The Experts below are selected from a list of 297 Experts worldwide ranked by ideXlab platform
Russell G Death - One of the best experts on this subject based on the ideXlab platform.
-
an accurate Comparison of Methods for quantifying variable importance in artificial neural networks using simulated data
Ecological Modelling, 2004Co-Authors: Julian D Olden, Russell G DeathAbstract:Artificial neural networks (ANNs) are receiving greater attention in the ecological sciences as a powerful statistical modeling technique; however, they have also been labeled a “black box” because they are believed to provide little explanatory insight into the contributions of the independent variables in the prediction process. A recent paper published in Ecological Modelling [Review and Comparison of Methods to study the contribution of variables in artificial neural network models, Ecol. Model. 160 (2003) 249–264] addressed this concern by providing a comprehensive Comparison of eight different methodologies for estimating variable importance in neural networks that are commonly used in ecology. Unfortunately, Comparisons of the different methodologies were based on an empirical dataset, which precludes the ability to establish generalizations regarding the true accuracy and precisionof the different approaches because the true importance of the variablesis unknown. Here, we provide a more appropriate Comparison of the different methodologies by using Monte Carlo simulations with data exhibiting defined (and consequently known) numeric relationships. Our results show that a Connection Weight Approach that uses raw input-hidden and hidden-output connection weights in the neural network provides the best methodology for accurately quantifying variable importance and should be favored over the other approaches commonly used in the ecological literature. Average similarity between true and estimated ranked variable importance using this approach was 0.92, whereas, similarity coefficients ranged between 0.28 and 0.74 for the other approaches. Furthermore, the Connection Weight Approach was the only method that consistently identified the correct ranked importance of all predictor variables, whereas, the other Methods either only identified the first few important variables in the network or no variables at all. The most notably result was that Garson’s Algorithm was the poorest performing approach, yet is the most commonly used in the ecological literature. In conclusion, this study provides a robust Comparison of different methodologies for assessing variable importance in neural networks that can be generalized to other data and from which valid recommendations can be made for future studies. © 2004 Elsevier B.V. All rights reserved.
Lawrence J Shimkets - One of the best experts on this subject based on the ideXlab platform.
-
Comparison of Methods of DNA Extraction from Stream Sediments
APPLIED AND ENVIRONMENTAL MICROBIOLOGY, 1995Co-Authors: Laura G Leff, James R Dana, J Vaun Mcarthur, Lawrence J ShimketsAbstract:In Upper Three Runs Creek (Aiken, S.C.) and many other environments, less than 1% of bacteria visible microscopically can be cultured. Exploitation of molecular biology techniques has led to development of new Methods, such as extraction of nucleic acids from soils or sediments, to study the dominant, nonculturable bacteria. The purpose of this study was to compare three published Methods of DNA extraction that fall into two general categories: those in which cells are lysed in sediments (the Ogram and Tsai and Methods [A. Ogram, G. S. Sayler, and T. Barkay, J. Microbiol. Methods 7:57–66, 1987; Y. L. Tsai and B. H. Olson, Appl. Environ. Microbiol. 57:1070–1074, 1991]) and those in which cells are removed from sediments prior to lysis (the Jacobsen method [C. S. Jacobsen and O. S. Rasmussen; Appl. Environ. Microbiol. 58:2458–2462, 1992]). DNA yield varied with extraction method; the Ogram method had a significantly higher yield than the other Methods. However, DNA extracted via the Ogram method was badly sheared and contained a smaller propor-tion of eubacterial DNA. The Tsai method was less time consuming than the other Methods, but DNA samples were of lower purity. If DNA purity is of paramount concern (as would be the case if PCR was to be performed) and quantity is not important, the Jacobsen method is recommended because of the low concentration of contaminants. If DNA is to be used directly in DNA-DNA hybridizations, the Ogram method is recommended since it gives maximal yields. However, if a Southern blot is to be performed, the Tsai method is recommended because of the high degree of DNA fragmentation observed with the other Methods. Widespread