Machine Learning in Protein Science

Efficient Prediction of Protein Structures and Properties

Inbunden, Engelska, 2025

AvJinjin Li,Yanqiang Han,China) Li, Jinjin (Shanghai Jiao Tong University,China) Han, Yanqiang (Shanghai Jiao Tong University

2 049 kr

Beställningsvara. Skickas inom 3-6 vardagar. Fri frakt för medlemmar vid köp för minst 249 kr.

Harness the power of machine learning for quick and efficient calculations of protein structures and properties Machine Learning in Protein Science is a unique and practical reference that shows how to employ machine learning approaches for full quantum mechanical (FQM) calculations of protein structures and properties, thereby saving costly computing time and making this technology available for routine users. Machine Learning in Protein Science provides comprehensive coverage of topics including: Machine learning models and algorithms, from deep neural network (DNN) and transfer learning (TL) to hybrid unsupervised and supervised learningProtein structure predictions with AlphaFold to predict the effects of point mutationsModeling and optimization of the catalytic activity of enzymesProperty calculations (energy, force field, stability, protein-protein interaction, thermostability, molecular dynamics)Protein design and large language models (LLMs) of protein systemsMachine Learning in Protein Science is an essential reference on the subject for biochemists, molecular biologists, theoretical chemists, biotechnologists, and medicinal chemists, as well as students in related programs of study.

Produktinformation

Utgivningsdatum2025-11-26
Mått170 x 244 x 15 mm
Vikt680 g
FormatInbunden
SpråkEngelska
Antal sidor240
FörlagWiley-VCH Verlag GmbH
ISBN9783527352159

Tillhör följande kategorier

Organisk kemi inom Naturvetenskap och teknik
Biokemi inom Naturvetenskap och teknik
Biologi inom Naturvetenskap och teknik
Systemvetenskap och AI inom Data och IT

Jinjin Li is a Professor at the School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University in Shanghai, China. She performed postdoctoral work at the University of Illinois, USA and was a Senior Research Fellow at the University of California, USA. Yanqiang Han is an Assistant Professor at the School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University in Shanghai, China.

1 Introduction 11.1 Background and Motivation 1Bibliography 122 Fundamental of Theoretical Calculations on Protein Systems 152.1 Strategies for Protein Calculations and Predictions 152.2 Force Field-based Calculation on Protein Systems 212.3 Quantum Mechanical Calculation on Protein Systems 282.4 ml on Protein Systems 34Bibliography 393 Protein Structure Prediction by Artificial Intelligence 433.1 AlphaFold from Google 433.1.1 Overview 433.1.2 Previous Work 433.1.3 What Is AlphaFold Expected to Do 443.1.4 Architecture of AlphaFold 443.1.4.1 Overall Architecture 443.1.4.2 Evoformer Block Architecture 453.1.4.3 Structure Prediction Model 473.1.5 Training Methods: Using Both Labeled and Unlabeled Data 483.1.6 Interpretation of the Network 483.1.7 Conclusion and Discussion 483.2 ESM and ESMFold from Meta AI 483.2.1 Meta’s ESM 2 493.2.1.1 Background 493.2.1.2 Methods 493.2.1.3 Evaluation and Results 493.2.1.4 Conclusion 513.2.2 Meta’s ESMFold 523.2.2.1 Related Work 523.2.2.2 Method 523.2.2.3 Results and Discussions 54Bibliography 544 Methods and Tools for Predicting Protein Folding Free Energy Change upon Mutation 574.1 Introduction 574.1.1 Background 574.1.2 Experimental Methods 584.1.3 Non-machine Learning Methods 584.1.4 ML-based Methods 594.2 Clustered Tree Regression 604.2.1 Overview 614.2.2 Data Distribution and Cleaning 624.2.3 Feature Engineering 634.2.4 Model Training 654.2.5 Performance of CTR 654.3 Materials and Methods 684.3.1 Data Preparation 684.3.2 Feature Extraction 684.3.3 Experimental Setup 694.4 Conclusion 69Bibliography 705 Deep Neural Network-assisted Full-system Quantum Mechanical (FQM) Calculations of Proteins 755.1 Introduction 755.1.1 Background 755.1.2 Advances in DNNs for Molecular Calculations 815.2 DNN-based GFCC Method 845.2.1 Methodology Overview 845.2.2 Methods 875.2.3 Results and Discussion 905.2.4 Conclusion 935.3 DNN-based Two-body Molecular Fractionation with Conjugate Caps 955.3.1 Methodology Overview 955.3.2 Neural Network Training and Energy Reconstruction 985.3.3 Discussion and Implications 1015.4 Conclusion 106Bibliography 1076 Transfer Learning-assisted FQM Calculations of Proteins 1116.1 Introduction 1116.1.1 Background 1116.1.2 Bridging the Gap: from Classical Methods to TL in Protein FQM Calculations 1126.2 Inductive Transfer Learning Force Field 1136.2.1 Introduction 1136.2.2 Methods 1146.2.3 Discussion and Implications 1166.2.4 Conclusion and Outlook 1186.3 Transfer-learning-based Deep Learning Protocol for FQM Calculations 1206.3.1 Introduction 1206.3.2 Methods 1216.3.3 Discussion and Implications 1246.3.4 Conclusion and Outlook 126Bibliography 1277 Protein Interaction Prediction with Artificial Intelligence 1297.1 Background 1297.2 Methods and Technical Framework 1317.2.1 Sequence-based Methods 1317.2.2 Structure-based Methods 1337.2.3 Network-based Approaches 1357.2.4 Text Mining and Literature-based Prediction 1367.2.5 Hybrid Approaches 1397.3 Results 1417.4 Summary and Outlook 1437.4.1 Summary of Achievements 1437.4.2 Outlook and Future Directions 144Bibliography 1468 Protein Function Annotation with Machine Learning 1498.1 Background 1498.2 Methods and Technical Framework 1528.3 Protein Function Annotation 1548.3.1 Homology-based Annotation 1568.3.2 Structural Annotation 1568.3.3 Ontology-based Annotation 1588.3.4 Network-based Annotation 1598.3.5 ML- and AI-based Methods 1608.3.6 High-throughput Experimental Techniques 1618.3.7 Hybrid Methods 162Bibliography 1639 Machine Learning-driven Ab Initio Protein Design 1659.1 Background 1659.2 Advances and Applications in ML-driven Ab Initio Protein Design 1679.3 Graph Neural Networks for Flexible Protein Design 1719.3.1 Energy Function of Neural Networks for Protein Design 1739.3.2 ml Models and Technologies 1769.3.3 ml and AI-based Methods 1779.3.4 Conclusion and Outlook 179Bibliography 18310 Large Language Model of Protein Systems 18510.1 Background 18510.2 Methodology and Training of Protein Language Models 18910.2.1 Methodological Framework for Protein Language Models 18910.2.2 Training Strategies for PLMs 19110.3 Applications of PLMs 19210.3.1 Case Studies in the Application of PLMs 19210.4 Case Introduction: Decoding Protein Interactions Using ESM 19510.4.1 Technical Foundations 19510.4.2 Applications in Protein Design 19610.4.3 Future Directions 19810.5 Conclusion and Outlook 201Bibliography 20311 Outlook 20711.1 Background 20711.2 AI’s Transformative Role 21011.3 Applications Across Protein Science 21411.4 AI-Augmented Experimental Techniques in Modern Protein Research 217Bibliography 220Index 223