東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Casual inference methods in statisti...

Chaibub Neto, Elias.

FindBook

Google Book

Amazon

博客來

Casual inference methods in statistical genetics.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Casual inference methods in statistical genetics./
作者:	Chaibub Neto, Elias.
面頁冊數:	140 p.
附註:	Source: Dissertation Abstracts International, Volume: 72-05, Section: B, page: 2852.
Contained By:	Dissertation Abstracts International72-05B.
標題:	Biology, Genetics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3448835
ISBN:	9781124550572

Casual inference methods in statistical genetics.
Chaibub Neto, Elias.

Casual inference methods in statistical genetics. - 140 p.

Source: Dissertation Abstracts International, Volume: 72-05, Section: B, page: 2852.

Thesis (Ph.D.)--The University of Wisconsin - Madison, 2010.

Causal inference methods have received a great deal of attention in the current statistical genetics literature. These approaches aim to learn causal relationships between phenotypes making use of naturally occurring genetic variability in segregating populations. A key objective of biomedical research is to unravel the biochemical and genetical mechanism underlying complex disease traits. Statistical methods capable to discover causal relationships between phenotypes are specially important since they can lead directly to drug targets and biomarkers of disease. Current approaches for causal inference in systems genetics can be classified into network methods, which focus on the inference whole networks, or pairwise methods, which focus on causal relationships among pairs of phenotypes. Pairwise methods can be used as a screen tool to detect key regulators with widespread effects on downstream molecular and clinical phenotypes. Putative regulators and their putative targets can then be used to construct network models of disease and molecular pathways. In this dissertation we present novel pairwise and network methods for causal inference in systems genetics. First, we develop an asymptotic hypothesis test (CMST) that extends Vuong's model selection test to the case of three misspecified models, to handle the full range of possible causal relationships among a pair of traits, namely, causal, reactive or independent models. The ability to properly address misspecified models for systems genetics is key since in general any two phenotypes may be part of a complex network that is grossly oversimplified by the pairwise models. Second, we develop a quantitative trait loci driven phenotype network method (QTLnet) to jointly infer a causal phenotype network and associated genetic architecture for sets of correlated phenotypes. The genetic architecture for each phenotype is inferred conditional on the phenotype network. Because the phenotype network structure is itself unknown, the algorithm iterates between updating the network structure and genetic architecture using a Markov chain Monte Carlo approach. The posterior sample of network structures is summarized by Bayesian model averaging. Tailoring quantitative trait loci (QTL) mapping to network structure avoids the false detection of QTLs with indirect effects and improves phenotype network structure inference.

ISBN: 9781124550572Subjects--Topical Terms:

1017730
Biology, Genetics.

Casual inference methods in statistical genetics.
LDR:03276nam 2200277 4500 001 1404630
005 20111130124104.5
008 130515s2010 ||||||||||||||||| ||eng d
020 $a 9781124550572
035 $a (UMI)AAI3448835
035 $a AAI3448835
040 $a UMI $c UMI
100 1 $a Chaibub Neto, Elias. $3 1683964
245 1 0 $a Casual inference methods in statistical genetics.
300 $a 140 p.
500 $a Source: Dissertation Abstracts International, Volume: 72-05, Section: B, page: 2852.
500 $a Adviser: Brian S. Yandell.
502 $a Thesis (Ph.D.)--The University of Wisconsin - Madison, 2010.
520 $a Causal inference methods have received a great deal of attention in the current statistical genetics literature. These approaches aim to learn causal relationships between phenotypes making use of naturally occurring genetic variability in segregating populations. A key objective of biomedical research is to unravel the biochemical and genetical mechanism underlying complex disease traits. Statistical methods capable to discover causal relationships between phenotypes are specially important since they can lead directly to drug targets and biomarkers of disease. Current approaches for causal inference in systems genetics can be classified into network methods, which focus on the inference whole networks, or pairwise methods, which focus on causal relationships among pairs of phenotypes. Pairwise methods can be used as a screen tool to detect key regulators with widespread effects on downstream molecular and clinical phenotypes. Putative regulators and their putative targets can then be used to construct network models of disease and molecular pathways. In this dissertation we present novel pairwise and network methods for causal inference in systems genetics. First, we develop an asymptotic hypothesis test (CMST) that extends Vuong's model selection test to the case of three misspecified models, to handle the full range of possible causal relationships among a pair of traits, namely, causal, reactive or independent models. The ability to properly address misspecified models for systems genetics is key since in general any two phenotypes may be part of a complex network that is grossly oversimplified by the pairwise models. Second, we develop a quantitative trait loci driven phenotype network method (QTLnet) to jointly infer a causal phenotype network and associated genetic architecture for sets of correlated phenotypes. The genetic architecture for each phenotype is inferred conditional on the phenotype network. Because the phenotype network structure is itself unknown, the algorithm iterates between updating the network structure and genetic architecture using a Markov chain Monte Carlo approach. The posterior sample of network structures is summarized by Bayesian model averaging. Tailoring quantitative trait loci (QTL) mapping to network structure avoids the false detection of QTLs with indirect effects and improves phenotype network structure inference.
590 $a School code: 0262.
650 4 $a Biology, Genetics. $3 1017730
650 4 $a Statistics. $3 517247
690 $a 0369
690 $a 0463
710 2 $a The University of Wisconsin - Madison. $3 626640
773 0 $t Dissertation Abstracts International $g 72-05B.
790 1 0 $a Yandell, Brian S., $e advisor
790 $a 0262
791 $a Ph.D.
792 $a 2010
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3448835