use of nucleic acid-specific stains in bacterial ecology (i.e., direct bacterial counts) (3) revealed that in many ecosystems, culturable bacteria represented only a fraction of the total bacterial assemblage. To study these nonculturable bacteria, which may contain species never previously discov-ered, scientists have frequently relied on extraction of nucleic acids from environmental samples. As this approach has be-come more popular, a number of different Methods have been developed to extract DNA from soils and sediments (5–7, 9, 12–14). Methods of DNA extraction from sediments and soils can be divided into two categories: those in which cells are lysed following removal from sediments, and those in which cells are lysed within the sediments. In this study, three DNA extraction techniques (6, 9, 14) were compared on the basis of yield, purity, quality, and taxonomic composition. When each method was published, the strengths and weaknesses of the method were discussed, but a Comparison of all of these meth-ods has not been reported (4, 7, 12, 13), making method se-lection difficult. Approximately 600 g (wet weight) of sediment was collected from Upper Three Runs Creek on the U.S. Department of Energy's Savannah River Site near Aiken, S.C. Sediment, con-sisting of sand, clay, and detritus, was homogenized in the laboratory and subdivided into 50-g (wet weight) subsamples. DNA was extracted from four subsamples by each of the three Methods. In the method of Ogram et al. (subsequently referred to as the Ogram method), a bead beater was used to disrupt cells following incubation in 1.25% sodium dodecyl sulfate (SDS; in sodium phosphate buffer [pH 8]) at 70ЊC for 1 h (9). After centrifugation to remove glass beads and sediment particles, polyethylene glycol (Sigma) was added to precipitate DNA. Polyethylene glycol was removed by phenol-chloroform extrac-tion. Following extraction, CsCl-ethidium bromide density gra-dient ultracentrifugation was used to concentrate and purify the DNA. In the method of Tsai and Olson (subsequently referred to as the Tsai method), sediments were treated with lysozyme, and cells were lysed by rapid freezing and thawing (Ϫ70 to 65ЊC three times) (14). Following phenol-chloroform extrac-tion, DNA was precipitated with isopropanol, and impurities were removed by gel filtration with Sephadex 100 (Pharmacia) as described by Moran et al. (8). The method of Jacobsen and Rasmussen (subsequently re-ferred to as the Jacobsen method) differed from the other two Methods in that cells were removed from sediments prior to lysis (6). A cation-exchange resin (Chelex 100; Bio-Rad) was used to break the attraction of the cells for sediment particles. Resin and sediment were removed by centrifugation, and cells were treated with lysozyme and pronase. CsCl-ethidium bro-mide density gradient ultracentrifugation was used to further purify the extracted DNA. Following DNA extraction, DNA concentrations were de-termined by the addition of Hoescht 33258 dye, which inter-calates specifically with DNA (10). Intercalation was detected with a fluorescence spectrophotometer (Perkin-Elmer model 650-40). Contamination of extracted DNA by humic com-pounds and other organic materials was assessed by determin-ing the A 260 and A 280 (4) with a spectrophotometer (Beckman DU-40). The relative amounts of eubacterial DNA obtained by the three extraction procedures were determined with a eubacte-rium-specific oligonucleotide. Environmental DNA (1.0, 0.25, and 0.0625 g per sample) was blotted onto Hybond-N nylon (Amersham) with a Mini-Fold II slot blot apparatus (Schlei-cher & Schuell). The eubacterium-specific oligonucleotide probe (5Ј-GCTGCCTCCCGTAGGAGT-3Ј), which hybridizes
Beth Wilmot - One of the best experts on this subject based on the ideXlab platform.
-
Comparison of Methods to identify aberrant expression patterns in individual patients: augmenting our toolkit for precision medicine
Genome Medicine, 2013Co-Authors: Daniel Bottomly, Peter Ryabinin, Jeffrey W. Tyner, Bill H. Chang, Marc Loriaux, Brian J. Druker, Shannon Mcweeney, Beth WilmotAbstract:Background Patient-specific aberrant expression patterns in conjunction with functional screening assays can guide elucidation of the cancer genome architecture and identification of therapeutic targets. Since most statistical Methods for expression analysis are focused on differences between experimental groups, the performance of approaches for patient-specific expression analyses are currently less well characterized. A Comparison of Methods for the identification of genes that are dysregulated relative to a single sample in a given set of experimental samples, to our knowledge, has not been performed.
