基于布谷鸟算法与BP神经网络的煤灰变形温度预测

以120种煤样为数据基础,采用布谷鸟算法(CS)优化BP(Back Propagation)神经网络,建立了CSBP模型对单煤、煤掺添加剂和配煤等3类样本的煤灰变形温度(DT)样本进行预测。模型以煤灰化学成分及其组合参数等13个变量作为输入量,以变形温度(DT)作为输出量。CSBP模型预测结果与BP神经网络模型预测结果进行对比发现,无论是单煤、煤掺添加剂还是配煤,CSBP模型较BP模型对煤灰变形温度(DT)的预测都更加精准,平均相对误差分别达到了3.11%、4.08%和4.22%。另外,对比3类样本预测结果发现,无论是CSBP模型还是BP模型,相比单煤预测而言,煤掺添加剂及配煤的预测误差都有明显的增加。     

Exploring the mechanism of Cremastra Appendiculata (SUANPANQI) against breast cancer by network pharmacology and molecular docking

BackgroundSUANPANQI, the pseudo phosphorous stem of Cremastra appendiculata, is one of the most well-known traditional Chinese medicine, which has been shown to inhibit tumorigenesis in various human cancers. However, the underlying mechanism of SUANPANQI treatment against breast cancer (BRCA) remains unclear. In this study. we aim to investigate the bioactive compounds and mechanisms of SUANPANQI in the treatment of BRCA based on network pharmacology and molecular docking.MethodsThe compounds were collected from previous research. SwissADME was used to screen bioactive compounds. The targets corresponding to SUANPANQI and BRCA were obtained using MalaCards and SwissTargetPrediction. SUANPANQI-related and BRCA-related targets were found and then overlapped to get intersections, which represented potential anti-BRCA targets of SUANPANQI. The Cytoscape software was used to construct bioactive compounds targeting the BRCA network. Gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis of the targets was extracted from the metascape database, then conducted using the Cluster Profiler package in R software. Protein-Protein interaction (PPI) network was constructed using the STRING online database and analyzed using Cytoscape software. Pivotal genes were screened using the topological analysis, survival analysis, and pathological stage analysis. Molecular docking analysis was used to verify whether the bioactive compounds had a definite affinity with the pivotal targets.ResultsSixty-five bioactive compounds of SUANPANQI were involved with 225 predicted BRCA targets. Then, a compound-target network and a PPI network were constructed. The GO analysis and KEGG enrichment analysis suggested that SUANPANQI worked against BRCA via PI3K-Akt, Ras, FoxO, Rap1, and ErbB signaling pathways, etc. After topological analysis, survival analysis, and pathological stage analysis of the SUANPANQI potential targets against BRCA, 6 pivotal target genes (AR, HSP90AA1, MMP9, PGR, PTGS2, TNF) that were highly responsible for the therapeutic effects of SUANPANQI against BRCA were obtained. Molecular docking results showed that 6 bioactive compounds of SUANPANQI had strong binding efficiency with the 6 pivotal genes.ConclusionsThe present study clarifies the mechanism of SUANPANQI against BRCA through multiple targets and pathways, and provides evidence to support its clinical use.     

Exploration of the mechanism of Zisheng Shenqi decoction against gout arthritis using network pharmacology

BackgroundIn this study, the network pharmacological methods were used to predict the target of effective components of compounds in Zisheng Shenqi Decoction (ZSD, or Nourishing Kidney Qi Decoction) in the treatment of gouty arthritis (GA).MethodThe main effective components and corresponding key targets of herbs in the ZSD were discerned through the Traditional Chinese Medicine Systems Pharmacology Database and Analysis (TCMSP), Bioinformatics Analysis Tool for Molecular mechanism of Traditional Chinese Medicine (BATMAN-TCM) database. UniProt database and Swiss Target Prediction (STP) database was used to rectify and unify the target names and supply the target information. The targets related to GA were obtained by using GeneCards database. After we discovered the potential common targets between ZSD and GA, the interaction network diagram of “ZSD-component-GA-target” was constructed by Cytoscape software (Version 3.7.1). Subsequently, the Protein-protein interaction (PPI) network of ZSD effective components-targets and GA-related targets was constructed by Search Tool for the Retrieval of Interacting Genes Database (STRING). Bioconductor package “org.Hs.eg.db” and “cluster profiler” package were installed in R software (Version 3.6.0) which used for Gene Ontology analysis and KEGG (Kyoto Encyclopedia of Genes and Genomes) pathway enrichment analysis.Results146 components and 613 targets of 11 herbal medicines in the ZSD were got from TCMSP database and BATMAN-TCM database. 987 targets of GA were obtained from GeneCards database. After intersected and removed duplications, 132 common targets between ZSD and GA were screened out by Cytoscape software (Version 3.7.1). These common targets derived from 81 effective components of 146 components, such as quercetin, stigmasterol and kaempferol. They were closely related to anti-inflammatory, analgesic and anti oxidative stress and the principal targets comprised of Purinergic receptor P2X, ligand-gated ion channel 7 (P2x7R), Nod-like receptor protein 3 (NLRP3) and IL-1β. GO enrichment analysis and KEGG pathway enrichment analysis by R software (Version 3.6.0) showed that the key target genes had close relationship with oxidative stress, reactive oxygen species (ROS) metabolic process and leukocyte migration in aspects of biological process, cell components and molecular function. It also indicated that ZSD could decrease inflammatory reaction, alleviate ROS accumulation and attenuate pain by regulating P2 × 7R and NOD like receptor signaling pathway of inflammatory reaction.ConclusionA total of 81 effective components and 132 common target genes between ZSD and GA were screened by network pharmacology. The PPI network, GO enrichment analysis and KEGG pathway enrichment analysis suggested that ZSD can exerte anti-inflammatory and analgesic effects on the treatment of GA by reducing decreasing inflammatory reaction, alleviating ROS accumulation, and attenuating pain. The possible molecular mechanism of it mainly involved multiple components, multiple targets and multiple signaling pathways, which provided a comprehensive understanding for further study. In general, the network pharmacological method applied in this study provides an alternative strategy for the mechanism of ZSD in the treatment of GA.     

