No description available.

The amount of available protein sequences is rapidly increasing, mainly as a consequence of the development and application of high throughput sequencing technologies in the life sciences. It is a key question in the life sciences to identify the functions of proteins, and furthermore to identify the phenotypes that may be associated with a loss (or gain) of function in these proteins. Protein functions are generally determined experimentally, and it is clear that experimental determination of protein functions will not scale to the current { and rapidly increasing { amount of available protein sequences (over 300 million). Furthermore, identifying phenotypes resulting from loss of function is even more challenging as the phenotype is modi ed by whole organism interactions and environmental variables. It is clear that accurate computational prediction of protein functions and loss of function phenotypes would be of signi cant value both to academic research and to the biotechnology industry. We developed and expanded novel methods for representation learning, predicting protein functions and their loss of function phenotypes. We use deep neural network algorithm and combine them with symbolic inference into neural-symbolic algorithms. Our work signi cantly improves previously developed methods for predicting protein functions through methodological advances in machine learning, incorporation of broader data types that may be predictive of functions, and improved systems for neural-symbolic integration. The methods we developed are generic and can be applied to other domains in which similar types of structured and unstructured information exist. In future, our methods can be applied to prediction of protein function for metagenomic samples in order to evaluate the potential for discovery of novel proteins of industrial value. Also our methods can be applied to the prediction of loss of function phenotypes in human genetics and incorporate the results in a variant prioritization tool that can be applied to diagnose patients with Mendelian disorders.

High throughput technologies such as microarrays and modern genome sequencers produce enormous amounts of data that require novel data processing. This thesis proposes a method called Interdependent Correlation Cluster (ICC) to analyze the relations between genes represented by microarray data that are conditioned on a specific target gene. Based on Correlation Clustering, the proposed method analyzes a large set of correlation values related to the gene expression profiles extracted from given microarray datasets. The proposed method works on any size microarray datasets and could be applied to any target gene. In this study the selected target gene, NSF1 /USV1 / YPL230W, encodes a poorly characterized C2H2 zinc finger transcription factor (TF) involved in stress responses in yeast. The method is successful in the identification of novel NSF1 functional roles during fermentation stress conditions in the M2 industrial yeast strain. The new identified functions include regulation of energy and sulfur metabolism, protein synthesis, ribosomal assembly and protein trafficking as well as other processes. NSF1 involvement in sulfur metabolism was experimentally confirmed using biological laboratory techniques. Importantly, implication of NSF1 in sulfur metabolism regulation has highly relevant implications to wine and beer production industries concerned with production of compounds having sulfur-like off odour (SLO) and toxic properties. The correlation clustering also provides a means of understanding complex interactions existing between genes. / The pdf file contains numerous hyperlinks and bookmarks to facilitate navigation. This thesis will be of interest to those working with topics such as data mining of microarray data, novel gene function discovery and prediction, and genome-wide responses to fermentation stresses. / Ministry of Training, Colleges and Universities of Ontario (Ontario Graduate Scholarship and Ontario Graduate Scholarships in Science and Technology); The Natural Sciences and Engineering Research Council of Canada (NSERC)