Interrelationship between 2019-nCov receptor DPP4 and diabetes mellitus targets based on protein interaction network

Patients with diabetes are more likely to be infected with Coronavirus disease 2019 (COVID-19), and the risk of death is significantly higher than ordinary patients. Dipeptidyl peptidase-4 (DPP4) is one of the functional receptor of human coronavirus. Exploring the relationship between diabetes mellitus targets and DPP4 is particularly important for the management of patients with diabetes and COVID-19. We intend to study the protein interaction through the protein interaction network in order to find a new clue for the management of patients with diabetes with COVID-19. Diabetes mellitus targets were obtained from GeneCards database. Targets with a relevance score exceeding 20 were included, and DPP4 protein was added manually. The initial protein interaction network was obtained through String. The targets directly related to DPP4 were selected as the final analysis targets. Importing them into String again to obtain the protein interaction network. Module identification, gene ontology (GO) analysis and Kyoto encyclopedia of genes and genomes (KEGG) pathway analysis were carried out respectively. The impact of DPP4 on the whole network was analyzed by scoring the module where it located. 43 DPP4-related proteins were finally selected from the diabetes mellitus targets and three functional modules were found by the cluster analysis. Module 1 was involved in insulin secretion and glucagon signaling pathway, module 2 and module 3 were involved in signaling receptor binding. The scoring results showed that LEP and apoB in module 1 were the highest, and the scores of INS, IL6 and ALB of cross module associated proteins of module 1 were the highest. DPP4 is widely associated with key proteins in diabetes mellitus. COVID-19 may affect DPP4 in patients with diabetes mellitus, leading to high mortality of diabetes mellitus combined with COVID-19. DPP4 inhibitors and IL-6 antagonists can be considered to reduce the effect of COVID-19 infection on patients with diabetes.

Supervised learning techniques to predict compounds in pathway modules based on molecular properties

Machine learning algorithms provide significant indications in metabolomics to predict chemical compounds in metabolic pathways and in their modules. The modules in the metabolic pathway are sub networks of functionally related genes based on rules such as protein-protein interactions, co-regulated expression, coordinated physiological activity, and successive reaction steps. Fully functional modules are helpful to improve the diseases process, drug discover, and prediction of missing reaction. All modules in the metabolic pathway are not functional due to missing reaction steps. The structural mapping of chemical compounds with the pathway module is helpful to understand the mechanism of prediction unknown reaction step. The main purpose of this paper to predict the chemical compounds in pathway modules and their classes. We have constructed binary and multi-label classification data sets to predict pathway module and module classes, respectively. In order to identify the pathway module and its classes, we have built an ensemble Extra trees classifier to learn the molecular and atomic properties of chemical compounds. We have also experimented with different ensemble machine learning algorithm for the prediction of pathway modules. The overall prediction rate of the classifier 98.59%, indicating extra tree classifier features are more interpretable and have a high predictive performance on various tasks.

Supervised learning techniques to predict compounds in pathway modules based on molecular properties

<div># Machine learning Classifiers for prediction of Pathway module & it classes </div><div>We use SMILES representation of query molecules to generate relevant fingerprints, which are then fed to the machine learning classifiers ETC for producing binary labels corresponding pathway module & its classes. The details of the works are described in our paper.</div><div>A dataset of 6597 downloaded from KEGG, 4612 compounds either belong or not to Pathway module in metabolic pathway the remaining 1985 compounds belong to module classes prediction problems </div><div>### Requirements</div><div>*Chemoinformatics tools</div><div>* Python</div><div>* scikit-learn</div><div>* RDKit</div><div>* Jupyter Notebook</div><div>### Usage</div><div>We provide two folder containing Classifiers files,grid search for optimization of hyperparameters, and datasets(module, module classes</div>

Supervised learning techniques to predict compounds in pathway modules based on molecular properties

