Network Based Prediction Model for Genomics Data Analysis.
Ontology highlight
ABSTRACT:
SUBMITTER: Huang Y
PROVIDER: S-EPMC3859188 | biostudies-literature | 2012 Apr
REPOSITORIES: biostudies-literature
Publications
Network Based Prediction Model for Genomics Data Analysis.
Statistics in biosciences 20120401 1
Biological networks, such as genetic regulatory networks and protein interaction networks, provide important information for studying gene/protein activities. In this paper, we propose a new method, NetBoosting, for incorporating a priori biological network information in analyzing high dimensional genomics data. Specially, we are interested in constructing prediction models for disease phenotypes of interest based on genomics data, and at the same time identifying disease susceptible genes. We ...[more]
Similar Datasets
Project description:BACKGROUND:Functional genomics employs several experimental approaches to investigate gene functions. High-throughput techniques, such as loss-of-function screening and transcriptome profiling, allow to identify lists of genes potentially involved in biological processes of interest (so called hit list). Several computational methods exist to analyze and interpret such lists, the most widespread of which aim either at investigating of significantly enriched biological processes, or at extracting significantly represented subnetworks. RESULTS:Here we propose a novel network analysis method and corresponding computational software that employs the shortest path approach and centrality measure to discover members of molecular pathways leading to the studied phenotype, based on functional genomics screening data. The method works on integrated interactomes that consist of both directed and undirected networks - HIPPIE, SIGNOR, SignaLink, TFactS, KEGG, TransmiR, miRTarBase. The method finds nodes and short simple paths with significant high centrality in subnetworks induced by the hit genes and by so-called final implementers - the genes that are involved in molecular events responsible for final phenotypic realization of the biological processes of interest. We present the application of the method to the data from miRNA loss-of-function screen and transcriptome profiling of terminal human muscle differentiation process and to the gene loss-of-function screen exploring the genes that regulates human oxidative DNA damage recognition. The analysis highlighted the possible role of several known myogenesis regulatory miRNAs (miR-1, miR-125b, miR-216a) and their targets (AR, NR3C1, ARRB1, ITSN1, VAV3, TDGF1), as well as linked two major regulatory molecules of skeletal myogenesis, MYOD and SMAD3, to their previously known muscle-related targets (TGFB1, CDC42, CTCF) and also to a number of proteins such as C-KIT that have not been previously studied in the context of muscle differentiation. The analysis also showed the role of the interaction between H3 and SETDB1 proteins for oxidative DNA damage recognition. CONCLUSION:The current work provides a systematic methodology to discover members of molecular pathways in integrated networks using functional genomics screening data. It also offers a valuable instrument to explain the appearance of a set of genes, previously not associated with the process of interest, in the hit list of each particular functional genomics screening.
| S-EPMC7491077 | biostudies-literature
Project description:BACKGROUND:Stratification of patient subpopulations that respond favorably to treatment or experience and adverse reaction is an essential step toward development of new personalized therapies and diagnostics. It is currently feasible to generate omic-scale biological measurements for all patients in a study, providing an opportunity for machine learning models to identify molecular markers for disease diagnosis and progression. However, the high variability of genetic background in human populations hampers the reproducibility of omic-scale markers. In this paper, we develop a biological network-based regularized artificial neural network model for prediction of phenotype from transcriptomic measurements in clinical trials. To improve model sparsity and the overall reproducibility of the model, we incorporate regularization for simultaneous shrinkage of gene sets based on active upstream regulatory mechanisms into the model. RESULTS:We benchmark our method against various regression, support vector machines and artificial neural network models and demonstrate the ability of our method in predicting the clinical outcomes using clinical trial data on acute rejection in kidney transplantation and response to Infliximab in ulcerative colitis. We show that integration of prior biological knowledge into the classification as developed in this paper, significantly improves the robustness and generalizability of predictions to independent datasets. We provide a Java code of our algorithm along with a parsed version of the STRING DB database. CONCLUSION:In summary, we present a method for prediction of clinical phenotypes using baseline genome-wide expression data that makes use of prior biological knowledge on gene-regulatory interactions in order to increase robustness and reproducibility of omic-scale markers. The integrated group-wise regularization methods increases the interpretability of biological signatures and gives stable performance estimates across independent test sets.
