Mapping of Environmental Data Using Kernel-Based Methods

Recently, kernel-based Machine Learning methods have gained great popularity in many data analysis and data mining fields: pattern recognition, biocomputing, speech and vision, engineering, remote sensing etc. The paper describes the use of kernel methods to approach the processing of large datasets from environmental monitoring networks. Several typical problems of the environmental sciences and their solutions provided by kernel-based methods are considered: classification of categorical data (soil type classification), mapping of environmental and pollution continuous information (pollution of soil by radionuclides), mapping with auxiliary information (climatic data from Aral Sea region). The promising developments, such as automatic emergency hot spot detection and monitoring network optimization are discussed as well.

Mult-class differentiation of cannabis seedlings in a forensic context

This article presents an experimental study about the classification ability of several classifiers for multi-classclassification of cannabis seedlings. As the cultivation of drug type cannabis is forbidden in Switzerland lawenforcement authorities regularly ask forensic laboratories to determinate the chemotype of a seized cannabisplant and then to conclude if the plantation is legal or not. This classification is mainly performed when theplant is mature as required by the EU official protocol and then the classification of cannabis seedlings is a timeconsuming and costly procedure. A previous study made by the authors has investigated this problematic [1]and showed that it is possible to differentiate between drug type (illegal) and fibre type (legal) cannabis at anearly stage of growth using gas chromatography interfaced with mass spectrometry (GC-MS) based on therelative proportions of eight major leaf compounds. The aims of the present work are on one hand to continueformer work and to optimize the methodology for the discrimination of drug- and fibre type cannabisdeveloped in the previous study and on the other hand to investigate the possibility to predict illegal cannabisvarieties. Seven classifiers for differentiating between cannabis seedlings are evaluated in this paper, namelyLinear Discriminant Analysis (LDA), Partial Least Squares Discriminant Analysis (PLS-DA), Nearest NeighbourClassification (NNC), Learning Vector Quantization (LVQ), Radial Basis Function Support Vector Machines(RBF SVMs), Random Forest (RF) and Artificial Neural Networks (ANN). The performance of each method wasassessed using the same analytical dataset that consists of 861 samples split into drug- and fibre type cannabiswith drug type cannabis being made up of 12 varieties (i.e. 12 classes). The results show that linear classifiersare not able to manage the distribution of classes in which some overlap areas exist for both classificationproblems. Unlike linear classifiers, NNC and RBF SVMs best differentiate cannabis samples both for 2-class and12-class classifications with average classification results up to 99% and 98%, respectively. Furthermore, RBFSVMs correctly classified into drug type cannabis the independent validation set, which consists of cannabisplants coming from police seizures. In forensic case work this study shows that the discrimination betweencannabis samples at an early stage of growth is possible with fairly high classification performance fordiscriminating between cannabis chemotypes or between drug type cannabis varieties.

Radial forearm free flap donor site morbidity: ulnar-based transposition flap vs split-thickness skin graft.

OBJECTIVES: To evaluate morbidity associated with the radial forearm free flap donor site and to compare functional and aesthetic outcomes of ulnar-based transposition flap (UBTF) vs split-thickness skin graft (STSG) closure of the donor site.¦DESIGN: Case-control study.¦SETTING: Tertiary care institution.¦PATIENTS: The inclusion criteria were flap size not exceeding 30 cm(2), patient availability for a single follow-up visit, and performance of surgery at least 6 months previously. Forty-four patients were included in the study and were reviewed. Twenty-two patients had UBTF closure, and 22 had STSG closure.¦MAIN OUTCOME MEASURES: Variables analyzed included wrist mobility, Michigan Hand Outcomes Questionnaire scores, pinch and grip strength (using a dynamometer), and hand sensitivity (using monofilament testing over the radial nerve distribution). In analyses of operated arms vs nonoperated arms, variables obtained only for the operated arms included Vancouver Scar Scale scores and visual analog scale scores for Aesthetics and Overall Arm Function.¦RESULTS: The mean (SD) wrist extension was significantly better in the UBTF group (56.0° [10.4°] for nonoperated arms and 62.0° [9.7°] for operated arms) than in the STSG group (59.0° [7.1°] for nonoperated arms and 58.4° [12.1°] for operated arms) (P = .02). The improvement in wrist range of motion for the UBTF group approached statistical significance (P = .07). All other variables (Michigan Hand Outcomes Questionnaire scores, pinch and grip strength, hand sensitivity, and visual analog scale scores) were significantly better for nonoperated arms vs operated arms, but no significant differences were observed between the UBTF and STSG groups.¦CONCLUSIONS: The radial forearm free flap donor site carries significant morbidity. Donor site UBTF closure was associated with improved wrist extension and represents an alternative method of closure for small donor site defects.