-
Comparison of Methods to identify aberrant expression patterns in individual patients: augmenting our toolkit for precision medicine
Genome Medicine, 2013Co-Authors: Daniel Bottomly, Peter Ryabinin, Jeffrey W. Tyner, Bill H. Chang, Marc Loriaux, Brian J. Druker, Shannon Mcweeney, Beth WilmotAbstract:Background Patient-specific aberrant expression patterns in conjunction with functional screening assays can guide elucidation of the cancer genome architecture and identification of therapeutic targets. Since most statistical Methods for expression analysis are focused on differences between experimental groups, the performance of approaches for patient-specific expression analyses are currently less well characterized. A Comparison of Methods for the identification of genes that are dysregulated relative to a single sample in a given set of experimental samples, to our knowledge, has not been performed. Methods We systematically evaluated several Methods including variations on the nearest neighbor based outlying degree method, as well as the Zscore and a robust variant for their suitability to detect patient-specific events. The Methods were assessed using both simulations and expression data from a cohort of pediatric acute B lymphoblastic leukemia patients. Results We first assessed power and false discovery rates using simulations and found that even under optimal conditions, high effect sizes (>4 unit differences) were necessary to have acceptable power for any method (>0.9) though high false discovery rates (>0.1) were pervasive across simulation conditions. Next we introduced a technical factor into the simulation and found that performance was reduced for all Methods and that using weights with the outlying degree could provide performance gains depending on the number of samples and genes affected by the technical factor. In our use case that highlights the integration of functional assays and aberrant expression in a patient cohort (the identification of gene dysregulation events associated with the targets from a siRNA screen), we demonstrated that both the outlying degree and the Zscore can successfully identify genes dysregulated in one patient sample. However, only the outlying degree can identify genes dysregulated across several patient samples. Conclusion Our results show that outlying degree Methods may be a useful alternative to the Zscore or Rscore in a personalized medicine context especially in small to medium sized (between 10 and 50 samples) expression datasets with moderate to high sample-to-sample variability. From these results we provide guidelines for detection of aberrant expression in a precision medicine context.
Julian D Olden - One of the best experts on this subject based on the ideXlab platform.
-
an accurate Comparison of Methods for quantifying variable importance in artificial neural networks using simulated data
Ecological Modelling, 2004Co-Authors: Julian D Olden, Russell G DeathAbstract:Artificial neural networks (ANNs) are receiving greater attention in the ecological sciences as a powerful statistical modeling technique; however, they have also been labeled a “black box” because they are believed to provide little explanatory insight into the contributions of the independent variables in the prediction process. A recent paper published in Ecological Modelling [Review and Comparison of Methods to study the contribution of variables in artificial neural network models, Ecol. Model. 160 (2003) 249–264] addressed this concern by providing a comprehensive Comparison of eight different methodologies for estimating variable importance in neural networks that are commonly used in ecology. Unfortunately, Comparisons of the different methodologies were based on an empirical dataset, which precludes the ability to establish generalizations regarding the true accuracy and precisionof the different approaches because the true importance of the variablesis unknown. Here, we provide a more appropriate Comparison of the different methodologies by using Monte Carlo simulations with data exhibiting defined (and consequently known) numeric relationships. Our results show that a Connection Weight Approach that uses raw input-hidden and hidden-output connection weights in the neural network provides the best methodology for accurately quantifying variable importance and should be favored over the other approaches commonly used in the ecological literature. Average similarity between true and estimated ranked variable importance using this approach was 0.92, whereas, similarity coefficients ranged between 0.28 and 0.74 for the other approaches. Furthermore, the Connection Weight Approach was the only method that consistently identified the correct ranked importance of all predictor variables, whereas, the other Methods either only identified the first few important variables in the network or no variables at all. The most notably result was that Garson’s Algorithm was the poorest performing approach, yet is the most commonly used in the ecological literature. In conclusion, this study provides a robust Comparison of different methodologies for assessing variable importance in neural networks that can be generalized to other data and from which valid recommendations can be made for future studies. © 2004 Elsevier B.V. All rights reserved.
Laura G Leff - One of the best experts on this subject based on the ideXlab platform.
