Machine learning algorithms for spatial data. Case studies: Environmental pollution, natural hazards, renewable resources

This paper presents general problems and approaches for the spatial data analysis using machine learning algorithms. Machine learning is a very powerful approach to adaptive data analysis, modelling and visualisation. The key feature of the machine learning algorithms is that they learn from empirical data and can be used in cases when the modelled environmental phenomena are hidden, nonlinear, noisy and highly variable in space and in time. Most of the machines learning algorithms are universal and adaptive modelling tools developed to solve basic problems of learning from data: classification/pattern recognition, regression/mapping and probability density modelling. In the present report some of the widely used machine learning algorithms, namely artificial neural networks (ANN) of different architectures and Support Vector Machines (SVM), are adapted to the problems of the analysis and modelling of geo-spatial data. Machine learning algorithms have an important advantage over traditional models of spatial statistics when problems are considered in a high dimensional geo-feature spaces, when the dimension of space exceeds 5. Such features are usually generated, for example, from digital elevation models, remote sensing images, etc. An important extension of models concerns considering of real space constrains like geomorphology, networks, and other natural structures. Recent developments in semi-supervised learning can improve modelling of environmental phenomena taking into account on geo-manifolds. An important part of the study deals with the analysis of relevant variables and models' inputs. This problem is approached by using different feature selection/feature extraction nonlinear tools. To demonstrate the application of machine learning algorithms several interesting case studies are considered: digital soil mapping using SVM, automatic mapping of soil and water system pollution using ANN; natural hazards risk analysis (avalanches, landslides), assessments of renewable resources (wind fields) with SVM and ANN models, etc. The dimensionality of spaces considered varies from 2 to more than 30. Figures 1, 2, 3 demonstrate some results of the studies and their outputs. Finally, the results of environmental mapping are discussed and compared with traditional models of geostatistics.

Vasoactive intestinal peptide, pituitary adenylate cyclase-activating peptide, and noradrenaline induce the transcription factors CCAAT/enhancer binding protein (C/EBP)-beta and C/EBP delta in mouse cortical astrocytes: involvement in cAMP-regulated glycogen metabolism.

We have described previously a transcription-dependent induction of glycogen resynthesis by the vasoactive intestinal peptide (VIP) or noradrenaline (NA) in astrocytes, which is mediated by cAMP. Because it has been postulated that the cAMP-mediated regulation of energy balance in hepatocytes and adipocytes is channeled at least in part through the CCAAT/enhancer binding protein (C/EBP) family of transcription factors, we tested the hypothesis that C/EBP isoforms could be expressed in mouse cortical astrocytes and that their level of expression could be regulated by VIP, by the VIP-related neuropeptide pituitary adenylate cyclase-activating peptide (PACAP), or by NA. We report in this study that in these cells, C/EBP beta and C/EBP delta are induced by VIP, PACAP, or NA via the cAMP second-messenger pathway. Induction of C/EBP beta and -delta mRNA by VIP occurs in the presence of a protein synthesis inhibitor. Thus, c/ebp beta and c/ebp delta behave as cAMP-inducible immediate-early genes in astrocytes. Moreover, transfection of astrocytes with expression vectors selectively producing the transcriptionally active form of C/EBP beta, termed liver-enriched transcriptional activator protein, or C/EBP delta enhance the glycogen resynthesis elicited by NA, whereas an expression vector producing the transcriptionally inactive form of C/EBP beta, termed liver-enriched transcriptional inhibitory protein, reduces this resynthesis. These results support the idea that C/EBP beta and -delta regulate gene expression of energy metabolism-related enzymes in astrocytes.

In vivo binding of the Cry11Bb toxin of Bacillus thuringiensis subsp. medellin to the midgut of mosquito larvae (Diptera: Culicidae)

Bacillus thuringiensis subsp. medellin produces numerous proteins among which 94 kDa known as Cry11Bb, has mosquitocidal activity. The mode of action of the Cry11 proteins has been described as similar to those of the Cry1 toxins, nevertheless, the mechanism of action is still not clear. In this study we investigated the in vivo binding of the Cry11Bb toxin to the midgut of the insect species Anopheles albimanus, Aedes aegypti, and Culex quinquefasciatus by immunohistochemical analysis. Spodoptera frugiperda was included as negative control. The Cry11Bb protein was detected on the apical microvilli of the midgut epithelial cells, mostly on the posterior midgut and gastric caeca of the three mosquito species. Additionally, the toxin was detected in the Malpighian tubules of An. albimanus, Ae. aegypti, Cx. quinquefasciatus, and in the basal membrane of the epithelial cells of Ae. aegypti midgut. No toxin accumulation was observed in the peritrophic membrane of any of the mosquito species studied. These results confirm that the primary site of action of the Cry11 toxins is the apical membrane of the midgut epithelial cells of mosquito larvae.

