847-859"},"PeriodicalIF":1.5,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10042080","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Targets and Mechanisms of Xuebijing in the Treatment of Acute Kidney Injury Associated with Sepsis: A Network Pharmacology-based Study.","authors":"Jing Wang, Chengyu Luo, Mengling Luo, Siwen Zhou, Guicheng Kuang","doi":"10.2174/1573409919666230519121138","DOIUrl":"10.2174/1573409919666230519121138","url":null,"abstract":"<p><strong>Introduction: </strong>Sepsis is a state of the systemic inflammatory response of the host induced by infection, frequently affecting numerous organs and producing varied degrees of damage. The most typical consequence of sepsis is sepsis-associated acute kidney injury(SA-AKI). Xuebijing is developed based on XueFuZhuYu Decoction. Five Chinese herbal extracts, including Carthami Flos, Radix Paeoniae Rubra, Chuanxiong Rhizoma, Radix Salviae, and Angelicae Sinensis Radix, make up the majority of the mixture. It has properties that are anti-inflammatory and anti-oxidative stress. Xuebijing is an effective medication for the treatment of SA-AKI, according to clinical research. But its pharmacological mechanism is still not completely understood.</p><p><strong>Methods: </strong>First, the composition and target information of Carthami Flos, Radix Paeoniae Rubra, Chuanxiong Rhizoma, Radix Salviae, and Angelicae Sinensis Radix were collected from the TCMSP database, while the therapeutic targets of SA-AKI were exported from the gene card database. To do a GO and KEGG enrichment analysis, we first screened the key targets using a Venn diagram and Cytoscape 3.9.1. To assess the binding activity between the active component and the target, we lastly used molecular docking.</p><p><strong>Results: </strong>For Xuebijing, a total of 59 active components and 267 corresponding targets were discovered, while for SA-AKI, a total of 1,276 targets were connected. There were 117 targets in all that was shared by goals for active ingredients and objectives for diseases. The TNF signaling pathway and the AGE-RAGE pathway were later found to be significant pathways for the therapeutic effects of Xuebijing by GO analysis and KEGG pathway analysis. Quercetin, luteolin, and kaempferol were shown to target and modulate CXCL8, CASP3, and TNF, respectively, according to molecular docking results.</p><p><strong>Conclusion: </strong>This study predicts the mechanism of action of the active ingredients of Xuebijing in the treatment of SA-AKI, which provides a basis for future applications of Xuebijing and studies targeting the mechanism.</p>","PeriodicalId":10886,"journal":{"name":"Current computer-aided drug design","volume":" ","pages":"752-763"},"PeriodicalIF":1.5,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9552035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"<i>Hibiscus sabdariffa</i> Linn. Extract Increases the mRNA Expression of the Arcuate Nucleus Leptin Receptor and is Predicted <i>in silico</i> as an Anti-obesity Agent.","authors":"Neng Tine Kartinah, Suci Anggraini, Fadilah Fadilah, Rickie Rickie","doi":"10.2174/1573409920666230822115144","DOIUrl":"10.2174/1573409920666230822115144","url":null,"abstract":"<p><strong>Background: </strong>Leptin is predominant in regulating body weight by stimulating energy expenditure through its neuronal action in the brain. Moreover, it is projected to adipose tissue and induces adipocyte browning by activating the β3-adrenergic receptor (β3AR). However, the expression of leptin receptor (Lep-R) and β3AR in people with obesity is downregulated.</p><p><strong>Aim: </strong>We hypothesized that <i>Hibiscus sabdariffa</i> Linn. extract (HSE) would increase hypothalamus arcuate nucleus (ARC) Lep-R and white adipose tissue (WAT) β3AR mRNA expression in DIO rats. This study also analyzed the potency of <i>H. sabdariffa</i> bioactive compounds as activators of Lep-R and β3AR by an <i>in-silico</i> experiment.</p><p><strong>Methods: </strong>Twenty-four male <i>Sprague-Dawley</i> rats were divided into four groups: Control (standard food), DIO (high-fat diet), DIO-Hib200 (HFD+HSE 200 mg/kg BW), and DIO-Hib400 (HFD+HSE400 mg/kg BW). HSE was administered orally for five weeks, once a day.</p><p><strong>Results: </strong>HSE administration significantly (p <0,05) increased the ARC Lep-R expression. The Lee index significantly decreased to the normal range (≤ 310) with p <0,001 for DIO-Hib200 and p <0,01 for DIO-Hib400. Among 39 bioactive compounds, <i>5-O-caffeoyl shikimic</i> acid exhibited high free binding scores (-8,63) for Lep-R, and <i>myricetin_3_arabinogalactoside</i> had high free binding scores (-9,39) for β3AR. These binding predictions could activate Lep-R and β3AR.</p><p><strong>Conclusion: </strong>This study highlights that HSE could be a potential therapeutic target for obesity by increasing LepR mRNA and leptin sensitivity, enhancing energy expenditure, and reducing obesity.</p>","PeriodicalId":10886,"journal":{"name":"Current computer-aided drug design","volume":" ","pages":"811-821"},"PeriodicalIF":1.5,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10407782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design, In Silico Screening, Synthesis, Characterisation and DFT-based Electronic Properties of Dihydropyridine-based Molecule as L-type Calcium Channel Blocker","authors":"Sujoy Karmakar, Hriday Kumar Basak, Uttam Paswan, Soumen Saha, Samir Kumar Mandal, Abhik Chatterjee","doi":"10.2174/0115734099273719231005062524","DOIUrl":"https://doi.org/10.2174/0115734099273719231005062524","url":null,"abstract":"Objective: The objectives of this study are first to design potential antihypertensive drugs based on the DHP scaffold, secondly, to analyse drug-likeness properties of the ligands and investigate their molecular mechanisms of binding to the model protein Cav1.2 and finally to synthesise the best