Influence of the implanted pulse generator as reference electrode in finite element model of monopolar deep brain stimulation.

Electrical deep brain stimulation (DBS) is an efficient method to treat movement disorders. Many models of DBS, based mostly on finite elements, have recently been proposed to better understand the interaction between the electrical stimulation and the brain tissues. In monopolar DBS, clinically widely used, the implanted pulse generator (IPG) is used as reference electrode (RE). In this paper, the influence of the RE model of monopolar DBS is investigated. For that purpose, a finite element model of the full electric loop including the head, the neck and the superior chest is used. Head, neck and superior chest are made of simple structures such as parallelepipeds and cylinders. The tissues surrounding the electrode are accurately modelled from data provided by the diffusion tensor magnetic resonance imaging (DT-MRI). Three different configurations of RE are compared with a commonly used model of reduced size. The electrical impedance seen by the DBS system and the potential distribution are computed for each model. Moreover, axons are modelled to compute the area of tissue activated by stimulation. Results show that these indicators are influenced by the surface and position of the RE. The use of a RE model corresponding to the implanted device rather than the usually simplified model leads to an increase of the system impedance (+48%) and a reduction of the area of activated tissue (-15%).

The ENCODE (ENCyclopedia Of DNA Elements) Project.

The ENCyclopedia Of DNA Elements (ENCODE) Project aims to identify all functional elements in the human genome sequence. The pilot phase of the Project is focused on a specified 30 megabases (approximately 1%) of the human genome sequence and is organized as an international consortium of computational and laboratory-based scientists working to develop and apply high-throughput approaches for detecting all sequence elements that confer biological function. The results of this pilot phase will guide future efforts to analyze the entire human genome.

Oscillation modes of microtubules.

Microtubules are long, filamentous protein complexes which play a central role in several cellular physiological processes, such as cell division transport and locomotion. Their mechanical properties are extremely important since they determine the biological function. In a recently published experiment [Phys. Rev. Lett. 89 (2002) 248101], microtubule's Young's and shear moduli were simultaneously measured, proving that they are highly anisotropic. Together with the known structure, this finding opens the way to better understand and predict their mechanical behavior under a particular set of conditions. In the present study, we modeled microtubules by using the finite elements method and analyzed their oscillation modes. The analysis revealed that oscillation modes involving a change in the diameter of the microtubules strongly depend on the shear modulus. In these modes, the correlation times of the movements are just slightly shorter than diffusion times of free molecules surrounding the microtubule. It could be therefore speculated that the matching of the two timescales could play a role in facilitating the interactions between microtubules and MT associated proteins, and between microtubules and tubulins themselves.

Orthotropic active strain models for the numerical simulation of cardiac biomechanics

An active strain formulation for orthotropic constitutive laws arising in cardiac mechanics modeling is introduced and studied. The passive mechanical properties of the tissue are described by the Holzapfel-Ogden relation. In the active strain formulation, the Euler-Lagrange equations for minimizing the total energy are written in terms of active and passive deformation factors, where the active part is assumed to depend, at the cell level, on the electrodynamics and on the specific orientation of the cardiac cells. The well-posedness of the linear system derived from a generic Newton iteration of the original problem is analyzed and different mechanical activation functions are considered. In addition, the active strain formulation is compared with the classical active stress formulation from both numerical and modeling perspectives. Taylor-Hood and MINI finite elements are employed to discretize the mechanical problem. The results of several numerical experiments show that the proposed formulation is mathematically consistent and is able to represent the main key features of the phenomenon, while allowing savings in computational costs.

A comparison of methods for differential expression analysis of RNA-seq data.

