國立虎尾科技大學 |

Genomic selection with deep neural networks.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Genomic selection with deep neural networks./
作者:	McDowell, Riley.
面頁冊數:	1 online resource (49 pages)
附註:	Source: Masters Abstracts International, Volume: 56-03.
標題:	Plant sciences. -
電子資源:	click for full text (PQDT)
ISBN:	9781369528244

Genomic selection with deep neural networks.
McDowell, Riley.

Genomic selection with deep neural networks. - 1 online resource (49 pages)

Source: Masters Abstracts International, Volume: 56-03.

Thesis (M.S.)--Iowa State University, 2016.

Includes bibliographical references

Reduced costs for DNA marker technology has generated a huge amount of molecular data and made it economically feasible to generate dense genome-wide marker maps of lines in a breeding program. Increased data density and volume has driven an exploration of tools and techniques to analyze these data for cultivar improvement. Data science theory and application has experienced a resurgence of research into techniques to detect or "learn" patterns in noisy data in a variety of technical applications. Several variants of machine learning have been proposed for analyzing large DNA marker data sets to aid in phenotype prediction and genomic selection. Here, we present a review of the genomic prediction and machine learning literature. We apply deep learning techniques from machine learning research to six phenotypic prediction tasks using published reference datasets. Because regularization frequently improves neural network prediction accuracy, we included regularization methods in the neural network models. The neural network models are compared to a selection of regularized Bayesian and linear regression techniques commonly employed for phenotypic prediction and genomic selection. On three of the phenotype prediction tasks, regularized neural networks were the most accurate of the models evaluated. Surprisingly, for these data sets the depth of the network architecture did not affect the accuracy of the trained model. We also find that concerns about the computer processing time needed to train neural network models to perform well in genomic prediction tasks may not apply when Graphics Processing Units are used for model training.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9781369528244Subjects--Topical Terms:

1179743
Plant sciences.
Index Terms--Genre/Form:

554714
Electronic books.

Genomic selection with deep neural networks.
LDR:02833ntm a2200337K 4500 001 915265
005 20180727125211.5
006 m o u
007 cr mn||||a|a||
008 190606s2016 xx obm 000 0 eng d
020 $a 9781369528244
035 $a (MiAaPQ)AAI10243302
035 $a (MiAaPQ)iastate:16108
035 $a AAI10243302
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a McDowell, Riley. $3 1188571
245 1 0 $a Genomic selection with deep neural networks.
264 0 $c 2016
300 $a 1 online resource (49 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 56-03.
500 $a Includes supplementary digital materials.
500 $a Advisers: David Grant; William Beavis.
502 $a Thesis (M.S.)--Iowa State University, 2016.
504 $a Includes bibliographical references
520 $a Reduced costs for DNA marker technology has generated a huge amount of molecular data and made it economically feasible to generate dense genome-wide marker maps of lines in a breeding program. Increased data density and volume has driven an exploration of tools and techniques to analyze these data for cultivar improvement. Data science theory and application has experienced a resurgence of research into techniques to detect or "learn" patterns in noisy data in a variety of technical applications. Several variants of machine learning have been proposed for analyzing large DNA marker data sets to aid in phenotype prediction and genomic selection. Here, we present a review of the genomic prediction and machine learning literature. We apply deep learning techniques from machine learning research to six phenotypic prediction tasks using published reference datasets. Because regularization frequently improves neural network prediction accuracy, we included regularization methods in the neural network models. The neural network models are compared to a selection of regularized Bayesian and linear regression techniques commonly employed for phenotypic prediction and genomic selection. On three of the phenotype prediction tasks, regularized neural networks were the most accurate of the models evaluated. Surprisingly, for these data sets the depth of the network architecture did not affect the accuracy of the trained model. We also find that concerns about the computer processing time needed to train neural network models to perform well in genomic prediction tasks may not apply when Graphics Processing Units are used for model training.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Plant sciences. $3 1179743
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0479
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Iowa State University. $b Agronomy. $3 1148552
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10243302 $z click for full text (PQDT)