Accuracy and bias of genomic prediction with different de-regression methods

ABSTRACTBayesian multiple-regression methods incorporating different mixture priors for marker effects are widely used in genomic prediction. Improvement in prediction accuracies from using those methods, such as BayesB, BayesC and BayesCπ, have been shown in single-trait analyses with both simulated data and real data. These methods have been extended to multi-trait analyses, but only under a specific limited circumstance that assumes a locus affects all the traits or none of them. In this paper, we develop and implement the most general multi-trait BayesCΠ and BayesB methods allowing a broader range of mixture priors. Further, we compare them to single-trait methods and the “restricted” multi-trait formulation using real data. In those data analyses, significant higher prediction accuracies were sometimes observed from these new broad-based multi-trait Bayesian multiple-regression methods. The software tool JWAS offers routines to perform the analyses.

Download Full-text

Regularized group regression methods for genomic prediction: Bridge, MCP, SCAD, group bridge, group lasso, sparse group lasso, group MCP and group SCAD

BMC Proceedings ◽

10.1186/1753-6561-8-s5-s7 ◽

2014 ◽

Vol 8 (S5) ◽

Cited By ~ 17

Author(s):

Joseph O Ogutu ◽

Hans-Peter Piepho

Keyword(s):

Genomic Prediction ◽

Group Lasso ◽

Regression Methods ◽

Sparse Group Lasso ◽

Bridge Group ◽

Group Regression

Download Full-text

A guide for kernel generalized regression methods for genomic-enabled prediction

Heredity ◽

10.1038/s41437-021-00412-1 ◽

2021 ◽

Author(s):

Abelardo Montesinos-López ◽

Osval Antonio Montesinos-López ◽

José Cricelio Montesinos-López ◽

Carlos Alberto Flores-Cortes ◽

Roberto de la Rosa ◽

...

Keyword(s):

Kernel Methods ◽

Genomic Prediction ◽

Regression Models ◽

Primary Objective ◽

Linear Regression Models ◽

Regression Methods ◽

Building Process ◽

Generalized Kernel ◽

Sparse Kernel Methods ◽

Sparse Kernel

AbstractThe primary objective of this paper is to provide a guide on implementing Bayesian generalized kernel regression methods for genomic prediction in the statistical software R. Such methods are quite efficient for capturing complex non-linear patterns that conventional linear regression models cannot. Furthermore, these methods are also powerful for leveraging environmental covariates, such as genotype × environment (G×E) prediction, among others. In this study we provide the building process of seven kernel methods: linear, polynomial, sigmoid, Gaussian, Exponential, Arc-cosine 1 and Arc-cosine L. Additionally, we highlight illustrative examples for implementing exact kernel methods for genomic prediction under a single-environment, a multi-environment and multi-trait framework, as well as for the implementation of sparse kernel methods under a multi-environment framework. These examples are followed by a discussion on the strengths and limitations of kernel methods and, subsequently by conclusions about the main contributions of this paper.

Download Full-text

Harnessing multivariate, penalized regression methods for genomic prediction and QTL detection of drought-related traits in grapevine

G3 Genes|Genome|Genetics ◽

10.1093/g3journal/jkab248 ◽

2021 ◽

Author(s):

Charlotte Brault ◽

Agnès Doligez ◽

Loïc le Cunff ◽

Aude Coupel-Ledru ◽

Thierry Simonneau ◽

...

Keyword(s):

