scholarly journals Linear regression equations to predict β-lactam, macrolide, lincosamide and fluoroquinolone minimum inhibitory concentrations from molecular antimicrobial resistance determinants in Streptococcus pneumoniae

2021 ◽  
Author(s):  
Walter Demczuk ◽  
Irene Martin ◽  
Averil Griffith ◽  
Brigitte Lefebvre ◽  
Allison McGeer ◽  
...  
Keyword(s):  
Streptococcus Pneumoniae ◽  
Antimicrobial Resistance ◽  
Linear Regression ◽  
Training Data ◽  
Data Sets ◽  
Sequencing Analysis ◽  
Regression Equations ◽  
Validation Data ◽  
Resistance Determinants ◽  
Multiple Variable

Antimicrobial resistance in Streptococcus pneumoniae represents a threat to public health and monitoring the dissemination of resistant strains is essential to guiding health policy. Multiple-variable linear regression modeling was used to determine the contributions of molecular antimicrobial resistance determinants to antimicrobial minimum inhibitory concentration (MIC) for penicillin, ceftriaxone, erythromycin, clarithromycin, clindamycin, levofloxacin, and trimethoprim/sulfamethoxazole. Training data sets consisting of Canadian S. pneumoniae isolated from 1995 to 2019 were used to generate multiple-variable linear regression equations for each antimicrobial. The regression equations were then applied to validation data sets of Canadian (n=439) and USA (n=607 and n=747) isolates. The MIC for β-lactam antimicrobials were fully explained by amino acid substitutions in motif regions of the penicillin binding proteins PBP1a, PPB2b, and PBP2x. Accuracy of predicted MICs within one doubling dilution to phenotypically determined MICs for penicillin was 97.4%, ceftriaxone 98.2%; erythromycin 94.8%; clarithromycin 96.6%; clindamycin 98.2%; levofloxacin 100%; and trimethoprim/sulfamethoxazole 98.8%; with an overall sensitivity of 95.8% and specificity of 98.0%. Accuracy of predicted MICs to the phenotypically determined MICs was similar to phenotype-only MIC comparison studies. The ability to acquire detailed antimicrobial resistance information directly from molecular determinants will facilitate the transition from routine phenotypic testing to whole genome sequencing analysis and can fill the surveillance gap in an era of increased reliance on nucleic acid assay diagnostics to better monitor the dynamics of S. pneumoniae .

scholarly journals Equations To Predict Antimicrobial MICs in Neisseria gonorrhoeae Using Molecular Antimicrobial Resistance Determinants

2019 ◽  
Vol 64 (3) ◽  
Author(s):  
Walter Demczuk ◽  
Irene Martin ◽  
Pam Sawatzky ◽  
Vanessa Allen ◽  
Brigitte Lefebvre ◽  
...  
Keyword(s):  
Antimicrobial Resistance ◽  
Neisseria Gonorrhoeae ◽  
Training Data ◽  
Sequencing Analysis ◽  
Regression Equations ◽  
Validation Data ◽  
Data Set ◽  
Content Type ◽  
Resistance Determinants ◽  
Extended Spectrum

ABSTRACT The emergence of Neisseria gonorrhoeae strains that are resistant to azithromycin and extended-spectrum cephalosporins represents a public health threat, that of untreatable gonorrhea infections. Multivariate regression modeling was used to determine the contributions of molecular antimicrobial resistance determinants to the overall antimicrobial MICs for ceftriaxone, cefixime, azithromycin, tetracycline, ciprofloxacin, and penicillin. A training data set consisting of 1,280 N. gonorrhoeae strains was used to generate regression equations which were then applied to validation data sets of Canadian (n = 1,095) and international (n = 431) strains. The predicted MICs for extended-spectrum cephalosporins (ceftriaxone and cefixime) were fully explained by 5 amino acid substitutions in PenA, A311V, A501P/T/V, N513Y, A517G, and G543S; the presence of a disrupted mtrR promoter; and the PorB G120 and PonA L421P mutations. The correlation of predicted MICs within one doubling dilution to phenotypically determined MICs of the Canadian validation data set was 95.0% for ceftriaxone, 95.6% for cefixime, 91.4% for azithromycin, 98.2% for tetracycline, 90.4% for ciprofloxacin, and 92.3% for penicillin, with an overall sensitivity of 99.9% and specificity of 97.1%. The correlations of predicted MIC values to the phenotypically determined MICs were similar to those from phenotype MIC-only comparison studies. The ability to acquire detailed antimicrobial resistance information directly from molecular data will facilitate the transition to whole-genome sequencing analysis from phenotypic testing and can fill the surveillance gap in an era of increased reliance on nucleic acid assay testing (NAAT) diagnostics to better monitor the dynamics of N. gonorrhoeae.

