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

Advancing Biological Modeling and Di...

Tan, Jimin,

FindBook

Google Book

Amazon

博客來

Advancing Biological Modeling and Discovery With Machine Learning /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Advancing Biological Modeling and Discovery With Machine Learning // Jimin Tan.
作者:	Tan, Jimin,
面頁冊數:	1 electronic resource (183 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-09, Section: B.
Contained By:	Dissertations Abstracts International86-09B.
標題:	Bioinformatics. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31564400
ISBN:	9798304997164

Advancing Biological Modeling and Discovery With Machine Learning /
Tan, Jimin,

Advancing Biological Modeling and Discovery With Machine Learning /Jimin Tan. - 1 electronic resource (183 pages)

Source: Dissertations Abstracts International, Volume: 86-09, Section: B.

Understanding the mechanisms underlying biological systems has enabled us to engineer interventions and even reverse certain biological processes. Learning and modeling biological systems remain challenging due to their complexity. Machine learning, particularly deep neural networks, has emerged as a powerful data-driven approach for modeling complex systems and has been successful in various areas. However, its efficacy is constrained by data and computational limitations, necessitating the development of domain-specific and efficient models for biological research. In this thesis, we use machine learning to explore two distinct areas of biology: 3D chromatin architecture and tumor microenvironments. We present two novel approaches that demonstrate the potential of machine learning in advancing biological discovery.First, we introduce C.Origami, a multimodal deep neural network that predicts cell-type-specific chromatin organization using DNA sequence and genomic features. This tool enables in silico experiments to examine the impact of genetic changes on chromatin interactions and facilitates the discovery of novel chromatin regulation circuits in disease-related cells.Second, we propose CANVAS, a self-supervised representation learning framework for analyzing the tumor microenvironment using high-dimensional multiplexed imaging data. CANVAS employs a vision transformer architecture and masked image modeling training objective to capture subtle morphological differences and characterize distinct tumor microenvironment signatures without supervision.These approaches demonstrate the power of tailored machine learning models both in advancing our understanding of complex biological systems and as engines driving new discoveries.

English

ISBN: 9798304997164Subjects--Topical Terms:

553671
Bioinformatics.
Subjects--Index Terms:

Computational biology

Advancing Biological Modeling and Discovery With Machine Learning /
LDR:03363nmm a22004933i 4500 001 2432603
005 20250731101854.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798304997164
035 $a (MiAaPQD)AAI31564400
035 $a AAI31564400
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Tan, Jimin, $e author. $3 3821893
245 1 0 $a Advancing Biological Modeling and Discovery With Machine Learning / $c Jimin Tan.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (183 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: 86-09, Section: B.
500 $a Advisors: Tsirigos, Aristotelis; Fenyo, David Committee members: Boeke, Jef D.; Cho, Kyunghyun; Moreira, Andre L.; Maurano, Matthew T.
502 $b Ph.D. $c New York University $d 2025.
520 $a Understanding the mechanisms underlying biological systems has enabled us to engineer interventions and even reverse certain biological processes. Learning and modeling biological systems remain challenging due to their complexity. Machine learning, particularly deep neural networks, has emerged as a powerful data-driven approach for modeling complex systems and has been successful in various areas. However, its efficacy is constrained by data and computational limitations, necessitating the development of domain-specific and efficient models for biological research. In this thesis, we use machine learning to explore two distinct areas of biology: 3D chromatin architecture and tumor microenvironments. We present two novel approaches that demonstrate the potential of machine learning in advancing biological discovery.First, we introduce C.Origami, a multimodal deep neural network that predicts cell-type-specific chromatin organization using DNA sequence and genomic features. This tool enables in silico experiments to examine the impact of genetic changes on chromatin interactions and facilitates the discovery of novel chromatin regulation circuits in disease-related cells.Second, we propose CANVAS, a self-supervised representation learning framework for analyzing the tumor microenvironment using high-dimensional multiplexed imaging data. CANVAS employs a vision transformer architecture and masked image modeling training objective to capture subtle morphological differences and characterize distinct tumor microenvironment signatures without supervision.These approaches demonstrate the power of tailored machine learning models both in advancing our understanding of complex biological systems and as engines driving new discoveries.
546 $a English
590 $a School code: 0146
650 4 $a Bioinformatics. $3 553671
650 4 $a Computer science. $3 523869
650 4 $a Genetics. $3 530508
650 4 $a Systematic biology. $3 3173492
650 4 $a Pathology. $3 643180
650 4 $a Medical imaging. $3 3172799
653 $a Computational biology
653 $a Deep learning
653 $a Genomics
653 $a Machine learning
653 $a Tumor microenvironments
690 $a 0715
690 $a 0984
690 $a 0369
690 $a 0571
690 $a 0423
690 $a 0574
690 $a 0800
710 2 $a New York University. $b Basic Medical Science. $e degree granting institution. $3 3821894
720 1 $a Tsirigos, Aristotelis $e degree supervisor.
720 1 $a Fenyo, David $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-09B.
790 $a 0146
791 $a Ph.D.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31564400