請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/90064完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 張書瑋 | zh_TW |
| dc.contributor.advisor | Shu-Wei Chang | en |
| dc.contributor.author | 陳諺霖 | zh_TW |
| dc.contributor.author | Yen-Lin Chen | en |
| dc.date.accessioned | 2023-09-22T17:15:48Z | - |
| dc.date.available | 2023-11-09 | - |
| dc.date.copyright | 2023-09-22 | - |
| dc.date.issued | 2023 | - |
| dc.date.submitted | 2023-08-09 | - |
| dc.identifier.citation | [1] Chapman, J., A.E. Ismail, and C.Z. Dinu, Industrial Applications of Enzymes: Recent Advances, Techniques, and Outlooks. Catalysts, 2018. 8(6): p. 238.
[2] Bommarius, A.S. and M.F. Paye, Stabilizing biocatalysts. Chemical Society Reviews, 2013. 42(15): p. 6534-6565. [3] Xu, Z., et al., Recent advances in the improvement of enzyme thermostability by structure modification. Critical Reviews in Biotechnology, 2020. 40(1): p. 83-98. [4] Nezhad, N.G., et al., Thermostability engineering of industrial enzymes through structure modification. Applied Microbiology and Biotechnology, 2022. 106(13): p. 4845-4866. [5] Ahmed, Z., H. Zulfiqar, L. Tang, and H. Lin, A Statistical Analysis of the Sequence and Structure of Thermophilic and Non-Thermophilic Proteins. International Journal of Molecular Sciences, 2022. 23(17): p. 10116. [6] Polizzi, K.M., A.S. Bommarius, J.M. Broering, and J.F. Chaparro-Riggers, Stability of biocatalysts. Current Opinion in Chemical Biology, 2007. 11(2): p. 220-225. [7] Pucci, F., J.M. Kwasigroch, and M. Rooman, SCooP: an accurate and fast predictor of protein stability curves as a function of temperature. Bioinformatics, 2017. 33(21): p. 3415-3422. [8] Pucci, F., M. Dhanani, Y. Dehouck, and M. Rooman, Protein Thermostability Prediction within Homologous Families Using Temperature-Dependent Statistical Potentials. PLOS ONE, 2014. 9(3): p. e91659. [9] Roberts, G., The role of protein dynamics in allosteric effects—introduction. Biophysical Reviews, 2015. 7(2): p. 161-163. [10] Loutchko, D. and H. Flechsig, Allosteric communication in molecular machines via information exchange: what can be learned from dynamical modeling. Biophysical Reviews, 2020. 12(2): p. 443-452. [11] Tzeng, S.-R. and C.G. Kalodimos, Protein dynamics and allostery: an NMR view. Current Opinion in Structural Biology, 2011. 21(1): p. 62-67. [12] Peng, J.W., Communication Breakdown: Protein Dynamics and Drug Design. Structure, 2009. 17(3): p. 319-320. [13] Mittag, T., L.E. Kay, and J.D. Forman-Kay, Protein dynamics and conformational disorder in molecular recognition. Journal of Molecular Recognition, 2010. 23(2): p. 105-116. [14] Berendsen, H.J.C. and S. Hayward, Collective protein dynamics in relation to function. Current Opinion in Structural Biology, 2000. 10(2): p. 165-169. [15] Kumar, S., D. Seth, and P.A. Deshpande, Molecular dynamics simulations identify the regions of compromised thermostability in SazCA. Proteins: Structure, Function, and Bioinformatics, 2021. 89(4): p. 375-388. [16] Karshikoff, A., L. Nilsson, and R. Ladenstein, Rigidity versus flexibility: the dilemma of understanding protein thermal stability. The FEBS Journal, 2015. 282(20): p. 3899-3917. [17] Tang, Q.-Y. and K. Kaneko, Long-range correlation in protein dynamics: Confirmation by structural data and normal mode analysis. PLOS Computational Biology, 2020. 16(2): p. e1007670. [18] Schlick, T. and S. Portillo-Ledesma, Biomolecular modeling thrives in the age of technology. Nature Computational Science, 2021. 1(5): p. 321-331. [19] Ku, T., et al., Predicting melting temperature directly from protein sequences. Computational Biology and Chemistry, 2009. 33(6): p. 445-450. [20] Gorania, M., H. Seker, and P.I. Haris. Predicting a protein's melting temperature from its amino acid sequence. in 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology. 2010. [21] Pucci, F. and M. Rooman, Towards an accurate prediction of the thermal stability of homologous proteins. Journal of Biomolecular Structure and Dynamics, 2016. 