A Sequence-Based Dynamic Ensemble Learning System for Protein Ligand-Binding Site Prediction

Zhang, Youzhi; Hu, Shanshan; Zhang, Jun; Gao, Xin; Li, Jinyan; Xia, Junfeng; Wang, Bing

doi:10.1109/tcbb.2015.2505286

Cited by 39 publications

(17 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One reason is that the TargetS training used a high threshold for ligand binding and spatial clustering, which eliminated many of positive binding residues and thus decreased the sensitivity of the predictions. There are other sequence-based methods that were designed for generic ligand binding site predictions based on dynamic ensemble learning, such as LigandRFs (Chen et al, 2014) and LigandDSES (Chen et al, 2016). In addition to the different feature selection and training processes, one of the major distinctions of IonSeq, in comparison to these generic binding modeling methods, is that IonSeq focuses on a set of small metal and radical ion ligands, which allows a ligand-specific training to enhance the specificity and accuracy of training models.…”

Section: Comparison With Other Ligand-specific Methodsmentioning

confidence: 99%

“…Therefore, accurate identification of the protein-ion-binding sites is important for understanding the mechanism of protein function and for new drug discovery. Many computational methods have been proposed in the last two decades for predicting general ligand-protein binding sites, which can be roughly grouped into two categories of sequencebased (Capra and Singh, 2007;Chen et al, 2014Chen et al, , 2016Magliery and Regan, 2005;Rausell et al, 2010) and structure-based (Brylinski and Skolnick, 2008;Capra et al, 2009;Hendlich et al, 1997;Laskowski, 1995;Roche et al, 2011;Roy and Zhang, 2012;Wass et al, 2010;Yang et al, 2013b) approaches. The sequence-based methods mostly rely on residue conservation analyses under the assumption that ligand-binding residues are functionally important and therefore should be conserved in the evolution.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recognizing metal and acid radical ion-binding sites by integrating ab initio modeling with template-based transferals

et al. 2016

View full text Add to dashboard Cite

show abstract

Section: Comparison With Other Ligand-specific Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Recognizing metal and acid radical ion-binding sites by integrating ab initio modeling with template-based transferals

et al. 2016

View full text Add to dashboard Cite

show abstract

“…Protein sequence profiles are always obtained by a BLAST (Basic Local Alignment Search Tool) program, such as the commonly-used program of PSI-BLAST (Position-Specific Iterative Basic Local Alignment Search Tool) [ 33 ]. Therefore, for the residue

of one protein sequence, the multiplication

of the sequence profile

of residue

and one physicochemical amino acid property

can represent the statistical evolution of the amino acid property [ 34 , 35 , 36 ], i.e.,

, where

and

are both vectors of

. The multiplication for residue

results in a set of 20 numerical vectors

.…”

Section: Methodsmentioning

confidence: 99%

Prediction of Protein Hotspots from Whole Protein Sequences by a Random Projection Ensemble System

Jin-jian

Wang

Zhang

et al. 2017

IJMS

Self Cite

View full text Add to dashboard Cite

Hotspot residues are important in the determination of protein-protein interactions, and they always perform specific functions in biological processes. The determination of hotspot residues is by the commonly-used method of alanine scanning mutagenesis experiments, which is always costly and time consuming. To address this issue, computational methods have been developed. Most of them are structure based, i.e., using the information of solved protein structures. However, the number of solved protein structures is extremely less than that of sequences. Moreover, almost all of the predictors identified hotspots from the interfaces of protein complexes, seldom from the whole protein sequences. Therefore, determining hotspots from whole protein sequences by sequence information alone is urgent. To address the issue of hotspot predictions from the whole sequences of proteins, we proposed an ensemble system with random projections using statistical physicochemical properties of amino acids. First, an encoding scheme involving sequence profiles of residues and physicochemical properties from the AAindex1 dataset is developed. Then, the random projection technique was adopted to project the encoding instances into a reduced space. Then, several better random projections were obtained by training an IBk classifier based on the training dataset, which were thus applied to the test dataset. The ensemble of random projection classifiers is therefore obtained. Experimental results showed that although the performance of our method is not good enough for real applications of hotspots, it is very promising in the determination of hotspot residues from whole sequences.

show abstract

“…Furthermore, the Receiver Operating Characteristic (ROC) curves and area under ROC curve (AUC) values can be also used as evaluation criteria. Among them, F1, MCC and AUC are the important metrics to comprehensively evaluate models [33,34]. In this study, confusion matrix was adopted to calculate evaluation index [35].…”

Section: Evaluation Criteriamentioning

confidence: 99%

Hot spot prediction in protein-protein interactions by an ensemble system

et al. 2018

Self Cite

View full text Add to dashboard Cite

Background: Hot spot residues are functional sites in protein interaction interfaces. The identification of hot spot residues is time-consuming and laborious using experimental methods. In order to address the issue, many computational methods have been developed to predict hot spot residues. Moreover, most prediction methods are based on structural features, sequence characteristics, and/or other protein features. Results: This paper proposed an ensemble learning method to predict hot spot residues that only uses sequence features and the relative accessible surface area of amino acid sequences. In this work, a novel feature selection technique was developed, an auto-correlation function combined with a sliding window technique was applied to obtain the characteristics of amino acid residues in protein sequence, and an ensemble classifier with SVM and KNN base classifiers was built to achieve the best classification performance. Conclusion: The experimental results showed that our model yields the highest F1 score of 0.92 and an MCC value of 0.87 on ASEdb dataset. Compared with other machine learning methods, our model achieves a big improvement in hot spot prediction. Availability: http://deeplearner.ahu.edu.cn/web/HotspotEL.htm.

show abstract

A Sequence-Based Dynamic Ensemble Learning System for Protein Ligand-Binding Site Prediction

Cited by 39 publications

References 40 publications

Recognizing metal and acid radical ion-binding sites by integrating ab initio modeling with template-based transferals

Recognizing metal and acid radical ion-binding sites by integrating ab initio modeling with template-based transferals

Prediction of Protein Hotspots from Whole Protein Sequences by a Random Projection Ensemble System

Hot spot prediction in protein-protein interactions by an ensemble system

Contact Info

Product

Resources

About