Candidate Genes ◽

Genomic Prediction ◽

Penalized Regression ◽

Interval Mapping ◽

Evidence Base ◽

Qtl Detection ◽

Wine Quality ◽

Positional Candidate ◽

Regression Methods ◽

Marker Selection

Abstract Viticulture has to cope with climate change and to decrease pesticide inputs, while maintaining yield and wine quality. Breeding is a key lever to meet this challenge, and genomic prediction a promising tool to accelerate breeding programs. Multivariate methods are potentially more accurate than univariate ones. Moreover, some prediction methods also provide marker selection, thus allowing quantitative trait loci (QTLs) detection and the identification of positional candidate genes. To study both genomic prediction and QTL detection for drought-related traits in grapevine, we applied several methods, interval mapping as well as univariate and multivariate penalized regression, in a bi-parental progeny. With a dense genetic map, we simulated two traits under four QTL configurations. The penalized regression method Elastic Net (EN) for genomic prediction, and controlling the marginal False Discovery Rate on EN selected markers to prioritize the QTLs. Indeed, penalized methods were more powerful than interval mapping for QTL detection across various genetic architectures. Multivariate prediction did not perform better than its univariate counterpart, despite strong genetic correlation between traits. Using 14 traits measured in semi-controlled conditions under different watering conditions, penalized regression methods proved very efficient for intra-population prediction whatever the genetic architecture of the trait, with predictive abilities reaching 0.68. Compared to a previous study on the same traits, these methods applied on a denser map found new QTLs controlling traits linked to drought tolerance and provided relevant candidate genes. Overall, these findings provide a strong evidence base for implementing genomic prediction in grapevine breeding.

Download Full-text

Genomic Prediction from Multiple-Trait Bayesian Regression Methods Using Mixture Priors

Genetics ◽

10.1534/genetics.118.300650 ◽

2018 ◽

Vol 209 (1) ◽

pp. 89-103 ◽

Cited By ~ 13

Author(s):

Hao Cheng ◽

Kadir Kizilkaya ◽

Jian Zeng ◽

Dorian Garrick ◽

Rohan Fernando

Keyword(s):

Genomic Prediction ◽

Bayesian Regression ◽

Multiple Trait ◽

Regression Methods

Download Full-text

Harnessing multivariate, penalized regression methods for genomic prediction and QTL detection to cope with climate change affecting grapevine

10.1101/2020.10.26.355420 ◽

2020 ◽

Author(s):

Charlotte Brault ◽

Agnès Doligez ◽

Loïc le Cunff ◽

Aude Coupel-Ledru ◽

Thierry Simonneau ◽

...

Keyword(s):

Climate Change ◽

Candidate Genes ◽

Genomic Prediction ◽

Penalized Regression ◽

Interval Mapping ◽

Qtl Detection ◽

Wine Quality ◽

Positional Candidate ◽

Regression Methods ◽

Marker Selection

ABSTRACTViticulture has to cope with climate change and decrease pesticide inputs, while maintaining yield and wine quality. Breeding is a potential key to meet this challenge, and genomic prediction is a promising tool to accelerate breeding programs, multivariate methods being potentially more accurate than univariate ones. Moreover, some prediction methods also provide marker selection, thus allowing quantitative trait loci (QTLs) detection and allowing the identification of positional candidate genes. We applied several methods, interval mapping as well as univariate and multivariate penalized regression, in a bi-parental grapevine progeny, in order to compare their ability to predict genotypic values and detect QTLs. We used a new denser genetic map, simulated two traits under four QTL configurations, and re-analyzed 14 traits measured in semi-controlled conditions under different watering conditions. Using simulations, we recommend the penalized regression method Elastic Net (EN) as a default for genomic prediction, and controlling the marginal False Discovery Rate on EN selected markers to prioritize the QTLs. Indeed, penalized methods were more powerful than interval mapping for QTL detection across various genetic architectures. Multivariate prediction did not perform better than its univariate counterpart, despite strong genetic correlation between traits. Using experimental data, penalized regression methods proved as very efficient for intra-population prediction whatever the genetic architecture of the trait, with accuracies reaching 0.68. These methods applied on the denser map found new QTLs controlling traits linked to drought tolerance and provided relevant candidate genes. These methods can be applied to other traits and species.

