No abstract

During the past decade, with the significant progress of computational power as well as ever-rising data availability, deep learning techniques became increasingly popular due to their excellent performance on computer vision problems. The size of the Protein Data Bank (PDB) has increased more than 15-fold since 1999, which enabled the expansion of models that aim at predicting enzymatic function via their amino acid composition. Amino acid sequence, however, is less conserved in nature than protein structure and therefore considered a less reliable predictor of protein function. This paper presents EnzyNet, a novel 3D convolutional neural networks classifier that predicts the Enzyme Commission number of enzymes based only on their voxel-based spatial structure. The spatial distribution of biochemical properties was also examined as complementary information. The two-layer architecture was investigated on a large dataset of 63,558 enzymes from the PDB and achieved an accuracy of 78.4% by exploiting only the binary representation of the protein shape. Code and datasets are available at .

Abstract. The analysis of brain activations using functional magnetic resonance imaging (fMRI) is an active area of neuropsychological research. Standard techniques for analysis have traditionally focused on finding the most significant areas of brain activation, and have only recently begun to explore the importance of their spatial characteristics. We compare fMRI contrast images and significance maps to training sets of similar maps using the spatial distribution of activation values. We demonstrate that a Fisher linear discriminant (FLD) classifier for either type of map can differentiate patients from controls accurately for Alzheimer's disease, schizophrenia, and mild traumatic brain injury (MTBI).

Closed-head injury-induced lesions in the right putamen in children are associated with subsequent development of secondary ADHD. Depiction software is useful in guiding statistical analysis of image data.

No abstract

BackgroundReceptor protein tyrosine phosphatase beta/zeta (RPTPβ/ζ) is a chondroitin sulphate (CS) transmembrane protein tyrosine phosphatase and is a receptor for pleiotrophin (PTN). RPTPβ/ζ interacts with ανβ3 on the cell surface and upon binding of PTN leads to c-Src dephosphorylation at Tyr530, β3 Tyr773 phosphorylation, cell surface nucleolin (NCL) localization and stimulation of cell migration. c-Src-mediated β3 Tyr773 phosphorylation is also observed after vascular endothelial growth factor 165 (VEGF165) stimulation of endothelial cells and is essential for VEGF receptor type 2 (VEGFR2) - ανβ3 integrin association and subsequent signaling. In the present work, we studied whether RPTPβ/ζ mediates angiogenic actions of VEGF.MethodsHuman umbilical vein endothelial, human glioma U87MG and stably transfected Chinese hamster ovary cells expressing different β3 subunits were used. Protein-protein interactions were studied by a combination of immunoprecipitation/Western blot, immunofluorescence and proximity ligation assays, properly quantified as needed. RPTPβ/ζ expression was down-regulated using small interference RNA technology. Migration assays were performed in 24-well microchemotaxis chambers, using uncoated polycarbonate membranes with 8 μm pores.ResultsRPTPβ/ζ mediates VEGF165-induced c-Src-dependent β3 Tyr773 phosphorylation, which is required for VEGFR2-ανβ3 interaction and the downstream activation of phosphatidylinositol 3-kinase (PI3K) and cell surface NCL localization. RPTPβ/ζ directly interacts with VEGF165, and this interaction is not affected by bevacizumab, while it is interrupted by both CS-E and PTN. Down-regulation of RPTPβ/ζ by siRNA or administration of exogenous CS-E abolishes VEGF165-induced endothelial cell migration, while PTN inhibits the migratory effect of VEGF165 to the levels of its own effect.ConclusionsThese data identify RPTPβ/ζ as a cell membrane binding partner for VEGF that regulates angiogenic functions of endothelial cells and suggest that it warrants further validation as a potential target for development of additive or alternative anti-VEGF therapies.Electronic supplementary materialThe online version of this article (doi:10.1186/s12943-015-0287-3) contains supplementary material, which is available to authorized users.

Will we ever have a theory of data mining analogous to the relational algebra in databases? Why do we have so many clearly different clustering algorithms? Could data mining be automated? We show that the answer to all these questions is negative, because data mining is closely related to compression and Kolmogorov complexity; and the latter is undecidable. Therefore, data mining will always be an art, where our goal will be to find better models (patterns) that fit our datasets as best as possible.

No abstract