BACKGROUND: Finding genes that are differentially expressed between conditions is an integral part of understanding the molecular basis of phenotypic variation. In the past decades, DNA microarrays have been used extensively to quantify the abundance of mRNA corresponding to different genes, and more recently high-throughput sequencing of cDNA (RNA-seq) has emerged as a powerful competitor. As the cost of sequencing decreases, it is conceivable that the use of RNA-seq for differential expression analysis will increase rapidly. To exploit the possibilities and address the challenges posed by this relatively new type of data, a number of software packages have been developed especially for differential expression analysis of RNA-seq data. RESULTS: We conducted an extensive comparison of eleven methods for differential expression analysis of RNA-seq data. All methods are freely available within the R framework and take as input a matrix of counts, i.e. the number of reads mapping to each genomic feature of interest in each of a number of samples. We evaluate the methods based on both simulated data and real RNA-seq data. CONCLUSIONS: Very small sample sizes, which are still common in RNA-seq experiments, impose problems for all evaluated methods and any results obtained under such conditions should be interpreted with caution. For larger sample sizes, the methods combining a variance-stabilizing transformation with the 'limma' method for differential expression analysis perform well under many different conditions, as does the nonparametric SAMseq method.

Machine learning for geospatial data : algorithms, software tools and case studies

Résumé Cette thèse est consacrée à l'analyse, la modélisation et la visualisation de données environnementales à référence spatiale à l'aide d'algorithmes d'apprentissage automatique (Machine Learning). L'apprentissage automatique peut être considéré au sens large comme une sous-catégorie de l'intelligence artificielle qui concerne particulièrement le développement de techniques et d'algorithmes permettant à une machine d'apprendre à partir de données. Dans cette thèse, les algorithmes d'apprentissage automatique sont adaptés pour être appliqués à des données environnementales et à la prédiction spatiale. Pourquoi l'apprentissage automatique ? Parce que la majorité des algorithmes d'apprentissage automatiques sont universels, adaptatifs, non-linéaires, robustes et efficaces pour la modélisation. Ils peuvent résoudre des problèmes de classification, de régression et de modélisation de densité de probabilités dans des espaces à haute dimension, composés de variables informatives spatialisées (« géo-features ») en plus des coordonnées géographiques. De plus, ils sont idéaux pour être implémentés en tant qu'outils d'aide à la décision pour des questions environnementales allant de la reconnaissance de pattern à la modélisation et la prédiction en passant par la cartographie automatique. Leur efficacité est comparable au modèles géostatistiques dans l'espace des coordonnées géographiques, mais ils sont indispensables pour des données à hautes dimensions incluant des géo-features. Les algorithmes d'apprentissage automatique les plus importants et les plus populaires sont présentés théoriquement et implémentés sous forme de logiciels pour les sciences environnementales. Les principaux algorithmes décrits sont le Perceptron multicouches (MultiLayer Perceptron, MLP) - l'algorithme le plus connu dans l'intelligence artificielle, le réseau de neurones de régression généralisée (General Regression Neural Networks, GRNN), le réseau de neurones probabiliste (Probabilistic Neural Networks, PNN), les cartes auto-organisées (SelfOrganized Maps, SOM), les modèles à mixture Gaussiennes (Gaussian Mixture Models, GMM), les réseaux à fonctions de base radiales (Radial Basis Functions Networks, RBF) et les réseaux à mixture de densité (Mixture Density Networks, MDN). Cette gamme d'algorithmes permet de couvrir des tâches variées telle que la classification, la régression ou l'estimation de densité de probabilité. L'analyse exploratoire des données (Exploratory Data Analysis, EDA) est le premier pas de toute analyse de données. Dans cette thèse les concepts d'analyse exploratoire de données spatiales (Exploratory Spatial Data Analysis, ESDA) sont traités selon l'approche traditionnelle de la géostatistique avec la variographie expérimentale et selon les principes de l'apprentissage automatique. La variographie expérimentale, qui étudie les relations entre pairs de points, est un outil de base pour l'analyse géostatistique de corrélations spatiales anisotropiques qui permet de détecter la présence de patterns spatiaux descriptible par une statistique. L'approche de l'apprentissage automatique pour l'ESDA est présentée à travers l'application de la méthode des k plus proches voisins qui est très simple et possède d'excellentes qualités d'interprétation et de visualisation. Une part importante de la thèse traite de sujets d'actualité comme la cartographie automatique de données spatiales. Le réseau de neurones de régression généralisée est proposé pour résoudre cette tâche efficacement. Les performances du GRNN sont démontrées par des données de Comparaison d'Interpolation