Morphing projections: a new visual technique for fast and interactive large-scale analysis of biomedical datasets

Abstract

Motivation Biomedical research entails analyzing high dimensional records of biomedical features with hundreds or thousands of samples each. This often involves using also complementary clinical metadata, as well as a broad user domain knowledge. Common data analytics software makes use of machine learning algorithms or data visualization tools. However, they are frequently one-way analyses, providing little room for the user to reconfigure the steps in light of the observed results. In other cases, reconfigurations involve large latencies, requiring a retraining of algorithms or a large pipeline of actions. The complex and multiway nature of the problem, nonetheless, suggests that user interaction feedback is a key element to boost the cognitive process of analysis, and must be both broad and fluid. Results In this paper we present a technique for biomedical data analytics, based on blending meaningful views in an efficient manner, allowing to provide a natural smooth way to transition among different but complementary representations of data and knowledge. Our hypothesis is that the confluence of diverse complementary information from different domains on a highly interactive interface allows the user to discover relevant relationships or generate new hypotheses to be investigated by other means. We illustrate the potential of this approach with two case studies involving gene expression data and clinical metadata, as representative examples of high dimensional, multidomain, biomedical data. Availability and implementation Code and demo app to reproduce the results available at https://gitlab.com/idiazblanco/morphing-projections-demo-and-dataset-preparation

Differential HIF2α Protein Expression in Human Carotid Body and Adrenal Medulla under Physiologic and Tumorigenic Conditions

“…For HNPGL, we used published microarray data obtained with the Affymetrix GeneChip Human Genome U133 Plus 2.0 Arrays [ 21 ]. See [ 28 , 29 , 30 , 31 ] and Appendix A for details on gene expression analysis.…”

“…In the setup for gene expression analysis, is set to 2, resulting in a 2D scatter plot where each point represents a biological sample defined by a large number of gene expression attributes, and two close points in the visual map correspond to biological samples with similar gene expression patterns. Part of the data analysis pipeline was carried out using a visual analytics tool featuring the Morphing Projections (MP) technique [ 31 ]. MP allowed smooth switching between different 2D scatterplots of the samples, with spatial arrangements based on different criteria.…”

“…Part of the data analysis pipeline was carried out using a visual analytics tool featuring the Morphing Projections (MP) technique [ 31 ]. MP allowed smooth switching between different 2D scatterplots of the samples, with spatial arrangements based on different criteria.…”

Interactive visual analytics for medical data: application to COVID-19 clinical information during the first wave

“…As a main interactive visualization approach, we used the morphing projections (MP) technique [1]. MP is based on linearly mixing two or more meaningful views, resulting into smooth transitions among different but complementary representations of data and knowledge.…”

“…Recently, a highly interactive approach for biomedical data analysis called Morphing Projections (MP) was proposed [1], that proved to be useful to discover useful knowledge by cross-analyzing genomic and clinical data. In this paper, we propose the application of the MP approach, including time series dimensionality reduction, to carry out a comprehensive analysis of a large public dataset "Covid Data Saves Lives" with a large amount of time-referenced COVID-19 biomedical data.…”