Predicting homologous signaling pathways using machine learning.

MOTIVATION: In general, each cell signaling pathway involves many proteins, each with one or more specific roles. As they are essential components of cell activity, it is important to understand how these proteins work-and in particular, to determine which of the species' proteins participate in each role. Experimentally determining this mapping of proteins to roles is difficult and time consuming. Fortunately, many pathways are similar across species, so we may be able to use known pathway information of one species to understand the corresponding pathway of another. RESULTS: We present an automatic approach, Predict Signaling Pathway (PSP), which uses the signaling pathways in well-studied species to predict the roles of proteins in less-studied species. We use a machine learning approach to create a predictor that achieves a generalization F-measure of 78.2% when applied to 11 different pathways across 14 different species. We also show our approach is very effective in predicting the pathways that have not yet been experimentally studied completely. AVAILABILITY: The list of predicted proteins for all pathways over all considered species is available at http://www.cs.ualberta.ca/~bioinfo/signaling.

Improving subcellular localization prediction using text classification and the gene ontology.

MOTIVATION: Each protein performs its functions within some specific locations in a cell. This subcellular location is important for understanding protein function and for facilitating its purification. There are now many computational techniques for predicting location based on sequence analysis and database information from homologs. A few recent techniques use text from biological abstracts: our goal is to improve the prediction accuracy of such text-based techniques. We identify three techniques for improving text-based prediction: a rule for ambiguous abstract removal, a mechanism for using synonyms from the Gene Ontology (GO) and a mechanism for using the GO hierarchy to generalize terms. We show that these three techniques can significantly improve the accuracy of protein subcellular location predictors that use text extracted from PubMed abstracts whose references are recorded in Swiss-Prot.

The Path-A metabolic pathway prediction web server.

Pathway Analyst (Path-A) is a publicly available web server (http://path-a.cs.ualberta.ca) that predicts metabolic pathways. It takes a FASTA format file containing a set of query protein sequences from a single organism (a partial or complete proteome) and identifies those sequences that are likely to participate in any of its supported metabolic pathways (currently 10). Path-A uses a number of machine-learning and sequence analysis techniques (e.g. SVM, BLAST and HMM) to predict pathways. Each machine-learned classifier exploits similarity between sequences in the pathways of its model organisms and sequences in the query set. It predicts the pathways that are present in the query organism and annotates each predicted reaction and catalyst, using the appropriate sequences from the query set. Path-A also provides a browsable and searchable database of the pathways for the model organisms that are used to make its predictions. Path-A's predictor sets (using different classifier technologies) have been evaluated using standard cross-validation techniques on a dataset of 10 metabolic pathways across 13 model organisms--a total of 125 organism-specific pathways. The most accurate classifier technology obtained a mean precision of 78.3% and a mean recall of 92.6% in predicting all catalyst proteins, of all reactions, in all pathways present in the dataset. Although Path-A currently only supports metabolic pathways, the underlying prediction techniques are general enough for other types of pathways. Consequently, it is our intent to extend Path-A to predict other types of pathways, including signalling pathways.

BASys: a web server for automated bacterial genome annotation.

BASys (Bacterial Annotation System) is a web server that supports automated, in-depth annotation of bacterial genomic (chromosomal and plasmid) sequences. It accepts raw DNA sequence data and an optional list of gene identification information and provides extensive textual annotation and hyperlinked image output. BASys uses >30 programs to determine approximately 60 annotation subfields for each gene, including gene/protein name, GO function, COG function, possible paralogues and orthologues, molecular weight, isoelectric point, operon structure, subcellular localization, signal peptides, transmembrane regions, secondary structure, 3D structure, reactions and pathways. The depth and detail of a BASys annotation matches or exceeds that found in a standard SwissProt entry. BASys also generates colorful, clickable and fully zoomable maps of each query chromosome to permit rapid navigation and detailed visual analysis of all resulting gene annotations. The textual annotations and images that are provided by BASys can be generated in approximately 24 h for an average bacterial chromosome (5 Mb). BASys annotations may be viewed and downloaded anonymously or through a password protected access system. The BASys server and databases can also be downloaded and run locally. BASys is accessible at http://wishart.biology.ualberta.ca/basys.

PA-GOSUB: a searchable database of model organism protein sequences with their predicted Gene Ontology molecular function and subcellular localization.

PA-GOSUB (Proteome Analyst: Gene Ontology Molecular Function and Subcellular Localization) is a publicly available, web-based, searchable and downloadable database that contains the sequences, predicted GO molecular functions and predicted subcellular localizations of more than 107,000 proteins from 10 model organisms (and growing), covering the major kingdoms and phyla for which annotated proteomes exist (http://www.cs.ualberta.ca/~bioinfo/PA/GOSUB). The PA-GOSUB database effectively expands the coverage of subcellular localization and GO function annotations by a significant factor (already over five for subcellular localization, compared with Swiss-Prot v42.7), and more model organisms are being added to PA-GOSUB as their sequenced proteomes become available. PA-GOSUB can be used in three main ways. First, a researcher can browse the pre-computed PA-GOSUB annotations on a per-organism and per-protein basis using annotation-based and text-based filters. Second, a user can perform BLAST searches against the PA-GOSUB database and use the annotations from the homologs as simple predictors for the new sequences. Third, the whole of PA-GOSUB can be downloaded in either FASTA or comma-separated values (CSV) formats.

Proteome Analyst: custom predictions with explanations in a web-based tool for high-throughput proteome annotations.

Proteome Analyst (PA) (http://www.cs.ualberta.ca/~bioinfo/PA/) is a publicly available, high-throughput, web-based system for predicting various properties of each protein in an entire proteome. Using machine-learned classifiers, PA can predict, for example, the GeneQuiz general function and Gene Ontology (GO) molecular function of a protein. In addition, PA is currently the most accurate and most comprehensive system for predicting subcellular localization, the location within a cell where a protein performs its main function. Two other capabilities of PA are notable. First, PA can create a custom classifier to predict a new property, without requiring any programming, based on labeled training data (i.e. a set of examples, each with the correct classification label) provided by a user. PA has been used to create custom classifiers for potassium-ion channel proteins and other general function ontologies. Second, PA provides a sophisticated explanation feature that shows why one prediction is chosen over another. The PA system produces a Naïve Bayes classifier, which is amenable to a graphical and interactive approach to explanations for its predictions; transparent predictions increase the user's confidence in, and understanding of, PA.