Analysis of aging-related protein interactome and cross-network module comparisons across tissues provide new insights into aging

Delaying the human aging process and thus eliminating the risk factors for age-related diseases is one of the prime objectives. While various aging-associated genes and proteins have been characterized, which provide a significant understanding of the human aging process, a significant success in regulating aging is not achieved yet. Understanding how aging proteins interact with each other and also with other proteins could provide important insights into the underlying mechanisms governing the aging process. Therefore, in this work, information of gene expression was included to the static aging-related protein interactome to understand the network-based relationships among aging-related essential (AE) proteins, aging-related non-essential (ANE) proteins, and housekeeping-proteins that could regulate or influence aging. Comprehensive analyses provided various systems-level insights into the regulatory characteristics of aging; for example, (i) network-based correlation analysis predicted functional relationships among AE proteins and ANE proteins; (ii) network variability analysis predicted aging to affect different tissues in strikingly different ways by differentially regulating various regulatory interactions; (iii) cross-network comparisons identified two aging-related modules to be significantly conserved across most of the tissues. Overall, the findings obtained during this study could be helpful for researchers to delay, prevent, or even reverse various aspects of the aging.     

Prediction of human-Streptococcus pneumoniae protein-protein interactions using logistic regression

Streptococcus pneumoniae is a major cause of mortality in children under five years old. In recent years, the emergence of antibiotic-resistant strains of S. pneumoniae increases the threat level of this pathogen. For that reason, the exploration of S. pneumoniae protein virulence factors should be considered in developing new drugs or vaccines, for instance by the analysis of host-pathogen protein-protein interactions (HP-PPIs). In this research, prediction of protein-protein interactions was performed with a logistic regression model with the number of protein domain occurrences as features. By utilizing HP-PPIs of three different pathogens as training data, the model achieved 57–77 % precision, 64–75 % recall, and 96–98 % specificity. Prediction of human-S. pneumoniae protein-protein interactions using the model yielded 5823 interactions involving thirty S. pneumoniae proteins and 324 human proteins. Pathway enrichment analysis showed that most of the pathways involved in the predicted interactions are immune system pathways. Network topology analysis revealed β-galactosidase (BgaA) as the most central among the S. pneumoniae proteins in the predicted HP-PPI networks, with a degree centrality of 1.0 and a betweenness centrality of 0.451853. Further experimental studies are required to validate the predicted interactions and examine their roles in S. pneumoniae infection.     

A network-based pharmacology study of active compounds and targets of Fritillaria thunbergii against influenza

Seasonal and pandemic influenza infections are serious threats to public health and the global economy. Since antigenic drift reduces the effectiveness of conventional therapies against the virus, herbal medicine has been proposed as an alternative. Fritillaria thunbergii (FT) have been traditionally used to treat airway inflammatory diseases such as coughs, bronchitis, pneumonia, and fever-based illnesses. Herein, we used a network pharmacology-based strategy to predict potential compounds from Fritillaria thunbergii (FT), target genes, and cellular pathways to better combat influenza and influenza-associated diseases. We identified five compounds, and 47 target genes using a compound-target network (C-T). Two compounds (beta-sitosterol and pelargonidin) and nine target genes (BCL2, CASP3, HSP90AA1, ICAM1, JUN, NOS2, PPARG, PTGS1, PTGS2) were identified using a compound-influenza disease target network (C-D). Protein-protein interaction (PPI) network was constructed and we identified eight proteins from nine target genes formed a network. The compound-disease-pathway network (C-D-P) revealed three classes of pathways linked to influenza: cancer, viral diseases, and inflammation. Taken together, our systems biology data from C-T, C-D, PPI and C-D-P networks predicted potent compounds from FT and new therapeutic targets and pathways involved in influenza.     

一种改进的Jacobi正交多项式的BP神经网络算法

 根据多项式理论,构造一种以Jacobi正交多项式作为隐层神经元激励函数的BP(back-propagation)神经网络模型.针对该网络,提出一种改进算法即隐层神经元数可快速确定的权值直接确定算法.首先介绍正交基函数和Jacobi多项式的定义,以及BP神经网络的基本原理.然后进行网络隐层数设计及其隐神经元数的确定,且设置各层连接权值、给出改进算法的步骤.最后,将其与传统矩阵迭代法和Levenberg-Marquardt训练算法进行比较.计算机实验结果表明,该算法具有比传统的BP迭代法更快的计算速度,并且能够达到更高的工作精度.