Prediction of Protein–Protein Interactions with Physicochemical Descriptors and Wavelet Transform via Random Forests

Xiao, Xuan; Liu, Bingxiang

doi:10.1177/2211068215581487

Cited by 14 publications

(8 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RF can also be of use in the missing data recovery. Owing to the unique features of the random forest and decision trees, they are frequently utilized in computational biology and bioinformatics for the classification of biological data, especially those required for the prediction of PPIs (34,35).…”

Section: Machine Learning Algorithm-based Methods With the Utilization Of Heterogeneous Genomic/proteomic Featuresmentioning

confidence: 99%

Protein-protein interaction networks and protein-ligand docking: Contemporary insights and future perspectives

Velesinović¹,

Nikolić²

2021

Acta fac medic Naissensis

View full text Add to dashboard Cite

Traditional research means, such as in vitro and in vivo models, have consistently been used by scientists to test hypotheses in biochemistry. Computational (in silico) methods have been increasingly devised and applied to testing and hypothesis development in biochemistry over the last decade. The aim of in silico methods is to analyze the quantitative aspects of scientific (big) data, whether these are stored in databases for large data or generated with the use of sophisticated modeling and simulation tools; to gain a fundamental understanding of numerous biochemical processes related, in particular, to large biological macromolecules by applying computational means to big biological data sets, and by computing biological system behavior. Computational methods used in biochemistry studies include proteomics-based bioinformatics, genome-wide mapping of protein-DNA interaction, as well as high-throughput mapping of the protein-protein interaction networks. Some of the vastly used molecular modeling and simulation techniques are Monte Carlo and Langevin (stochastic, Brownian) dynamics, statistical thermodynamics, molecular dynamics, continuum electrostatics, protein-ligand docking, protein-ligand affinity calculations, protein modeling techniques, and the protein folding process and enzyme action computer simulation. This paper presents a short review of two important methods used in the studies of biochemistry - protein-ligand docking and the prediction of protein-protein interaction networks.

show abstract

Section: Machine Learning Algorithm-based Methods With the Utilization Of Heterogeneous Genomic/proteomic Featuresmentioning

confidence: 99%

Protein-protein interaction networks and protein-ligand docking: Contemporary insights and future perspectives

Velesinović¹,

Nikolić²

2021

Acta fac medic Naissensis

View full text Add to dashboard Cite

show abstract

“…Random forest (RF) [ 31 ] is a popular tree-based ensemble machine learning technique that is a highly adaptive method for high dimensional datasets. RF has been applied in many structural bioinformatics contexts, such as fold recognition [ 49 ], protein-protein interaction prediction [ 50 , 51 ], and protein-RNA binding site prediction [ 52 ]. Essentially, the RF is a combination of a number of decision trees.…”

Section: Methodsmentioning

confidence: 99%

RF-Phos: A Novel General Phosphorylation Site Prediction Tool Based on Random Forest

Ismail

Jones

Kim

et al. 2016

BioMed Research International

View full text Add to dashboard Cite

Protein phosphorylation is one of the most widespread regulatory mechanisms in eukaryotes. Over the past decade, phosphorylation site prediction has emerged as an important problem in the field of bioinformatics. Here, we report a new method, termed Random Forest-based Phosphosite predictor 2.0 (RF-Phos 2.0), to predict phosphorylation sites given only the primary amino acid sequence of a protein as input. RF-Phos 2.0, which uses random forest with sequence and structural features, is able to identify putative sites of phosphorylation across many protein families. In side-by-side comparisons based on 10-fold cross validation and an independent dataset, RF-Phos 2.0 compares favorably to other popular mammalian phosphosite prediction methods, such as PhosphoSVM, GPS2.1, and Musite.

show abstract

“…Finally, the bidirectional GRUbased classifier used the concatenated features to predict PPIs. Jia et al [8] used a discrete wavelet transform (DWT) to extract the corresponding protein information and obtained a variety of physicochemical descriptors. e random forests model was used to classify the prediction results.…”

Section: Introductionmentioning

confidence: 99%

Self-Interacting Proteins Prediction from PSSM Based on Evolutionary Information

Wang

et al. 2021

Scientific Programming

View full text Add to dashboard Cite

Self-interacting proteins (SIPs) play an influential role in regulating cell structure and function. Thus, it is critically important to identify whether proteins themselves interact with each other. Although there are some existing experimental methods for self-interaction recognition, the limitations of these methods are both expensive and time-consuming. Therefore, it is very necessary to develop an efficient and stable computational method for predicting SIPs. In this study, we develop an effective computational method for predicting SIPs based on rotation forest (RF) classifier, combined with histogram of oriented gradients (HOG) and synthetic minority oversampling technique (SMOTE). When performing SIPs prediction on yeast and human datasets, the proposed method achieves superior accuracies of 97.28% and 89.41%, respectively. In addition, the proposed approach was compared with the state-of-the-art support vector machine (SVM) classifiers and other different methods on the same datasets. The experimental results demonstrate that our method has good robustness and effectiveness and can be regarded as a useful tool for SIPs prediction.

show abstract

Prediction of Protein–Protein Interactions with Physicochemical Descriptors and Wavelet Transform via Random Forests

Cited by 14 publications

References 43 publications

Protein-protein interaction networks and protein-ligand docking: Contemporary insights and future perspectives

Protein-protein interaction networks and protein-ligand docking: Contemporary insights and future perspectives

RF-Phos: A Novel General Phosphorylation Site Prediction Tool Based on Random Forest

Self-Interacting Proteins Prediction from PSSM Based on Evolutionary Information

Contact Info

Product

Resources

About