A benchmarking between deep learning, support vector machine and bayesian threshold best linear unbiased prediction for predicting ordinal traits in plant breeding
Genomic selection is revolutionizing plant breeding. However, still lacking are better statistical models for ordinal phenotypes to improve the accuracy of the selection of candidate genotypes. For this reason, in this paper we explore the genomic based prediction performance of two popular machine learning methods: the Multi Layer Perceptron (MLP) and support vector machine (SVM) methods vs. the Bayesian threshold genomic best linear unbiased prediction (TGBLUP) model. We used the percentage of cases correctly classified (PCCC) as a metric to measure the prediction performance, and seven real data sets to evaluate the prediction accuracy, and found that the best predictions (in four out of the seven data sets) in terms of PCCC occurred under the TGLBUP model, while the worst occurred under the SVM method. Also, in general we found no statistical differences between using 1, 2 and 3 layers under the MLP models, which means that many times the conventional neuronal network model with only one layer is enough. However, although even that the TGBLUP model was better, we found that the predictions of MLP and SVM were very competitive with the advantage that the SVM was the most efficient in terms of the computational time required.
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article biblioteca |
| Language: | English |
| Published: |
Genetics Society of America
2019
|
| Subjects: | AGRICULTURAL SCIENCES AND BIOTECHNOLOGY, Threshold GBLUP, Deep Learning, Support Vector Machine, Genomic Selection, Genomic Prediction, GenPred, Shared Data Resources, BAYESIAN THEORY, STATISTICAL METHODS, MACHINE LEARNING, ARTIFICIAL SELECTION, PLANT BREEDING, CROP FORECASTING, DATA ANALYSIS, |
| Online Access: | https://hdl.handle.net/10883/20090 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
dig-cimmyt-10883-20090 |
|---|---|
| record_format |
koha |
| spelling |
dig-cimmyt-10883-200902024-03-13T15:16:57Z A benchmarking between deep learning, support vector machine and bayesian threshold best linear unbiased prediction for predicting ordinal traits in plant breeding Montesinos-Lopez, O.A. Martin-Vallejo, J. Crossa, J. Gianola, D. Hernández Suárez, C.M. Montesinos-Lopez, A. Juliana, P. Singh, R.P. AGRICULTURAL SCIENCES AND BIOTECHNOLOGY Threshold GBLUP Deep Learning Support Vector Machine Genomic Selection Genomic Prediction GenPred Shared Data Resources BAYESIAN THEORY STATISTICAL METHODS MACHINE LEARNING ARTIFICIAL SELECTION PLANT BREEDING CROP FORECASTING DATA ANALYSIS Genomic selection is revolutionizing plant breeding. However, still lacking are better statistical models for ordinal phenotypes to improve the accuracy of the selection of candidate genotypes. For this reason, in this paper we explore the genomic based prediction performance of two popular machine learning methods: the Multi Layer Perceptron (MLP) and support vector machine (SVM) methods vs. the Bayesian threshold genomic best linear unbiased prediction (TGBLUP) model. We used the percentage of cases correctly classified (PCCC) as a metric to measure the prediction performance, and seven real data sets to evaluate the prediction accuracy, and found that the best predictions (in four out of the seven data sets) in terms of PCCC occurred under the TGLBUP model, while the worst occurred under the SVM method. Also, in general we found no statistical differences between using 1, 2 and 3 layers under the MLP models, which means that many times the conventional neuronal network model with only one layer is enough. However, although even that the TGBLUP model was better, we found that the predictions of MLP and SVM were very competitive with the advantage that the SVM was the most efficient in terms of the computational time required. 601-618 2019-03-20T01:25:13Z 2019-03-20T01:25:13Z 2019 Article Published Version ESSN: 2160-1836 https://hdl.handle.net/10883/20090 10.1534/g3.118.200998 English Open Access PDF Bethesda, MD Genetics Society of America 2 9 G3: Genes, Genomes, Genetics |
