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

Deep Learning Methods and Datasets f...

King, Jonathan Edward,

Linked to FindBook

Google Book

Amazon

博客來

Deep Learning Methods and Datasets for All-Atom Protein Structure Prediction /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Deep Learning Methods and Datasets for All-Atom Protein Structure Prediction // Jonathan Edward King.
Author:	King, Jonathan Edward,
Description:	1 electronic resource (104 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
Contained By:	Dissertations Abstracts International85-11B.
Subject:	Systematic biology. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31233863
ISBN:	9798382227887

Deep Learning Methods and Datasets for All-Atom Protein Structure Prediction /
King, Jonathan Edward,

Deep Learning Methods and Datasets for All-Atom Protein Structure Prediction /Jonathan Edward King. - 1 electronic resource (104 pages)

Source: Dissertations Abstracts International, Volume: 85-11, Section: B.

Over the past decade, significant progress has been made in protein structure prediction, largely thanks to tools like AlphaFold2. This paper tackles several lingering challenges in this field. First, we introduce SidechainNet, a dataset and toolkit designed to streamline the handling of protein sequence and structure data for machine learning and increase its accessibility. This initiative addresses the prevalent issue of effectively collecting and organizing data, especially in the realm of protein science, where data quality and availability may vary. Furthermore, leading methods have been observed to fall short in real-world tasks like molecular docking. To enhance the physical realism of predictions made by deep learning models, we implement potential energy as a loss function through OpenMM-Loss. This technique reduces potential energy and clashes in predicted structures, potentially rendering these predictions more viable for various applications. We also scrutinize AlphaFold2 with the aim of refining its sidechain modeling-a crucial aspect of drug discovery. Although we don't pinpoint a significantly more accurate model, our analysis reveals comparable performance between ResNet and Transformer models in sidechain prediction tasks. In light of these results, we recommend that future efforts concentrate on more holistic sidechain modeling efforts. Finally, we discuss potential future developments and extensions of our methods.

English

ISBN: 9798382227887Subjects--Topical Terms:

3173492
Systematic biology.
Subjects--Index Terms:

SidechainNet

Deep Learning Methods and Datasets for All-Atom Protein Structure Prediction /
LDR:03098nmm a22004933i 4500 001 2429325
005 20250430100800.5
006 m o d
007 cr|nu||||||||
008 261011s2023 miu||||||m |||||||eng d
020 $a 9798382227887
035 $a (MiAaPQD)AAI31233863
035 $a (MiAaPQD)Pittsburgh45461
035 $a AAI31233863
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a King, Jonathan Edward, $e author. $3 3817104
245 1 0 $a Deep Learning Methods and Datasets for All-Atom Protein Structure Prediction / $c Jonathan Edward King.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 1 electronic resource (104 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: 85-11, Section: B.
500 $a Advisors: VanDemark, Andrew P.; Isayev, Olexandr; Durrant, Jacob; Koes, David R.
502 $b Ph.D. $c University of Pittsburgh $d 2023.
520 $a Over the past decade, significant progress has been made in protein structure prediction, largely thanks to tools like AlphaFold2. This paper tackles several lingering challenges in this field. First, we introduce SidechainNet, a dataset and toolkit designed to streamline the handling of protein sequence and structure data for machine learning and increase its accessibility. This initiative addresses the prevalent issue of effectively collecting and organizing data, especially in the realm of protein science, where data quality and availability may vary. Furthermore, leading methods have been observed to fall short in real-world tasks like molecular docking. To enhance the physical realism of predictions made by deep learning models, we implement potential energy as a loss function through OpenMM-Loss. This technique reduces potential energy and clashes in predicted structures, potentially rendering these predictions more viable for various applications. We also scrutinize AlphaFold2 with the aim of refining its sidechain modeling-a crucial aspect of drug discovery. Although we don't pinpoint a significantly more accurate model, our analysis reveals comparable performance between ResNet and Transformer models in sidechain prediction tasks. In light of these results, we recommend that future efforts concentrate on more holistic sidechain modeling efforts. Finally, we discuss potential future developments and extensions of our methods.
546 $a English
590 $a School code: 0178
650 4 $a Systematic biology. $3 3173492
650 4 $a Bioinformatics. $3 553671
650 4 $a Biochemistry. $3 518028
653 $a SidechainNet
653 $a AlphaFold2
653 $a Protein structure
653 $a Deep learning
653 $a ResNet
690 $a 0423
690 $a 0487
690 $a 0800
690 $a 0715
710 2 $a University of Pittsburgh. $e degree granting institution. $3 3759199
720 1 $a VanDemark, Andrew P. $e degree supervisor.
720 1 $a Isayev, Olexandr $e degree supervisor.
720 1 $a Durrant, Jacob $e degree supervisor.
720 1 $a Koes, David R. $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 85-11B.
790 $a 0178
791 $a Ph.D.
792 $a 2023
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31233863