| S-EPMC5735940 | biostudies-literature
Project description:Inference of protein functions is one of the most important aims of modern biology. To fully exploit the large volumes of genomic data typically produced in modern-day genomic experiments, automated computational methods for protein function prediction are urgently needed. Established methods use sequence or structure similarity to infer functions but those types of data do not suffice to determine the biological context in which proteins act. Current high-throughput biological experiments produce large amounts of data on the interactions between proteins. Such data can be used to infer interaction networks and to predict the biological process that the protein is involved in. Here, we develop a probabilistic approach for protein function prediction using network data, such as protein-protein interaction measurements. We take a Bayesian approach to an existing Markov Random Field method by performing simultaneous estimation of the model parameters and prediction of protein functions. We use an adaptive Markov Chain Monte Carlo algorithm that leads to more accurate parameter estimates and consequently to improved prediction performance compared to the standard Markov Random Fields method. We tested our method using a high quality S. cereviciae validation network with 1622 proteins against 90 Gene Ontology terms of different levels of abstraction. Compared to three other protein function prediction methods, our approach shows very good prediction performance. Our method can be directly applied to protein-protein interaction or coexpression networks, but also can be extended to use multiple data sources. We apply our method to physical protein interaction data from S. cerevisiae and provide novel predictions, using 340 Gene Ontology terms, for 1170 unannotated proteins and we evaluate the predictions using the available literature.
| S-EPMC2827541 | biostudies-literature
Project description:The Soybean Gene Atlas project provides a comprehensive map for understanding gene expression patterns in major soybean tissues from flower, root, leaf, nodule, seed, and shoot and stem. The RNA-Seq data generated in the project serve as a valuable resource for discovering tissue-specific transcriptome behavior of soybean genes in different tissues. We developed a computational pipeline for Soybean context-specific network (SoyCSN) inference with a suite of prediction tools to analyze, annotate, retrieve, and visualize soybean context-specific networks at both transcriptome and interactome levels. BicMix and Cross-Conditions Cluster Detection algorithms were applied to detect modules based on co-expression relationships across all the tissues. Soybean context-specific interactomes were predicted by combining soybean tissue gene expression and protein-protein interaction data. Functional analyses of these predicted networks provide insights into soybean tissue specificities. For example, under symbiotic, nitrogen-fixing conditions, the constructed soybean leaf network highlights the connection between the photosynthesis function and rhizobium-legume symbiosis. SoyCSN data and all its results are publicly available via an interactive web service within the Soybean Knowledge Base (SoyKB) at http://soykb.org/SoyCSN. SoyCSN provides a useful web-based access for exploring context specificities systematically in gene regulatory mechanisms and gene relationships for soybean researchers and molecular breeders.
| S-EPMC6747016 | biostudies-literature
Project description:Severe bioprosthetic mitral valve calcification is a significant problem in cardiovascular surgery. Unfortunately, clinical markers did not demonstrate efficacy in prediction of severe bioprosthetic mitral valve calcification. Here, we examined whether a genomics-based approach is efficient in predicting the risk of severe bioprosthetic mitral valve calcification. A total of 124 consecutive Russian patients who underwent mitral valve replacement surgery were recruited. We investigated the associations of the inherited variation in innate immunity, lipid metabolism and calcium metabolism genes with severe bioprosthetic mitral valve calcification. Genotyping was conducted utilizing the TaqMan assay. Eight gene polymorphisms were significantly associated with severe bioprosthetic mitral valve calcification and were therefore included into stepwise logistic regression which identified male gender, the T/T genotype of the rs3775073 polymorphism within the TLR6 gene, the C/T genotype of the rs2229238 polymorphism within the IL6R gene, and the A/A genotype of the rs10455872 polymorphism within the LPA gene as independent predictors of severe bioprosthetic mitral valve calcification. The developed genomics-based model had fair predictive value with area under the receiver operating characteristic (ROC) curve of 0.73. In conclusion, our genomics-based approach is efficient for the prediction of severe bioprosthetic mitral valve calcification.
| S-EPMC5037665 | biostudies-literature
Project description:PurposeGastric cancer (GC) is a product of multiple genetic abnormalities, including genetic and epigenetic modifications. This study aimed to integrate various biomolecules, such as miRNAs, mRNA, and DNA methylation, into a genome-wide network and develop a nomogram for predicting the overall survival (OS) of GC.Materials and methodsA total of 329 GC cases, as a training cohort with a random of 150 examples included as a validation cohort, were screened from The Cancer Genome Atlas database. A genome-wide network was constructed based on a combination of univariate Cox regression and least absolute shrinkage and selection operator analyses, and a nomogram was established to predict 1-, 3-, and 5-year OS in the training cohort. The nomogram was then assessed in terms of calibration, discrimination, and clinical usefulness in the validation cohort. Afterward, in order to confirm the superiority of the whole gene network model and further reduce the biomarkers for the improvement of clinical usefulness, we also constructed eight other models according to the different combinations of miRNAs, mRNA, and DNA methylation sites and made corresponding comparisons. Finally, Gene Ontology (GO), and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses were also performed to describe the function of this genome-wide network.ResultsA multivariate analysis revealed a novel prognostic factor, a genomics score (GS) comprising seven miRNAs, eight mRNA, and 19 DNA methylation sites. In the validation cohort, comparing to patients with low GS, high-GS patients (HR, 12.886; P < 0.001) were significantly associated with increased all-cause mortality. Furthermore, after stratification of the TNM stage (I, II, III, and IV), there were significant differences revealed in the survival rates between the high-GS and low-GS groups as well (P < 0.001). The 1-, 3-, and 5-year C-index of whole genomics-based nomogram were 0.868, 0.895, and 0.928, respectively. The other models have comparable or relatively poor comprehensive performance, while they had fewer biomarkers. Besides that, DAVID 6.8 further revealed multiple molecules and pathways related to the genome-wide network, such as cytomembranes, cell cycle, and adipocytokine signaling.ConclusionWe successfully developed a GS based on genome-wide network, which may represent a novel prognostic factor for GC. A combination of GS and TNM staging provides additional precision in stratifying patients with different OS prognoses, constituting a more comprehensive sub-typing system. This could potentially play an important role in future clinical practice.