LDpred-funct: incorporating functional priors improves polygenic prediction accuracy in UK Biobank and 23andMe data sets

2018 ◽  
Author(s):  
Carla Márquez-Luna ◽  
Steven Gazal ◽  
Po-Ru Loh ◽  
Samuel S. Kim ◽  
Nicholas Furlotte ◽  
...  
Keyword(s):  
Complex Traits ◽  
Prediction Accuracy ◽  
Causal Effect ◽  
Complex Trait ◽  
Training Data ◽  
Data Sets ◽  
Uk Biobank ◽  
Validation Data ◽  
Functional Regions ◽  
The Uk

AbstractGenetic variants in functional regions of the genome are enriched for complex trait heritability. Here, we introduce a new method for polygenic prediction, LDpred-funct, that leverages trait-specific functional priors to increase prediction accuracy. We fit priors using the recently developed baseline-LD model, which includes coding, conserved, regulatory and LD-related annotations. We analytically estimate posterior mean causal effect sizes and then use cross-validation to regularize these estimates, improving prediction accuracy for sparse architectures. LDpred-funct attained higher prediction accuracy than other polygenic prediction methods in simulations using real genotypes. We applied LDpred-funct to predict 21 highly heritable traits in the UK Biobank. We used association statistics from British-ancestry samples as training data (avg N=373K) and samples of other European ancestries as validation data (avg N=22K), to minimize confounding. LDpred-funct attained a +4.6% relative improvement in average prediction accuracy (avg prediction R2=0.144; highest R2=0.413 for height) compared to SBayesR (the best method that does not incorporate functional information). For height, meta-analyzing training data from UK Biobank and 23andMe cohorts (total N=1107K; higher heritability in UK Biobank cohort) increased prediction R2 to 0.431. Our results show that incorporating functional priors improves polygenic prediction accuracy, consistent with the functional architecture of complex traits.

SaltSeg: Automatic 3D salt segmentation using a deep convolutional neural network

2019 ◽  
Vol 7 (3) ◽  
pp. SE113-SE122 ◽  
Author(s):  
Yunzhi Shi ◽  
Xinming Wu ◽  
Sergey Fomel
Keyword(s):  
Large Scale ◽  
Model Building ◽  
Ground Truth ◽  
Velocity Model ◽  
Training Data ◽  
Data Sets ◽  
Validation Data ◽  
Data Set ◽  
Seismic Image ◽  
Data Generator

Salt boundary interpretation is important for the understanding of salt tectonics and velocity model building for seismic migration. Conventional methods consist of computing salt attributes and extracting salt boundaries. We have formulated the problem as 3D image segmentation and evaluated an efficient approach based on deep convolutional neural networks (CNNs) with an encoder-decoder architecture. To train the model, we design a data generator that extracts randomly positioned subvolumes from large-scale 3D training data set followed by data augmentation, then feed a large number of subvolumes into the network while using salt/nonsalt binary labels generated by thresholding the velocity model as ground truth labels. We test the model on validation data sets and compare the blind test predictions with the ground truth. Our results indicate that our method is capable of automatically capturing subtle salt features from the 3D seismic image with less or no need for manual input. We further test the model on a field example to indicate the generalization of this deep CNN method across different data sets.

Comparison of a class of regression equations

1984 ◽  
Vol 246 (3) ◽  
pp. R271-R276
Author(s):  
T. E. Jackson
Keyword(s):  
Linear Regression ◽  
Linear Model ◽  
Computer Analysis ◽  
Matrix Algebra ◽  
Full Rank ◽  
Confidence Regions ◽  
Regression Equation ◽  
Data Sets ◽  
Regression Equations ◽  
Testing Hypotheses

The method described in this paper offers a means of comparing linear regression equations with many parameters by utilizing joint parameter confidence regions. It is useful when comparing sets of data in which each set is represented by a similar regression equation. The method consists of establishing a full-rank linear model with the data sets to be considered and then testing hypotheses concerning parameters of the model. It is conveniently expressed in matrix algebra form and is amenable to computer analysis.

scholarly journals Comparison of Metamodel Performances on an Electronic Circuit Problem

2021 ◽  
pp. 1-11
Author(s):  
Muzaffer Balaban
Keyword(s):  
Linear Regression ◽  
Radial Basis Function ◽  
Basis Function ◽  
Ordinary Kriging ◽  
Electronic Circuit ◽  
Training Data ◽  
Validation Data ◽  
Data Set ◽  
Simple Kriging ◽  
Radial Basis