Download Full-text

PENGARUH FAKTOR-FAKTOR INTERNAL PERBANKAN TERHADAP NON PERFORMING FINANCING PADA BANK UMUM SYARIAH

Jurnal Riset Manajemen Sekolah Tinggi Ilmu Ekonomi Widya Wiwaha Program Magister Manajemen ◽

10.32477/jrm.v6i2.353 ◽

2019 ◽

Vol 6 (2) ◽

pp. 115-130

Author(s):

Eka Ambara Harci Putranta ◽

Lilik Ambarwati

Keyword(s):

Linear Regression ◽

Multiple Linear Regression ◽

Linear Regression Analysis ◽

Multiple Linear Regression Analysis ◽

Capital Adequacy ◽

Annual Reports ◽

Regression Methods ◽

Capital Adequacy Ratio ◽

Negative Effect ◽

Independent Variable

The study aims to analyze the influence of internal banking factors in the form of: Capital Adequency Ratio (CAR), Financing to Deposit Ratio (FDR) and Total Assets (TA) to Non Performing Financing at Sharia Banks. This research method used multiple linear regression analysis with the help of SPSS 16.00 software which is used to see the influence between the independent variables in the form of Capital Adequacy Ratio (CAR), Financing to Deposit Ratio (FDR) and Total Assets (TA) to Non Performing Financing. The sample of this study was 3 Islamic Commercial Banks, so there were 36 annual reports obtained through purposive sampling, then analyzed using multiple linear regression methods. The results showed that based on the F Test, the independent variable had an effect on the NPF, indicated by the F value of 17,016 and significance of 0,000, overall the independent variable was able to explain the effect of 69.60%. While based on the partial t test, showed that CAR has a significant negative effect, Total assets have a significant positive effect with a significance value below 0.05 (5%). Meanwhile FDR does not affect NPF.

Download Full-text

PENGARUH PENYELENGGARAAN HAJI TERHADAP PENINGKATAN AKTIVITAS EKONOMl DI WILAYAH PROPINSI DKI JAKARTA

ALQALAM ◽

10.32678/alqalam.v30i2.1420 ◽

2013 ◽

Vol 30 (2) ◽

pp. 380

Author(s):

Chairul Akmal

Keyword(s):

