Physical Sciences and Mathematics Commons^™

Multi-Label Model For Toxicity Prediction, Xiu Huan Yap, Michael L. Raymer

Symposium of Student Research, Scholarship, and Creative Activities Materials

Most computational predictive models are specifically trained for a single toxicity endpoint. Since more than 1300 toxicity assays have been reported in the TOXCAST dashboard, achieving high coverage over this growing number of toxicity endpoints remains challenging. Furthermore, single-endpoint models lack the ability to learn dependencies between endpoints, such as those targeting similar biological pathways, which may be used to boost model performance. In this study, we characterize the performance of 3 multi-label classification (MLC) models, namely Classifier Chains (CC), Label Powersets (LP) and Stacking (SBR), on Tox21 challenge data. These MLC models employ the Problem Transformation approach, which is …

Measuring Nomophobia And Exploration Of Consequences And Comorbidities, Sarah Marie Fryman, William L. Romine

Symposium of Student Research, Scholarship, and Creative Activities Materials

Excessive use of smartphones has coined the term “Nomophobia”, or fear of not being able to use your smartphone. For many, these devices have become an extension of ourselves, which raises hesitation on whether or not society has become addicted to smartphones. Specific diagnostic criteria for smartphone addiction have yet to be settled, and even appropriate to use the word “addiction” when describing excessive usage of smartphones is controversial.

We therefore explore utilize current measures to explore the symptoms of nomophobia and their hierarchy, as well as comorbidities including social anxiety, self-esteem, distracted driving and sleep quality. A total of …