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

Augmenting Subnetwork Inference with...

Kiblawi, Sid H.

FindBook

Google Book

Amazon

博客來

Augmenting Subnetwork Inference with Information Extracted from the Scientific Literature.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Augmenting Subnetwork Inference with Information Extracted from the Scientific Literature./
作者:	Kiblawi, Sid H.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2019,
面頁冊數:	163 p.
附註:	Source: Dissertations Abstracts International, Volume: 80-12, Section: B.
Contained By:	Dissertations Abstracts International80-12B.
標題:	Biostatistics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13897437
ISBN:	9781392239148

Augmenting Subnetwork Inference with Information Extracted from the Scientific Literature.
Kiblawi, Sid H.

Augmenting Subnetwork Inference with Information Extracted from the Scientific Literature. - Ann Arbor : ProQuest Dissertations & Theses, 2019 - 163 p.

Source: Dissertations Abstracts International, Volume: 80-12, Section: B.

Thesis (Ph.D.)--The University of Wisconsin - Madison, 2019.

This item must not be sold to any third party vendors.

Many biological studies involve manipulating some aspect of a cell and then simultaneously measuring the effect on some biological response of interest. A common challenge is to explain how a set of genes identified as relevant in the given experiment are organized into a subnetwork that accounts for the response. This task, which we call subnetwork inference, is dependent on the information present in publicly available databases, which suffer from incompleteness. Much relevant information (gene relevance, interactions between entities, etc.) resides only within the text of scientific literature. We contend that by exploiting this information, we can improve the explanatory power of subnetwork inference in multiple applications.We contribute to subnetwork inference methodology by incorporating information present in the scientific literature. We show that by using tools that mine the scientific literature we can (i) augment the set of nodes identified as being relevant in the subnetwork inference task, (ii) augment the set of interactions used to infer subnetworks, and (iii) support targeted browsing of a large inferred subnetwork by identifying nodes and edges that are closely related to concepts of interest. We show the applicability of our approach by uncovering pathways involved in interactions between different viruses and a human host cell, and pathways that involve a transcription factor associated with breast cancer.We also contribute to the task of extracting relations between biological entities by developing an undirected graphical model that combines evidence across multiple instances in a corpus. This evidence combination approach attempts to predict the probability that at least one instance from our corpus describes a specific relation of interest between entities.

ISBN: 9781392239148Subjects--Topical Terms:

1002712
Biostatistics.

Augmenting Subnetwork Inference with Information Extracted from the Scientific Literature.
LDR:02905nmm a2200325 4500 001 2210856
005 20191121124322.5
008 201008s2019 ||||||||||||||||| ||eng d
020 $a 9781392239148
035 $a (MiAaPQ)AAI13897437
035 $a (MiAaPQ)wisc:16229
035 $a AAI13897437
040 $a MiAaPQ $c MiAaPQ
100 1 $a Kiblawi, Sid H. $3 3437998
245 1 0 $a Augmenting Subnetwork Inference with Information Extracted from the Scientific Literature.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2019
300 $a 163 p.
500 $a Source: Dissertations Abstracts International, Volume: 80-12, Section: B.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Advisor: Craven, Mark W.
502 $a Thesis (Ph.D.)--The University of Wisconsin - Madison, 2019.
506 $a This item must not be sold to any third party vendors.
520 $a Many biological studies involve manipulating some aspect of a cell and then simultaneously measuring the effect on some biological response of interest. A common challenge is to explain how a set of genes identified as relevant in the given experiment are organized into a subnetwork that accounts for the response. This task, which we call subnetwork inference, is dependent on the information present in publicly available databases, which suffer from incompleteness. Much relevant information (gene relevance, interactions between entities, etc.) resides only within the text of scientific literature. We contend that by exploiting this information, we can improve the explanatory power of subnetwork inference in multiple applications.We contribute to subnetwork inference methodology by incorporating information present in the scientific literature. We show that by using tools that mine the scientific literature we can (i) augment the set of nodes identified as being relevant in the subnetwork inference task, (ii) augment the set of interactions used to infer subnetworks, and (iii) support targeted browsing of a large inferred subnetwork by identifying nodes and edges that are closely related to concepts of interest. We show the applicability of our approach by uncovering pathways involved in interactions between different viruses and a human host cell, and pathways that involve a transcription factor associated with breast cancer.We also contribute to the task of extracting relations between biological entities by developing an undirected graphical model that combines evidence across multiple instances in a corpus. This evidence combination approach attempts to predict the probability that at least one instance from our corpus describes a specific relation of interest between entities.
590 $a School code: 0262.
650 4 $a Biostatistics. $3 1002712
650 4 $a Computer science. $3 523869
690 $a 0308
690 $a 0984
710 2 $a The University of Wisconsin - Madison. $b Computer Sciences. $3 2099760
773 0 $t Dissertations Abstracts International $g 80-12B.
790 $a 0262
791 $a Ph.D.
792 $a 2019
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13897437