| institution |
CIMMYT |
| collection |
DSpace |
| country |
México |
| countrycode |
MX |
| component |
Bibliográfico |
| access |
En linea |
| databasecode |
dig-cimmyt |
| tag |
biblioteca |
| region |
America del Norte |
| libraryname |
CIMMYT Library |
| language |
English |
| topic |
AGRICULTURAL SCIENCES AND BIOTECHNOLOGY Threshold GBLUP Deep Learning Support Vector Machine Genomic Selection Genomic Prediction GenPred Shared Data Resources BAYESIAN THEORY STATISTICAL METHODS MACHINE LEARNING ARTIFICIAL SELECTION PLANT BREEDING CROP FORECASTING DATA ANALYSIS AGRICULTURAL SCIENCES AND BIOTECHNOLOGY Threshold GBLUP Deep Learning Support Vector Machine Genomic Selection Genomic Prediction GenPred Shared Data Resources BAYESIAN THEORY STATISTICAL METHODS MACHINE LEARNING ARTIFICIAL SELECTION PLANT BREEDING CROP FORECASTING DATA ANALYSIS |
| spellingShingle |
AGRICULTURAL SCIENCES AND BIOTECHNOLOGY Threshold GBLUP Deep Learning Support Vector Machine Genomic Selection Genomic Prediction GenPred Shared Data Resources BAYESIAN THEORY STATISTICAL METHODS MACHINE LEARNING ARTIFICIAL SELECTION PLANT BREEDING CROP FORECASTING DATA ANALYSIS AGRICULTURAL SCIENCES AND BIOTECHNOLOGY Threshold GBLUP Deep Learning Support Vector Machine Genomic Selection Genomic Prediction GenPred Shared Data Resources BAYESIAN THEORY STATISTICAL METHODS MACHINE LEARNING ARTIFICIAL SELECTION PLANT BREEDING CROP FORECASTING DATA ANALYSIS Montesinos-Lopez, O.A. Martin-Vallejo, J. Crossa, J. Gianola, D. Hernández Suárez, C.M. Montesinos-Lopez, A. Juliana, P. Singh, R.P. A benchmarking between deep learning, support vector machine and bayesian threshold best linear unbiased prediction for predicting ordinal traits in plant breeding |
| description |
Genomic selection is revolutionizing plant breeding. However, still lacking are better statistical models for ordinal phenotypes to improve the accuracy of the selection of candidate genotypes. For this reason, in this paper we explore the genomic based prediction performance of two popular machine learning methods: the Multi Layer Perceptron (MLP) and support vector machine (SVM) methods vs. the Bayesian threshold genomic best linear unbiased prediction (TGBLUP) model. We used the percentage of cases correctly classified (PCCC) as a metric to measure the prediction performance, and seven real data sets to evaluate the prediction accuracy, and found that the best predictions (in four out of the seven data sets) in terms of PCCC occurred under the TGLBUP model, while the worst occurred under the SVM method. Also, in general we found no statistical differences between using 1, 2 and 3 layers under the MLP models, which means that many times the conventional neuronal network model with only one layer is enough. However, although even that the TGBLUP model was better, we found that the predictions of MLP and SVM were very competitive with the advantage that the SVM was the most efficient in terms of the computational time required. |
| format |
Article |
| topic_facet |
AGRICULTURAL SCIENCES AND BIOTECHNOLOGY Threshold GBLUP Deep Learning Support Vector Machine Genomic Selection Genomic Prediction GenPred Shared Data Resources BAYESIAN THEORY STATISTICAL METHODS MACHINE LEARNING ARTIFICIAL SELECTION PLANT BREEDING CROP FORECASTING DATA ANALYSIS |
| author |
Montesinos-Lopez, O.A. Martin-Vallejo, J. Crossa, J. Gianola, D. Hernández Suárez, C.M. Montesinos-Lopez, A. Juliana, P. Singh, R.P. |
| author_facet |
Montesinos-Lopez, O.A. Martin-Vallejo, J. Crossa, J. Gianola, D. Hernández Suárez, C.M. Montesinos-Lopez, A. Juliana, P. Singh, R.P. |
