A NETWORK OF MOLECULAR AND FUNCTIONAL INTERACTIONS TO ANALYSE GEMMA OMICS DATASETS

A NETWORK OF MOLECULAR AND FUNCTIONAL INTERACTIONS TO ANALYSE GEMMA OMICS DATASETS

We developed a pipeline to assess the performance of GEMMA biomarkers in distinguishing children with ASD from neurotypical children. Given a list of biomarkers and a series of third-party features-by-subjects datasets, the pipeline provides methods for data pre-processing. Subsequently, it uses machine learning models (neural networks, random forests, support vector machines) to test the performance of the biomarkers in distinguishing ASD vs controls on each dataset.