Bioinformatics.org
|
|
Research
|
Online databases
Online analysis tools
Online education tools
|
Development
|
|
Forums
|
News & Commentary
Jobs Forum (Career Center)
|
|
Epistatic MAP Imputation - Summary
|
|
|
|
All categories :: bioinformatics software development :: Epistatic MAP Imputation Epistatic MAPs(E-MAP) are a high-throughput approach capable of quantifying aggravating or alleviating genetic interactions between gene pairs. This project contains applications for imputing / predicting missing values in E-MAP datasets.
Public areas
|
This project has many places for you to explore and participate. The icons displayed below are also available at the top of the page for easy navigation.
Project homepage
This home page points to the official page for this project, which may or may not be hosted at Bioinformatics.org.
Public forums
There are 2 messages in
2 forums.
Project manager
There are 0 open, public tasks, 0 total.
Support tickets
There are 0
open tickets, 0 total.
Mailing lists
There are 0 public mailing lists.
Public surveys
There are 0 active surveys.
SCM repository
The SCM repository is a place for this project to store its source code. Members have access to change this master repository, while anonymous users may browse the most recent development version of this project.
Instructions
Download directory
Projects may choose to have files other than their main releases available via this directory.
|
|
Latest announcements
|
We are pleased to announce the first version of our imputation tools to be hosted on bioinformatics.org
Epistatic MAPs (E-MAP) are a high-throughput approach capable of quantifying aggravating or alleviating genetic interactions between gene pairs. This project contains applications for imputing / predicting missing values in E-MAP datasets.
A notable addition to this release (v 1.1) is a tool for performing K fold cross validation, which allows users to estimate the accuracy of imputation on a given dataset.
This functions by partitioning the present interactions into ten equally sized folds. Imputation is then performed ten times, with the interactions from one fold hidden in each run. These artificially introduced missing values allow us to estimate the accuracy of the the imputation.
|
|
|
|
|