An empirical evaluation of the Random Forests classifier models for variable selection in a large-scale lung cancer case-control study

Random Forests™ is reported to be one of the most accurate classification algorithms in complex data analysis. It shows excellent performance even when most predictors are noisy and the number of variables is much larger than the number of observations. In this thesis Random Forests was applied to a large-scale lung cancer case-control study. A novel way of automatically selecting prognostic factors was proposed. Also, synthetic positive control was used to validate Random Forests method. Throughout this study we showed that Random Forests can deal with large number of weak input variables without overfitting. It can account for non-additive interactions between these input variables. Random Forests can also be used for variable selection without being adversely affected by collinearities. ^ Random Forests can deal with the large-scale data sets without rigorous data preprocessing. It has robust variable importance ranking measure. Proposed is a novel variable selection method in context of Random Forests that uses the data noise level as the cut-off value to determine the subset of the important predictors. This new approach enhanced the ability of the Random Forests algorithm to automatically identify important predictors for complex data. The cut-off value can also be adjusted based on the results of the synthetic positive control experiments. ^ When the data set had high variables to observations ratio, Random Forests complemented the established logistic regression. This study suggested that Random Forests is recommended for such high dimensionality data. One can use Random Forests to select the important variables and then use logistic regression or Random Forests itself to estimate the effect size of the predictors and to classify new observations. ^ We also found that the mean decrease of accuracy is a more reliable variable ranking measurement than mean decrease of Gini. ^

A hybrid method in combining treatment effects from matched and unmatched studies

In the biomedical studies, the general data structures have been the matched (paired) and unmatched designs. Recently, many researchers are interested in Meta-Analysis to obtain a better understanding from several clinical data of a medical treatment. The hybrid design, which is combined two data structures, may create the fundamental question for statistical methods and the challenges for statistical inferences. The applied methods are depending on the underlying distribution. If the outcomes are normally distributed, we would use the classic paired and two independent sample T-tests on the matched and unmatched cases. If not, we can apply Wilcoxon signed rank and rank sum test on each case. ^ To assess an overall treatment effect on a hybrid design, we can apply the inverse variance weight method used in Meta-Analysis. On the nonparametric case, we can use a test statistic which is combined on two Wilcoxon test statistics. However, these two test statistics are not in same scale. We propose the Hybrid Test Statistic based on the Hodges-Lehmann estimates of the treatment effects, which are medians in the same scale.^ To compare the proposed method, we use the classic meta-analysis T-test statistic on the combined the estimates of the treatment effects from two T-test statistics. Theoretically, the efficiency of two unbiased estimators of a parameter is the ratio of their variances. With the concept of Asymptotic Relative Efficiency (ARE) developed by Pitman, we show ARE of the hybrid test statistic relative to classic meta-analysis T-test statistic using the Hodges-Lemann estimators associated with two test statistics.^ From several simulation studies, we calculate the empirical type I error rate and power of the test statistics. The proposed statistic would provide effective tool to evaluate and understand the treatment effect in various public health studies as well as clinical trials.^

Advanced Protein Modeling Method: Benchmarking and Applications in Computer-Aided Drug Discovery

Development of homology modeling methods will remain an area of active research. These methods aim to develop and model increasingly accurate three-dimensional structures of yet uncrystallized therapeutically relevant proteins e.g. Class A G-Protein Coupled Receptors. Incorporating protein flexibility is one way to achieve this goal. Here, I will discuss the enhancement and validation of the ligand-steered modeling, originally developed by Dr. Claudio Cavasotto, via cross modeling of the newly crystallized GPCR structures. This method uses known ligands and known experimental information to optimize relevant protein binding sites by incorporating protein flexibility. The ligand-steered models were able to model, reasonably reproduce binding sites and the co-crystallized native ligand poses of the β2 adrenergic and Adenosine 2A receptors using a single template structure. They also performed better than the choice of template, and crude models in a small scale high-throughput docking experiments and compound selectivity studies. Next, the application of this method to develop high-quality homology models of Cannabinoid Receptor 2, an emerging non-psychotic pain management target, is discussed. These models were validated by their ability to rationalize structure activity relationship data of two, inverse agonist and agonist, series of compounds. The method was also applied to improve the virtual screening performance of the β2 adrenergic crystal structure by optimizing the binding site using β2 specific compounds. These results show the feasibility of optimizing only the pharmacologically relevant protein binding sites and applicability to structure-based drug design projects.