Search

Technical report TR03-05. Modern sequencing technology now permits the sequencing of entire genomes, leading to thousands of new gene sequences in need of detailed annotation. It is too time consuming to predict the properties of each protein sequence manually and to organize the results of many prediction tools by hand. The prediction process must be automated so the predictions can be automatically organized, but the predictions must also be transparent. That is, the rationale for each prediction should be easily examinable by anyone that wishes to use the prediction. Proteome Analyst (PA) is a web-based system for predicting the properties of each protein in a proteome. PA has three interesting features. First, it provides a single web-based tool that allows the user to select a wide range of analytic tools and automatically apply them to each protein in a proteome. In essence, PA provides one-stop automatic high-throughput analysis. Second, PA has the ability to explain its predictions to users. PA is based on established machine learning techniques, but makes every prediction transparent to its users. Third, PA allows users to easily create their own transparent custom predictors without programming. | TRID-ID TR03-05

Technical report TR03-09. Naive Bayes classifiers, a popular tool for predicting the labels of query instances, are typically learned from a training set. However, since many training sets contain noisy data, a classifier user may be reluctant to blindly trust a predicted label. We present a novel graphical explanation facility for Naive Bayes classifiers that serves three purposes. First, it transparently explains the reasoning used by the classifier to foster user confidence in the prediction. Second, it enhances the user's understanding of the complex relationships between the features and the labels. Third, it can help the user to identify suspicious training data. We demonstrate these ideas in the context of our implemented web-based system, which uses examples from molecular biology.-based system, which uses examples from molecular biology. | TRID-ID TR03-09

Technical report TR03-14. Identifying the destination or localization of proteins is key to understanding their function and facilitating their purification. A number of existing computational prediction methods are based on sequence analysis. However, these methods are limited in scope, accuracy and most particularly breadth of coverage. Rather than using sequence information alone, we have explored the use of database text annotations from homologs and machine learning to substantially improve the prediction of subcellular location. Results: We have constructed five machine-learning classifiers for predicting subcellular localization of proteins from animals, plants, fungi, Gram-negative bacteria and Gram-positive bacteria, which are 81% accurate for fungi and 92% to 94% accurate for the other four categories. These are the most accurate subcellular predictors across the widest set of organisms ever published. Our predictors are part of the Proteome Analyst (PA) web-service. Availability http://www.cs.ualberta.ca/~bioinfo/PA/Sub http://www.cs.ualberta.ca/~bioinfo/PA Supplementary Information http://www.cs.ualberta.ca/~bioinfo/PA/Subcellular Contact bioinfo@cs.ualberta.ca | TRID-ID TR03-14