東華大學圖書館 |

Deep Learning in Biomedical Research and Statistical Inference on Time Warping Functions /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Deep Learning in Biomedical Research and Statistical Inference on Time Warping Functions // Menghan Lin.
Author:	Lin, Menghan,
Description:	1 electronic resource (106 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-12, Section: B.
Contained By:	Dissertations Abstracts International86-12B.
Subject:	Statistics. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31842740
ISBN:	9798280722989

Deep Learning in Biomedical Research and Statistical Inference on Time Warping Functions /
Lin, Menghan,

Deep Learning in Biomedical Research and Statistical Inference on Time Warping Functions /Menghan Lin. - 1 electronic resource (106 pages)

Source: Dissertations Abstracts International, Volume: 86-12, Section: B.

In this dissertation, I will present two research projects that I have been working on during my doctoral study at Florida State University. I will provide a brief summary for each of these projects as follows. The detailed studies will be given in the chapters of this dissertation.Deep Learning ApplicationPart 1: Protein-Ligand Docking Deep learning has transformed protein-ligand docking by improving the accuracy and efficiency of interaction predictions, surpassing traditional molecular docking and free-energy simulation methods that often suffer from computational limitations and predefined heuristics. This study explores deep learning-based approaches for protein-ligand docking, emphasizing the role of reinforcement learning, generative models, and geometric deep learning in optimizing ligand placement within protein binding pockets. Our previous study formulated docking as a sequential decision-making problem, and applied a reinforcement learning (RL) method the Asynchronous Advantage Actor-Critic (A3C) model to optimize docking trajectories. To further enhance protein-ligand docking, we introduce DisDock, a deep learning-based method specifically designed for metal ion redocking. DisDock employs a U-net architecture with axial-attention modules to process pairwise distance matrices, capturing spatial relationships between metal ions and protein atoms. Two postprocessing techniques-multidimensional scaling alignment and direct estimation via distance constraints-are implemented to refine metal ion localization. Evaluations on large-scale datasets reveal that DisDock significantly outperforms existing methods, including BioMetAll, AutoDock Vina, and RL-based docking models.To address docking challenges where binding pockets are unknown, we propose to adopt and fine-tune ESM-GearNet, a structure-aware docking residue prediction model that integrates sequence-based protein representations with geometric deep learning. Pretrained on large-scale protein databases, GearNet effectively captures residue-level spatial dependencies, facilitating the identification of potential ligand-binding sites.Part 2: Biomedical Relation Extraction Biomedical relation extraction (RE) is essential for identifying relationships between biomedical entities such as genes, diseases, and chemicals in scientific literature. In this study, we enhance RE by leveraging pretrained language models, including PubMedBERT, RoBERTa, and BioLinkBERT, evaluating their performance to optimize the extraction pipeline. We investigate various pretraining strategies, such as warmup scheduling and multi-corpus training, to improve model effectiveness. Ablation studies confirm that data augmentation and warmup training enhance both robustness and accuracy.Statistical Inference on Time Warping Functions Time-warping functions capture phase variability in functional data. However, statistical modeling and inference for time-warping functions remain challenging due to their non-linearity in conventional L2 space. In this work, we propose a statistical inference framework for time-warping functions by employing a linear, generative, and stochastic model under the centered log-ratio (CLR) transformation. By establishing an isometric isomorphism between the time-warping function space and a subspace of L2, we enable the direct application of statistical models.To demonstrate the utility of our framework, we introduce hypothesis tests for the mean and covariance structures of time-warping functions. The test for equality of means assesses whether two groups of time-warping functions have the same mean functions-i.e., whether they exhibit similar phase variability on average. Meanwhile, the test for equality of covariance structures evaluates differences in the covariance structure of phase variability across groups. Specifically, we implement an L2 -norm-based test statistic, whose distribution is approximated using the eigenvalues of the covariance operator. Simulation studies confirm the effectiveness of these tests, demonstrating their power in detecting subtle variations in phase structure.

