Cerebral Spinal Fluid Volumetrics and Paralimbic Predictors of Executive Dysfunction in Congenital Heart Disease: A Machine Learning Approach Informing Mechanistic Insights.

The relationship between increased cerebral spinal fluid (CSF) ventricular compartments, structural and microstructural dysmaturation, and executive function in patients with congenital heart disease (CHD) is unknown. Here, we leverage a novel machine-learning data-driven technique to delineate interrelationships between CSF ventricular volume, structural and microstructural alterations, clinical risk factors, and sub-domains of executive dysfunction in adolescent CHD patients. We trained random forest regression models to predict measures of executive function (EF) from the NIH Toolbox, the Delis-Kaplan Executive Function System (D-KEFS), and the Behavior Rating Inventory of Executive Function (BRIEF) and across three subdomains of EF - mental flexibility, working memory, and inhibition. We estimated the best parameters for the random forest algorithm via a randomized grid search of parameters using 10-fold cross-validation on the training set only. The best parameters were then used to fit the model on the full training set and validated on the test set. Algorithm performance was measured using root-mean squared-error (RMSE). As predictors, we included patient clinical variables, perioperative clinical measures, microstructural white matter (diffusion tensor imaging- DTI), and structural volumes (volumetric magnetic resonance imaging- MRI). Structural white matter was measured using along-tract diffusivity measures of 13 inter-hemispheric and cortico-association fibers. Structural volumes were measured using FreeSurfer and manual segmentation of key structures. Variable importance was measured by the average Gini-impurity of each feature across all decision trees in which that feature is present in the model, and functional ontology mapping (FOM) was used to measure the degree of overlap in feature importance for each EF subdomain and across subdomains. We found that CSF structural properties (including increased lateral ventricular volume and reduced choroid plexus volumes) in conjunction with proximate cortical projection and paralimbic-related association white matter tracts that straddle the lateral ventricles and distal paralimbic-related subcortical structures (basal ganglia, hippocampus, cerebellum) are predictive of two-specific subdomains of executive dysfunction in CHD patients: cognitive flexibility and inhibition. These findings in conjunction with combined RF models that incorporated clinical risk factors, highlighted important clinical risk factors, including the presence of microbleeds, altered vessel volume, and delayed PDA closure, suggesting that CSF-interstitial fluid clearance, vascular pulsatility, and glymphatic microfluid dynamics may be pathways that are impaired in CHD, providing mechanistic information about the relationship between CSF and executive dysfunction.

Excessive concentrations of kinase inhibitors in translational studies impede effective drug repurposing.

Drug repositioning seeks to leverage existing clinical knowledge to identify alternative clinical settings for approved drugs. However, repositioning efforts fail to demonstrate improved success rates in late-stage clinical trials. Focusing on 11 approved kinase inhibitors that have been evaluated in 139 repositioning hypotheses, we use data mining to characterize the state of clinical repurposing. Then, using a simple experimental correction with human serum proteins in in vitro pharmacodynamic assays, we develop a measurement of a drug's effective exposure. We show that this metric is remarkably predictive of clinical activity for a panel of five kinase inhibitors across 23 drug variant targets in leukemia. We then validate our model's performance in six other kinase inhibitors for two types of solid tumors: non-small cell lung cancer (NSCLC) and gastrointestinal stromal tumors (GISTs). Our approach presents a straightforward strategy to use existing clinical information and experimental systems to decrease the clinical failure rate in drug repurposing studies.

Genomic and experimental evidence that ALKATI does not predict single agent sensitivity to ALK inhibitors.

Genomic data can facilitate personalized treatment decisions by enabling therapeutic hypotheses in individual patients. Mutual exclusivity has been an empirically useful signal for identifying activating mutations that respond to single agent targeted therapies. However, a low mutation frequency can underpower this signal for rare variants. We develop a resampling based method for the direct pairwise comparison of conditional selection between sets of gene pairs. We apply this method to a transcript variant of anaplastic lymphoma kinase (ALK) in melanoma, termed ALKATI that was suggested to predict sensitivity to ALK inhibitors and we find that it is not mutually exclusive with key melanoma oncogenes. Furthermore, we find that ALKATI is not likely to be sufficient for cellular transformation or growth, and it does not predict single agent therapeutic dependency. Our work strongly disfavors the role of ALKATI as a targetable oncogenic driver that might be sensitive to single agent ALK treatment.