Aims: Investigation of building and validation of metamodels which of linear regression, simple kriging, ordinary kriging and radial basis function for an electronic circuit problem are the main aim of this study. Study Design: An electronic circuit problem was considered to compare the performances of the metamodels. Latin hypercube design was used for experimental design of five input variables of the considered problem. Methodology: A training data set consisting of 45 experiments and a validation data set consisting of 500 experiments were obtained using Latin hypercube design. Input variables were used by coded to calculate the spatial distances between observation points more consistently. Then using training data set linear regression, simple kriging, ordinary kriging and radial basis function metamodels were built. And, performance measures were calculated for the validation data set. Results: It has been shown that simple kriging which are applied to outputs the differences from the mean, and ordinary kriging metamodels, produce superior solutions compared to the linear regression and radial basis function metamodels for the electronic circuit problem considered in this study. Prediction superiority of SK and OK than RBF on five-dimensional problem is another important result of the study. Conclusion: Kriging metamodels are considered to be strong alternatives to the other metamodels for the problems that are considered in this study and have a similar nature. Since the superiority of metamodel methods to each other may vary from problem to problem, it is another important issue to compare their performance by considering more than one method in problem solving stage.

Estimating weights when fitting linear regression models for tree volume

1993 ◽  
Vol 23 (8) ◽  
pp. 1725-1731 ◽  
Author(s):  
Michael S. Williams ◽  
Timothy G. Gregoire
Keyword(s):  
Linear Regression ◽  
Weight Function ◽  
Loblolly Pine ◽  
Weighted Least Squares ◽  
Data Sets ◽  
Regression Equations ◽  
Linear Regression Models ◽  
White Oak ◽  
Data Set ◽  
Error Structure

The method of weighted least squares can be used to achieve homogeneity of variance with linear regression that has a heterogeneous error structure. A weight function commonly used when constructing regression equations to predict tree volume is [Formula: see text], where k1 ≈ 1.0–2.1. This paper examines the weight function [Formula: see text] for modelling the error structure in two loblolly pine (Pinustaeda L.) data sets and one white oak (Quercusalba L.) data set. The weight function [Formula: see text] is recommended for all three data sets, for which the k1 values ranged from 1.80 to 2.07.

scholarly journals Improving the resolution of migrated images by approximating the inverse Hessian using deep learning

Geophysics ◽  
2020 ◽  
Vol 85 (4) ◽  
pp. WA173-WA183 ◽  
Author(s):  
Harpreet Kaur ◽  
Nam Pham ◽  
Sergey Fomel
Keyword(s):  
Field Data ◽  
Velocity Model ◽  
Image Resolution ◽  
Training Data ◽  
Generative Adversarial Networks ◽  
Data Sets ◽  
Computationally Efficient ◽  
Validation Data ◽  
Network Output

We have estimated migrated images with meaningful amplitudes matching least-squares migrated images by approximating the inverse Hessian using generative adversarial networks (GANs) in a conditional setting. We use the CycleGAN framework and extend it to the conditional CycleGAN such that the mapping from the migrated image to the true reflectivity is subjected to a velocity attribute condition. This algorithm is applied after migration and is computationally efficient. It produces results comparable to iterative inversion but at a significantly reduced cost. In numerical experiments with synthetic and field data sets, the adopted method improves image resolution, attenuates noise, reduces migration artifacts, and enhances reflection amplitudes. We train the network with three different data sets and test on three other data sets, which are not a part of training. Tests on validation data sets verify the effectiveness of the approach. In addition, the field-data example also highlights the effect of the bandwidth of the training data and the quality of the velocity model on the quality of the deep neural network output.

scholarly journals Etemadi Fuzzy Linear Regression (EFLR)

2022 ◽  
Author(s):  
Sepideh Etemadi ◽  
Mehdi Khashei
Keyword(s):  
Linear Regression ◽  
Fuzzy Modeling ◽  
Point Estimation ◽  
Training Data ◽  
Fuzzy Linear Regression ◽  
Validation Data ◽  
Suitable Alternative ◽  
Explanatory Variables ◽  
Benchmark Datasets ◽  
Fuzzy Parameters

