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

切換: 標籤 | MARC模式 | ISBD

Machine Learning Methods for Protein...

Wang, Chenran.

FindBook

Google Book

Amazon

博客來

Machine Learning Methods for Protein Design and Protein-Ligand Docking.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Machine Learning Methods for Protein Design and Protein-Ligand Docking./
作者:	Wang, Chenran.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	133 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-01, Section: B.
Contained By:	Dissertations Abstracts International83-01B.
標題:	Statistics. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28319867
ISBN:	9798516066115

Machine Learning Methods for Protein Design and Protein-Ligand Docking.
Wang, Chenran.

Machine Learning Methods for Protein Design and Protein-Ligand Docking. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 133 p.

Source: Dissertations Abstracts International, Volume: 83-01, Section: B.

Thesis (Ph.D.)--The Florida State University, 2021.

This item must not be sold to any third party vendors.

Project 1: ProDCoNN: Protein Design using a Convolutional Neural Network. Designing protein sequences that fold to a given three-dimensional (3D) structure has long been a challenging problem in computational structural biology with significant theoretical and practical implications. In this study, we first formulated this problem as predicting the residue type given the 3D structural environment around the Cα atom of a residue, which is repeated for each residue of a protein. We designed a nine-layer 3D deep convolutional neural network (CNN) that takes as input a gridded box with the atomic coordinates and types around a residue. Several CNN layers were designed to capture structure information at different scales, such as bond lengths, bond angles, torsion angles, and secondary structures. Trained on a very large number of protein structures, the method, called ProDCoNN (Protein Design with Convolutional Neural Network), achieved state-of-the-art performance when tested on large numbers of test proteins and benchmark datasets.Project 2: Protein-Ligand Docking using Reinforcement Learning. Protein-ligand docking is an important part of molecular docking, which aims to find the conformations and orientations within a given protein structure. This field has been extensively investigated, which resulted in successful applications in medicine designs. In this study, we propose a supervised learning algorithm based on a reinforcement learning method called Asynchronous Advantage Actor Critic to address the protein-ligand docking problem. A three-dimensional gridded box, which contains protein environment, docking site and ligand, will be used as the training input. We design different convolutional neural networks for simulation studies, and then adopt these models to real experimental data. With a large amount of proteins in training, the proposed model can reasonably search for the true docking site in the gridded box using only protein environment and ligand location. Both simulations and real data results indicate that this method can effectively produce appropriate searching path which leads to the true docking site.Project 3: A Unified Framework on Defining Depth for Point Process using Function Smoothing. The notion of statistical depth has been extensively studied in multivariate and functional data over the past few decades. In contrast, the depth on temporal point process is still under-explored. The problem is challenging because a point process has two types of randomness: 1) the number of events in a process, and 2) the distribution of these events given the number is known. Recent studies proposed depths in a weighted product of two terms, describing the above two types of randomness, respectively. In this project, we propose to unify these two randomnesses under one framework by a smoothing procedure. Basically, we transform the point process observations into functions using conventional kernel smoothing methods, and then adopt the well-known functional h-depth and its modified, center-based, version to describe the center-outward rank in the original data. To do so, we define a proper metric on the point processes with smoothed functions. We then propose an efficient algorithm to estimated the defined "center''. We further explore the mathematical properties of the newly defined depths and study asymptotics. Simulation results show that the proposed depths can properly rank the point process observations. Finally, we demonstrate the new method in a classification task using a real neuronal spike train dataset.

ISBN: 9798516066115Subjects--Topical Terms:

517247
Statistics.
Subjects--Index Terms:

Center-out ranks

Machine Learning Methods for Protein Design and Protein-Ligand Docking.
LDR:04812nmm a2200397 4500 001 2284865
005 20211124093241.5
008 220723s2021 ||||||||||||||||| ||eng d
020 $a 9798516066115
035 $a (MiAaPQ)AAI28319867
035 $a AAI28319867
040 $a MiAaPQ $c MiAaPQ
100 1 $a Wang, Chenran. $0 (orcid)0000-0002-9205-0894 $3 3564060
245 1 0 $a Machine Learning Methods for Protein Design and Protein-Ligand Docking.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 133 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-01, Section: B.
500 $a Advisor: Wu, Wei.
502 $a Thesis (Ph.D.)--The Florida State University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Project 1: ProDCoNN: Protein Design using a Convolutional Neural Network. Designing protein sequences that fold to a given three-dimensional (3D) structure has long been a challenging problem in computational structural biology with significant theoretical and practical implications. In this study, we first formulated this problem as predicting the residue type given the 3D structural environment around the Cα atom of a residue, which is repeated for each residue of a protein. We designed a nine-layer 3D deep convolutional neural network (CNN) that takes as input a gridded box with the atomic coordinates and types around a residue. Several CNN layers were designed to capture structure information at different scales, such as bond lengths, bond angles, torsion angles, and secondary structures. Trained on a very large number of protein structures, the method, called ProDCoNN (Protein Design with Convolutional Neural Network), achieved state-of-the-art performance when tested on large numbers of test proteins and benchmark datasets.Project 2: Protein-Ligand Docking using Reinforcement Learning. Protein-ligand docking is an important part of molecular docking, which aims to find the conformations and orientations within a given protein structure. This field has been extensively investigated, which resulted in successful applications in medicine designs. In this study, we propose a supervised learning algorithm based on a reinforcement learning method called Asynchronous Advantage Actor Critic to address the protein-ligand docking problem. A three-dimensional gridded box, which contains protein environment, docking site and ligand, will be used as the training input. We design different convolutional neural networks for simulation studies, and then adopt these models to real experimental data. With a large amount of proteins in training, the proposed model can reasonably search for the true docking site in the gridded box using only protein environment and ligand location. Both simulations and real data results indicate that this method can effectively produce appropriate searching path which leads to the true docking site.Project 3: A Unified Framework on Defining Depth for Point Process using Function Smoothing. The notion of statistical depth has been extensively studied in multivariate and functional data over the past few decades. In contrast, the depth on temporal point process is still under-explored. The problem is challenging because a point process has two types of randomness: 1) the number of events in a process, and 2) the distribution of these events given the number is known. Recent studies proposed depths in a weighted product of two terms, describing the above two types of randomness, respectively. In this project, we propose to unify these two randomnesses under one framework by a smoothing procedure. Basically, we transform the point process observations into functions using conventional kernel smoothing methods, and then adopt the well-known functional h-depth and its modified, center-based, version to describe the center-outward rank in the original data. To do so, we define a proper metric on the point processes with smoothed functions. We then propose an efficient algorithm to estimated the defined "center''. We further explore the mathematical properties of the newly defined depths and study asymptotics. Simulation results show that the proposed depths can properly rank the point process observations. Finally, we demonstrate the new method in a classification task using a real neuronal spike train dataset.
590 $a School code: 0071.
650 4 $a Statistics. $3 517247
650 4 $a Biomedical engineering. $3 535387
650 4 $a Biostatistics. $3 1002712
650 4 $a Computational chemistry. $3 3350019
650 4 $a Biophysics. $3 518360
653 $a Center-out ranks
653 $a Point process depth
653 $a Convolutional neural network
653 $a Reinforcement learning
653 $a Function smoothing
690 $a 0463
690 $a 0786
690 $a 0541
690 $a 0219
690 $a 0308
710 2 $a The Florida State University. $b Statistics. $3 3185231
773 0 $t Dissertations Abstracts International $g 83-01B.
790 $a 0071
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28319867