Spatiale (SIC) de 2004 pour lesquelles le GRNN bat significativement toutes les autres méthodes, particulièrement lors de situations d'urgence. La thèse est composée de quatre chapitres : théorie, applications, outils logiciels et des exemples guidés. Une partie importante du travail consiste en une collection de logiciels : Machine Learning Office. Cette collection de logiciels a été développée durant les 15 dernières années et a été utilisée pour l'enseignement de nombreux cours, dont des workshops internationaux en Chine, France, Italie, Irlande et Suisse ainsi que dans des projets de recherche fondamentaux et appliqués. Les cas d'études considérés couvrent un vaste spectre de problèmes géoenvironnementaux réels à basse et haute dimensionnalité, tels que la pollution de l'air, du sol et de l'eau par des produits radioactifs et des métaux lourds, la classification de types de sols et d'unités hydrogéologiques, la cartographie des incertitudes pour l'aide à la décision et l'estimation de risques naturels (glissements de terrain, avalanches). Des outils complémentaires pour l'analyse exploratoire des données et la visualisation ont également été développés en prenant soin de créer une interface conviviale et facile à l'utilisation. Machine Learning for geospatial data: algorithms, software tools and case studies Abstract The thesis is devoted to the analysis, modeling and visualisation of spatial environmental data using machine learning algorithms. In a broad sense machine learning can be considered as a subfield of artificial intelligence. It mainly concerns with the development of techniques and algorithms that allow computers to learn from data. In this thesis machine learning algorithms are adapted to learn from spatial environmental data and to make spatial predictions. Why machine learning? In few words most of machine learning algorithms are universal, adaptive, nonlinear, robust and efficient modeling tools. They can find solutions for the classification, regression, and probability density modeling problems in high-dimensional geo-feature spaces, composed of geographical space and additional relevant spatially referenced features. They are well-suited to be implemented as predictive engines in decision support systems, for the purposes of environmental data mining including pattern recognition, modeling and predictions as well as automatic data mapping. They have competitive efficiency to the geostatistical models in low dimensional geographical spaces but are indispensable in high-dimensional geo-feature spaces. The most important and popular machine learning algorithms and models interesting for geo- and environmental sciences are presented in details: from theoretical description of the concepts to the software implementation. The main algorithms and models considered are the following: multi-layer perceptron (a workhorse of machine learning), general regression neural networks, probabilistic neural networks, self-organising (Kohonen) maps, Gaussian mixture models, radial basis functions networks, mixture density networks. This set of models covers machine learning tasks such as classification, regression, and density estimation. Exploratory data analysis (EDA) is initial and very important part of data analysis. In this thesis the concepts of exploratory spatial data analysis (ESDA) is considered using both traditional geostatistical approach such as_experimental variography and machine learning. Experimental variography is a basic tool for geostatistical analysis of anisotropic spatial correlations which helps to understand the presence of spatial patterns, at least described by two-point statistics. A machine learning approach for ESDA is presented by applying the k-nearest neighbors (k-NN) method which is simple and has very good interpretation and visualization properties. Important part of the thesis deals with a hot topic of nowadays, namely, an automatic mapping of geospatial data. General regression neural networks (GRNN) is proposed as efficient model to solve this task. Performance of the GRNN model is demonstrated on Spatial Interpolation Comparison (SIC) 2004 data where GRNN model significantly outperformed all other approaches, especially in case of emergency conditions. The thesis consists of four chapters and has the following structure: theory, applications, software tools, and how-to-do-it examples. An important part of the work is a collection of software tools - Machine Learning Office. Machine Learning Office tools were developed during last 15 years and was used both for many teaching courses, including international workshops in China, France, Italy, Ireland, Switzerland and for realizing fundamental and applied research projects. Case studies considered cover wide spectrum of the real-life low and high-dimensional geo- and environmental problems, such as air, soil and water pollution by radionuclides and heavy metals, soil types and hydro-geological units classification, decision-oriented mapping with uncertainties, natural hazards (landslides, avalanches) assessments and susceptibility mapping. Complementary tools useful for the exploratory data analysis and visualisation were developed as well. The software is user friendly and easy to use.

