genequad

GeneQuad summary for GeneRIF using N-Gram Markov Model and other techniques

Goal

The goal of this project is to summarize the function of each gene using four keywords. The source of information to find which words will be used is mainly 'geneRif' (ftp://ftp.ncbi.nih.gov/gene/GeneRIF/generifs_basic.gz). Since this file records almost 500,000 descriptions, some different approaches will need to be tested. This project has been divided into two subprojects GenDex and GeneQuad.

Project Description

Main activities can be seen in the ActivityLog.

Project in Action

Watch the Rails web application made to interface with the data acquired through GeneQuad (http://rails-dev.bioinformatics.northwestern.edu/app-name/genequad) and GenDex (http://rails-dev.bioinformatics.northwestern.edu/app-name/gendex)