Originally designed application in the context of resource-limited plant research and breeding programs, waves provides an open-source solution to spectral data processing and model development by bringing useful packages together into a streamlined pipeline. This package is wrapper for functions related to the analysis of point visible and near-infrared reflectance measurements. It includes visualization, filtering, aggregation, pretreatment, cross-validation set formation, model training, and prediction functions to enable open-source association of spectral and reference data.
Please note: function names were updated as of version 0.2.0. Old function names still work in this version but will be retired in upcoming package versions.
This package is documented in a peer-reviewed manuscript in the Plant Phenome Journal. Please cite the manuscript if you have found this package to be useful!
Hershberger, J, Morales, N, Simoes, CC, Ellerbrock, B, Bauchet, G, Mueller, LA, Gore MA. Making waves in Breedbase: An integrated spectral data storage and analysis pipeline for plant breeding programs. Plant Phenome J. 2021; 4:e20012. https://doi.org/10.1002/ppj2.20012
Follow the installation instructions below, and then go wild! Use waves to analyze your own data. Please report any bugs or feature requests by opening issues in this repository.
More detailed examples can be found in the package vignette. The vignette can also be found by running the following:
vignette("waves")Install the latest waves release directly from CRAN:
install.packages("waves")Alternatively, install the development version to get the most up-to-date (but not necessarily thoroughly tested) version:
# install.packages("devtools")
devtools::install_github("GoreLab/waves")-
Format your data. Match spectra with reference values so that you have a dataframe with unique identifiers, reference values, and other metadata as columns to the left of spectral values. Spectral column names should start with "X".
-
Visualize and filter spectra using
plot_spectra()andfilter_spectra(). -
If you have more than one scan per unique identifier, aggregate the scans by mean or median with
aggregate_spectra(). -
Use
test_spectra()to perform spectral pretreatment, cross-validation set formation, and model training functions over multiple iterations.- Applies any of 12 combinations of spectral pretreatment methods using
pretreat_spectra(). - Determines cross-validation scheme with
format_cv(). Choose from random, stratified random, or a plant breeding-specific scheme from Jarquín et al., 2017. The Plant Genome. - Trains spectral prediction models using
train_spectra().- Choose from partial least squares regression, random forest, and support vector machine algorithms
- Uses k-fold cross validation within the training set to tune model hyperparameters
- Outputs model performance statistics (RMSE, R2, Bias, etc.) as assessed with test set
- Applies any of 12 combinations of spectral pretreatment methods using
-
Save trained prediction models with
save_model().- Intended for a production environment
- Can evaluate spectral pretreatment methods using the input dataset
- Selects best model using the metric provided (RMSE or R2)
- Returns trained model with option to save as .Rds object
-
Predict phenotypic values with new spectra and a saved model using
predict_spectra().
The package comes with an example dataset (ikeogu.2017) from Ikeogu et al. (2017) PLoS ONE that can be used to try out package capabilities. This dataset includes vis-NIR spectra from cassava roots as well as two reference phenotypes:
- Root dry matter content as measured by the oven method for the four studies included in the example dataset
- Total carotenoid content as measured by HPLC