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

Liu, Quanya; Zhang, Youzhi; Wang, Bing; Zhang, Jun; Li, Jinyan

doi:10.1186/s12918-018-0665-8

Cited by 35 publications

(25 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fortunately, predicting protein-protein interaction sites using computational methods has become a hot topic with the development of machine learning algorithms [4][5][6][7][8]. Previous studies showed that support vector machine (SVM) and its improved methods can predict effectively protein interaction sites [9][10][11][12][13][14]. Computational algorithms such as random forests, KNN, and Naive Bayes Classifier have been also applied to the prediction of PPIs [15][16][17][18].…”

Section: Introductionmentioning

confidence: 99%

Developing Computational Model to Predict Protein-Protein Interaction Sites Based on the XGBoost Algorithm

Deng

Zhang

Wang

et al. 2020

IJMS

Self Cite

View full text Add to dashboard Cite

The study of protein-protein interaction is of great biological significance, and the prediction of protein-protein interaction sites can promote the understanding of cell biological activity and will be helpful for drug development. However, uneven distribution between interaction and non-interaction sites is common because only a small number of protein interactions have been confirmed by experimental techniques, which greatly affects the predictive capability of computational methods. In this work, two imbalanced data processing strategies based on XGBoost algorithm were proposed to re-balance the original dataset from inherent relationship between positive and negative samples for the prediction of protein-protein interaction sites. Herein, a feature extraction method was applied to represent the protein interaction sites based on evolutionary conservatism of proteins, and the influence of overlapping regions of positive and negative samples was considered in prediction performance. Our method showed good prediction performance, such as prediction accuracy of 0.807 and MCC of 0.614, on an original dataset with 10,455 surface residues but only 2297 interface residues. Experimental results demonstrated the effectiveness of our XGBoost-based method.

show abstract

Section: Introductionmentioning

confidence: 99%

Developing Computational Model to Predict Protein-Protein Interaction Sites Based on the XGBoost Algorithm

Deng

Zhang

Wang

et al. 2020

IJMS

Self Cite

View full text Add to dashboard Cite

show abstract

“…Instead, 75 vectors taken from the position-sensitive biophysical property matrix are necessary to properly split the groups, including both simple properties like charge, hydrophobicity, flexibility, and bulkiness and more carefully curated properties like the often used Kidera factors and the hotspot detecting variables of Liu et. al [39,40,54]. The inability to arrive at a core few biophysical properties that could effectively distinguish polyreactive and non-polyreactive antibodies necessitated the application of further approaches, namely information theory.…”

Section: Discussionmentioning

confidence: 99%

“…and Liu et. al [39,40]. A complete description of these properties can be found in Supplemental Table 1.…”

Section: A R N D C Q E G H I L K M F P S T W Y V a R N D C Q E G H I mentioning

confidence: 99%

Biochemical Patterns of Antibody Polyreactivity Revealed Through a Bioinformatics-Based Analysis of CDR Loops

Boughter

Borowska

Guthmiller

et al. 2020

Preprint

View full text Add to dashboard Cite

Antibodies are critical components of adaptive immunity, binding with high affinity to pathogenic epitopes. Antibodies undergo rigorous selection to achieve this high affinity, yet some maintain an additional basal level of low affinity, broad reactivity to diverse epitopes, a phenomenon termed “polyreactivity”. While polyreactivity has been observed in antibodies isolated from various immunological niches, the biophysical properties that allow for promiscuity in a protein selected for high affinity binding to a single target remain unclear. Using a database of nearly 1,500 polyreactive and non-polyreactive antibody sequences, we created a bioinformatic pipeline to isolate key determinants of polyreactivity. These determinants, which include an increase in inter-loop crosstalk and a propensity for an “inoffensive” binding surface, are sufficient to generate a classifier able to identify polyreactive antibodies with over 75% accuracy. The framework from which this classifier was built is generalizable, and represents a powerful, automated pipeline for future immune repertoire analysis.

show abstract

“…Robetta [6,10], HotPoint [2,3,5], MAPPIS [1], KFC [11], SpotOn [12], PredHS [13], iPPHOT [14], the method using docking approach [15], HSPred [16], HEP [17]) or physico-chemical properties of their residues (e.g. method using random projection-based classifier [18], MSCA [19], method applying ensemble learning [20], DICFC [21], iFrag [22]). Most of the aforementioned algorithms require knowledge of the protein structure, which is a significant drawback of these methods because the protein structure has been determined only for a limited number of proteins.…”

Section: Methods Of Hot Spot Identificationmentioning

confidence: 99%

Hot spot identification by means of classification methods employing wavelet transform-based features

Tamulewicz¹,

Tkacz²,

Provazník³

2020

Preprint

View full text Add to dashboard Cite

Background: Proteins can interact with one another by an interface composed of two proteins. Some of the interface residues - called hot spots - have the greatest impact on binding energy in a protein complex. This paper introduces the application of continuous wavelet transform based on the fast Fourier transform (CWTFT) to the analysis of hot spots in proteins.Results: The algorithm was evaluated by using data sets containing 30 proteins. From the number of tested classifiers the best 10 models were preferred. The classifiers achieved sensitivity of 52% - 71%, specificity of 70% - 83% and accuracy of 70% - 74%.Conclusion: The analyses show that the method combining CWTFT and classification algorithms is able to identify hot spot residues with valuable results.Methods: The basis of the algorithm is extraction of features from spectra obtained by using CWTFT with different wavelet functions including Morlet, m^th order derivative of Gaussian, Paul and Bump wavelets. Then, the classifiers that are able to separate hot spot from non-hot spot residues according to these features are applied.

show abstract

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

Cited by 35 publications

References 41 publications

Developing Computational Model to Predict Protein-Protein Interaction Sites Based on the XGBoost Algorithm

Developing Computational Model to Predict Protein-Protein Interaction Sites Based on the XGBoost Algorithm

Biochemical Patterns of Antibody Polyreactivity Revealed Through a Bioinformatics-Based Analysis of CDR Loops

Hot spot identification by means of classification methods employing wavelet transform-based features

Contact Info

Product

Resources

About