Towards Faster Gene Expression Prediction via Dimensionality Reduction and Feature Selection.

The majority of genes have a genetic component to their expression. Elastic nets have been shown effective at predicting tissue-specific, individual-level gene expression from genotype data. We apply principal component analysis (PCA), linkage disequilibrium pruning, or the combination of the two to reduce, or generate, a lower-dimensional representation of the genetic variants used as inputs to the elastic net models for the prediction of gene expression. Our results show that, in general, elastic nets attain their best performance when all genetic variants are included as inputs; however, a relatively low number of principal components can effectively summarize the majority of genetic variation while reducing the overall computation time. Specifically, 100 principal components reduce the computational time of the models by over 80% with only an 8% loss in R2. Finally, linkage disequilibrium pruning does not effectively reduce the genetic variants for predicting gene expression. As predictive models are commonly made for over 27,000 genes for more than 50 tissues, PCA may provide an effective method for reducing the computational burden of gene expression analysis.

Cdc42 prevents precocious Rho1 activation during cytokinesis in a Pak1-dependent manner.

During cytokinesis, a series of coordinated events partition a dividing cell. Accurate regulation of cytokinesis is essential for proliferation and genome integrity. In fission yeast, these coordinated events ensure that the actomyosin ring and septum start ingressing only after chromosome segregation. How cytokinetic events are coordinated remains unclear. The GTPase Cdc42 promotes recruitment of certain cell wall-building enzymes whereas the GTPase Rho1 activates these enzymes. We show that Cdc42 prevents early Rho1 activation during fission yeast cytokinesis. Using an active Rho probe, we find that although the Rho1 activators Rgf1 and Rgf3 localize to the division site in early anaphase, Rho1 is not activated until late anaphase, just before the onset of ring constriction. We find that loss of Cdc42 activation enables precocious Rho1 activation in early anaphase. Furthermore, we provide functional and genetic evidence that Cdc42-dependent Rho1 inhibition is mediated by the Cdc42 target Pak1 kinase. Our work proposes a mechanism of Rho1 regulation by active Cdc42 to coordinate timely septum formation and cytokinesis fidelity.

Adapting Random Forests to Predict Obesity-Associated Gene Expression.

Random forests (RFs) are effective at predicting gene expression from genotype data. However, a comparison of RF regressors and classifiers, including feature selection and encoding, has been under-explored in the context of gene expression prediction. Specifically, we examine the role of ordinal or one-hot encoding and of data balancing via oversam-pling in the prediction of obesity-associated gene expression. Our work shows that RFs compete with PrediXcan in the prediction of obesity-associated gene expression in subcutaneous adipose tissue, a highly relevant tissue to obesity. Additionally, RFs generate predictions for obesity-associated genes where PrediXcan fails to do so.

Evaluating the Fitness-to-Drive Using Evoked Visual Responses in Alzheimer's Disease.

Alzheimer's Disease (AD) is the sixth leading cause of death in the US. AD causes significant disability due to the devastating impact on the patients' day-to-day living activities and their loss of independence. One such day-to-day activity is driving, a complex task that requires attention, concentration, the ability to follow particular steps, react to stimuli promptly, and the ability to perceive and interpret visual-spatial information, all of which can be impaired in AD. Therefore, to ensure the safety of AD patients and other drivers, it is important to develop accurate and low-cost diagnostic tools to assess patients' fitness-to-drive. In this study, we develop machine learning (ML) models to predict fitness-to-drive using the electroencephalogram (EEG) technique of event-related potential (ERP). Specifically, we develop random forest (RF) models using EEG signals in early-stage AD patients and age-matched controls and conduct numerical experiments to predict fitness-to-drive and other driving performance metrics, collected from driving simulator data. Our results show that RF models predict patients' fitness-to-drive with AUC=0.83 and provide accurate measures of other driving performance metrics. Therefore, ML and ERP offer a valuable approach to assess driving safety for patients with early AD symptoms in the laboratory setting.

A novel interplay between GEFs orchestrates Cdc42 activity during cell polarity and cytokinesis in fission yeast.

Cdc42, a conserved regulator of cell polarity, is activated by two GEFs, Gef1 and Scd1, in fission yeast. Why the cell needs two GEFs is unclear, given that they are partially redundant and activate the same GTPase. Using the GEF localization pattern during cytokinesis as a paradigm, we report a novel interplay between Gef1 and Scd1 that spatially modulates Cdc42. We find that Gef1 promotes Scd1 localization to the division site during cytokinesis through recruitment of the scaffold protein Scd2, via a Cdc42 feedforward pathway. Similarly, during interphase Gef1 promotes Scd1 recruitment at the new end to enable the transition from monopolar to bipolar growth. Reciprocally, Scd1 restricts Gef1 localization to prevent ectopic Cdc42 activation during cytokinesis to promote cell separation, and to maintain cell shape during interphase. Our findings reveal an elegant regulatory pattern in which Gef1 primes Cdc42 activation at new sites to initiate Scd1-dependent polarized growth, while Scd1 restricts Gef1 to sites of polarization. We propose that crosstalk between GEFs is a conserved mechanism that orchestrates Cdc42 activation during complex cellular processes.This article has an associated First Person interview with the first author of the paper.