Back

Omics BioAnalytics: Reproducible Research using R Shiny and Alexa

Singh, A.; Tebbutt, S. J.; McManus, B. M.

2020-05-07 bioinformatics
10.1101/2020.05.05.024323 bioRxiv
Show abstract

SummaryHigh-throughput technologies produce complex high-dimensional datasets which are analyzed using a variety of ever-evolving bioinformatics tools. Well-designed web frameworks enable more intuitive and efficient analysis such that less time is spent on coding and more time is spent on interpretation of results and addressing insightful biological questions aided by interactive visualizations. Here, we present Omics BioAnalytics, a full-service Web framework that enables comprehensive, multi-level characterization, analysis, and integration of omics datasets. Blending web-based (R Shiny) and voice-based (Amazons Alexa) analytics, Omics BioAnalytics can be used both by expert computational biologists and non-coding biological domain experts, alike. Our web framework can be utilized to explore complex datasets and identify biosignatures and discriminative biomarkers of health and disease processes, and generate testable hypotheses relating to underlying molecular mechanisms. AvailabilityOmics BioAnalytics is freely available at https://github.com/singha53/omicsBioAnalytics and the web app is deployed at https://amritsingh.shinyapps.io/omicsBioAnalytics/. The source code for the companion Alexa Skill can be found at https://github.com/singha53/omics-bioanalytics-alexa-skill.

Matching journals

The top 2 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.