Typing mineral deposits using their grades and tonnages in an artificial neural network

A test of the ability of a probabilistic neural network to classify deposits into types on the basis of deposit tonnage and average Cu, Mo, Ag, Au, Zn, and Pb grades is conducted. The purpose is to examine whether this type of system might serve as a basis for integrating geoscience information available in large mineral databases to classify sites by deposit type. Benefits of proper classification of many sites in large regions are relatively rapid identification of terranes permissive for deposit types and recognition of specific sites perhaps worthy of exploring further. Total tonnages and average grades of 1,137 well-explored deposits identified in published grade and tonnage models representing 13 deposit types were used to train and test the network. Tonnages were transformed by logarithms and grades by square roots to reduce effects of skewness. All values were scaled by subtracting the variable's mean and dividing by its standard deviation. Half of the deposits were selected randomly to be used in training the probabilistic neural network and the other half were used for independent testing. Tests were performed with a probabilistic neural network employing a Gaussian kernel and separate sigma weights for each class (type) and each variable (grade or tonnage). Deposit types were selected to challenge the neural network. For many types, tonnages or average grades are significantly different from other types, but individual deposits may plot in the grade and tonnage space of more than one type. Porphyry Cu, porphyry Cu-Au, and porphyry Cu-Mo types have similar tonnages and relatively small differences in grades. Redbed Cu deposits typically have tonnages that could be confused with porphyry Cu deposits, also contain Cu and, in some situations, Ag. Cyprus and kuroko massive sulfide types have about the same tonnages. Cu, Zn, Ag, and Au grades. Polymetallic vein, sedimentary exhalative Zn-Pb, and Zn-Pb skarn types contain many of the same metals. Sediment-hosted Au, Comstock Au-Ag, and low-sulfide Au-quartz vein types are principally Au deposits with differing amounts of Ag. Given the intent to test the neural network under the most difficult conditions, an overall 75% agreement between the experts and the neural network is considered excellent. Among the largestclassification errors are skarn Zn-Pb and Cyprus massive sulfide deposits classed by the neuralnetwork as kuroko massive sulfides—24 and 63% error respectively. Other large errors are the classification of 92% of porphyry Cu-Mo as porphyry Cu deposits. Most of the larger classification errors involve 25 or fewer training deposits, suggesting that some errors might be the result of small sample size. About 91% of the gold deposit types were classed properly and 98% of porphyry Cu deposits were classes as some type of porphyry Cu deposit. An experienced economic geologist would not make many of the classification errors that were made by the neural network because the geologic settings of deposits would be used to reduce errors. In a separate test, the probabilistic neural network correctly classed 93% of 336 deposits in eight deposit types when trained with presence or absence of 58 minerals and six generalized rock types. The overall success rate of the probabilistic neural network when trained on tonnage and average grades would probably be more than 90% with additional information on the presence of a few rock types.

Identification of a Golgi-localised GRIP domain protein from Arabidopsis thaliana

A family of Golgi-localised molecules was recently described in animals and fungi possessing extensive coiled regions and a short (similar to40 residues) conserved C-terminal domain, called the GRIP domain, which is responsible for their location to this organelle. Using the model plant Arabidopsis thaliana, we identified a gene (AtGRIP) encoding a putative GRIP protein. We demonstrated that the C-terminal domain from AtGRIP functions as a Golgi-targeting sequence in plant cells. Localisation studies in living cells expressing the AtGRIP fused to a DsRed2 fluorescent probe, showed extensive co-location with the Golgi marker alpha-mannosidase I in transformed tobacco protoplasts. GRIP-like sequences were also found in genomic databases of rice, maize, wheat and alfalfa, suggesting that this domain may be a useful Golgi marker for immunolocalisation studies. Despite low sequence identity amongst GRIP domains, the plant GRIP sequence was able to target to the Golgi of mammalian cells. Taken together, these data indicate that GRIP domain proteins might be implicated in a targeting mechanism that is conserved amongst eukaryotes.

Ultrastructural identification of uncoated caveolin-independent early endocytic vehicles

Using quantitative light microscopy and a modified immunoelectron microscopic technique, we have characterized the entry pathway of the cholera toxin binding subunit (CTB) in primary embryonic fibroblasts. CTB trafficking to the Golgi complex was identical in caveolin-1 null (Cav1 -/-) mouse embryonic fibroblasts (MEFs) and wild-type (WT) MEFs. CTB entry in the Cav1 -/- MEFs was predominantly clathrin and dynamin independent but relatively cholesterol dependent. Immunoelectron microscopy was used to quantify budded and surface-connected caveoloe and to identify noncaveolar endocytic vehicles. In WT MEFs a small fraction of the total Cav1-positive structures were shown to bud from the plasma membrane (2 % per minute), and budding increased upon okadaic acid or lactosyl ceramide treatment. However, the major carriers involved in initial entry of CTB were identified as uncoated tubular or ring-shaped structures. These carriers contained GPI-anchored proteins and fluid phase markers and represented the major vehicles mediating CTB uptake in both WT and caveolae-null cells.

GPNN: Power studies and applications of a neural network method for detecting gene-gene interactions in studies of human disease

Background The identification and characterization of genes that influence the risk of common, complex multifactorial disease primarily through interactions with other genes and environmental factors remains a statistical and computational challenge in genetic epidemiology. We have previously introduced a genetic programming optimized neural network (GPNN) as a method for optimizing the architecture of a neural network to improve the identification of gene combinations associated with disease risk. The goal of this study was to evaluate the power of GPNN for identifying high-order gene-gene interactions. We were also interested in applying GPNN to a real data analysis in Parkinson's disease. Results We show that GPNN has high power to detect even relatively small genetic effects (2–3% heritability) in simulated data models involving two and three locus interactions. The limits of detection were reached under conditions with very small heritability (

GPNN: Power studies and applications of a neural network method for detecting gene-gene interactions in studies of human disease

Background: The identification and characterization of genes that influence the risk of common, complex multifactorial disease primarily through interactions with other genes and environmental factors remains a statistical and computational challenge in genetic epidemiology. We have previously introduced a genetic programming optimized neural network (GPNN) as a method for optimizing the architecture of a neural network to improve the identification of gene combinations associated with disease risk. The goal of this study was to evaluate the power of GPNN for identifying high-order gene-gene interactions. We were also interested in applying GPNN to a real data analysis in Parkinson's disease. Results: We show that GPNN has high power to detect even relatively small genetic effects (2-3% heritability) in simulated data models involving two and three locus interactions. The limits of detection were reached under conditions with very small heritability (