Ensemble of deep capsule neural networks: an application to pediatric pneumonia prediction.

Pneumonia disease accounts for 15% of all deaths in children under the age of five and early detection of the disease significantly improves survival chances. In this work, we introduce a novel deep neural network model for evaluating pediatric pneumonia from chest radio-graph images. The proposed network is an ensemble of multiple candidate networks, each with interleaved convolutional and capsule layers.

Integrative genomic analyses of sporadic clear cell renal cell carcinoma define disease subtypes and potential new therapeutic targets.

Sporadic clear cell renal cell carcinoma (ccRCC), the most common type of adult kidney cancer, is often associated with genomic copy number aberrations on chromosomes 3p and 5q. Aberrations on chromosome 3p are associated with inactivation of the tumor suppressor gene von-Hippel Lindau (VHL), which activates the hypoxia-inducible factors HIF1α and HIF2α. In contrast, ccRCC genes on chromosome 5q remain to be defined.

Hypoxia-inducible factors in stem cells and cancer.

Cellular properties are influenced by complex factors inherent to their microenvironments. While oxygen deprivation (hypoxia) occurs in tumours because of rapid cell proliferation and aberrant blood vessel formation, embryonic cells develop in a naturally occurring hypoxic environment. Cells respond to hypoxia by stabilizing hypoxia-inducible factors (HIFs), which are traditionally viewed to function by altering cellular metabolism and blood vessel architecture.

HIF-alpha effects on c-Myc distinguish two subtypes of sporadic VHL-deficient clear cell renal carcinoma.

von Hippel-Lindau (VHL) tumor suppressor loss results in hypoxia-inducible factor alpha (HIF-alpha) stabilization and occurs in 70% of sporadic clear cell renal carcinomas (ccRCCs). To determine whether opposing influences of HIF-1alpha and HIF-2alpha on c-Myc activity regulate human ccRCC progression, we analyzed VHL genotype and HIF-alpha expression in 160 primary tumors, which segregated into three groups with distinct molecular characteristics. Interestingly, ccRCCs with intact VHL, as well as pVHL-deficient HIF-1alpha/HIF-2alpha-expressing ccRCCs, exhibited enhanced Akt/mTOR and ERK/MAPK signaling.

In silico gene selection for custom oligonucleotide microarray design.

A method for systematically selecting the large number of sequences needed to custom design an oligonucleotide microarray was presented. This approach uses a Perl script to query sequence databases with gene lists obtained from previously designed (and publicly available) microarrays. Homologous sequences passing a user-defined threshold are returned and stored in a candidate gene database.

Progress in the development of nucleic acid therapeutics.

Abnormal gene expression is a hallmark of many diseases. Gene-specific downregulation of aberrant genes could be useful therapeutically and potentially less toxic than conventional therapies due its specificity. Over the years, many strategies have been proposed for silencing gene expression in a gene-specific manner.

In silico gene selection strategy for custom microarray design.

Microarray technology has become an important tool for studying large-scale gene expression for a diversity of biological applications. However, there are a number of experimental settings for which commercial arrays are either unsuitable or unavailable despite the existence of sequence information. With the increasing availability of custom array manufacturing services, it is now feasible to design high-density arrays for any organism having sequence data.

DBParser: web-based software for shotgun proteomic data analyses.

We describe a web-based program called 'DBParser' for rapidly culling, merging, and comparing sequence search engine results from multiple LC-MS/MS peptide analyses. DBParser employs the principle of parsimony to consolidate redundant protein assignments and derive the most concise set of proteins consistent with all of the assigned peptide sequences observed in an experiment or series of experiments. The resulting reports summarize peptide and protein identifications from multidimensional experiments that may contain a single data set or combine data from a group of data sets, all related to a single analytical sample.

The vesicular glutamate transporter 1 (xVGlut1) is expressed in discrete regions of the developing Xenopus laevis nervous system.

As the major excitatory neurotransmitter in the vertebrate nervous system, glutamate not only plays an essential role in adult neural signaling, but has also been implicated as a trophic factor in neuronal cell maturation, differentiation, and survival. An essential component of the glutamatergic neurotransmission system is the family of glutamate transporters, a multigene family that codes for plasma membrane-bound as well as vesicle-bound proteins responsible for the removal of glutamate from the cleft and its re-uptake into the synaptic vesicle. Here we describe the spatial and temporal expression of the vesicular glutamate transporter (xVGlut1) during the early developmental stages of the amphibian Xenopus laevis.