Multi-Label Classification Based On Subcellular Region-Guided Feature Description For Protein Localisation

This study aimed to assess the effect of gonadotrophin suppression and FSH replacement on testicular tight junction dynamics and blood–testis barrier (BTB) organisation in vivo, utilising the seasonal breeding Djungarian hamster. Confocal immunohistology was used to assess the cellular organisation of tight junction proteins and real-time PCR to quantify tight junction mRNA. The effect of tight junction protein organisation on the BTB permeability was also investigated using a biotin-linked tracer. Tight junction protein (claudin-3, junctional adhesion molecule (JAM)-A and occludin) localisation was present but disorganised after gonadotrophin suppression, while mRNA levels (claudin-11, claudin-3 and occludin) were significantly (two- to threefold) increased. By contrast, both protein localisation and mRNA levels for the adaptor protein zona occludens-1 decreased after gonadotrophin suppression. FSH replacement induced a rapid reorganisation of tight junction protein localisation. The functionality of the BTB (as inferred by biotin tracer permeation) was found to be strongly associated with the organisation and localisation of claudin-11. Surprisingly, JAM-A was also recognised on spermatogonia, suggesting an additional novel role for this protein in trans-epithelial migration of germ cells across the BTB. It is concluded that gonadotrophin regulation of tight junction proteins forming the BTB occurs primarily at the level of protein organisation and not gene transcription in this species, and that immunolocalisation of the organised tight junction protein claudin-11 correlates with BTB functionality.

Download Full-text

LaserVAE for Feature Description and an Application of Global Self-localization

Transactions of the Society of Instrument and Control Engineers ◽

10.9746/sicetr.55.476 ◽

2019 ◽

Vol 55 (7) ◽

pp. 476-483

Author(s):

Shohei WAKITA ◽

Takayuki NAKAMURA ◽

Hirotaka HACHIYA

Keyword(s):

Feature Description

Download Full-text

DEEP LEARNING BASED FEATURE MATCHING AND ITS APPLICATION IN IMAGE ORIENTATION

ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-annals-v-2-2020-25-2020 ◽

2020 ◽

Vol V-2-2020 ◽

pp. 25-33 ◽

Cited By ~ 1

Author(s):

L. Chen ◽

F. Rottensteiner ◽

C. Heipke

Keyword(s):

Deep Learning ◽

Feature Matching ◽

Shape Estimation ◽

Feature Description ◽

Performance Benchmark ◽

Matching Performance ◽

Affine Shape ◽

Image Orientation ◽

Learned Features ◽

Better Than

Abstract. Matching images containing large viewpoint and viewing direction changes, resulting in large perspective differences, still is a very challenging problem. Affine shape estimation, orientation assignment and feature description algorithms based on detected hand crafted features have shown to be error prone. In this paper, affine shape estimation, orientation assignment and description of local features is achieved through deep learning. Those three modules are trained based on loss functions optimizing the matching performance of input patch pairs. The trained descriptors are first evaluated on the Brown dataset (Brown et al., 2011), a standard descriptor performance benchmark. The whole pipeline is then tested on images of small blocks acquired with an aerial penta camera, to compute image orientation. The results show that learned features perform significantly better than alternatives based on hand crafted features.

Download Full-text

New Algorithms for Feature Description, Analysis and Recognition of Binary Image Contours

Computational and Information Science - Lecture Notes in Computer Science ◽

10.1007/978-3-540-30497-5_179 ◽

2004 ◽

pp. 1168-1174

Author(s):

Donggang Yu ◽

Wei Lai

Keyword(s):

Binary Image ◽

Feature Description ◽

New Algorithms

Download Full-text

A putative stem-loop structure in Drosophila crumbs is required for mRNA localisation in epithelia and germline cells

Journal of Cell Science ◽

10.1242/jcs.236497 ◽

2020 ◽

pp. jcs.236497

Author(s):

Srija Bhagavatula ◽

Elisabeth Knust

Keyword(s):

Epithelial Cells ◽

Transmembrane Protein ◽

Loop Structure ◽

Stem Loop ◽

Stem Loop Structure ◽

Evolutionarily Conserved ◽

Mrna Enrichment ◽

Egg Chambers ◽

Protein Localisation ◽

Localization Element

Crumbs (Crb) is an evolutionarily conserved transmembrane protein localised in the apical membrane of epithelial cells. Loss or mis-localisation of Crb is often associated with disruption of apico-basal cell polarity. crb mRNA is also apically enriched in epithelial cells, and, as shown here, accumulates in the oocyte of developing egg chambers. We narrowed down the Localization Element (LE) of crb mRNA to 47 nucleotides forming a putative stem-loop structure, suggesting to be recognised by Egalitarian (Egl). Mutations in conserved nucleotides abrogate apical transport. crb mRNA enrichment in the oocyte is affected in egl mutant egg chambers. A CRISPR based genomic deletion of the crb locus that includes the LE disrupts asymmetric crb mRNA localisation in epithelia and prevents its accumulation in the oocyte during early stages of oogenesis, but does not affect Crb protein localisation in embryonic and follicular epithelia. However, flies lacking the LE show ectopic Crb protein expression in the nurse cells. These data suggest an additional role of the Drosophila 3’-UTR in regulating translation in a tissue specific manner.

Download Full-text

The new proposed method for texture modification of closed up face image based on image processing using local weighting pattern (LWP) with enhancement technique

International Journal of Engineering & Technology ◽

10.14419/ijet.v7i2.2.12742 ◽

2018 ◽

Vol 7 (2.2) ◽

pp. 94

Author(s):

Achmad Fanany Onnilita Gaffar ◽

Darius Shyafary ◽

Rony H ◽

Arief Baramanto Wicaksono Putra

Keyword(s):

Three Dimensional ◽

Texture Feature ◽

Face Image ◽

Design Element ◽

Feature Description ◽

Local Pattern ◽

Spatial Intensity Distribution ◽

Texture Modification ◽

Rgb Image

The texture is a two- and three-dimensional design element that is distinguished by the visual and physical properties perceived. Textured areas in the image can be marked with uniform or varying spatial intensity distribution. There are many techniques and methods from simple to sophisticated which available including machine learning-based methods to modify the texture map. The texture feature description becomes a new challenge in the field of computer vision and pattern recognition since the emergence of the local pattern binary method (LBP). This study proposes a new method called Local Weighting Pattern (LWP) for modifying textures based on the pixel's neighborhood of an RGB image. The results of this study obtained that LWP method produces a texture with a unique and artistic visualization. The Log function has been used to improve the image quality of the LWP method.

Download Full-text