34(5): p. 1132-1142. [22] Dehouck, Y., B. Folch, and M. Rooman, Revisiting the correlation between proteins' thermoresistance and organisms' thermophilicity. Protein Engineering, Design and Selection, 2008. 21(4): p. 275-278. [23] Miotto, M., et al., Insights on protein thermal stability: a graph representation of molecular interactions. Bioinformatics, 2018. 35(15): p. 2569-2577. [24] Jarzab, A., et al., Meltome atlas—thermal proteome stability across the tree of life. Nature Methods, 2020. 17(5): p. 495-503. [25] Nikam, R., et al., ProThermDB: thermodynamic database for proteins and mutants revisited after 15 years. Nucleic Acids Research, 2021. 49(D1): p. D420-D424. [26] Yang, Y., et al., ProTstab – predictor for cellular protein stability. BMC Genomics, 2019. 20(1): p. 804. [27] Yang, Y., J. Zhao, L. Zeng, and M. Vihinen, ProTstab2 for Prediction of Protein Thermal Stabilities. International Journal of Molecular Sciences, 2022. 23(18): p. 10798. [28] Jung, F., K. Frey, D. Zimmer, and T. Mühlhaus DeepSTABp: A Deep Learning Approach for the Prediction of Thermal Protein Stability. International Journal of Molecular Sciences, 2023. 24, DOI: 10.3390/ijms24087444. [29] Vaswani, A., et al. Attention Is All You Need. 2017. arXiv:1706.03762 DOI: 10.48550/arXiv.1706.03762. [30] Rao, R., et al. Evaluating Protein Transfer Learning with TAPE. 2019. arXiv:1906.08230 DOI: 10.48550/arXiv.1906.08230. [31] Elnaggar, A., et al., ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022. 44(10): p. 7112-7127. [32] Alley, E.C., et al., Unified rational protein engineering with sequence-based deep representation learning. Nature Methods, 2019. 16(12): p. 1315-1322. [33] Brandes, N., et al., ProteinBERT: a universal deep-learning model of protein sequence and function. Bioinformatics, 2022. 38(8): p. 2102-2110. [34] Morozov, V., C.H.M. Rodrigues, and D.B. Ascher CSM-Toxin: A Web-Server for Predicting Protein Toxicity. Pharmaceutics, 2023. 15, DOI: 10.3390/pharmaceutics15020431. [35] Aizenshtein-Gazit, S. and Y. Orenstein, DeepZF: improved DNA-binding prediction of C2H2-zinc-finger proteins by deep transfer learning. Bioinformatics, 2022. 38(Supplement_2): p. ii62-ii67. [36] Marco, A., A.P.M.d.S. Vitor, and S. Edoardo, PortPred: exploiting deep learning embeddings of amino acid sequences for the identification of transporter proteins and their substrates. bioRxiv, 2023: p. 2023.01.26.525714. [37] Senior, A.W., et al., Protein structure prediction using multiple deep neural networks in the 13th Critical Assessment of Protein Structure Prediction (CASP13). Proteins: Structure, Function, and Bioinformatics, 2019. 87(12): p. 1141-1148. [38] Jumper, J., et al., Highly accurate protein structure prediction with AlphaFold. Nature, 2021. 596(7873): p. 583-589. [39] Varadi, M., et al., AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models. Nucleic Acids Research, 2022. 50(D1): p. D439-D444. [40] Zhou, J., et al., Graph neural networks: A review of methods and applications. AI Open, 2020. 1: p. 57-81. [41] Zhang, X.-M., L. Liang, L. Liu, and M.-J. Tang, Graph Neural Networks and Their Current Applications in Bioinformatics. Frontiers in Genetics, 2021. 12. [42] Husic, B.E., et al., Coarse graining molecular dynamics with graph neural networks. The Journal of Chemical Physics, 2020. 153(19). [43] Strokach, A., et al., Fast and Flexible Protein Design Using Deep Graph Neural Networks. Cell Systems, 2020. 11(4): p. 402-411.e4. [44] Wang, X., S.T. Flannery, and D. Kihara, Protein Docking Model Evaluation by Graph Neural Networks. Frontiers in Molecular Biosciences, 2021. 8. [45] Li, S., et al., Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinity, in Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 2021, Association for Computing Machinery: Virtual Event, Singapore. p. 975–985. [46] Xia, Y., C.-Q. Xia, X. Pan, and H.-B. Shen, GraphBind: protein structural context embedded rules learned by hierarchical graph neural networks for recognizing nucleic-acid-binding residues. Nucleic Acids Research, 2021. 