P
Patrick Aboyoun
Researcher at Business International Corporation
Publications - 6
Citations - 3507
Patrick Aboyoun is an academic researcher from Business International Corporation. The author has contributed to research in topics: Bioconductor & Artificial neural network. The author has an hindex of 5, co-authored 6 publications receiving 2637 citations. Previous affiliations of Patrick Aboyoun include Fred Hutchinson Cancer Research Center.
Papers
More filters
Journal ArticleDOI
Software for computing and annotating genomic ranges.
Michael F. Lawrence,Wolfgang Huber,Hervé Pagès,Patrick Aboyoun,Marc R. J. Carlson,Robert Gentleman,Martin Morgan,Vincent J. Carey +7 more
TL;DR: This work describes Bioconductor infrastructure for representing and computing on annotated genomic ranges and integrating genomic data with the statistical computing features of R and its extensions, including those for sequence analysis, differential expression analysis and visualization.
Journal ArticleDOI
ShortRead: a bioconductor package for input, quality assessment and exploration of high-throughput sequence data
TL;DR: ShortRead is a package for input, quality assessment, manipulation and output of high-throughput sequencing data, provided in the R and Bioconductor environments, allowing ready access to additional facilities for advanced statistical analysis, data transformation, visualization and integration with diverse genomic resources.
Patent
Minimizing Global Error in an Artificial Neural Network
TL;DR: In this paper, a mixed-integer linear program (MILP) is proposed to minimize an approximate global error in an artificial neural network model at least in part by causing evaluation of a mixed integer linear program that determines weights between artificial neurons.
Patent
Overloading r language constructs with database engine constructs
TL;DR: In this article, the authors describe a system for interfacing an R language client with a separate database engine environment, where the R language code fragment is interpreted to identify and select R language constructs and transformed into queries or other database language constructs to execute within the database engine.
Patent
Novel Quadratic Regularization For Neural Network With Skip-Layer Connections
TL;DR: In this paper, a neural network comprising input neurons, output neurons, hidden neurons, skip-layer connections, and non-skip layer connections is used to analyze the target data based on an overall objective function that comprises a linear regression part, the neural network's unregularized objective function, and a regularization term.