An active strain electromechanical model for cardiac tissue

We propose a finite element approximation of a system of partial differential equations describing the coupling between the propagation of electrical potential and large deformations of the cardiac tissue. The underlying mathematical model is based on the active strain assumption, in which it is assumed that a multiplicative decomposition of the deformation tensor into a passive and active part holds, the latter carrying the information of the electrical potential propagation and anisotropy of the cardiac tissue into the equations of either incompressible or compressible nonlinear elasticity, governing the mechanical response of the biological material. In addition, by changing from an Eulerian to a Lagrangian configuration, the bidomain or monodomain equations modeling the evolution of the electrical propagation exhibit a nonlinear diffusion term. Piecewise quadratic finite elements are employed to approximate the displacements field, whereas for pressure, electrical potentials and ionic variables are approximated by piecewise linear elements. Various numerical tests performed with a parallel finite element code illustrate that the proposed model can capture some important features of the electromechanical coupling, and show that our numerical scheme is efficient and accurate.

Superficial and deep changes of cellular mechanical properties following cytoskeleton disassembly.

The cytoskeleton, composed of actin filaments, intermediate filaments, and microtubules, is a highly dynamic supramolecular network actively involved in many essential biological mechanisms such as cellular structure, transport, movements, differentiation, and signaling. As a first step to characterize the biophysical changes associated with cytoskeleton functions, we have developed finite elements models of the organization of the cell that has allowed us to interpret atomic force microscopy (AFM) data at a higher resolution than that in previous work. Thus, by assuming that living cells behave mechanically as multilayered structures, we have been able to identify superficial and deep effects that could be related to actin and microtubule disassembly, respectively. In Cos-7 cells, actin destabilization with Cytochalasin D induced a decrease of the visco-elasticity close to the membrane surface, while destabilizing microtubules with Nocodazole produced a stiffness decrease only in deeper parts of the cell. In both cases, these effects were reversible. Cell softening was measurable with AFM at concentrations of the destabilizing agents that did not induce detectable effects on the cytoskeleton network when viewing the cells with fluorescent confocal microscopy. All experimental results could be simulated by our models. This technology opens the door to the study of the biophysical properties of signaling domains extending from the cell surface to deeper parts of the cell.