| author_sort |
Montesinos-Lopez, O.A. |
| title |
A benchmarking between deep learning, support vector machine and bayesian threshold best linear unbiased prediction for predicting ordinal traits in plant breeding |
| title_short |
A benchmarking between deep learning, support vector machine and bayesian threshold best linear unbiased prediction for predicting ordinal traits in plant breeding |
| title_full |
A benchmarking between deep learning, support vector machine and bayesian threshold best linear unbiased prediction for predicting ordinal traits in plant breeding |
| title_fullStr |
A benchmarking between deep learning, support vector machine and bayesian threshold best linear unbiased prediction for predicting ordinal traits in plant breeding |
| title_full_unstemmed |
A benchmarking between deep learning, support vector machine and bayesian threshold best linear unbiased prediction for predicting ordinal traits in plant breeding |
| title_sort |
benchmarking between deep learning, support vector machine and bayesian threshold best linear unbiased prediction for predicting ordinal traits in plant breeding |
| publisher |
Genetics Society of America |
| publishDate |
2019 |
| url |
https://hdl.handle.net/10883/20090 |
| work_keys_str_mv |
AT montesinoslopezoa abenchmarkingbetweendeeplearningsupportvectormachineandbayesianthresholdbestlinearunbiasedpredictionforpredictingordinaltraitsinplantbreeding AT martinvallejoj abenchmarkingbetweendeeplearningsupportvectormachineandbayesianthresholdbestlinearunbiasedpredictionforpredictingordinaltraitsinplantbreeding AT crossaj abenchmarkingbetweendeeplearningsupportvectormachineandbayesianthresholdbestlinearunbiasedpredictionforpredictingordinaltraitsinplantbreeding AT gianolad abenchmarkingbetweendeeplearningsupportvectormachineandbayesianthresholdbestlinearunbiasedpredictionforpredictingordinaltraitsinplantbreeding AT hernandezsuarezcm abenchmarkingbetweendeeplearningsupportvectormachineandbayesianthresholdbestlinearunbiasedpredictionforpredictingordinaltraitsinplantbreeding AT montesinoslopeza abenchmarkingbetweendeeplearningsupportvectormachineandbayesianthresholdbestlinearunbiasedpredictionforpredictingordinaltraitsinplantbreeding AT julianap abenchmarkingbetweendeeplearningsupportvectormachineandbayesianthresholdbestlinearunbiasedpredictionforpredictingordinaltraitsinplantbreeding AT singhrp abenchmarkingbetweendeeplearningsupportvectormachineandbayesianthresholdbestlinearunbiasedpredictionforpredictingordinaltraitsinplantbreeding AT montesinoslopezoa benchmarkingbetweendeeplearningsupportvectormachineandbayesianthresholdbestlinearunbiasedpredictionforpredictingordinaltraitsinplantbreeding AT martinvallejoj benchmarkingbetweendeeplearningsupportvectormachineandbayesianthresholdbestlinearunbiasedpredictionforpredictingordinaltraitsinplantbreeding AT crossaj benchmarkingbetweendeeplearningsupportvectormachineandbayesianthresholdbestlinearunbiasedpredictionforpredictingordinaltraitsinplantbreeding AT gianolad benchmarkingbetweendeeplearningsupportvectormachineandbayesianthresholdbestlinearunbiasedpredictionforpredictingordinaltraitsinplantbreeding AT hernandezsuarezcm benchmarkingbetweendeeplearningsupportvectormachineandbayesianthresholdbestlinearunbiasedpredictionforpredictingordinaltraitsinplantbreeding AT montesinoslopeza benchmarkingbetweendeeplearningsupportvectormachineandbayesianthresholdbestlinearunbiasedpredictionforpredictingordinaltraitsinplantbreeding AT julianap benchmarkingbetweendeeplearningsupportvectormachineandbayesianthresholdbestlinearunbiasedpredictionforpredictingordinaltraitsinplantbreeding AT singhrp benchmarkingbetweendeeplearningsupportvectormachineandbayesianthresholdbestlinearunbiasedpredictionforpredictingordinaltraitsinplantbreeding |
| _version_ |
1794797624980668416 |