Home

Welcome to the gdaphen wiki!

We propose Gdaphen, a fast pipeline allowing the identification of most important predictor qualitative and quantitative variables to discriminate between genotypes, treatments or sex. Taking as input behavioral/clinical data using a multi factor analysis (MFA) to deal with groups of variables recorded from the same individuals or anonymize genotype-based recordings. Gdaphen uses as optimized input the non-correlated variables with 30% correlation or higher on the MFA-PCA, increasing the discriminant power and the classifier’s predictive models efficiency. We are able to determine the variables keener to predict gene dosage changes thanks to the GLM based classifiers or determine the most discriminative not linear distributed variables thanks to RF implementation. Moreover, we provide the efficacy of each classifier and several visualization options to fully understand and support the results as easily readable plots ready to be included in publications. We demonstrate Gdaphen capabilities on several datasets and provide easy followed vignettes.