Amino acids of the alpha1B-adrenergic receptor involved in agonist binding: differences in docking catecholamines to receptor subtypes.

Site-directed mutagenesis and molecular dynamics analysis of the 3-D model of the alpha1B-adrenergic receptor (AR) were combined to identify the molecular determinants of the receptor involved in catecholamine binding. Our results indicate that the three conserved serines in the fifth transmembrane domain (TMD) of the alpha1B-AR play a distinct role in catecholamine binding versus receptor activation. In addition to the amino acids D125 in TMDIII and S207 in TMDV directly involved in ligand binding, our findings identify a large number of polar residues playing an important role in the activation process of the alpha1B-AR thus providing new insights into the structure/function relationship of G protein-coupled receptors.

Ezrin-Radixin-Moesin-binding Sequence of PSGL-1 Glycoprotein Regulates Leukocyte Rolling on Selectins and Activation of Extracellular Signal-regulated Kinases.

P-selectin glycoprotein ligand-1 (PSGL-1) mediates the capture (tethering) of free-flowing leukocytes and subsequent rolling on selectins. PSGL-1 interactions with endothelial selectins activate Src kinases and spleen tyrosine kinase (Syk), leading to α(L)β(2) integrin-dependent leukocyte slow rolling, which promotes leukocyte recruitment into tissues. In addition, but through a distinct pathway, PSGL-1 engagement activates ERK. Because ezrin, radixin and moesin proteins (ERMs) link PSGL-1 to actin cytoskeleton and because they serve as adaptor molecules between PSGL-1 and Syk, we examined the role of PSGL-1 ERM-binding sequence (EBS) on cell capture, rolling, and signaling through Syk and MAPK pathways. We carried out mutational analysis and observed that deletion of EBS severely reduced 32D leukocyte tethering and rolling on L-, P-, and E-selectin and slightly increased rolling velocity. Alanine substitution of Arg-337 and Lys-338 showed that these residues play a key role in supporting leukocyte tethering and rolling on selectins. Importantly, EBS deletion or Arg-337 and Lys-338 mutations abrogated PSGL-1-induced ERK activation, whereas they did not prevent Syk phosphorylation or E-selectin-induced leukocyte slow rolling. These studies demonstrate that PSGL-1 EBS plays a critical role in recruiting leukocytes on selectins and in activating the MAPK pathway, whereas it is dispensable to phosphorylate Syk and to lead to α(L)β(2)-dependent leukocyte slow rolling.

Identification of proteoglycans as the APRIL-specific binding partners.

B cell activating factor of the tumor necrosis factor (TNF) family (BAFF) and a proliferation-inducing ligand (APRIL) are closely related ligands within the TNF superfamily that play important roles in B lymphocyte biology. Both ligands share two receptors--transmembrane activator and calcium signal--modulating cyclophilin ligand interactor (TACI) and B cell maturation antigen (BCMA)--that are predominantly expressed on B cells. In addition, BAFF specifically binds BAFF receptor, whereas the nature of a postulated APRIL-specific receptor remains elusive. We show that the TNF homology domain of APRIL binds BCMA and TACI, whereas a basic amino acid sequence (QKQKKQ) close to the NH2 terminus of the mature protein is required for binding to the APRIL-specific "receptor." This interactor was identified as negatively charged sulfated glycosaminoglycan side chains of proteoglycans. Although T cell lines bound little APRIL, the ectopic expression of glycosaminoglycan-rich syndecans or glypicans conferred on these cells a high binding capacity that was completely dependent on APRIL's basic sequence. Moreover, syndecan-1-positive plasma cells and proteoglycan-rich nonhematopoietic cells displayed high specific, heparin-sensitive binding to APRIL. Inhibition of BAFF and APRIL, but not BAFF alone, prevented the survival and/or the migration of newly formed plasma cells to the bone marrow. In addition, costimulation of B cell proliferation by APRIL was only effective upon APRIL oligomerization. Therefore, we propose a model whereby APRIL binding to the extracellular matrix or to proteoglycan-positive cells induces APRIL oligomerization, which is the prerequisite for the triggering of TACI- and/or BCMA-mediated activation, migration, or survival signals.