49(9): p. e51-e51. [47] Réau, M., N. Renaud, L.C. Xue, and A.M.J.J. Bonvin, DeepRank-GNN: a graph neural network framework to learn patterns in protein–protein interfaces. Bioinformatics, 2022. 39(1). [48] Gligorijević, V., et al., Structure-based protein function prediction using graph convolutional networks. Nature Communications, 2021. 12(1): p. 3168. [49] Chiang, Y., W.-H. Hui, and S.-W. Chang, Encoding protein dynamic information in graph representation for functional residue identification. Cell Reports Physical Science, 2022. 3(7): p. 100975. [50] Mendez, R. and U. Bastolla, Torsional Network Model: Normal Modes in Torsion Angle Space Better Correlate with Conformation Changes in Proteins. Physical Review Letters, 2010. 104(22): p. 228103. [51] Eckart, C., Some Studies Concerning Rotating Axes and Polyatomic Molecules. Physical Review, 1935. 47(7): p. 552-558. [52] Murray-Rust, P. Peptide Torsion Angles and Secondary Structure. 1996 [cited 2023 July 20]; Available from: https://www.cryst.bbk.ac.uk/PPS95/course/9_quaternary/3_geometry/torsion.html. [53] Alfayate, A., C. Rodriguez Caceres, H. Gomes Dos Santos, and U. Bastolla, Predicted dynamical couplings of protein residues characterize catalysis, transport and allostery. Bioinformatics, 2019. 35(23): p. 4971-4978. [54] Kipf, T.N. and M. Welling Semi-Supervised Classification with Graph Convolutional Networks. 2016. arXiv:1609.02907 DOI: 10.48550/arXiv.1609.02907. [55] Defferrard, M., X. Bresson, and P. Vandergheynst Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. 2016. arXiv:1606.09375 DOI: 10.48550/arXiv.1606.09375. [56] Paszke, A., et al., PyTorch: an imperative style, high-performance deep learning library, in Proceedings of the 33rd International Conference on Neural Information Processing Systems. 2019, Curran Associates Inc. p. Article 721. [57] Fey, M. and J.E. Lenssen Fast Graph Representation Learning with PyTorch Geometric. 2019. arXiv:1903.02428 DOI: 10.48550/arXiv.1903.02428. [58] Selvaraju, R.R., et al. Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization. 2016. arXiv:1610.02391 DOI: 10.48550/arXiv.1610.02391. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/90064 | - |
| dc.description.abstract | 蛋白質之熱穩定性為蛋白質在極端溫度中維持可運作構型 (functional conformation) 的能力，並可被折疊態 (folded state) 與非折疊態 (unfolded state) 之間的雙態轉變 (two-state transition) 所量化。蛋白質於其原生環境溫度中大多呈折疊態，隨著系統升溫，非折疊態之蛋白質數量增加，此動態變動的過程中，當兩構型以相同數量存在的溫度即為蛋白質的熔點溫度 (melting temperature) ，為蛋白質熱穩定性的重要指標。由於工業上時常需要將酵素置於非原生之高溫環境中，使得熔點溫度成為蛋白質工業適用性的重要指標之一，在設計或篩選工業酵素時為一大考量。
先前研究已證實將蛋白質之結構 (structure) 與動力 (dynamics) 特徵加譯為圖 (graphs) 並利用圖神經網路 (graph neural networks, GNN) 預測蛋白質功能的可行性。於此，本研究串聯蛋白質熱穩定性、蛋白質功能性、蛋白質結構動力資訊，展示如何將蛋白質的結構與動態資訊用於蛋白熔點溫度之預測。為了泛用於尚未解出實驗結構的蛋白質，本研究採用AlphaFold的預測結果作為蛋白質的結構，再以此結構為基礎，建立扭矩網路模型 (torsional network model, TNM) ，並根據此力學模型獲得其簡正模態 (normal mode) ，提供後續蛋白質動力耦合 (dynamic coupling) 計算。最終，蛋白質結構將以接觸圖 (contact graph) 和PAE圖 (predicted aligned error graph) 表示，蛋白質動態資訊則以共向圖 (co-directionality graph) 、協調圖 (coordination graph) ，以及變位圖 (deformation graph) 表示。結果顯示，將蛋白質經過以上處理加譯為圖，搭配圖神經網路預測熔點溫度，與實驗量測結果比較，平均絕對誤差為3.291°C，方均根差為4.286°C，而R^2可達0.805。本研究亦利用影像辨識中特徵視覺化的技術，可反向檢視蛋白質中哪些殘基 (residues) 對於模型的預測有較高的影響力，亦可辨別資料中各種圖之於模型預測的重要程度。這些資訊再次指出蛋白動態對於熱穩定性的重要性，並提供了改善熱穩定性的可能關鍵區域，可作為提升蛋白質工業應用表現之參考，亦為未來研究提供指引。 | zh_TW |
| dc.description.abstract | Protein thermostability, the resistance or preservation of protein functions under extreme temperatures, plays a vital role in numerous biotechnological applications. Since designed proteins, such as industrial enzymes and biocatalysts, are often subjected to temperatures that significantly differ from the cellular environment, protein thermostability has always been critical to consider when making protein designs or searching for proteins suitable for a specific task. Commonly simplified as a two-state transition, protein thermostability is primarily characterized by the melting temperature, where the folded and unfolded states are equally favorable. This work focuses on the prediction of the melting temperature of protein. As protein dynamics is essential in understanding protein functions, an effective data representation