runGenphenSaap(genotype, phenotype, technique, fold.cv, boots)Using these two data types, it quantifies the association between each SAAP and the phenotype. SAAPs are more complex than SNPs because they may be composed of more than two genetic states, i.e. more than two types of amino acid states, whereas SNPs are exclusively composed of only two genetics states, i.e. two nucleotide states. To compute the association between a SAAP and a phenotype, the SAAP is first deconstructed into its amino acid substitution pairs. Following the deconstruction of a SAAP, the procedure computes the association between each amino acid substitution pair and the phenotype with respect to the two metics ``effect size'' and ``classification accuracy''.
The effect size of an amino acid substitution pair is estimated by computing the Cohen's d statistics (Cohen 1988). The 95% confidence intervals are computed as well. The effect size quantifies the phenotypic effect of substituting one amino acid state for the other at the specific SAAP site. Substitution pairs characterized with a substantial effect size and tight confidence intervals which do not include the null effect are to be prioritized.
Classification accuracy is the second metric which is computed using statistical learning techniques. This is the metric which is used to quantify the strength of the association between an amino acid substitution pair and a phenotype. The idea is to use either linear suppport vector machines or random forests to build a classification model between the phenotype vector and the substitution pair vector. The more accurate the model, the easier we can predict the two states of the substitution pair from the phenotype and hence the stronger is the mutual association between the two vectors. In order to obtain a robust classification accuracy measure, the classification analysis is done in a bootstrapping fashion. First a subset of the substitution- phenotype vectors is randomly selected to train a classifier, while the remaining data is used to test the classifier. This step is repeated multiple times after which the classification accuracies of all the classifiers are averaged into a single classification accuracy measure and the corresponding confidence intervals are computed.
In order to validate the classification accuracy, the tool also computes the Cohen's kappa statistics (Cohen 1960) which compares the observed classification accuracy with the expected classification accuracy. If the expected and observed classification accuracies are in concordance, the computed association can be taken seriously, otherwise it can be discarded as noise.
Cohen, J. (1960) A coefficient of agreement for nominal scales.
data(genotype.saap)
#or data(genotype.saap.msa) in this case you cannot subset genotype.saap[, 1:3]
data(phenotype.saap)
genphen.results <- runGenphenSaap(genotype = genotype.saap[, 1:3],
phenotype = phenotype.saap, technique = "svm", fold.cv = 0.66, boots = 100)
Run the code above in your browser using DataLab