-
Comparison of Methods of DNA Extraction from Stream Sediments
APPLIED AND ENVIRONMENTAL MICROBIOLOGY, 1995Co-Authors: Laura G Leff, James R Dana, J Vaun Mcarthur, Lawrence J ShimketsAbstract:In Upper Three Runs Creek (Aiken, S.C.) and many other environments, less than 1% of bacteria visible microscopically can be cultured. Exploitation of molecular biology techniques has led to development of new Methods, such as extraction of nucleic acids from soils or sediments, to study the dominant, nonculturable bacteria. The purpose of this study was to compare three published Methods of DNA extraction that fall into two general categories: those in which cells are lysed in sediments (the Ogram and Tsai and Methods [A. Ogram, G. S. Sayler, and T. Barkay, J. Microbiol. Methods 7:57–66, 1987; Y. L. Tsai and B. H. Olson, Appl. Environ. Microbiol. 57:1070–1074, 1991]) and those in which cells are removed from sediments prior to lysis (the Jacobsen method [C. S. Jacobsen and O. S. Rasmussen; Appl. Environ. Microbiol. 58:2458–2462, 1992]). DNA yield varied with extraction method; the Ogram method had a significantly higher yield than the other Methods. However, DNA extracted via the Ogram method was badly sheared and contained a smaller propor-tion of eubacterial DNA. The Tsai method was less time consuming than the other Methods, but DNA samples were of lower purity. If DNA purity is of paramount concern (as would be the case if PCR was to be performed) and quantity is not important, the Jacobsen method is recommended because of the low concentration of contaminants. If DNA is to be used directly in DNA-DNA hybridizations, the Ogram method is recommended since it gives maximal yields. However, if a Southern blot is to be performed, the Tsai method is recommended because of the high degree of DNA fragmentation observed with the other Methods. Widespread use of nucleic acid-specific stains in bacterial ecology (i.e., direct bacterial counts) (3) revealed that in many ecosystems, culturable bacteria represented only a fraction of the total bacterial assemblage. To study these nonculturable bacteria, which may contain species never previously discov-ered, scientists have frequently relied on extraction of nucleic acids from environmental samples. As this approach has be-come more popular, a number of different Methods have been developed to extract DNA from soils and sediments (5–7, 9, 12–14). Methods of DNA extraction from sediments and soils can be divided into two categories: those in which cells are lysed following removal from sediments, and those in which cells are lysed within the sediments. In this study, three DNA extraction techniques (6, 9, 14) were compared on the basis of yield, purity, quality, and taxonomic composition. When each method was published, the strengths and weaknesses of the method were discussed, but a Comparison of all of these meth-ods has not been reported (4, 7, 12, 13), making method se-lection difficult. Approximately 600 g (wet weight) of sediment was collected from Upper Three Runs Creek on the U.S. Department of Energy's Savannah River Site near Aiken, S.C. Sediment, con-sisting of sand, clay, and detritus, was homogenized in the laboratory and subdivided into 50-g (wet weight) subsamples. DNA was extracted from four subsamples by each of the three Methods. In the method of Ogram et al. (subsequently referred to as the Ogram method), a bead beater was used to disrupt cells following incubation in 1.25% sodium dodecyl sulfate (SDS; in sodium phosphate buffer [pH 8]) at 70ЊC for 1 h (9). After centrifugation to remove glass beads and sediment particles, polyethylene glycol (Sigma) was added to precipitate DNA. Polyethylene glycol was removed by phenol-chloroform extrac-tion. Following extraction, CsCl-ethidium bromide density gra-dient ultracentrifugation was used to concentrate and purify the DNA. In the method of Tsai and Olson (subsequently referred to as the Tsai method), sediments were treated with lysozyme, and cells were lysed by rapid freezing and thawing (Ϫ70 to 65ЊC three times) (14). Following phenol-chloroform extrac-tion, DNA was precipitated with isopropanol, and impurities were removed by gel filtration with Sephadex 100 (Pharmacia) as described by Moran et al. (8). The method of Jacobsen and Rasmussen (subsequently re-ferred to as the Jacobsen method) differed from the other two Methods in that cells were removed from sediments prior to lysis (6). A cation-exchange resin (Chelex 100; Bio-Rad) was used to break the attraction of the cells for sediment particles. Resin and sediment were removed by centrifugation, and cells were treated with lysozyme and pronase. CsCl-ethidium bro-mide density gradient ultracentrifugation was used to further purify the extracted DNA. Following DNA extraction, DNA concentrations were de-termined by the addition of Hoescht 33258 dye, which inter-calates specifically with DNA (10). Intercalation was detected with a fluorescence spectrophotometer (Perkin-Elmer model 650-40). Contamination of extracted DNA by humic com-pounds and other organic materials was assessed by determin-ing the A 260 and A 280 (4) with a spectrophotometer (Beckman DU-40). The relative amounts of eubacterial DNA obtained by the three extraction procedures were determined with a eubacte-rium-specific oligonucleotide. Environmental DNA (1.0, 0.25, and 0.0625 g per sample) was blotted onto Hybond-N nylon (Amersham) with a Mini-Fold II slot blot apparatus (Schlei-cher & Schuell). The eubacterium-specific oligonucleotide probe (5Ј-GCTGCCTCCCGTAGGAGT-3Ј), which hybridizes