<div># Machine learning Classifiers for prediction of Pathway module & it classes </div><div>We use SMILES representation of query molecules to generate relevant fingerprints, which are then fed to the machine learning classifiers ETC for producing binary labels corresponding pathway module & its classes. The details of the works are described in our paper.</div><div>A dataset of 6597 downloaded from KEGG, 4612 compounds either belong or not to Pathway module in metabolic pathway the remaining 1985 compounds belong to module classes prediction problems </div><div>### Requirements</div><div>*Chemoinformatics tools</div><div>* Python</div><div>* scikit-learn</div><div>* RDKit</div><div>* Jupyter Notebook</div><div>### Usage</div><div>We provide two folder containing Classifiers files,grid search for optimization of hyperparameters, and datasets(module, module classes</div>

ORN: Inferring patient-specific dysregulation status of pathway modules in cancer with OR-gate Network

Pathway level understanding of cancer plays a key role in precision oncology. However, the current amount of high-throughput data cannot support the elucidation of full pathway topology. In this study, instead of directly learning the pathway network, we adapted the probabilistic OR gate to model the modular structure of pathways and regulon. The resulting model, OR-gate Network (ORN), can simultaneously infer pathway modules of somatic alterations, patient-specific pathway dysregulation status, and downstream regulon. In a trained ORN, the differentially expressed genes (DEGs) in each tumour can be explained by somatic mutations perturbing a pathway module. Furthermore, the ORN handles one of the most important properties of pathway perturbation in tumours, the mutual exclusivity. We have applied the ORN to lower-grade glioma (LGG) samples and liver hepatocellular carcinoma (LIHC) samples in TCGA and breast cancer samples from METABRIC. Both datasets have shown abnormal pathway activities related to immune response and cell cycles. In LGG samples, ORN identified pathway modules closely related to glioma development and revealed two pathways closely related to patient survival. We had similar results with LIHC samples. Additional results from the METABRIC datasets showed that ORN could characterize critical mechanisms of cancer and connect them to less studied somatic mutations (e.g., BAP1, MIR604, MICAL3, and telomere activities), which may generate novel hypothesis for targeted therapy.

pmVAE: Learning Interpretable Single-Cell Representations with Pathway Modules

ABSTRACTMotivationDeep learning techniques have yielded tremendous progress in the field of computational biology over the last decade, however many of these techniques are opaque to the user. To provide interpretable results, methods have incorporated biological priors directly into the learning task; one such biological prior is pathway structure. While pathways represent most biological processes in the cell, the high level of correlation and hierarchical structure make it complicated to determine an appropriate computational representation.ResultsHere, we present pathway module Variational Autoencoder (pmVAE). Our method encodes pathway information by restricting the structure of our VAE to mirror gene-pathway memberships. Its architecture is composed of a set of subnetworks, which we refer to as pathway modules. The subnetworks learn interpretable latent representations by factorizing the latent space according to pathway gene sets. We directly address correlation between pathways by balancing a module-specific local loss and a global reconstruction loss. Furthermore, since many pathways are by nature hierarchical and therefore the product of multiple downstream signals, we model each pathway as a multidimensional vector. Due to their factorization over pathways, the representations allow for easy and interpretable analysis of multiple downstream effects, such as cell type and biological stimulus, within the contexts of each pathway. We compare pmVAE against two other state-of-the-art methods on two single-cell RNA-seq case-control data sets, demonstrating that our pathway representations are both more discriminative and consistent in detecting pathways targeted by a perturbation.Availability and implementationhttps://github.com/ratschlab/pmvae

Exploring the Pathogenesis and Potential Therapeutic Drugs of Chronic Obstructive Pulmonary Disease Based on Functional Disorder Modules

