A5044364996- Remote Sensing in Agriculture
- Bioinformatics and Genomic Networks
- Cancer Genomics and Diagnostics
- Remote-Sensing Image Classification
- Remote Sensing and LiDAR Applications
- Advanced Image Fusion Techniques
- Gene expression and cancer classification
- Cancer-related molecular mechanisms research
- Image Retrieval and Classification Techniques
- Forest ecology and management
- Soil Geostatistics and Mapping
- Genomics and Chromatin Dynamics
- RNA modifications and cancer
- Genomics and Rare Diseases
- Genetics, Bioinformatics, and Biomedical Research
- Evolution and Genetic Dynamics
- Soil and Unsaturated Flow
- Remote Sensing and Land Use
- RNA Research and Splicing
- MicroRNA in disease regulation
- Forest Ecology and Biodiversity Studies
- Soil Moisture and Remote Sensing
- Infrared Target Detection Methodologies
- Histone Deacetylase Inhibitors Research
- Genomic variations and chromosomal abnormalities
Ghent University
2013-2023
Imec the Netherlands
2020-2022
iMinds
2013-2017
KU Leuven
2013
Abstract Soft classification techniques avoid the loss of information characteristic to hard when handling mixed pixels. Sub‐pixel mapping is a method incorporating benefits both and soft techniques. In this paper an algorithm developed based on sub‐pixel/pixel attractions. The design accomplished using artificial imagery but testing done as well real synthetic imagery. evaluated visually quantitatively established accuracy indices. resulting images show increased compared hardened...
In remotely sensed images, mixed pixels will always be present. Soft classification defines the membership degree of these for different land cover classes. Sub-pixel mapping is a technique designed to use information contained in obtain sharpened image. Pixels are divided into sub-pixels, representing class fractions. Genetic algorithms combined with assumption spatial dependence assign location every sub-pixel. The algorithm was tested on synthetic and degraded real imagery. Obtained...
Abstract The catalog of cancer driver mutations in protein-coding genes has greatly expanded the past decade. However, non-coding are less well-characterized and only a handful recurrent mutations, most notably TERT promoter have been reported. Here, as part ICGC/TCGA Pan-Cancer Analysis Whole Genomes (PCAWG) Consortium, which aggregated whole genome sequencing data from 2658 across 38 tumor types, we perform multi-faceted pathway network analyses 2583 genomes 27 types compiled by PCAWG...
This study tackles a common, yet underrated problem in remote-sensing image analysis: the fact that human interpretation is highly variable among different operators. Despite current technological advancements, perception and are still vital components of map-making process. Consequently, errors can considerably bias both mapping modelling results. In our study, we present web-based tool to quantify operator variability identify external factors affecting this variability. Human operators...
Elevated aerobic glycolysis rate is a biochemical alteration associated with malignant transformation and cancer progression. This metabolic shift unavoidably generates methylglyoxal (MG), potent inducer of dicarbonyl stress through the formation advanced glycation end products (AGEs). We have previously shown that silencing glyoxalase 1 (GLO1), main MG detoxifying enzyme, endogenous resulting in enhanced growth metastasis vivo. However, molecular mechanisms which promotes development remain...
Significance Carbon fixation and accumulation as lignocellulosic biomass is of global ecological industrial importance most significantly occurs in the form wood development trees. Traits are highly complex and, aside from environmental factors, affected by many pathways thousands genes. We have applied a network-based data integration method for systems genetics analysis genes, processes, underlying bioenergy-related traits using segregating Eucalyptus hybrid tree populations. could link...
With the advances in high throughput technologies, increasing amounts of cancer somatic mutation data are being generated and made available. Only a small number (driver) mutations occur driver genes responsible for carcinogenesis, while majority (passenger) do not influence tumour biology. In this study, SomInaClust is introduced, method that accurately identifies based on their pattern across samples then classifies them into oncogenes or suppressor respectively. starts from observation...
The study of cancer, a highly heterogeneous disease with different causes and clinical outcomes, requires multi-angle approach the collection large multi-omics datasets that, ideally, should be analyzed simultaneously. We present new pathway relevance ranking method that is able to prioritize pathways according information contained in any combination tumor related omics datasets. Key conversion all available data into single comprehensive network representation containing not only genes but...