Spatial analysis of the distribution of leprosy in the State of Ceará, Northeast Brazil

The aim of this study was to describe spatial patterns of the distribution of leprosy and to investigate spatial clustering of incidence rates in the state of Ceará, Northeast Brazil. The average incidence rate of leprosy for the period of 1991 to 1999 was calculated for each municipality of Ceará. Maps were used to describe the spatial distribution of the disease, and spatial statistics were applied to explore large- and small-scale variations of incidence rates. Three regions were identified in which the incidence of leprosy was particularly high. A spatial gradient in the incidence rates was identified, with a tendency of high rates to be concentrated on the North-South axis in the middle region of the state. Moran's I statistic indicated that a significant spatial autocorrelation also existed. The spatial distribution of leprosy in Ceará is heterogeneous. The reasons for spatial clustering of disease rates are not known, but might be related to an heterogeneous distribution of other factors such as crowding, social inequality, and environmental characteristics which by themselves determine the transmission of Mycobacterium leprae.

Fine-scale spatial genetic structure and gene dispersal in Silene latifolia.

Plants are sessile organisms, often characterized by limited dispersal. Seeds and pollen are the critical stages for gene flow. Here we investigate spatial genetic structure, gene dispersal and the relative contribution of pollen vs seed in the movement of genes in a stable metapopulation of the white campion Silene latifolia within its native range. This short-lived perennial plant is dioecious, has gravity-dispersed seeds and moth-mediated pollination. Direct measures of pollen dispersal suggested that large populations receive more pollen than small isolated populations and that most gene flow occurs within tens of meters. However, these studies were performed in the newly colonized range (North America) where the specialist pollinator is absent. In the native range (Europe), gene dispersal could fall on a different spatial scale. We genotyped 258 individuals from large and small (15) subpopulations along a 60 km, elongated metapopulation in Europe using six highly variable microsatellite markers, two X-linked and four autosomal. We found substantial genetic differentiation among subpopulations (global F(ST)=0.11) and a general pattern of isolation by distance over the whole sampled area. Spatial autocorrelation revealed high relatedness among neighboring individuals over hundreds of meters. Estimates of gene dispersal revealed gene flow at the scale of tens of meters (5-30 m), similar to the newly colonized range. Contrary to expectations, estimates of dispersal based on X and autosomal markers showed very similar ranges, suggesting similar levels of pollen and seed dispersal. This may be explained by stochastic events of extensive seed dispersal in this area and limited pollen dispersal.

Sleep loss reduces the DNA-binding of BMAL1, CLOCK, and NPAS2 to specific clock genes in the mouse cerebral cortex.

We have previously demonstrated that clock genes contribute to the homeostatic aspect of sleep regulation. Indeed, mutations in some clock genes modify the markers of sleep homeostasis and an increase in homeostatic sleep drive alters clock gene expression in the forebrain. Here, we investigate a possible mechanism by which sleep deprivation (SD) could alter clock gene expression by quantifying DNA-binding of the core-clock transcription factors CLOCK, NPAS2, and BMAL1 to the cis-regulatory sequences of target clock genes in mice. Using chromatin immunoprecipitation (ChIP), we first showed that, as reported for the liver, DNA-binding of CLOCK and BMAL1 to target clock genes changes in function of time-of-day in the cerebral cortex. Tissue extracts were collected at ZT0 (light onset), -6, -12, and -18, and DNA enrichment of E-box or E'-box containing sequences was measured by qPCR. CLOCK and BMAL1 binding to Cry1, Dbp, Per1, and Per2 depended on time-of-day, with maximum values reached at around ZT6. We then observed that SD, performed between ZT0 and -6, significantly decreased DNA-binding of CLOCK and BMAL1 to Dbp, consistent with the observed decrease in Dbp mRNA levels after SD. The DNA-binding of NPAS2 and BMAL1 to Per2 was also decreased by SD, although SD is known to increase Per2 expression in the cortex. DNA-binding to Per1 and Cry1 was not affected by SD. Our results show that the sleep-wake history can affect the clock molecular machinery directly at the level of chromatin binding thereby altering the cortical expression of Dbp and Per2 and likely other targets. Although the precise dynamics of the relationship between DNA-binding and mRNA expression, especially for Per2, remains elusive, the results also suggest that part of the reported circadian changes in DNA-binding of core clock components in tissues peripheral to the suprachiasmatic nuclei could, in fact, be sleep-wake driven.