Secondary Data ◽

Travel Agency ◽

Economic Activities ◽

Factors Affecting ◽

Regression Methods ◽

The Social ◽

Travel Agencies ◽

Relationship Model ◽

Small Medium Enterprises ◽

Medium Enterprises

This research analyzes some factors affecting economic activities in relation with the conduct of pilgrimage. Those factors are the pilgrimage cost, the amount of pilgrims, and the amount of pilgrimage officers. The objective of this research is to acquire the information of how each factor and all factors together affect the economic activities. This research also analyzes the effect of foods and drinks expenses, the effect of nonfoods and drinks expenses, and the effect of miscellaneous expenses on UMKM - Micro, Small, Medium enterprises' economic activities. This research is conducted in DKI Jakarta in 2007. The population of this research is the average economic activities in DKI Jakarta in 2007. There are 42 respondents (Banks), 157 respondents (travel agencies), and 50 respondents (UMKM - Micro, Small, Medium enterprises) which are taken as samples from the population using the purposive sampling method. The data is obtained by the researcher using questioners and secondary data which is taken from 1990-2007. The methodology used in this research is based on. the causal relationship model In testing the hypothesis of this research, the researcher uses the simple and multiple regression methods, and path analysis method. The significant rate a = 0,05 used in determining the interpretation of the statistic result. The data is processed using SPSS (Statistical Packages for the Social Sciences) version 12.00. The results of the analysis in the 1st equation -are (i) the effect of the pilgrimage cost on banks' revenues is quite strong, (ii) the effect of the pilgrimage cost on travel agencies' revenues is quite strong, (iii) the effect of the pilgrimage cost on UMKM - Micro, Small, Medium enterprises' revenues is weak. The results of the analysis in the 2nd equation are (i) the effect, of the amount of pilgrims on Banks' revenues is very weak, (ii) the effect of the amount of pilgrims on travel agencies' revenues is very weak, (iii) the effect of the amount of pilgrims on UMKM - Micro, Smal4 Medium enterprises' revenues is very weak. The results of the analysis in the 3rd equation are (i) the effect of the amount of pilgrimage officers on banks' revenues is very weak, (ii) the effect of the amount of pilgrimage officers on travel agencies' revenues is very weak, (iii) the effect of the amount officers on UMKM-Micro, Small Medium enterprises' revenues is very weak. The results of the analysis in the 4th equation are (i) the effect of all three factors which are the pilgrimage cost, the amount of pilgrims, and the amount of pilgrimage officers simultaneously on banks' revenues is very strong, (ii) The effect of all three factors which are pilgrimage costs, the amount of pilgrims, and the amount of pilgrimage officers simultaneously on travel agencies' revenues is strong, (iii) The effect of all three factors which are pilgrimage costs, the amount of pilgrims, and the amount of pilgrimage officers simultaneously on UMKM-Micro, Small Medium enterprises' revenues is strong. The result of the analysis in the 5th equation is the effect of foods and drinks expenses on UMKM-Micro, Small Medium enterprises' revenues is weak. In the 6th equation, the effect of nonfoods and drinks expenses on UMKM-Micro, small Medium enterprises' revenues is weak. In the 7th equation, the effect of miscellaneous expenses on UMKM - Micro, Small Medium enterprises' revenues is quite strong. In the 8th equation, the effect of all three factors which are the effect of foods and drinks expenses, the effect of nonfoods and drinks expenses, and the effect of miscellaneous expenses simultaneously on UMKM-Micro, Small Medium enterprises' revenues is quite strong. The implication of the research results mentioned above is the factors in the conduct of pilgrimage do increase the economic activities (Banks, Travel Agencies, and UMKM - Micro, Smal4 Medium enterprises) in DKI Jakarta. Therefore, considering that matter, the General Director of the conduct of pilgrimage division of Department of Religion Republic of Indonesia should determine the pilgrimage cost which is affordable, increase the service, and provide a good information system which will result in a better conduct of the pilgrimage. Key word: The Costs of Hajj, Hajj Officer, Travel Agency, UMKM

Download Full-text

PENGARUH PRODUK DOMESTIK BRUTO, INFLASI DAN RASIO GINI TERHADAP PENGANGGURAN TERBUKA DI PROVINSI DKI JAKARTA

Jurnal Good Governance ◽

10.32834/jgg.v14i2.15 ◽

2018 ◽

Vol 14 (2) ◽

Cited By ~ 1

Author(s):

Sri Mahendra Putra Wirawan

Keyword(s):

Economic Growth ◽

Significant Influence ◽

Economic Conditions ◽

Research Model ◽

Economic Region ◽

Regression Methods ◽

Price Increases ◽

Comprehensive Picture ◽

Development Goals ◽

The Relationship

Gross Regional Domestic Product (GRDP) which provides a comprehensive picture of the economic conditions of a region is indicator for analyzing economic region development. Another indicator that is no less important is inflation as an indicator to see the level of changes in price increases due to an increase in the money supply that causes rising prices. The success of development must also look at the income inequality of its population which is illustrated by this ratio. One of the main regional development goals is to improve the welfare of its people, where to see the level of community welfare, among others, can be seen from the level of unemployment in an area. To that end, in order to get an overview of the effects of GRDP, inflation and the ratio of gini to unemployment in DKI Jakarta for the last ten years (2007-2016), an analysis was carried out using multiple linear regression methods. As a result, together the relationship between GRDP, inflation and the Gini ratio is categorized as "very strong" with a score of 0.936, and has a significant influence on unemployment. Partially, the GRDP gives a significant influence, but inflation and gini ratio do not have a significant influence. GDP, inflation and the Gini ratio together for the last ten years have contributed 81.4% to unemployment in DKI Jakarta, while the remaining 18.6% is influenced by other variables not included in this research model, so for reduce unemployment in DKI Jakarta, programs that are oriented to economic growth, suppressing inflation and decreasing this ratio need to be carried out simultaneously. Keywords: GRDP, inflation, unemployment, DKI Jakarta, GINI ratio

Download Full-text