Subtyping cancer is key to an improved and more personalized prognosis/treatment. The increasing availability of tumor related molecular data provides the opportunity identify subtypes in a data-driven way. Molecular are defined as groups samples that have similar mechanism at origin carcinogenesis. mechanisms reflected by subtype-specific mutational expression features. Data-driven subtyping complex problem identifying drive carcinogenesis confounded problems. Many current integrative...
Electromagnetic induction soil sensors are an increasingly important source of secondary information to predict texture. In a 10.5‐ha polder field, EM38DD survey was performed with resolution 2 by m and 78 samples were analyzed for sub‐ topsoil Due the presence former water channels in subsoil, coefficient variation subsoil clay content (45%) much larger compared (13%). The horizontal (EC –H) vertical –V) electrical conductivity measurements displayed similar pattern, indicating dominant...
An often undervalued but inevitable component in remote sensing image analysis is human perception and interpretation. Human intervention a requisite for visual interpretation, where the interpreter actually performs analysis. Although processing became more automated, screening interpretation remained indispensable at certain stages. One particular stage operator plays crucial role development of reference maps. This done by an operator. result adequately assessing automated systems'...
This paper focuses on a method to overcome some of the disadvantages that are related with use artificial neural networks (ANNs) as supervised classifiers. The proposed aims at speeding up network learning, improving classification accuracies and reducing variability performance due random weight initialization. can be realized by transferring implicit knowledge from previously learned source task new target using algorithm, Discriminality Based Transfer (DBT). presented approach is compared...
MicroRNAs (miRNAs) have been shown to play an important role in pathological initiation, progression and maintenance. Because identification the laboratory of disease-related miRNAs is not straightforward, numerous network-based methods developed predict novel silico. Homogeneous networks (in which every node a miRNA) based on targets shared between widely used their disease phenotypes. Although such homogeneous can potential disease-associated miRNAs, they do consider roles target genes...
Mapping dominant vegetation communities is important work for scientists. It very difficult to map using multispectral remote sensing data only, especially in mountain areas. However plant community contain useful information about the relationships between and their environment. In this paper, are linked with communities. The Bayesian soft classifier was used produce posterior probability images each class. These were calculate prior probabilities. One hundred eighty plots at Meili Snow...
Abstract The catalog of cancer driver mutations in protein-coding genes has greatly expanded the past decade. However, non-coding are less well-characterized and only a handful recurrent mutations, most notably TERT promoter have been reported. Motivated by success pathway network analyses prioritizing rare genes, we performed multi-faceted across 2,583 whole genomes from 27 tumor types compiled ICGC/TCGA PCAWG project. While few genomic elements were recurrently mutated this cohort,...
Remotely sensed images usually contain both pure and mixed pixels. Crisp classification techniques assign pixels to the class with highest proportion of coverage or probability. Unfortunately, during this process information is lost. Soft fuzzy were introduced make up for loss by assigning fractions land cover classes in correspondence area represented inside a pixel. A yields number fraction equal considered classification. However, assignment these renders no about location P.M. Atkinson...
Abstract Motivation: When genomic data are associated with gene expression data, the resulting quantitative trait loci (eQTL) will likely span multiple genes. eQTL prioritization techniques can be used to select most causal affecting of a target from list candidates. As an input, these use physical interaction networks that often contain highly connected genes and unreliable or irrelevant interactions interfere process. We present EPSILON, extendable framework for prioritization, which...
Recent technological evolutions have led to an exponential increase in data all the omics fields. It is expected that integration of these different sources, will drastically enhance our knowledge biological mechanisms behind genomic diseases such as cancer. However, still remains a challenge. In this work we propose intuitive workflow for integrative analysis expression, mutation and copy number taken from METABRIC study on breast First, present evidence expression profile many important...
The use of Artificial Neural Networks (ANNs) for the classification remotely sensed imagery offers several advantages over more conventional methods. Yet their training still requires a set pixels with known land cover. To increase ANN accuracy when few data are available, an algorithm was applied that allows experience gained in previous classifications to be reused. proposed method evaluated by classifying tropical savannah region northern Togo using Landsat Thematic Mapper (TM) imagery....