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

Statistical Learning Algorithms for ...

Kemmo Tsafack, Ulrich,

Linked to FindBook

Google Book

Amazon

博客來

Statistical Learning Algorithms for High Dimensional Multi-omics Data /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Statistical Learning Algorithms for High Dimensional Multi-omics Data // Ulrich Kemmo Tsafack.
Author:	Kemmo Tsafack, Ulrich,
Description:	1 electronic resource (50 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-03, Section: B.
Contained By:	Dissertations Abstracts International86-03B.
Subject:	Biostatistics. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31556431
ISBN:	9798384077657

Statistical Learning Algorithms for High Dimensional Multi-omics Data /
Kemmo Tsafack, Ulrich,

Statistical Learning Algorithms for High Dimensional Multi-omics Data /Ulrich Kemmo Tsafack. - 1 electronic resource (50 pages)

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

Traditional statistical methods are developed for data where the number of features (p) is less than the number of observations (n). Those methods become unstable when they are used for high-dimensional data where p ≥ n. With the evolution of storage technologies, it is now possible to collect and save abundant features per individual in such a way that p becomes much larger than n (p ≫ n), leading to what is called ultra-high dimensional data. The exploitation of such rich data requires adequate methods to leverage the most of information from them. Studies with multi-omics data are often ultra-high dimensional. To understand the biological processes of living beings, gene pathways and gene regulatory networks are being constructed to describe the relationship between genes based on biological experiments. However, many genes are still to be studied to define novel pathways. To address this, gene clustering algorithm has been used to group correlated genes together, based on the similarity of their gene expression level. The existing methods cluster genes based on only one type of omics data, which ignores the information from other types. Large sample size is required to achieve an accurate clustering structure for thousands of genes, which can be challenging due to the cost of multi-omics data. Meta-analysis has been used to aggregate the data from multiple studies and improve the analysis results. We propose a computationally efficient meta-analytic gene clustering algorithm that combines multi-omics datasets from multiple studies, using the fixed effects linear model and a modified weighted correlation network analysis framework. The simulation study shows that the proposed method outperforms existing single-omic-based clustering approaches when multi-omics data and/or multiple studies are available. A real-data example demonstrates that our meta-analytic method outperforms single-study based methods.In the context of ultra-high dimensional multi-omics data, identifying important genes and omics associated to the outcome variable is of great interest. However, applying the existing variable selection methods for ultra-high dimensional data may be inefficient when some genes are highly correlated. To address this issue, we first propose a gene clustering method to cluster the genes beforehand. Then, we propose a two-step variable selection method that consists of screening insignificant clusters and genes to make the number of features less than the sample size; then applying a penalized regression on the screened data. The proposed screening method select important variables at bi-level: at cluster-level and gene-level. We show that the proposed screening method possesses the sure screening property. Extensive simulations show that the proposed screening method outperforms competing methods. We apply the proposed variable selection method to the TCGA breast cancer dataset to identify genes and omics that are related to breast cancer.

English

ISBN: 9798384077657Subjects--Topical Terms:

1002712
Biostatistics.
Subjects--Index Terms:

Gene clustering algorithm

Statistical Learning Algorithms for High Dimensional Multi-omics Data /
LDR:04567nmm a22004693i 4500 001 2429384
005 20250430100814.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798384077657
035 $a (MiAaPQD)AAI31556431
035 $a AAI31556431
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Kemmo Tsafack, Ulrich, $e author. $3 3817202
245 1 0 $a Statistical Learning Algorithms for High Dimensional Multi-omics Data / $c Ulrich Kemmo Tsafack.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (50 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: Ahn, Kwang Woo; Lin, Chien-Wei Committee members: Wang, Tao; Auer, Paul; Kwitek, Anne.
502 $b Ph.D. $c The Medical College of Wisconsin $d 2024.
520 $a Traditional statistical methods are developed for data where the number of features (p) is less than the number of observations (n). Those methods become unstable when they are used for high-dimensional data where p ≥ n. With the evolution of storage technologies, it is now possible to collect and save abundant features per individual in such a way that p becomes much larger than n (p ≫ n), leading to what is called ultra-high dimensional data. The exploitation of such rich data requires adequate methods to leverage the most of information from them. Studies with multi-omics data are often ultra-high dimensional. To understand the biological processes of living beings, gene pathways and gene regulatory networks are being constructed to describe the relationship between genes based on biological experiments. However, many genes are still to be studied to define novel pathways. To address this, gene clustering algorithm has been used to group correlated genes together, based on the similarity of their gene expression level. The existing methods cluster genes based on only one type of omics data, which ignores the information from other types. Large sample size is required to achieve an accurate clustering structure for thousands of genes, which can be challenging due to the cost of multi-omics data. Meta-analysis has been used to aggregate the data from multiple studies and improve the analysis results. We propose a computationally efficient meta-analytic gene clustering algorithm that combines multi-omics datasets from multiple studies, using the fixed effects linear model and a modified weighted correlation network analysis framework. The simulation study shows that the proposed method outperforms existing single-omic-based clustering approaches when multi-omics data and/or multiple studies are available. A real-data example demonstrates that our meta-analytic method outperforms single-study based methods.In the context of ultra-high dimensional multi-omics data, identifying important genes and omics associated to the outcome variable is of great interest. However, applying the existing variable selection methods for ultra-high dimensional data may be inefficient when some genes are highly correlated. To address this issue, we first propose a gene clustering method to cluster the genes beforehand. Then, we propose a two-step variable selection method that consists of screening insignificant clusters and genes to make the number of features less than the sample size; then applying a penalized regression on the screened data. The proposed screening method select important variables at bi-level: at cluster-level and gene-level. We show that the proposed screening method possesses the sure screening property. Extensive simulations show that the proposed screening method outperforms competing methods. We apply the proposed variable selection method to the TCGA breast cancer dataset to identify genes and omics that are related to breast cancer.
546 $a English
590 $a School code: 0495
650 4 $a Biostatistics. $3 1002712
650 4 $a Oncology. $3 751006
650 4 $a Bioinformatics. $3 553671
650 4 $a Genetics. $3 530508
653 $a Gene clustering algorithm
653 $a Meta analysis
653 $a Multi-omics data
653 $a Screening
653 $a Ultra-high dimensional data
653 $a Variable selection
690 $a 0308
690 $a 0992
690 $a 0369
690 $a 0715
710 2 $a The Medical College of Wisconsin. $b Biostatistics. $e degree granting institution. $3 3817203
720 1 $a Ahn, Kwang Woo $e degree supervisor.
720 1 $a Lin, Chien-Wei $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-03B.
790 $a 0495
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31556431