ligand. Methods: Due to the lack of 3D structures for human Cav1.2, the protein structure was modelled using a homology modelling approach. A protein-ligand complex's strength and binding interaction were investigated using molecular docking and molecular dynamics techniques. DFT-based electronic properties of the ligands were calculated using the M06-2X/ def2-TZVP level of theory. The SwissADME website was used to study the ADMET properties. Results: In this study, a series of DHP compounds (19 compounds) were properly designed to act as calcium channel blockers. Among these compounds, compound 16 showed excellent binding scores (-11.6 kcal/mol). This compound was synthesised with good yield and characterised. To assess the structural features of the synthesised molecule quantum chemical calculations were performed. Conclusion: Based on molecular docking, molecular dynamics simulations, and drug-likeness properties of compound 16 can be used as a potential calcium channel blocker.","PeriodicalId":10886,"journal":{"name":"Current computer-aided drug design","volume":"20 1","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139054514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Novel Deep Learning Model for Drug-drug Interactions","authors":"Ali K. Abdul Raheem, Ban N. Dhannoon","doi":"10.2174/0115734099265663230926064638","DOIUrl":"https://doi.org/10.2174/0115734099265663230926064638","url":null,"abstract":"Introduction:: Drug-drug interactions (DDIs) can lead to adverse events and compromised treatment efficacy that emphasize the need for accurate prediction and understanding of these interactions Methods:: in this paper, we propose a novel approach for DDI prediction using two separate message-passing neural network (MPNN) models, each focused on one drug in a pair. By capturing the unique characteristics of each drug and their interactions, the proposed method aims to improve the accuracy of DDI prediction. The outputs of the individual MPNN models combine to integrate the information from both drugs and their molecular features. Evaluating the proposed method on a comprehensive dataset, we demonstrate its superior performance with an accuracy of 0.90, an area under the curve (AUC) of 0.99, and an F1-score of 0.80. These results highlight the effectiveness of the proposed approach in accurately identifying potential drugdrug interactions. Results:: The use of two separate MPNN models offers a flexible framework for capturing drug characteristics and interactions, contributing to our understanding of DDIs. The findings of this study have significant implications for patient safety and personalized medicine, with the potential to optimize treatment outcomes by preventing adverse events. Conclusion:: Further research and validation on larger datasets and real-world scenarios are necessary to explore the generalizability and practicality of this approach.","PeriodicalId":10886,"journal":{"name":"Current computer-aided drug design","volume":"82 2","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138507142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mechanism of Polygala-Acorus in Treating Autism Spectrum Disorder Based on Network Pharmacology and Molecular Docking","authors":"Haozhi Chen, Changlin Zhou, Wen Li, Yaoyao Bian","doi":"10.2174/0115734099266308231108112058","DOIUrl":"https://doi.org/10.2174/0115734099266308231108112058","url":null,"abstract":"Background:: Recent epidemic survey data have revealed a globally increasing prevalence of autism spectrum disorders (ASDs). Currently, while Western medicine mostly uses a combination of comprehensive intervention and rehabilitative treatment, patient outcomes remain unsatisfactory. Polygala–Acorus, used as a pair drug, positively affects the brain and kidneys, and can improve intelligence, wisdom, and awareness; however, the underlying mechanism of action is unclear. background: Recent epidemic survey data revealed a globally increasing prevalence of autism spectrum disorders (ASDs). Currently, Western medicine mostly uses a combination of comprehensive intervention and rehabilitative treatment, but patient outcomes remain unsatisfactory. Polygala–Acorus, used as a pair drug, positively affects the brain and kidneys and can improve intelligence, wisdom, and awareness. However, the underlying mechanism is unclear. Objective:: We performed network pharmacology analysis of the mechanism of Polygala– Acorus in treating ASD and its potential therapeutic effects to provide a scientific basis for the pharmaceutical’s clinical application. Methods:: The chemical compositions and targets corresponding to Polygala–Acorus were obtained using the Traditional Chinese Medicine Systematic Pharmacology Database and Analysis Platform, ChemSource.com, and PharmMapper database. Disease targets in ASD were screened using the DisGeNET, DrugBank, and GeneCards databases. Gene Ontology functional analysis and metabolic pathway analysis (Kyoto Encyclopedia of Genes and Genomes) were performed using the Metascape database and validated via molecular docking using AutoDock Vina and PyMOL software. Results:: Molecular docking analysis showed that the key active components of Polygala- Acorus interacted with the following key targets: EGFR, SRC, MAPK1, and ALB. Thus, the key active components of Polygala-Acorus (sibiricaxanthone A, sibiricaxanthone B tenuifolin, polygalic acid, cycloartenol, and 8-isopentenyl-kaempferol) have been found to bind to EGFR, SRC, MAPK1, and ALB. Conclusion:: This study has preliminarily revealed the active ingredients and underlying mechanism of Polygala-Acorus in the treatment of ASD, and our predictions need to be proven by further experimentation.","PeriodicalId":10886,"journal":{"name":"Current computer-aided drug design","volume":"157 ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138507097","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}