Clay Gloster

Social Cognitive Predictors of Academic Interests and Goals in Engineering: Utility for Women and Students at Historically Black Universities.

This study examined the utility of social cognitive career theory (SCCT; R. W. Lent, S. D. Brown, & G. Hackett, 1994) in predicting engineering interests and major choice goals among women and men and among students at historically Black and predominantly White universities. Participants (487 students in introductory engineering courses at 3 universities) completed measures of academic interests, goals, self-efficacy, outcome expectations, and environmental supports and barriers in relation to engineering majors. Findings indicated that the SCCT-based model of interest and choice goals produced good fit to the data across gender and university type. Implications for future research on SCCTs choice hypotheses, and particularly for the role of environmental supports and barriers in the choice of science and engineering fields, are discussed.

DomSVR: domain boundary prediction with support vector regression from sequence information alone

Protein domains are structural and fundamental functional units of proteins. The information of protein domain boundaries is helpful in understanding the evolution, structures and functions of proteins, and also plays an important role in protein classification. In this paper, we propose a support vector regression-based method to address the problem of protein domain boundary identification based on novel input profiles extracted from AAindex database. As a result, our method achieves an average sensitivity of ∼36.5% and an average specificity of ∼81% for multi-domain protein chains, which is overall better than the performance of published approaches to identify domain boundary. As our method used sequence information alone, our method is simpler and faster.

PROTEIN FOLD CLASSIFICATION WITH GENETIC ALGORITHMS AND FEATURE SELECTION

Protein fold classification is a key step to predicting protein tertiary structures. This paper proposes a novel approach based on genetic algorithms and feature selection to classifying protein folds. Our dataset is divided into a training dataset and a test dataset. Each individual for the genetic algorithms represents a selection function of the feature vectors of the training dataset. A support vector machine is applied to each individual to evaluate the fitness value (fold classification rate) of each individual. The aim of the genetic algorithms is to search for the best individual that produces the highest fold classification rate. The best individual is then applied to the feature vectors of the test dataset and a support vector machine is built to classify protein folds based on selected features. Our experimental results on Ding and Dubchaks benchmark dataset of 27-class folds show that our approach achieves an accuracy of 71.28%, which outperforms current state-of-the-art protein fold predictors.

Optimizing the Design of a Configurable Digital Signal Processor for Accelerated Execution of the 2-D Discrete Cosine Transform

The advance of mobile electronics technology has produced handheld appliances allowing both wireless voice and data communications. As data communications become increasingly important in mobile computing applications, traditional microprocessors and the accompanying software are increasingly less able to meet the size constraints of these applications while delivering increased performance. One of the most important operations in the realm of digital signal and image processing is the 2-D Discrete Cosine Transform, used to compress both still images and streaming video. The BISON Configurable Digital Signal Processor(BCDSP) architecture detailed here uses multiple memories, few instructions, and a special pipelined floating point arithmetic function core to run on a commercially available Field Programmable Gate Array(FPGA) board. The results demonstrate that although the clock speed of the FPGA board was 2 orders of magnitude slower than the microprocessor used in this study, the BCDSP implementation was still significantly faster.

Computer-Assistant Drug Discovery with the Netezza Architecture

While relational databases have become critically important in business applications and web services, they have played a relatively minor role in scientific computing, especially in computer-assistant drug discovery, which has generally been concerned with modeling and simulation activities. However, massively parallel database architectures are beginning to offer the ability to quickly search through terabytes of data with hundred-fold or even thousand-fold speedup over server-based architectures. These new machines may enable an entirely new class of algorithms for scientific applications. The drug discovery and development community is able now to make good use of these new database machines.

DomSVR: Domain Boundary Prediction with Support Vector Regression and Evolutionary Information

Protein domains are autonomous folding units and are fundamental structural and functional units of proteins. Protein domain boundaries are helpful to the classification of proteins and understanding the evolutions, structures and functions of proteins. In this paper, we propose a support vector regression based method to locate residues at protein domain boundaries with a combination of evolutionary information including sequence profiles, predicted secondary structures, predicted relative solvent accessibility, and profiles from HSSP items. Our proposed model achieved an average sensitivity of ~37% and an average specificity of ~77% on domain boundary identification on our dataset of multi-domain proteins and showed better predictive performance than previous domain identification models.

IRCDB: A Database of Inter-residues Contacts in Protein Chains

In protein structure prediction, identifying the inter-residue contacts is a very important task to understand the mechanism of complicated protein folding and therefore to predict three-dimensional structures of proteins. So far, many methods were developed to predict inter-residue contacts. However, no special database consisting of detailed inter-residue contacts for each PDB protein chain has been built. Our database of inter-residue contacts in protein chains consists of protein chains extracted from PDB database. For each protein chain, we analyzed its inter-residue contacts, classified it into one class, and obtained several groups of inter-residues contacts.