Exploring Neural Networks and Related Visualization Techniques in Gene Expression Data.
Ontology highlight
ABSTRACT:
SUBMITTER: Wilentzik Muller R
PROVIDER: S-EPMC7243731 | biostudies-literature | 2020
REPOSITORIES: biostudies-literature
Publications
Exploring Neural Networks and Related Visualization Techniques in Gene Expression Data.
Wilentzik Müller Roni R Gat-Viks Irit I
Frontiers in genetics 20200515
Over the past decade, neural networks have become one of the cutting-edge methods in various research fields, outshining specifically in complex classification problems. In this paper, we propose two main contributions: first, we conduct a methodological study of neural network modeling for classifying biological traits based on structured gene expression data. Then, we suggest an innovative approach for utilizing deep learning visualization techniques in order to reveal the specific genes impor ...[more]
Similar Datasets
Project description:BackgroundVisualization of DNA microarray data in two or three dimensional spaces is an important exploratory analysis step in order to detect quality issues or to generate new hypotheses. Principal Component Analysis (PCA) is a widely used linear method to define the mapping between the high-dimensional data and its low-dimensional representation. During the last decade, many new nonlinear methods for dimension reduction have been proposed, but it is still unclear how well these methods capture the underlying structure of microarray gene expression data. In this study, we assessed the performance of the PCA approach and of six nonlinear dimension reduction methods, namely Kernel PCA, Locally Linear Embedding, Isomap, Diffusion Maps, Laplacian Eigenmaps and Maximum Variance Unfolding, in terms of visualization of microarray data.ResultsA systematic benchmark, consisting of Support Vector Machine classification, cluster validation and noise evaluations was applied to ten microarray and several simulated datasets. Significant differences between PCA and most of the nonlinear methods were observed in two and three dimensional target spaces. With an increasing number of dimensions and an increasing number of differentially expressed genes, all methods showed similar performance. PCA and Diffusion Maps responded less sensitive to noise than the other nonlinear methods.ConclusionsLocally Linear Embedding and Isomap showed a superior performance on all datasets. In very low-dimensional representations and with few differentially expressed genes, these two methods preserve more of the underlying structure of the data than PCA, and thus are favorable alternatives for the visualization of microarray data.
| S-EPMC2998530 | biostudies-literature
Project description:Visualization algorithms are fundamental tools for interpreting single-cell data. However, standard methods, such as t-stochastic neighbor embedding (t-SNE), are not scalable to datasets with millions of cells and the resulting visualizations cannot be generalized to analyze new datasets. Here we introduce net-SNE, a generalizable visualization approach that trains a neural network to learn a mapping function from high-dimensional single-cell gene-expression profiles to a low-dimensional visualization. We benchmark net-SNE on 13 different datasets, and show that it achieves visualization quality and clustering accuracy comparable with t-SNE. Additionally we show that the mapping function learned by net-SNE can accurately position entire new subtypes of cells from previously unseen datasets and can also be used to reduce the runtime of visualizing 1.3 million cells by 36-fold (from 1.5 days to an hour). Our work provides a framework for bootstrapping single-cell analysis from existing datasets.
| S-EPMC6469860 | biostudies-literature
Project description:Prompt diagnostics and appropriate cancer therapy necessitate the use of gene expression databases. The integration of analytical methods can enhance detection precision by capturing intricate patterns and subtle connections in the data. This study proposes a diagnostic-integrated approach combining Empirical Bayes Harmonization (EBS), Jensen-Shannon Divergence (JSD), deep learning, and contour mathematics for cancer detection using gene expression data. EBS preprocesses the gene expression data, while JSD measures the distributional differences between cancerous and non-cancerous samples, providing invaluable insights into gene expression patterns. Deep learning (DL) models are employed for automatic deep feature extraction and to discern complex patterns from the data. Contour mathematics is applied to visualize decision boundaries and regions in the high-dimensional feature space. JSD imparts significant information to the deep learning model, directing it to concentrate on pertinent features associated with cancerous samples. Contour visualization elucidates the model's decision-making process, bolstering interpretability. The amalgamation of JSD, deep learning, and contour mathematics in gene expression dataset analysis diagnostics presents a promising pathway for precise cancer detection. This method taps into the prowess of deep learning for feature extraction while employing JSD to pinpoint distributional differences and contour mathematics for visual elucidation. The outcomes underscore its potential as a formidable instrument for cancer detection, furnishing crucial insights for timely diagnostics and tailor-made treatment strategies.