that includes the dynamics should benefit the melting temperature prediction. In this work, a graph-based (as in graph theory) representation of proteins that encompasses the protein sequence, structure, and dynamics is presented. A graph neural network architecture that uses message passing layers was designed to accommodate multiple types of connections. Protein structures were computed by AlphaFold, and the dynamics were computed based on the torsional network model (TNM) for training. Hence, the learned features and parameters can be readily applied to protein sequences without known experimental structure, satisfying the goal of aiding the prediction of design proteins. Critical regions that strongly influence the thermostability of proteins are identified by computing a graph regression activation map (RAM), which is based on the partial derivative of the predicted value with respect to the convolutional features map. The method provides an efficient approach to accessing the thermostability of new protein sequences. Further, it provides insights into the inner workings of proteins by identifying residues critical to thermostability. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-09-22T17:15:48Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2023-09-22T17:15:48Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 致謝 i
摘要 ii Abstract iv Table of Contents vi List of Figures viii List of Tables x Chapter 1. Introduction and Background 1 1.1 Protein Thermostability 1 1.1.1 Definitions 2 1.1.2 Relation with Protein Dynamics and Function 4 1.1.3 Protein Thermostability Prediction 5 1.2 Machine Learning and Proteins 8 1.2.1 ProteinBERT 8 1.2.2 AlphaFold 9 1.2.3 Graph Neural Networks in Protein Sciences 10 Chapter 2. Methodology 13 2.1 Torsional Network Model and Dynamical Coupling Graphs 13 2.2 Mapping Proteins to Graphs 21 2.2.1 Graph Theory 21 2.2.2 The Data Representation 23 2.3 Data Source and Feature Distribution 30 2.3.1 Data Processing 30 2.3.2 Feature Analysis 33 2.4 The Neural Network Model 40 2.4.1 Graph Neural Networks 40 2.4.2 Architecture 43 2.4.3 Training Setup 46 2.5 Regression Activation Map (RAM) 47 Chapter 3. Results and Discussion 49 3.1 The Graph Representation of Proteins 49 3.2 Model Performance 57 Graph Representation is Effective in T_m Prediction 57 Performance is Similar to the State-of-the-Art Method 60 Bias and Variance of the Model 61 3.3 Structural and Dynamical Influence on Protein Thermostability 65 Chapter 4. Conclusion and Outlook 73 Future Work 74 Bibliography 76 | - |
| dc.language.iso | en | - |
| dc.subject | 蛋白質 | zh_TW |
| dc.subject | 回歸激發圖 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 圖神經網路 | zh_TW |
| dc.subject | 簡正模態 | zh_TW |
| dc.subject | 融點溫度 | zh_TW |
| dc.subject | 熱穩定性 | zh_TW |
| dc.subject | melting temperature | en |
| dc.subject | proteins | en |
| dc.subject | regression activation map | en |
| dc.subject | deep learning | en |
| dc.subject | normal mode analysis | en |
| dc.subject | graph neural networks | en |
| dc.subject | thermostability | en |
| dc.title | 以蛋白質動力輔助圖神經網路預測蛋白質熱穩定性 | zh_TW |
| dc.title | Protein Thermostability Prediction by Graph Neural Network with Dynamics-Informed Graph Representation of Proteins | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 111-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 徐善慧;周佳靚;施智仁 | zh_TW |
| dc.contributor.oralexamcommittee | Shan-Hui Hsu;Chia-Ching Chou;Chih-Jen Shih | en |
| dc.subject.keyword | 蛋白質,熱穩定性,融點溫度,簡正模態,圖神經網路,深度學習,回歸激發圖, | zh_TW |
| dc.subject.keyword | proteins,thermostability,melting temperature,normal mode analysis,graph neural networks,deep learning,regression activation map, | en |
| dc.relation.page | 81 | - |
| dc.identifier.doi | 10.6342/NTU202303848 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2023-08-12 | - |
| dc.contributor.author-college | 工學院 | - |
| dc.contributor.author-dept | 土木工程學系 | - |
| 顯示於系所單位： | 土木工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-111-2.pdf | 1.8 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。