國立虎尾科技大學 |

Optimizing decision tree ensembles for gene-gene interaction detection.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Optimizing decision tree ensembles for gene-gene interaction detection./
作者:	Assareh, Amin.
面頁冊數:	1 online resource (149 pages)
附註:	Source: Dissertations Abstracts International, Volume: 74-08, Section: B.
Contained By:	Dissertations Abstracts International74-08B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9781267818157

Optimizing decision tree ensembles for gene-gene interaction detection.
Assareh, Amin.

Optimizing decision tree ensembles for gene-gene interaction detection. - 1 online resource (149 pages)

Source: Dissertations Abstracts International, Volume: 74-08, Section: B.

Thesis (Ph.D.)--Kent State University, 2012.

Includes bibliographical references

In recent years, genome-wide association studies (GWAS) have been dedicated to unraveling the genetic etiology of complex diseases. It is widely accepted that most common diseases such as neurodegenerative diseases (e.g., Alzheimer's and Parkinson's diseases), cardiovascular diseases, various cancers, diabetes and osteoporosis are the results of multiple genes, their interactions, environmental factors, and gene-by-environment interactions and thus cannot be explained by a simple Mendelian inheritance model. Consequently, the study of dissecting gene-gene and/or gene-environment interactions involved in complex diseases/traits has become an active research topic in computational genomics. However, high dimensionalities of genotype data and exponential complexity of the search space with respect to the order of targeted interactions, make most existing interaction detection strategies practically inapplicable. Because they are capable of capturing interactions among input variables in addition to the nonlinear effects, decision trees and their ensembles have been recently demonstrated to be effective strategies in detecting interactions in GWAS data. However, an individual decision tree (DT) is highly susceptible to some major limitations, most importantly high variance error, data fragmentation and representational problems, which make them unreliable for use in feature selection in a stand-alone fashion. Ensemble approaches have been proposed to increase the robustness of weak learners such as DTs, by using multiple different and potentially complementary representations of the data. Some of the limitations of individual decision trees would still exist in the ensemble level which may impact their interaction detection performance. The objectives of this dissertation are to: • Study the systematic limitations of individual decision trees which may impact their interaction detection performance and the possible solutions; • Investigate the application of decision tree ensembles in interaction detections, with respect to the functional characteristics of the applied ensemble strategy; • Compare four well-known ensemble frameworks, namely AdaBoost, LogitBoost, Bagging and Random Forest, and their pros and cons as far as interaction detection is concerned; • Provide a unified framework to optimize the application of DT ensembles in interaction detection.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9781267818157Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Decision treesIndex Terms--Genre/Form:

554714
Electronic books.

Optimizing decision tree ensembles for gene-gene interaction detection.
LDR:03755ntm a22003737 4500 001 1150046
005 20241023120628.5
006 m o d
007 cr bn ---uuuuu
008 250605s2012 xx obm 000 0 eng d
020 $a 9781267818157
035 $a (MiAaPQ)AAI3534606
035 $a (MiAaPQ)ohiolink:kent1353971575
035 $a AAI3534606
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Assareh, Amin. $3 1476459
245 1 0 $a Optimizing decision tree ensembles for gene-gene interaction detection.
264 0 $c 2012
300 $a 1 online resource (149 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: Dissertations Abstracts International, Volume: 74-08, Section: B.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Advisor: Volkert, L. Gwenn.
502 $a Thesis (Ph.D.)--Kent State University, 2012.
504 $a Includes bibliographical references
520 $a In recent years, genome-wide association studies (GWAS) have been dedicated to unraveling the genetic etiology of complex diseases. It is widely accepted that most common diseases such as neurodegenerative diseases (e.g., Alzheimer's and Parkinson's diseases), cardiovascular diseases, various cancers, diabetes and osteoporosis are the results of multiple genes, their interactions, environmental factors, and gene-by-environment interactions and thus cannot be explained by a simple Mendelian inheritance model. Consequently, the study of dissecting gene-gene and/or gene-environment interactions involved in complex diseases/traits has become an active research topic in computational genomics. However, high dimensionalities of genotype data and exponential complexity of the search space with respect to the order of targeted interactions, make most existing interaction detection strategies practically inapplicable. Because they are capable of capturing interactions among input variables in addition to the nonlinear effects, decision trees and their ensembles have been recently demonstrated to be effective strategies in detecting interactions in GWAS data. However, an individual decision tree (DT) is highly susceptible to some major limitations, most importantly high variance error, data fragmentation and representational problems, which make them unreliable for use in feature selection in a stand-alone fashion. Ensemble approaches have been proposed to increase the robustness of weak learners such as DTs, by using multiple different and potentially complementary representations of the data. Some of the limitations of individual decision trees would still exist in the ensemble level which may impact their interaction detection performance. The objectives of this dissertation are to: • Study the systematic limitations of individual decision trees which may impact their interaction detection performance and the possible solutions; • Investigate the application of decision tree ensembles in interaction detections, with respect to the functional characteristics of the applied ensemble strategy; • Compare four well-known ensemble frameworks, namely AdaBoost, LogitBoost, Bagging and Random Forest, and their pros and cons as far as interaction detection is concerned; • Provide a unified framework to optimize the application of DT ensembles in interaction detection.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Bioinformatics. $3 583857
653 $a Decision trees
653 $a Gene-gene interactions
655 7 $a Electronic books. $2 local $3 554714
690 $a 0715
690 $a 0984
710 2 $a Kent State University. $b Computer Science. $3 1476460
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Dissertations Abstracts International $g 74-08B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3534606 $z click for full text (PQDT)