| S-EPMC10670706 | biostudies-literature
Project description:Precision medicine in oncology aims at obtaining data from heterogeneous sources to have a precise estimation of a given patient's state and prognosis. With the purpose of advancing to personalized medicine framework, accurate diagnoses allow prescription of more effective treatments adapted to the specificities of each individual case. In the last years, next-generation sequencing has impelled cancer research by providing physicians with an overwhelming amount of gene-expression data from RNA-seq high-throughput platforms. In this scenario, data mining and machine learning techniques have widely contribute to gene-expression data analysis by supplying computational models to supporting decision-making on real-world data. Nevertheless, existing public gene-expression databases are characterized by the unfavorable imbalance between the huge number of genes (in the order of tenths of thousands) and the small number of samples (in the order of a few hundreds) available. Despite diverse feature selection and extraction strategies have been traditionally applied to surpass derived over-fitting issues, the efficacy of standard machine learning pipelines is far from being satisfactory for the prediction of relevant clinical outcomes like follow-up end-points or patient's survival. Using the public Pan-Cancer dataset, in this study we pre-train convolutional neural network architectures for survival prediction on a subset composed of thousands of gene-expression samples from thirty-one tumor types. The resulting architectures are subsequently fine-tuned to predict lung cancer progression-free interval. The application of convolutional networks to gene-expression data has many limitations, derived from the unstructured nature of these data. In this work we propose a methodology to rearrange RNA-seq data by transforming RNA-seq samples into gene-expression images, from which convolutional networks can extract high-level features. As an additional objective, we investigate whether leveraging the information extracted from other tumor-type samples contributes to the extraction of high-level features that improve lung cancer progression prediction, compared to other machine learning approaches.
| S-EPMC7098575 | biostudies-literature
Project description:Forecasting floods encompasses significant complexity due to the nonlinear nature of hydrological systems, which involve intricate interactions among precipitation, landscapes, river systems, and hydrological networks. Recent efforts in hydrology have aimed at predicting water flow, floods, and quality, yet most methodologies overlook the influence of adjacent areas and lack advanced visualization for water level assessment. Our contribution is two-fold: firstly, we introduce a graph neural network model (LocalFLoodNet) equipped with a graph learning module to capture the interconnections of water systems and the connectivity between stations to predict future water levels. Secondly, we develop a simulation prototype offering visual insights for decision-making in disaster prevention and policy-making. This prototype visualizes predicted water levels and facilitates data analysis using decades of historical information. Focusing on the Greater Montreal Area (GMA), particularly Terrebonne, Quebec, Canada, we apply LocalFLoodNet and prototype to demonstrate a comprehensive method for assessing flood impacts. By utilizing a digital twin of Terrebonne, our simulation tool allows users to interactively modify the landscape and simulate various flood scenarios, thereby providing valuable insights into preventive strategies. This research aims to enhance water level prediction and evaluation of preventive measures, setting a benchmark for similar applications across different geographic areas.
| S-EPMC11316733 | biostudies-literature
Project description:Supervised neural networks have been applied as a machine learning technique to identify and predict emergent patterns among multiple variables. A common criticism of these methods is the inability to characterize relationships among variables from a fitted model. Although several techniques have been proposed to "illuminate the black box", they have not been made available in an open-source programming environment. This article describes the NeuralNetTools package that can be used for the interpretation of supervised neural network models created in R. Functions in the package can be used to visualize a model using a neural network interpretation diagram, evaluate variable importance by disaggregating the model weights, and perform a sensitivity analysis of the response variables to changes in the input variables. Methods are provided for objects from many of the common neural network packages in R, including caret, neuralnet, nnet, and RSNNS. The article provides a brief overview of the theoretical foundation of neural networks, a description of the package structure and functions, and an applied example to provide a context for model development with NeuralNetTools. Overall, the package provides a toolset for neural networks that complements existing quantitative techniques for data-intensive exploration.