Researchers widely acknowledged that chronic obstructive pulmonary disease (COPD) became the third leading cause of death in the United States. At present, the pathogenesis and treatment of COPD still need to be further explored. In this study, the pathogenesis and treatment of COPD were modularized, and effective therapeutic drugs were explored. First, we identified 467 COPD-related genes from the NCBI-Gene database to explore the co-expression of these genes and their highly interacting proteins in patients with COPD. Secondly, COPD-related genes were analyzed using a co-expression module. Then, crosstalk analysis of co-expression modules was performed to reveal the interaction between these modules. Next, the enrichment of GO function and KEGG pathway module genes was analyzed. At the same time, non-coding RNAs (ncRNAs), transcription factors that regulate modules and potential drugs were predicted using hypergeometric tests. In summary, we obtained 22 co-expression modules, and a significant relationship was found between these modules. From the results of this study, we determined that the identified module genes are involved in the biological processes of cell growth, leukocyte activation, cytokine production, and humoral immune responses. Wnt, NF-kappa B, PI3 K-AKT, mitochondrial autophagy, oxidative stress, and other signaling pathways were significantly regulated. In addition, a ncRNA pivot (including microRNA-93-5p and microRNA-128-3p) and TF pivot (including NFKB1, RELA, and SP1) were identified as significant regulatory dysfunction modules. Finally, according to the target effect of drugs on the module genes, we found that drugs, such as fostamatinib and copper, demonstrate a certain therapeutic effect on COPD. In conclusion, COPD multifactorial dysfunction, in which helps to reveal the disease, at that meantime, to improve its basic molecular mechanisms. These findings provide valuable theoretical references for the diagnosis and personalized treatment of patients with COPD.

Analysing the meta-interaction between pathways by gene set topological impact analysis

Background Pathway analysis is widely applied in transcriptome analysis. Given certain transcriptomic changes, current pathway analysis tools tend to search for the most impacted pathways, which provides insight into underlying biological mechanisms. Further refining of the enriched pathways and extracting functional modules by “crosstalk” analysis have been proposed. However, the upstream/downstream relationships between the modules, which may provide extra biological insights such as the coordination of different functional modules and the signal transduction flow have been ignored. Results To quantitatively analyse the upstream/downstream relationships between functional modules, we developed a novel GEne Set Topological Impact Analysis (GESTIA), which could be used to assemble the enriched pathways and functional modules into a super-module with a topological structure. We showed the advantages of this analysis in the exploration of extra biological insight in addition to the individual enriched pathways and functional modules. Conclusions GESTIA can be applied to a broad range of pathway/module analysis result. We hope that GESTIA may help researchers to get one additional step closer to understanding the molecular mechanism from the pathway/module analysis results.

Differential metabolic activity and discovery of therapeutic targets using summarized metabolic pathway models

Backgroundin spite of the increasing availability of genomic and transcriptomic data, there is still a gap between the detection of perturbations in gene expression and the understanding of their contribution to the molecular mechanisms that ultimately account for the phenotype studied. Alterations in the metabolism are behind the initiation and progression of many diseases, including cancer. The wealth of available knowledge on metabolic processes can therefore be used to derive mechanistic models that link gene expression perturbations to changes in metabolic activity that provide relevant clues on molecular mechanisms of disease and drug modes of action (MoA). In particular, pathway modules, which recapitulate the main aspects of metabolism, are especially suitable for this type of modeling.Resultswe present Metabolizer, a web-based application that offers an intuitive, easy-to-use interactive interface to analyze differences in pathway module metabolic activities that can also be used for class prediction and in silico prediction of Knock-Out (KO) effects. Moreover, Metabolizer can automatically predict the optimal KO intervention for restoring a diseased phenotype. We provide different types of validations of some of the predictions made by Metabolizer.ConclusionsMetabolizer is a web tool that allows understanding molecular mechanisms of disease or the MoA of drugs within the context of the metabolism by using gene expression measurements. In addition, this tool automatically suggests potential therapeutic targets for individualized therapeutic interventions.Metabolizer can be found at:http://metabolizer.babelomics.org.