Abstract Modeling and forecasting are among the most powerful and widely-used tools in decision support systems. The Fuzzy Linear Regression (FLR) is the most fundamental method in the fuzzy modeling area in which the uncertain relationship between the target and explanatory variables is estimated and has been frequently used in a broad range of real-world applications efficaciously. The operation logic in this method is to minimize the vagueness of the model, defined as the sum of individual spreads of the fuzzy coefficients. Although this process is coherent and can obtain the narrowest α-cut interval and exceptionally the most accurate results in the training data sets, it can not guarantee to achieve the desired level of generalization. While the quality of made managerial decisions in the modeling-based field is dependent on the generalization ability of the used method. On the other hand, the generalizability of a method is generally dependent on the precision as well as reliability of results, simultaneously. In this paper, a novel methodology is presented for the fuzzy linear regression modeling; in which in contrast to conventional methods, the constructed models' reliability is maximized instead of minimizing the vagueness. In the proposed model, fuzzy parameters are estimated in such a way that the variety of the ambiguity of the model is minimized in different data conditions. In other words, the weighted variance of different ambiguities in each validation data situation is minimized in order to estimate the unknown fuzzy parameters. To comprehensively assess the proposed method's performance, 74 benchmark datasets are regarded from the UCI. Empirical outcomes show that, in 64.86% of case studies, the proposed method has better generalizability, i.e., narrower α-cut interval as well as more accurate results in the interval and point estimation, than classic versions. It is obviously demonstrated the importance of the outcomes' reliability in addition to the precision that is not considered in the traditional FLR modeling processes. Hence, the presented EFLR method can be considered as a suitable alternative in fuzzy modeling fields, especially when more generalization is favorable.

GENERATING CONCISE SETS OF LINEAR REGRESSION RULES FROM ARTIFICIAL NEURAL NETWORKS

2002 ◽  
Vol 11 (02) ◽  
pp. 189-202 ◽  
Author(s):  
RUDY SETIONO ◽  
ARNULFO AZCARRAGA
Keyword(s):  
Neural Networks ◽  
Linear Regression ◽  
Multiple Linear Regression ◽  
Function Approximation ◽  
Predictive Accuracy ◽  
Universal Function ◽  
Regression Equation ◽  
Training Data ◽  
Regression Equations ◽  
Input Variables

Neural networks with a single hidden layer are known to be universal function approximators. However, due to the complexity of the network topology and the nonlinear transfer function used in computing the hidden unit activations, the predictions of a trained network are difficult to comprehend. On the other hand, predictions from a multiple linear regression equation are easy to understand but are not accurate when the underlying relationship between the input variables and the output variable is nonlinear. We have thus developed a method for multivariate function approximation which combines neural network learning, clustering and multiple regression. This method generates a set of multiple linear regression equations using neural networks, where the number of regression equations is determined by clustering the weighted input variables. The predictions for samples of the same cluster are computed by the same regression equation. Experimental results on a number of real-world data demonstrate that this new method generates relatively few regression equations from the training data samples. Yet, drawing from the universal function approximation capacity of neural networks, the predictive accuracy is high. The prediction errors are comparable to or lower than those achieved by existing function approximation methods.

scholarly journals Estimating Aflatoxin in Farmers' Stock Peanut Lots by Measuring Aflatoxin in Various Peanut-Grade Components

1998 ◽  
Vol 81 (1) ◽  
pp. 61-67 ◽  
Author(s):  
Thomas B Whitaker ◽  
Winston M Hagler ◽  
Francis G Giesbrecht ◽  
Joe w Dorner ◽  
Floyd E Dowell ◽  
...  
Keyword(s):  
Linear Regression ◽  
Correlation Analysis ◽  
Correlation Coefficient ◽  
Test Sample ◽  
Statistical Analyses ◽  
Data Sets ◽  
Regression Equations ◽  
Total Aflatoxin ◽  
Accurate Predictor ◽  
Aflatoxin Concentration

Abstract Five, 2 kg test samples were taken from each of 120 farmers' stock peanut lots contaminated with aflatoxin. Kernels from each 2 kg sample were divided into the following grade components: sound mature kernels plus sound splits (SMKSS), other kernels (OK), loose shelled kernels (LSK), and damaged kernels (DAM). Kernel mass, aflatoxin mass, and aflatoxin concentration were measured for each of the 2400 component samples. For 120 lots tested, average aflatoxin concentrations in SMKSS, OK, LSK, and DAM components were 235, 2543, 11 775, and 69 775 ng/g, respectively. Aflatoxins in SMKSS, OK, LSK, and DAM components represented 6.9, 7.9, 33.3, and 51.9% of the total aflatoxin mass, respectively. Cumulatively, 3 aflatoxin risk components—OK, LSK, and DAM—accounted for 93.1% of total aflatoxin, but only 18.4% percent of test sample mass. Correlation analysis suggests that the most accurate predictor of aflatoxin concentration in the lot is the cumulative aflatoxin mass in the high 3 risk corn ponents OK + LSK + DAM (correlation coefficient, r = 0.996). If the aflatoxin in the combined OK + LSK + DAM components is expressed in concentration units, r decreases to 0.939. Linear regression equations relating aflatoxin in OK + LSK + DAM to aflatoxin concentration in the lot were developed. The cumulative aflatoxin in the OK + LSK + DAM components was not an accurate predictor (r = 0.539) of aflatoxin in the SMKSS component. Statistical analyses of 3 other data sets published previously yielded similar results.

Sign in / Sign up

Export Citation Format

Share Document