| S-EPMC6262849 | biostudies-literature
Project description:To evaluate ease of use and usefulness for nurses of visualizations of infectious disease transmission in a hospital.An observational study was used to evaluate perceptions of several visualizations of data extracted from electronic health records designed using a participatory approach. Twelve nurses in the master's program in an urban research-intensive nursing school participated in May 2015.A convergent parallel mixed method was used to evaluate nurses' perceptions on ease of use and usefulness of five visualization conveying trends in hospital infection transmission applying think-aloud, interview, and eye-tracking techniques.Subjective data from the interview and think-aloud techniques indicated that participants preferred the traditional line graphs in simple data representation due to their familiarity, clarity, and easiness to read. An objective quantitative measure of eye movement analysis (444,421 gaze events) identified a high degree of participants' attention span in infographics in all three scenarios. All participants responded with the correct answer within 1 min in comprehensive tests.A user-centric approach was effective in developing and evaluating visualizations for hospital infection transmission. For the visualizations designed by the users, the participants were easily able to comprehend the infection visualizations on both line graphs and infographics for simple visualization. The findings from the objective comprehension test and eye movement and subjective attitudes support the feasibility of integrating user-centric visualization designs into electronic health records, which may inspire clinicians to be mindful of hospital infection transmission. Future studies are needed to investigate visualizations and motivation, and the effectiveness of visualization on infection rate.This study designed visualization images using clinical data from electronic health records applying a user-centric approach. The design insights can be applied for visualizing patient data in electronic health records.
| S-EPMC4939395 | biostudies-literature
Project description:The empirical phase diagram (EPD) is a colored representation of overall structural integrity and conformational stability of macromolecules in response to various environmental perturbations. Numerous proteins and macromolecular complexes have been analyzed by EPDs to summarize results from large data sets from multiple biophysical techniques. The current EPD method suffers from a number of deficiencies including lack of a meaningful relationship between color and actual molecular features, difficulties in identifying contributions from individual techniques, and a limited ability to be interpreted by color-blind individuals. In this work, three improved data visualization approaches are proposed as techniques complementary to the EPD. The secondary, tertiary, and quaternary structural changes of multiple proteins as a function of environmental stress were first measured using circular dichroism, intrinsic fluorescence spectroscopy, and static light scattering, respectively. Data sets were then visualized as (1) RGB colors using three-index EPDs, (2) equiangular polygons using radar charts, and (3) human facial features using Chernoff face diagrams. Data as a function of temperature and pH for bovine serum albumin, aldolase, and chymotrypsin as well as candidate protein vaccine antigens including a serine threonine kinase protein (SP1732) and surface antigen A (SP1650) from S. pneumoniae and hemagglutinin from an H1N1 influenza virus are used to illustrate the advantages and disadvantages of each type of data visualization technique.
| S-EPMC3526995 | biostudies-literature
Project description:BackgroundDNA methylation is a major mechanism involved in the epigenetic state of a cell. It has been observed that the methylation status of certain CpG sites close to or within a gene can directly affect its expression, either by silencing or, in some cases, up-regulating transcription. However, a vertebrate genome contains millions of CpG sites, all of which are potential targets for methylation, and the specific effects of most sites have not been characterized to date. To study the complex interplay between methylation status, cellular programs, and the resulting phenotypes, we present PiiL, an interactive gene expression pathway browser, facilitating analyses through an integrated view of methylation and expression on multiple levels.ResultsPiiL allows for specific hypothesis testing by quickly assessing pathways or gene networks, where the data is projected onto pathways that can be downloaded directly from the online KEGG database. PiiL provides a comprehensive set of analysis features that allow for quick and specific pattern searches. Individual CpG sites and their impact on host gene expression, as well as the impact on other genes present in the regulatory network, can be examined. To exemplify the power of this approach, we analyzed two types of brain tumors, Glioblastoma multiform and lower grade gliomas.ConclusionAt a glance, we could confirm earlier findings that the predominant methylation and expression patterns separate perfectly by mutations in the IDH genes, rather than by histology. We could also infer the IDH mutation status for samples for which the genotype was not known. By applying different filtering methods, we show that a subset of CpG sites exhibits consistent methylation patterns, and that the status of sites affect the expression of key regulator genes, as well as other genes located downstream in the same pathways. PiiL is implemented in Java with focus on a user-friendly graphical interface. The source code is available under the GPL license from https://github.com/behroozt/PiiL.git .
| S-EPMC5541427 | biostudies-literature
Project description:Gene expression profiles of clinical cohorts can be used to identify genes that are correlated with a clinical variable of interest such as patient outcome or response to a particular drug. However, expression measurements are susceptible to technical bias caused by variation in extraneous factors such as RNA quality and array hybridization conditions. If such technical bias is correlated with the clinical variable of interest, the likelihood of identifying false positive genes is increased. Here we describe a method to visualize an expression matrix as a projection of all genes onto a plane defined by a clinical variable and a technical nuisance variable. The resulting plot indicates the extent to which each gene is correlated with the clinical variable or the technical variable. We demonstrate this method by applying it to three clinical trial microarray data sets, one of which identified genes that may have been driven by a confounding technical variable. This approach can be used as a quality control step to identify data sets that are likely to yield false positive results.
| S-EPMC3628873 | biostudies-literature