Physical Sciences and Mathematics Commons^™

Predicting Flavonoid Ugt Regioselectivity With Graphical Residue Models And Machine Learning., Arthur Rhydon Jackson

Electronic Theses and Dissertations

Machine learning is applied to a challenging and biologically significant protein classification problem: the prediction of flavonoid UGT acceptor regioselectivity from primary protein sequence. Novel indices characterizing graphical models of protein residues are introduced. The indices are compared with existing amino acid indices and found to cluster residues appropriately. A variety of models employing the indices are then investigated by examining their performance when analyzed using nearest neighbor, support vector machine, and Bayesian neural network classifiers. Improvements over nearest neighbor classifications relying on standard alignment similarity scores are reported.

Identifying Biomarkers For Resistance To Novel Cisplatin Analogues In Human Lung, Breast And Prostate Cancers, Becky Michelle Hess

UNLV Theses, Dissertations, Professional Papers, and Capstones

Cisplatin is a common therapeutic agent used in cancer treatment. Unfortunately, resistance to cisplatin in addition to severe side effects limits its use in cancer treatment. Two novel cisplatin analogues, 4DB and 4TB were shown to have varying cytotoxicity in lung, breast and prostate cancer cells. The hypothesis for this study states that the differences in 4DB and 4TB cytotoxicity among different tissue types is due to the type and efficiency of DNA repair mechanisms involved in response to these drugs.

To test the hypothesis, proteins involved in the rate limiting step of nucleotide excision repair (NER) and mismatch repair …