Explore the vast range of titles available.

The conserved protein UNC-16 (JIP3) inhibits the active transport of some cell soma organelles, such as lysosomes, early endosomes, and Golgi, to the synaptic region of axons. However, little is known about UNC-16’s organelle transport regulatory function, which is distinct from its Kinesin-1 adaptor function. We used an unc-16 suppressor screen in Caenorhabditis elegans to discover that UNC-16 acts through CDK-5 (Cdk5) and two conserved synapse assembly proteins: SAD-1 (SAD-A Kinase), and SYD-2 (Liprin-α). Genetic analysis of all combinations of double and triple mutants in unc-16(+) and unc-16(−) backgrounds showed that the three proteins (CDK-5, SAD-1, and SYD-2) are all part of the same organelle transport regulatory system, which we named the CSS system based on its founder proteins. Further genetic analysis revealed roles for SYD-1 (another synapse assembly protein) and STRADα (a SAD-1-interacting protein) in the CSS system. In an unc-16(−) background, loss of the CSS system improved the sluggish locomotion of unc-16 mutants, inhibited axonal lysosome accumulation, and led to the dynein-dependent accumulation of lysosomes in dendrites. Time-lapse imaging of lysosomes in CSS system mutants in unc-16(+) and unc-16(−) backgrounds revealed active transport defects consistent with the steady-state distributions of lysosomes. UNC-16 also uses the CSS system to regulate the distribution of early endosomes in neurons and, to a lesser extent, Golgi. The data reveal a new and unprecedented role for synapse assembly proteins, acting as part of the newly defined CSS system, in mediating UNC-16’s organelle transport regulatory function.

Rising antibiotic resistance rates pose a serious public health threat and are largely driven by overuse and inappropriate use of antibiotics. Antibiotic stewardship efforts have been established around the world to improve prescription practices, but further optimization of antibiotic usage is still needed. Improvement is particularly necessary in the empiric treatment setting, the period of time immediately after a patient presents with an infection, during which clinicians must select a treatment without microbiological testing results.In this thesis, we develop methods to learn treatment policies for empiric antibiotic prescription that are tailored to individual characteristics. We present three policy learning approaches and evaluate them in the setting of uncomplicated urinary tract infections (UTIs) using data from two Boston-area hospitals. All three approaches learn policies that significantly improve over clinicians and practice guidelines with respect to rates of inappropriate antibiotic therapy (IAT) and broad spectrum antibiotic usage, and are able to trade off between these two outcomes as desired.We then address considerations important for deploying such learned policies as clinical decision support tools in real-world medical settings. We present techniques for learning treatment policies with the ability to defer to clinician decisions and strategies for improving the interpretability and transparency of the learned policies. We are able to successfully derive an effective, clinically intuitive treatment policy that uses fewer than 20 features. Even after accounting for several real-world treatment considerations, this policy is able to reduce rates of IAT by 20% and broad spectrum usage by nearly 50% relative to clinicians. We hope that the work presented in this thesis provides a meaningful step towards using machine learning to improve antibiotic stewardship practices in the future.

In several medical decision-making problems, such as antibiotic prescription, laboratory testing can provide precise indications for how a patient will respond to different treatment options. This enables us to \"fully observe\" all potential treatment outcomes, but while present in historical data, these results are infeasible to produce in real-time at the point of the initial treatment decision. Moreover, treatment policies in these settings often need to trade off between multiple competing objectives, such as effectiveness of treatment and harmful side effects. We present, compare, and evaluate three approaches for learning individualized treatment policies in this setting: First, we consider two indirect approaches, which use predictive models of treatment response to construct policies optimal for different trade-offs between objectives. Second, we consider a direct approach that constructs such a set of policies without intermediate models of outcomes. Using a medical dataset of Urinary Tract Infection (UTI) patients, we show that all approaches learn policies that achieve strictly better performance on all outcomes than clinicians, while also trading off between different objectives. We demonstrate additional benefits of the direct approach, including flexibly incorporating other goals such as deferral to physicians on simple cases.