Machine Learning Methods Predict Locomotor Response to MK-801 in Mouse Models of Down Syndrome

Down syndrome (DS), caused by trisomy of human chromosome 21 (HSA21), is a common genetic cause of cognitive impairment. This disorder results from the overexpression of HSA21 genes and the resulting perturbations in many molecular pathways and cellular processes. Knowledge-based identification of targets for pharmacotherapies will require defining the most critical protein abnormalities among these many perturbations. Here the authors show that using the Ts65Dn and Ts1Cje mouse models of DS, which are trisomic for 88 and 69 reference protein coding genes, respectively, a simple linear Naive Bayes classifier successfully predicts behavioral outcome (level of locomotor activity) in response to treatment with the N-methyl-D-aspartate (NMDA) receptor antagonist MK-801. Input to the Naive Bayes method were simple protein profiles generated from cortex and output was locomotor activity binned into three levels: low, medium, and high. When Feature Selection was used with the Naive Bayes method, levels of three HSA21 and two non-HSA21 protein features were identified as making the most significant contributions to activity level. Using these five features, accuracies of up to 88% in prediction of locomotor activity were achieved. These predictions depend not only on genotype-specific differences but also on within-genotype individual variation in levels of molecular and behavioral parameters. With judicious choice of pathways and components, a similar approach may be useful in analysis of more complex behaviors, including those associated with learning and memory, and may facilitate identification of novel targets for pharmacotherapeutics.