English

ISBN: 9798280722989Subjects--Topical Terms:

517247
Statistics.
Subjects--Index Terms:

Protein-ligand docking

Deep Learning in Biomedical Research and Statistical Inference on Time Warping Functions /
LDR:05573nmm a22004333i 4500 001 2434810
005 20251001062530.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798280722989
035 $a (MiAaPQD)AAI31842740
035 $a AAI31842740
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Lin, Menghan, $e author. $0 (orcid)0009-0001-2558-5514 $3 3824923
245 1 0 $a Deep Learning in Biomedical Research and Statistical Inference on Time Warping Functions / $c Menghan Lin.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (106 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: 86-12, Section: B.
500 $a Advisors: Wu, Wei Committee members: Yang, Wei; Barbu, Adrian; Zhang, Jinfeng.
502 $b Ph.D. $c The Florida State University $d 2025.
520 $a In this dissertation, I will present two research projects that I have been working on during my doctoral study at Florida State University. I will provide a brief summary for each of these projects as follows. The detailed studies will be given in the chapters of this dissertation.Deep Learning ApplicationPart 1: Protein-Ligand Docking Deep learning has transformed protein-ligand docking by improving the accuracy and efficiency of interaction predictions, surpassing traditional molecular docking and free-energy simulation methods that often suffer from computational limitations and predefined heuristics. This study explores deep learning-based approaches for protein-ligand docking, emphasizing the role of reinforcement learning, generative models, and geometric deep learning in optimizing ligand placement within protein binding pockets. Our previous study formulated docking as a sequential decision-making problem, and applied a reinforcement learning (RL) method the Asynchronous Advantage Actor-Critic (A3C) model to optimize docking trajectories. To further enhance protein-ligand docking, we introduce DisDock, a deep learning-based method specifically designed for metal ion redocking. DisDock employs a U-net architecture with axial-attention modules to process pairwise distance matrices, capturing spatial relationships between metal ions and protein atoms. Two postprocessing techniques-multidimensional scaling alignment and direct estimation via distance constraints-are implemented to refine metal ion localization. Evaluations on large-scale datasets reveal that DisDock significantly outperforms existing methods, including BioMetAll, AutoDock Vina, and RL-based docking models.To address docking challenges where binding pockets are unknown, we propose to adopt and fine-tune ESM-GearNet, a structure-aware docking residue prediction model that integrates sequence-based protein representations with geometric deep learning. Pretrained on large-scale protein databases, GearNet effectively captures residue-level spatial dependencies, facilitating the identification of potential ligand-binding sites.Part 2: Biomedical Relation Extraction Biomedical relation extraction (RE) is essential for identifying relationships between biomedical entities such as genes, diseases, and chemicals in scientific literature. In this study, we enhance RE by leveraging pretrained language models, including PubMedBERT, RoBERTa, and BioLinkBERT, evaluating their performance to optimize the extraction pipeline. We investigate various pretraining strategies, such as warmup scheduling and multi-corpus training, to improve model effectiveness. Ablation studies confirm that data augmentation and warmup training enhance both robustness and accuracy.Statistical Inference on Time Warping Functions Time-warping functions capture phase variability in functional data. However, statistical modeling and inference for time-warping functions remain challenging due to their non-linearity in conventional L2 space. In this work, we propose a statistical inference framework for time-warping functions by employing a linear, generative, and stochastic model under the centered log-ratio (CLR) transformation. By establishing an isometric isomorphism between the time-warping function space and a subspace of L2, we enable the direct application of statistical models.To demonstrate the utility of our framework, we introduce hypothesis tests for the mean and covariance structures of time-warping functions. The test for equality of means assesses whether two groups of time-warping functions have the same mean functions-i.e., whether they exhibit similar phase variability on average. Meanwhile, the test for equality of covariance structures evaluates differences in the covariance structure of phase variability across groups. Specifically, we implement an L2 -norm-based test statistic, whose distribution is approximated using the eigenvalues of the covariance operator. Simulation studies confirm the effectiveness of these tests, demonstrating their power in detecting subtle variations in phase structure.
546 $a English
590 $a School code: 0071
650 4 $a Statistics. $3 517247
650 4 $a Biomedical engineering. $3 535387
650 4 $a Bioengineering. $3 657580
653 $a Protein-ligand docking
653 $a Reinforcement learning
653 $a Optimize docking
653 $a Binding pockets
653 $a Covariance structures
690 $a 0463
690 $a 0202
690 $a 0541
710 2 $a The Florida State University. $b Statistics. $e degree granting institution. $3 3817235
720 1 $a Wu, Wei $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-12B.
790 $a 0071
791 $a Ph.D.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31842740