Computational intelligence in protein-ligand interaction analysis /

Bibliographic Details
Corporate Author:	ScienceDirect (Online service)
Other Authors:	WANG, BING, Chen, Peng, Zhang, Jun
Format:	eBook
Language:	English
Published:	[S.l.] : Academic Press, 2024.
Subjects:	Protein binding. Ligand binding (Biochemistry) Computational intelligence. Protéines > Fixation. Ligands (Biochimie) > Fixation. Intelligence informatique. Electronic books.
Online Access:	Connect to the full text of this electronic book

Table of Contents:

Front Cover
Computational Intelligence in Protein-Ligand Interaction Analysis
Computational Intelligence in Protein-Ligand Interaction Analysis
Copyright
Contents
Contributors
1
Random forest method for predicting protein ligand-binding residues
1. Introduction
2. Methods
2.1 Datasets
2.2 Binding site definition
2.3 Feature vector representation of a residue
2.4 Combine different sliding windows
2.5 Ensemble of random forest classifiers
2.6 Evaluation criteria
3. Results and discussion
3.1 Prediction results on CASP9
3.2 Prediction results on CASP8
3.3 Comparison with other binding site prediction methods
3.4 Case studies
3.5 Discussion
4. Conclusions
References
2
Encoders of protein residues for identifying protein-protein interacting residues
1. Introduction
2. Methods
2.1 Data set
2.2 Sliding window technique
2.3 Generation of residue profiles
2.4 SVM-SOM classifiers
2.5 Classifiers combination
2.6 Measures for performance evaluation
3. Results
3.1 Determination of the sliding window length
3.2 Prediction performance without SOM
3.3 Prediction performance with the use of SOM
3.4 Improvement by using evolutionary context of residues with respect to hydrophobicity
3.5 A biological case of improvement by classifier ensemble
3.6 Comparison with other methods
3.7 Blind test
4. Conclusions
5. Supplementary materials
References
3
Ensemble method for the Identification of hotspot residues from protein sequences
1. Introduction
2. Methods
2.1 Data sets
2.2 Ensemble learning method
2.2.1 Feature selection
2.2.2 Classifier construction
2.3 Evaluation criteria
3. Results
3.1 Performance of ensemble classifiers on different M for auto-correlation function
3.2 Performance of different classifiers on ASEdb
3.3 Performance of our model on train and test sets
3.4 Comparison with other methods
3.5 Discussion
3.5.1 Feature selection algorithm
3.5.2 Feature correlation analysis
3.5.3 Descriptor cluster analysis
3.6 Case study
4. Conclusion
References
4
Predicting protein interaction sites from unlabeled sample information based on a semi-supervised approach
1. Introduction
2. Methods
2.1 Dataset
2.2 Feature extraction
2.3 Semi-supervised models
2.3.1 MeanS3VM_mkl
2.3.2 Means3vm-iter
2.3.3 S4VM
2.4 Evaluation criteria
3. Results
3.1 Prediction performance of three semi-supervised models
3.2 Prediction performance comparison between supervised and semi-supervised SVM
3.3 Comparison with other approaches
3.4 Visualization of experimental results
4. Conclusion
References
5
An XGBoost-based model to predict protein-protein interaction sites
1. Introduction
2. Materials and methods
2.1 Dataset
2.2 Feature extraction
2.3 Unbalanced datasets processing