Search

Abstract: Statistical machine translation systems are usually trained on large amounts of bilingual text (used to learn a translation model), and also large amounts of monolingual text in the target language (used to train a language model). In this article we explore the use of semi-supervised model adaptation methods for the effective use of monolingual data from the source language in order to improve translation quality. We propose several algorithms with this aim, and present the strengths and weaknesses of each one. We present detailed experimental evaluations on the French–English EuroParl data set and on data from the NIST Chinese–English large-data track. We show a significant improvement in translation quality on both tasks.

Prioritizing molecular alterations that act as drivers of cancer remains a crucial bottleneck in therapeutic development. Here we introduce HIT'nDRIVE, a computational method that integrates genomic and transcriptomic data to identify a set of patient-specific, sequence-altered genes, with sufficient collective influence over dysregulated transcripts. HIT'nDRIVE aims to solve the “random walk facility location” (RWFL) problem in a gene (or protein) interaction network, which differs from the standard facility location problem by its use of an alternative distance measure: “multihitting time,” the expected length of the shortest random walk from any one of the set of sequence-altered genes to an expression-altered target gene. When applied to 2200 tumors from four major cancer types, HIT'nDRIVE revealed many potentially clinically actionable driver genes. We also demonstrated that it is possible to perform accurate phenotype prediction for tumor samples by only using HIT'nDRIVE-seeded driver gene modules from gene interaction networks. In addition, we identified a number of breast cancer subtype-specific driver modules that are associated with patients’ survival outcome. Furthermore, HIT'nDRIVE, when applied to a large panel of pan-cancer cell lines, accurately predicted drug efficacy using the driver genes and their seeded gene modules. Overall, HIT'nDRIVE may help clinicians contextualize massive multiomics data in therapeutic decision making, enabling widespread implementation of precision oncology.

Discovering associations among variables is an important data mining task. The associations can be considered as statistical dependencies among random variables, expressed as the structure of an underlying probabilistic graphical model. Current methods for graphical model structure discovery either do not scale well to datasets with large sample sizes, or suffer from high false discovery rates when the number of dimensions is much larger than the sample size. In this paper, we propose a scalable and statistically efficient approach for graphical model structure discovery for multivariate data involving continuous variables. Our approach uses a minimum message length (MML)-based objective, for which we design a greedy algorithm where the best edges maximising improvements to the MML-based score are added incrementally to the graphical model. We present extensive empirical results on synthetic data with different sample, variable, clique and inverse correlation coefficient and show that our method outperforms strong baselines in terms of both speed and the accuracy of the predicted associations among the random variables in the graphical model. We also report that our method performs significantly very well in AML, BRCA cancer data and other real-life datasets.

Simultaneous interrogation of tumor genomes and transcriptomes is underway in unprecedented global efforts. Yet, despite the essential need to separate driver mutations modulating gene expression networks from transcriptionally inert passenger mutations, robust computational methods to ascertain the impact of individual mutations on transcriptional networks are underdeveloped. We introduce a novel computational framework, DriverNet, to identify likely driver mutations by virtue of their effect on mRNA expression networks. Application to four cancer datasets reveals the prevalence of rare candidate driver mutations associated with disrupted transcriptional networks and a simultaneous modulation of oncogenic and metabolic networks, induced by copy number co-modification of adjacent oncogenic and metabolic drivers. DriverNet is available on Bioconductor or at http://compbio.bccrc.ca/software/drivernet/.