Regulation of the Gac/Rsm pathway in "Pseudomonas fluorescens" CHA0

SUMMARY : Two-component systems are key mediators implicated in the response of numerous bacteria to a wide range of signals and stimuli. The two-component system comprised of the sensor kinase GacS and the response regulator GacA is broadly distributed among γ-proteobacteria bacteria and fulfils diverse functions such as regulation of carbon storage and expression of virulence. In Pseudomonas fluorescens, a soil bacterium which protects plants from root-pathogenic fungi and nematodes, the GacS/GacA two-component system has been shown to be essential for the production of secondary metabolites and exoenzymes required for the biocontrol activity of the bacterium. The regulatory cascade initiated by GacS/GacA consists of two translational repressor proteins, RsmA and RsmE, as well as three GacAcontrolled small regulatory RNAs RsmX, RsmY and RsmZ, which titrate RsmA and RsmE to allow the expression of biocontrol factors. Genetic analysis revealed that two additional sensor kinases termed RetS and Lads were involved as negative and positive control elements, respectively, in the Gac/Rsm pathway in P. fluoresens CHAO. Furthermore, it could be proposed that RetS and Lads interact with GacS, thereby modulating the expression of antibiotic compounds and hydrogen cyanide, as well as the rpoS gene encoding the stress and stationary phase sigma factor σ. Temperature was found to be an important environmental cue that influences the Gac/Rsm network. Indeed, the production of antibiotic compounds and hydrogen cyanide was reduced at 35°C, by comparison with the production at 30°C. RetS was identified to be involved in this temperature control. The small RNA RsmY was confirmed to be positively regulated by GacA and RsmA/RsmE. Two essential regions were identified in the rsmY promoter by mutational analysis, the upstream activating sequence (UAS) and the linker sequence. Although direct experimental evidence is still missing, several observations suggest that GacA may bind to the UAS, whereas the linker region would be recognized by intermediate RsmA/RsmEdependent repressors and/or activators. In conclusion, this work has revealed new elements contributing to the function of the signal transduction mechanisms in the Gac/Rsm pathway. RESUME : Les systèmes ä deux composants sont des mécanismes d'une importance notoire que beaucoup de bactéries utilisent pour faire face et répondre aux stimuli environnementaux. Le système à deux composants comprenant le senseur GacS et le régulateur de réponse GacA est très répandu chez les γ-protéobactéries et remplit des fonctions aussi diverses que la régulation du stockage de carbone ou l'expression de la virulence. Chez Pseudomonas fluorescens CHAO, une bactérie du sol qui protège les racines des plantes contre des attaques de champignons et nématodes pathogènes, le système à deux composants GacS/GacA est essentiel à la production de métabolites secondaires et d'exoenzymes requis pour l'activité de biocontrôle de la bactérie. La cascade régulatrice initiée pas GacS/GacA fait intervenir deux protéines répresseur de traduction, RsmA et RsmE, ainsi que trois petits ARNs RsmX, RsmY et RsmZ, dont la production est contrôlée par GacA. Ces petits ARNs ont pour rôle de contrecarrer l'action des protéines répressseur de la traduction, ce qui permet l'expression de facteurs de biocontrôle. Des analyses génétiques ont révélé la présence de deux senseurs supplémentaires, appelés Rets et Lads, qui interviennent dans la cascade Gac/Rsm de P. fluorescens. L'impact de ces senseurs est, respectivement, négatif et positif. Ces interactions ont apparenunent lieu au niveau de GacS et permettent une modulation de l'expression des antibiotiques et de l'acide cyanhydrique, ainsi que du gène rpoS codant pour le facteur sigma du stress. La température s'est révélée être un facteur environnemental important qui influence la cascade Gac/Rsm. Il s'avère en effet que la production d'antibiotiques ainsi que d'acide cyanhydrique est moins importante à 35°C qu'à 30°C. L'implication du senseur Rets dans ce contrôle par la température a pu être démontrée. La régulation positive du petit ARN RsmY par GacA et RsmA/RsmE a pu être confirmée; par le biais d'une analyse mutationelle, deux régions essentielles ont pu être mises en évidence dans la région promotrice de rsmY. Malgré le manque de preuves expérimentales directes, certains indices suggèrent que GacA puisse directement se fixer sur une des deux régions (appelée UAS), tandis que la deuxième région (appelée linker) serait plutôt reconnue par des facteurs intermédiaires (activateurs ou répresseurs) dépendant de RsmA/RsmE. En conclusion, ce travail a dévoilé de nouveaux éléments permettant d'éclairer les mécanismes de transduction des signaux dans la cascade Gac/Rsm.

Functional assessment of chest wall integrity after methylmethacrylate reconstruction.

BACKGROUND: All patients with extensive resection of the anterolateral chest wall and the sternum followed by reconstruction with methylmethacrylate substitutes were assessed prospectively 6 months after the operation to delineate chest wall integrity with pulmonary function and cine-magnetic resonance imaging. METHODS: Twenty-six patients underwent chest wall reconstruction by use of methylmethacrylate between 1994 and 1998 due to primary tumors in 35%, metastases in 27%, T3 lung cancer in 19%, and debridement for radionecrosis and osteomyelitis in 19% of patients. Three to eight ribs were resected and additional sternum resection was performed in 39% of patients. RESULTS: There was no 30-day mortality. All patients were extubated after the operation without need for reintubation. Prosthesis dislocation occurred in 1 patient and infection in 2 patients during follow-up. Nineteen patients (73%) suffered no restrictions of daily activities. Clinical examination revealed normal shoulder girdle function in 77% of patients. There was no significant difference between preoperative and postoperative FEV1 (forced expiratory volume in 1 second) measurements in patients with lobectomy or wedge resections. Cinemagnetic resonance imaging revealed concordant chest wall movements during respiration in 92% of patients without paradoxical movements or implant dislocations being observed. CONCLUSIONS: Large defects of the anterolateral chest wall and sternum can be reconstructed efficiently with methylmethacrylate substitutes with minimal morbidity and excellent cosmetic and functional outcome.