國立高雄大學圖資館 |

Language: English

Back

Single cell expression data analysis...

Pouyan, Maziyar Baran.

Single cell expression data analysis using advanced machine learning techniques.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Single cell expression data analysis using advanced machine learning techniques.
Author:	Pouyan, Maziyar Baran.
Published:	Ann Arbor : ProQuest Dissertations & Theses, 2016
Description:	95 p.
Notes:	Source: Dissertation Abstracts International, Volume: 77-12(E), Section: B.
Notes:	Adviser: Mehrdad Nourani.
Contained By:	Dissertation Abstracts International77-12B(E).
Subject:	Computer engineering.
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10151471
ISBN:	9781369062359

Single cell expression data analysis using advanced machine learning techniques.
Pouyan, Maziyar Baran.

Single cell expression data analysis using advanced machine learning techniques. - Ann Arbor : ProQuest Dissertations & Theses, 2016 - 95 p.

Source: Dissertation Abstracts International, Volume: 77-12(E), Section: B.

Thesis (Ph.D.)--The University of Texas at Dallas, 2016.

Single-cell cytometry is a technology that measures the expression of several cellular markers simultaneously for a large number of cells. Identification of homogeneous cell populations, currently done by manual biaxial gating, is highly subjective and time consuming. To overcome the shortcomings of manual gating, automatic algorithms have been proposed. However, the performance of these methods highly depends on the shape of populations and the dimension of the data. Although there have been numerous developments in recent years to design computational tools for cytometry data, there is still an extremely limited guidance available for the end users to use these methods efficiently. Two critical challenges in cytometry data analysis are studied in this research. The first major area emphasizes the identification of cell population from single-cell cytometry data collected from a single subject. Even though clustering is useful in identifying the cell populations, it provides limited information on cellular correlation to clinical outcomes. Thus, the second area focuses on methods capable of predicting disease state in a sample by using classification models trained on previously annotated samples. In this work, two clustering approaches are presented to address the first challenge. For the second problem, a hybrid classification technique is proposed to classify patients with various clinical outcomes (e.g, healthy or patient).

ISBN: 9781369062359Subjects--Topical Terms:

212944
Computer engineering.

Single cell expression data analysis using advanced machine learning techniques.
LDR:02397nmm a2200301 4500 001 502127
005 20170619070728.5
008 170818s2016 ||||||||||||||||| ||eng d
020 $a 9781369062359
035 $a (MiAaPQ)AAI10151471
035 $a AAI10151471
040 $a MiAaPQ $c MiAaPQ
100 1 $a Pouyan, Maziyar Baran. $3 766154
245 1 0 $a Single cell expression data analysis using advanced machine learning techniques.
260 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2016
300 $a 95 p.
500 $a Source: Dissertation Abstracts International, Volume: 77-12(E), Section: B.
500 $a Adviser: Mehrdad Nourani.
502 $a Thesis (Ph.D.)--The University of Texas at Dallas, 2016.
520 $a Single-cell cytometry is a technology that measures the expression of several cellular markers simultaneously for a large number of cells. Identification of homogeneous cell populations, currently done by manual biaxial gating, is highly subjective and time consuming. To overcome the shortcomings of manual gating, automatic algorithms have been proposed. However, the performance of these methods highly depends on the shape of populations and the dimension of the data. Although there have been numerous developments in recent years to design computational tools for cytometry data, there is still an extremely limited guidance available for the end users to use these methods efficiently. Two critical challenges in cytometry data analysis are studied in this research. The first major area emphasizes the identification of cell population from single-cell cytometry data collected from a single subject. Even though clustering is useful in identifying the cell populations, it provides limited information on cellular correlation to clinical outcomes. Thus, the second area focuses on methods capable of predicting disease state in a sample by using classification models trained on previously annotated samples. In this work, two clustering approaches are presented to address the first challenge. For the second problem, a hybrid classification technique is proposed to classify patients with various clinical outcomes (e.g, healthy or patient).
590 $a School code: 0382.
650 4 $a Computer engineering. $3 212944
650 4 $a Bioinformatics. $3 194415
650 4 $a Computer science. $3 199325
690 $a 0464
690 $a 0715
690 $a 0984
710 2 $a The University of Texas at Dallas. $b Electrical Engineering. $3 531015
773 0 $t Dissertation Abstracts International $g 77-12B(E).
790 $a 0382
791 $a Ph.D.
792 $a 2016
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10151471