Title: Random forest classifier performance differentiating premutation carrier mothers of individuals with FXS from mothers of individuals with autism spectrum disorders.
Legend: (A) Receiver operating characteristic (ROC) curves for classifiers using three different profiles of FX premutation carriers and the comparison group. ROC curves provide a comprehensive visualization to summarize accuracy of prediction methods. The diagram shows a test’s false-positive rate (FPR), or 1 – specificity versus its sensitivity. Cognitive profile has the worst diagnostic utility, and our proposed profile has shown the best performance. (B) F1 score measures the test’s accuracy. It considers both precision and recall. As the F1 score approaches 1, the test has better accuracy. The proposed profile has F1 score equal to 0.81, which indicates the best performance among the tested profiles.
Citation: Movaghar, A., Mailick, M., Sterling, A., Greenberg, J., & Saha, K. (2017). Automated screening for Fragile X premutation carriers based on linguistic and cognitive computational phenotypes. Scientific Reports, 7(1), 2674. https://doi.org/10.1038/s41598-017-02682-4
Abstract: Millions of people globally are at high risk for neurodegenerative disorders, infertility or having children with a disability as a result of the Fragile X (FX) premutation, a genetic abnormality in FMR1 that is underdiagnosed. Despite the high prevalence of the FX premutation and its effect on public health and family planning, most FX premutation carriers are unaware of their condition. Since genetic testing for the premutation is resource intensive, it is not practical to screen individuals for FX premutation status using genetic testing. In a novel approach to phenotyping, we have utilized audio recordings and cognitive profiling assessed via self-administered questionnaires on 200 females. Machine-learning methods were developed to discriminate FX premutation carriers from mothers of children with autism spectrum disorders, the comparison group. By using a random forest classifier, FX premutation carriers could be identified in an automated fashion with high precision and recall (0.81 F1 score). Linguistic and cognitive phenotypes that were highly associated with FX premutation carriers were high language dysfluency, poor ability to organize material, and low self-monitoring. Our framework sets the foundation for computational phenotyping strategies to pre-screen large populations for this genetic variant with nominal costs.
About the Lab: Saha Lab is affiliated with several multi-disciplinary centers including the Waisman Center, Wisconsin Institute for Discovery and the Stem Cell and Regenerative Medicine Center at UW-Madison. Our research dedicated to using human stem cells together with emerging engineering methods in material science and synthetic biology to make smarter therapeutics, model human disease, and advance personalized medicine. As a part of our effort to develop new prognosis and diagnosis tools together with Audra Sterling, Jan Greenberg and Marsha Mailick of the Waisman Center, we investigate methods that can improve our understanding of the genotype-phenotype correlation between various genes and the outcomes such as linguistic and cognitive phenotypes.