| S-EPMC7423976 | biostudies-literature
Project description:In an overwhelming demand scenario, such as the SARS-CoV-2 pandemic, pressure over health systems may outburst their predicted capacity to deal with such extreme situations. Therefore, in order to successfully face a health emergency, scientific evidence and validated models are needed to provide real-time information that could be applied by any health center, especially for high-risk populations, such as transplant recipients. We have developed a hybrid prediction model whose accuracy relative to several alternative configurations has been validated through a battery of clustering techniques. Using hospital admission data from a cohort of hospitalized transplant patients, our hybrid Data Envelopment Analysis (DEA)-Artificial Neural Network (ANN) model extrapolates the progression towards severe COVID-19 disease with an accuracy of 96.3%, outperforming any competing model, such as logistic regression (65.5%) and random forest (44.8%). In this regard, DEA-ANN allows us to categorize the evolution of patients through the values of the analyses performed at hospital admission. Our prediction model may help guiding COVID-19 management through the identification of key predictors that permit a sustainable management of resources in a patient-centered model.Supplementary informationThe online version contains supplementary material available at 10.1007/s10462-021-10008-0.
| S-EPMC8062617 | biostudies-literature
Project description:We present systemsDock, a web server for network pharmacology-based prediction and analysis, which permits docking simulation and molecular pathway map for comprehensive characterization of ligand selectivity and interpretation of ligand action on a complex molecular network. It incorporates an elaborately designed scoring function for molecular docking to assess protein-ligand binding potential. For large-scale screening and ease of investigation, systemsDock has a user-friendly GUI interface for molecule preparation, parameter specification and result inspection. Ligand binding potentials against individual proteins can be directly displayed on an uploaded molecular interaction map, allowing users to systemically investigate network-dependent effects of a drug or drug candidate. A case study is given to demonstrate how systemsDock can be used to discover a test compound's multi-target activity. systemsDock is freely accessible at http://systemsdock.unit.oist.jp/.
| S-EPMC4987901 | biostudies-other
Project description:Model-based meta-analysis (MBMA) is increasingly used in drug development to inform decision-making and future trial designs, through the use of complex dose and/or time course models. Network meta-analysis (NMA) is increasingly being used by reimbursement agencies to estimate a set of coherent relative treatment effects for multiple treatments that respect the randomization within the trials. However, NMAs typically either consider different doses completely independently or lump them together, with few examples of models for dose. We propose a framework, model-based network meta-analysis (MBNMA), that combines both approaches, that respects randomization, and allows estimation and prediction for multiple agents and a range of doses, using plausible physiological dose-response models. We illustrate our approach with an example comparing the efficacies of triptans for migraine relief. This uses a binary endpoint, although we note that the model can be easily modified for other outcome types.
| S-EPMC4999602 | biostudies-literature
Project description:Gene expression analysis is often used to investigate the molecular and functional underpinnings of a phenotype. However, differential expression of individual genes is limited in that it does not consider how the genes interact with each other in networks. To address this shortcoming we propose a number of network-based analyses that give additional functional insights into the studied process. These were applied to a dataset of sex-specific gene expression in the chicken gonad and brain at different developmental stages. We first constructed a global chicken interaction network. Combining the network with the expression data showed that most sex-biased genes tend to have lower network connectivity, that is, act within local network environments, although some interesting exceptions were found. Genes of the same sex bias were generally more strongly connected with each other than expected. We further studied the fates of duplicated sex-biased genes and found that there is a significant trend to keep the same pattern of sex bias after duplication. We also identified sex-biased modules in the network, which reveal pathways or complexes involved in sex-specific processes. Altogether, this work integrates evolutionary genomics with systems biology in a novel way, offering new insights into the modular nature of sex-biased genes.
| S-EPMC3540752 | biostudies-literature