Population Assignment using Genetic, Non-Genetic or Integrated Data in a Machine Learning Framework

Use Monte-Carlo and K-fold cross-validation coupled with machine-learning classification algorithms to perform population assignment, with functionalities of evaluating discriminatory power of independent training samples, identifying informative loci, reducing data dimensionality for genomic data, integrating genetic and non-genetic data, and visualizing results.

An R package for population assignment using genomic, non-genetic or integrated data in a machine-learning framework

The assignPOP package helps perform population assignment using a machine learning framework. It employs supervised machine learning methods to evaluate the discriminatory power of your known data set, and is capable of analyzing large genetic, non-genetic, or integrated (genetic plus non-genetic) data sets. This framework is also designed for solving the upwardly biased issue that was discussed in previous studies. Other features are listed below.

  • Use principle component analysis (PCA) for dimensionality reduction (or data transformation)
  • Use Monte-Carlo cross-validation to evaluate the variation of assignment accuracy
  • Use K-fold cross-validation to estimate membership probability
  • Allow to resample training individuals with various proportions or numbers
  • Allow to resample training loci with various proportions either randomly or based on locus FST value
  • Provide several machine learning classifiers, including LDA, SVM, naive Bayes, decision tree, and random forest to build tunable predictive models.
  • Output results in publication-quality plots while being editable using ggplot2 library

In your R/Rstudio console,

  • step 1. Install devtools package by entering install.packages("devtools")
  • step 2. Import the library, library(devtools)
  • step 3. Call the function, install_github("alexkychen/assignPOP")

Please visit the following page for more infomration


Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


1.1.3 by Kuan-Yu (Alex) Chen, 5 months ago

https://github.com/alexkychen/assignPOP, http://alexkychen.github.io/assignPOP/

Browse source code at https://github.com/cran/assignPOP

Authors: Kuan-Yu (Alex) Chen [aut, cre], Elizabeth A. Marschall [aut], Michael G. Sovic [aut], Anthony C. Fries [aut], H. Lisle Gibbs [aut], Stuart A. Ludsin [aut]

Documentation:   PDF Manual  

GPL (>= 2) license

Imports caret, doParallel, e1071, foreach, ggplot2, MASS, parallel, randomForest, reshape2, stringr, tree

Suggests gtable, iterators, klaR, stringi, knitr, rmarkdown, testthat

See at CRAN