東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Methods for Gene Regulatory Network-...

Najnin, Tanzira,

Linked to FindBook

Google Book

Amazon

博客來

Methods for Gene Regulatory Network-Based Knowledge Discovery and Cancer Outcome Prediction /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Methods for Gene Regulatory Network-Based Knowledge Discovery and Cancer Outcome Prediction // Tanzira Najnin.
Author:	Najnin, Tanzira,
Description:	1 electronic resource (109 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-03, Section: B.
Contained By:	Dissertations Abstracts International86-03B.
Subject:	Computer science. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31490542
ISBN:	9798384081302

Methods for Gene Regulatory Network-Based Knowledge Discovery and Cancer Outcome Prediction /
Najnin, Tanzira,

Methods for Gene Regulatory Network-Based Knowledge Discovery and Cancer Outcome Prediction /Tanzira Najnin. - 1 electronic resource (109 pages)

Source: Dissertations Abstracts International, Volume: 86-03, Section: B.

High-throughput experimental technology such as DNA microarray and next-generation sequencing has produced a vast amount of data that revolutionized biology. Consequently, sophisticated algorithms and computational methods are much needed to analyze these massive datasets for unbiased knowledge discoveries and realistic predictions. Gene regulatory networks (GRNs), which use graph-based representations of gene regulations, are a prevalent method for uncovering complex relationships among genes and understanding cellular functions at a systems level. GRNs can be constructed in various ways and have diverse applications. This study investigates techniques for constructing GRNs and explores their applications in both fundamental and applied biological sciences. Specifically, this research sets out three objectives to uncover biological knowledge using GRNs: 1) to improve the prediction of transcription factor functions and binding sites in the model plant Arabidopsis thaliana, 2) to identify key genes associated with metastatic breast cancer and predict survival outcomes for breast cancer patients, and 3) to apply knowledge-driven approaches across different cancer types (pan-cancer) to construct outcome prediction models. For the first objective, we designed a GRN-based method using gene expression profiles of transcription factors and genes. Determining the functions of transcription factors is crucial for biological knowledge discovery, and our network also predicts binding sites for each transcription factor, a critical area of research. The results, presented in this dissertation, demonstrate the effectiveness of our method. For the second objective, we constructed GRNs from both metastatic and non-metastatic cancer patients and utilized these networks to identify genes and regulators involved in the metastatic process. Our findings not only align with existing knowledge but also provide additional biological insights. Additionally, we developed a GRN-based model to predict the metastatic status of an unknown patient, showing that this knowledge-based, interpretable model outperformed several state-of-the-art classifiers. Finally, for the third objective, we hypothesize that patients from different cancer types may share common properties based on their molecular characteristics rather than tissue origins. Thus, we introduce two knowledge-based pan-cancer outcome prediction methods based on system-level knowledge. In conclusion, this dissertation demonstrates the value of GRNs in advancing data-driven biological knowledge discovery and improving the performance of standard machine learning models in biomedical applications.

English

ISBN: 9798384081302Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Breast cancer patients

Methods for Gene Regulatory Network-Based Knowledge Discovery and Cancer Outcome Prediction /
LDR:04229nmm a22004573i 4500 001 2434093
005 20250905091342.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798384081302
035 $a (MiAaPQD)AAI31490542
035 $a AAI31490542
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Najnin, Tanzira, $e author. $0 (orcid)0009-0005-3647-4253 $3 3823957
245 1 0 $a Methods for Gene Regulatory Network-Based Knowledge Discovery and Cancer Outcome Prediction / $c Tanzira Najnin.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (109 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: 86-03, Section: B.
500 $a Advisors: Ruan, Jianhua Committee members: Gibson-Lopez, Matthew; Najafirad, Peyman; Wang, Wei; Wang, Yufeng.
502 $b Ph.D. $c The University of Texas at San Antonio $d 2024.
520 $a High-throughput experimental technology such as DNA microarray and next-generation sequencing has produced a vast amount of data that revolutionized biology. Consequently, sophisticated algorithms and computational methods are much needed to analyze these massive datasets for unbiased knowledge discoveries and realistic predictions. Gene regulatory networks (GRNs), which use graph-based representations of gene regulations, are a prevalent method for uncovering complex relationships among genes and understanding cellular functions at a systems level. GRNs can be constructed in various ways and have diverse applications. This study investigates techniques for constructing GRNs and explores their applications in both fundamental and applied biological sciences. Specifically, this research sets out three objectives to uncover biological knowledge using GRNs: 1) to improve the prediction of transcription factor functions and binding sites in the model plant Arabidopsis thaliana, 2) to identify key genes associated with metastatic breast cancer and predict survival outcomes for breast cancer patients, and 3) to apply knowledge-driven approaches across different cancer types (pan-cancer) to construct outcome prediction models. For the first objective, we designed a GRN-based method using gene expression profiles of transcription factors and genes. Determining the functions of transcription factors is crucial for biological knowledge discovery, and our network also predicts binding sites for each transcription factor, a critical area of research. The results, presented in this dissertation, demonstrate the effectiveness of our method. For the second objective, we constructed GRNs from both metastatic and non-metastatic cancer patients and utilized these networks to identify genes and regulators involved in the metastatic process. Our findings not only align with existing knowledge but also provide additional biological insights. Additionally, we developed a GRN-based model to predict the metastatic status of an unknown patient, showing that this knowledge-based, interpretable model outperformed several state-of-the-art classifiers. Finally, for the third objective, we hypothesize that patients from different cancer types may share common properties based on their molecular characteristics rather than tissue origins. Thus, we introduce two knowledge-based pan-cancer outcome prediction methods based on system-level knowledge. In conclusion, this dissertation demonstrates the value of GRNs in advancing data-driven biological knowledge discovery and improving the performance of standard machine learning models in biomedical applications.
546 $a English
590 $a School code: 1283
650 4 $a Computer science. $3 523869
650 4 $a Bioinformatics. $3 553671
650 4 $a Cellular biology. $3 3172791
650 4 $a Oncology. $3 751006
650 4 $a Genetics. $3 530508
653 $a Breast cancer patients
653 $a Disease prediction
653 $a Gene regulatory network
653 $a Network analysis
653 $a Transcriptional regulation
690 $a 0984
690 $a 0715
690 $a 0379
690 $a 0992
690 $a 0369
710 2 $a The University of Texas at San Antonio. $b Computer Science. $e degree granting institution. $3 3822048
720 1 $a Ruan, Jianhua $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-03B.
790 $a 1283
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31490542