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 到查詢結果 [ null ]

切換: 標籤 | MARC模式 | ISBD

Developing and Applying Machine Lear...

Choi, Jerome J.,

FindBook

Google Book

Amazon

博客來

Developing and Applying Machine Learning and Artificial Intelligence Approaches to Leverage Multi-Omics to Advance Understanding of Alzheimer's Disease Pathology /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Developing and Applying Machine Learning and Artificial Intelligence Approaches to Leverage Multi-Omics to Advance Understanding of Alzheimer's Disease Pathology // Jerome J Choi.
作者:	Choi, Jerome J.,
面頁冊數:	1 electronic resource (159 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-11, Section: B.
Contained By:	Dissertations Abstracts International86-11B.
標題:	Bioinformatics. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32045365
ISBN:	9798315751137

Developing and Applying Machine Learning and Artificial Intelligence Approaches to Leverage Multi-Omics to Advance Understanding of Alzheimer's Disease Pathology /
Choi, Jerome J.,

Developing and Applying Machine Learning and Artificial Intelligence Approaches to Leverage Multi-Omics to Advance Understanding of Alzheimer's Disease Pathology /Jerome J Choi. - 1 electronic resource (159 pages)

Source: Dissertations Abstracts International, Volume: 86-11, Section: B.

Alzheimer's disease (AD) is a progressive neurodegenerative disorder driven by complex, multifactorial processes involving genetic, epigenetic, transcriptomic, and metabolic dysregulation. Understanding the molecular mechanisms underlying AD requires approaches that can capture the dynamic interactions across these biological layers. The disease is not the result of a single molecular event but emerges from disruptions in coordinated biological networks, making it difficult to identify clear causal pathways or biomarkers. Multi-omics technologies provide a means to interrogate these layers simultaneously, offering a comprehensive view of disease biology by linking genetic variation to downstream molecular and cellular phenotypes. However, the integration and interpretation of multi-omics data pose significant analytical challenges due to high dimensionality, heterogeneity, sparsity, and biological noise. Machine learning (ML) offers powerful tools to address these challenges by modeling non-linear relationships, uncovering hidden patterns, learning from high-dimensional data, and enabling accurate and interpretable phenotype prediction. This dissertation develops and applies novel ML-based frameworks for integrative multi-omics analysis in the context of AD. First, the roles of cooperative transcription factor (TF) pairs in regulating target genes within the gene regulatory networks (GRNs) of oligodendrocytes were characterized, utilizing multi-omics data and deep learning approaches. Second, COSIME: Cooperative Multi-view Integration and Scalable and Interpretable Model Explainer was developed with applications to Alzheimer's Disease (AD). Third, multi-omics integration of transcriptomics and metabolomics with machine learning was used to uncover novel risk factors for AD. By combining computational innovation with biological insight, this work advances systems-level understanding of AD and contributes new tools for precision medicine and biomarker discovery.

English

ISBN: 9798315751137Subjects--Topical Terms:

553671
Bioinformatics.
Subjects--Index Terms:

Alzheimer's disease

Developing and Applying Machine Learning and Artificial Intelligence Approaches to Leverage Multi-Omics to Advance Understanding of Alzheimer's Disease Pathology /
LDR:03700nmm a22004693i 4500 001 2432729
005 20250731101921.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798315751137
035 $a (MiAaPQD)AAI32045365
035 $a AAI32045365
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Choi, Jerome J., $e author. $3 3822064
245 1 0 $a Developing and Applying Machine Learning and Artificial Intelligence Approaches to Leverage Multi-Omics to Advance Understanding of Alzheimer's Disease Pathology / $c Jerome J Choi.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (159 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: 86-11, Section: B.
500 $a Advisors: Engleman, Corinne D.; Wang, Daifeng Committee members: Svaren, John; Anderson, Shaneda Warren; Zuelsdorff, Megan; Lu, Tianyuan.
502 $b Ph.D. $c The University of Wisconsin - Madison $d 2025.
520 $a Alzheimer's disease (AD) is a progressive neurodegenerative disorder driven by complex, multifactorial processes involving genetic, epigenetic, transcriptomic, and metabolic dysregulation. Understanding the molecular mechanisms underlying AD requires approaches that can capture the dynamic interactions across these biological layers. The disease is not the result of a single molecular event but emerges from disruptions in coordinated biological networks, making it difficult to identify clear causal pathways or biomarkers. Multi-omics technologies provide a means to interrogate these layers simultaneously, offering a comprehensive view of disease biology by linking genetic variation to downstream molecular and cellular phenotypes. However, the integration and interpretation of multi-omics data pose significant analytical challenges due to high dimensionality, heterogeneity, sparsity, and biological noise. Machine learning (ML) offers powerful tools to address these challenges by modeling non-linear relationships, uncovering hidden patterns, learning from high-dimensional data, and enabling accurate and interpretable phenotype prediction. This dissertation develops and applies novel ML-based frameworks for integrative multi-omics analysis in the context of AD. First, the roles of cooperative transcription factor (TF) pairs in regulating target genes within the gene regulatory networks (GRNs) of oligodendrocytes were characterized, utilizing multi-omics data and deep learning approaches. Second, COSIME: Cooperative Multi-view Integration and Scalable and Interpretable Model Explainer was developed with applications to Alzheimer's Disease (AD). Third, multi-omics integration of transcriptomics and metabolomics with machine learning was used to uncover novel risk factors for AD. By combining computational innovation with biological insight, this work advances systems-level understanding of AD and contributes new tools for precision medicine and biomarker discovery.
546 $a English
590 $a School code: 0262
650 4 $a Bioinformatics. $3 553671
650 4 $a Biostatistics. $3 1002712
650 4 $a Epidemiology. $3 568544
650 4 $a Pathology. $3 643180
653 $a Alzheimer's disease
653 $a Machine learning
653 $a Transcription factor
653 $a Gene regulatory networks
653 $a Metabolic dysregulation
690 $a 0715
690 $a 0308
690 $a 0766
690 $a 0800
690 $a 0571
710 2 $a The University of Wisconsin - Madison. $b Population Health. $e degree granting institution. $3 3822065
720 1 $a Engleman, Corinne D. $e degree supervisor.
720 1 $a Wang, Daifeng $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-11B.
790 $a 0262
791 $a Ph.D.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32045365