Spatial distribution of schistosomiasis foci on Itamaracá Island, Pernambuco, Brazil

Acute cases of schistosomiasis have been found on the coastal area of Pernambuco, Brazil, due to environmental disturbances and disorderly occupation of the urban areas. This study identifies and spatially marks the main foci of the snail host species, Biomphalaria glabrata on Itamaracá Island. The chaotic occupation of the beach resorts has favoured the emergence of transmission foci, thus exposing residents and tourists to the risk of infection. A database covering five years of epidemiological investigation on snails infected by Schistosoma mansoni in the island was produced with information from the geographic positioning of the foci, number of snails collected, number of snails tested positive, and their infection rate. The spatial position of the foci were recorded through the Global Positioning System (GPS), and the geographical coordinates were imported by AutoCad. The software packages ArcView and Spring were used for data processing and spatial analysis. AutoCad 2000 was used to plot the pairs of coordinates obtained from GPS. Between 1998 and 2002 5009 snails, of which 12.2% were positive for S. mansoni, were collected in Forte Beach. A total of 27 foci and areas of environmental risk were identified and spatially analyzed allowing the identification of the areas exposed to varying degrees of risk.

Cathepsin X cleavage of the beta2 integrin regulates talin-binding and LFA-1 affinity in T cells.

T cell migration, essential for immune surveillance and response, is mediated by the integrin LFA-1. CatX, a cysteine carboxypeptidase, is involved in the regulation of T cell migration by interaction with LFA-1. We show that sequential cleavage of C-terminal amino acids from the β(2) cytoplasmic tail of LFA-1, by CatX, enhances binding of the adaptor protein talin to LFA-1 and triggers formation of the latter's high-affinity form. As shown by SPR analysis of peptides constituting the truncated β(2) tail, the cleavage of three C-terminal amino acids by CatX resulted in a 1.6-fold increase of talin binding. Removal of one more amino acid resulted in a 2.5-fold increase over the intact tail. CatX cleavage increased talin-binding affinity to the MD but not the MP talin-binding site on the β(2) tail. This was shown by molecular modeling of the β(2) tail/talin F3 complex to be a result of conformational changes affecting primarily the distal-binding site. Analysis of LFA-1 by conformation-specific mAb showed that CatX modulates LFA-1 affinity, promoting formation of high-affinity from intermediate-affinity LFA-1 but not the initial activation of LFA-1 from a bent to extended form. CatX post-translational modifications may thus represent a mechanism of LFA-1 fine-tuning that enables the trafficking of T cells.

Hiding the evidence: The State and spatial inequalities in health in Ireland

The Irish State has consistently reduced its production of publicly accessible disease / mortality maps over the last fifty years. State health statistics, and the small number of disease / mortality maps that have been produced in official publications, show a declining level of detail and are routinely out of date. Following a review of the production of disease / mortality maps in Ireland by the State and allied health agencies, two reasons are suggested for this decline. The first explanation relates to spatial inequalities in healthcare provision and to the absence of a health funding formulae in Ireland. The second explanation focuses on the potential politicisation of spatial inequalities in health status. Researchers in these fields are urged to disseminate information widely on spatial inequalities in healthcare provision, healthcare access and health status, both within and outside of the academic literature. Researchers in these fields are also urged to adopt an advocacy role on these issues, or to develop strategic alliances with such advocates.����

Decreased expression of peroxisome proliferator-activated receptor alpha and liver fatty acid binding protein after partial hepatectomy of rats and mice.

BACKGROUND AIMS: Marked changes in metabolism, including liver steatosis and hypoglycemia, occur after partial hepatectomy. Peroxisome proliferator-activated receptor alpha (PPAR alpha) is a nuclear hormone receptor that is activated by fatty acids and involved in hepatic fatty acid metabolism and regeneration. Liver fatty acid binding protein (LFABP) is an abundant protein in liver cytosol whose expression is regulated by PPAR alpha. It is involved in fatty acid uptake and diffusion and in PPAR alpha signaling. The aim of this study was to investigate the expression of PPAR alpha and LFABP during liver regeneration. METHODS: Male Sprague-Dawley rats and male C57 Bl/6 mice were subjected to 2/3 hepatectomy and LFABP and PPAR alpha mRNA and protein levels were measured at different time points after surgery. The effect of partial hepatectomy was followed during 48 h in rats and 72 h in mice. RESULTS: PPAR alpha mRNA and protein levels were decreased 26 h after hepatectomy of rats. The LFABP mRNA and protein levels paralleled those of PPAR alpha and were also decreased 26 h after hepatectomy. In mice, the mRNA level was decreased after 36 and 72 h after hepatectomy. In this case, LFABP mRNA levels decreased more slowly after partial hepatectomy than in rats. CONCLUSIONS: A marked decrease in PPAR alpha expression may be important for changed gene expression, e.g. LFABP, and metabolic changes, such as hypoglycemia, during liver regeneration.