New algorithms for automated phylogenetic reconstruction using artificial intelligence and data mining techniques

Academic and industrial research in the late 90s have brought about an exponential explosion of DNA sequence data. Automated expert systems are being created to help biologists to extract patterns, trends and links from this ever-deepening ocean of information. Two such systems aimed on retrieving and subsequently utilizing phylogenetically relevant information have been developed in this dissertation, the major objective of which was to automate the often difficult and confusing phylogenetic reconstruction process. ^ Popular phylogenetic reconstruction methods, such as distance-based methods, attempt to find an optimal tree topology (that reflects the relationships among related sequences and their evolutionary history) by searching through the topology space. Various compromises between the fast (but incomplete) and exhaustive (but computationally prohibitive) search heuristics have been suggested. An intelligent compromise algorithm that relies on a flexible “beam” search principle from the Artificial Intelligence domain and uses the pre-computed local topology reliability information to adjust the beam search space continuously is described in the second chapter of this dissertation. ^ However, sometimes even a (virtually) complete distance-based method is inferior to the significantly more elaborate (and computationally expensive) maximum likelihood (ML) method. In fact, depending on the nature of the sequence data in question either method might prove to be superior. Therefore, it is difficult (even for an expert) to tell a priori which phylogenetic reconstruction method—distance-based, ML or maybe maximum parsimony (MP)—should be chosen for any particular data set. ^ A number of factors, often hidden, influence the performance of a method. For example, it is generally understood that for a phylogenetically “difficult” data set more sophisticated methods (e.g., ML) tend to be more effective and thus should be chosen. However, it is the interplay of many factors that one needs to consider in order to avoid choosing an inferior method (potentially a costly mistake, both in terms of computational expenses and in terms of reconstruction accuracy.) ^ Chapter III of this dissertation details a phylogenetic reconstruction expert system that selects a superior proper method automatically. It uses a classifier (a Decision Tree-inducing algorithm) to map a new data set to the proper phylogenetic reconstruction method. ^

SURVIVAL PREDICTION FOR BRAIN TUMOR PATIENTS USING GENE EXPRESSION DATA

Brain tumor is one of the most aggressive types of cancer in humans, with an estimated median survival time of 12 months and only 4% of the patients surviving more than 5 years after disease diagnosis. Until recently, brain tumor prognosis has been based only on clinical information such as tumor grade and patient age, but there are reports indicating that molecular profiling of gliomas can reveal subgroups of patients with distinct survival rates. We hypothesize that coupling molecular profiling of brain tumors with clinical information might improve predictions of patient survival time and, consequently, better guide future treatment decisions. In order to evaluate this hypothesis, the general goal of this research is to build models for survival prediction of glioma patients using DNA molecular profiles (U133 Affymetrix gene expression microarrays) along with clinical information. First, a predictive Random Forest model is built for binary outcomes (i.e. short vs. long-term survival) and a small subset of genes whose expression values can be used to predict survival time is selected. Following, a new statistical methodology is developed for predicting time-to-death outcomes using Bayesian ensemble trees. Due to a large heterogeneity observed within prognostic classes obtained by the Random Forest model, prediction can be improved by relating time-to-death with gene expression profile directly. We propose a Bayesian ensemble model for survival prediction which is appropriate for high-dimensional data such as gene expression data. Our approach is based on the ensemble "sum-of-trees" model which is flexible to incorporate additive and interaction effects between genes. We specify a fully Bayesian hierarchical approach and illustrate our methodology for the CPH, Weibull, and AFT survival models. We overcome the lack of conjugacy using a latent variable formulation to model the covariate effects which decreases computation time for model fitting. Also, our proposed models provides a model-free way to select important predictive prognostic markers based on controlling false discovery rates. We compare the performance of our methods with baseline reference survival methods and apply our methodology to an unpublished data set of brain tumor survival times and gene expression data, selecting genes potentially related to the development of the disease under study. A closing discussion compares results obtained by Random Forest and Bayesian ensemble methods under the biological/clinical perspectives and highlights the statistical advantages and disadvantages of the new methodology in the context of DNA microarray data analysis.

Learning What Works: Demonstrating Practice Effectiveness with Children and Families Through Retrospective Investigation

Intensive family preservation services (IFPS), designed to stabilize at-risk families and avert out-of-home care, have been the focus of many randomized, experimental studies. Employing a retrospective “clinical data-mining” (CDM) methodology (Epstein, 2001), this study makes use of available information extracted from client records in one IFPS agency over the course of two years. The primary goal of this descriptive and associational study was to gain a clearer understanding of IFPS service delivery and effectiveness. Interventions provided to families are delineated and assessed for their impact on improved family functioning, their impact on the reduction of family violence, as well as placement prevention. Findings confirm the use of a wide range of services consistent with IFPS program theory. Because the study employs a quasi-experimental, retrospective use of available information, clinical outcomes described cannot be causally attributed to interventions employed as with randomized controlled trials. With regard to service outcomes, findings suggest that family education, empowerment services and advocacy are most influential in placement prevention and in ameliorating unmanageable behaviors in children as well as the incidence of family violence.

Looking Inside The Black Box

Intensive family preservation services (IFPS), designed to stabilize at-risk families and avert out-of-home care, have been the focus of many randomized, experimental studies. The emphasis on "gold-standard" evaluation of IFPS has resulted in fewer "black box" studies that describe actual IFPS service patterns and the fidelity with which they adhere to IFPS program theory. Intervention research is important to the advancement of programs designed to protect the safety of children, improve family functioning, as well as prevent out-of-home placement. Employing a retrospective “clinical data-mining” (CDM) methodology, this exploratory study of Families First, an IFPS program, makes use of available information extracted from client records to describe interventions and service patterns provided over a two year period. This study uncovers actual IFPS service patterns, demonstrates IFPS program fidelity, as well as reveals the usefulness of CDM as a social work research methodology. These findings are particularly valuable for program planning and treatment, policy development and evidence-based practice research.