Search

Understanding the protein-RNA interaction mechanism can help us to further explore various biological processes. The experimental techniques still have some limitations, such as the high cost of economy and time. Predicting protein-RNA-binding sites by using computational methods is an excellent research tool. Here, we developed a universal method for predicting protein-specific RNA-binding sites, so one general model for a given protein was constructed on a fixed dataset by fusing the data of different experimental techniques. At the same time, information theory was employed to characterize the sequence conservation of RNA-binding segments. Conversation difference profiles between binding and nonbinding segments were constructed by information entropy (IE), which indicates a significant difference. Finally, the 19 proteins-specific models based on random forest (RF) were built based on IE encoding. The performance on the independent datasets demonstrates that our method can obtain competitive results when compared with the current best prediction model., Competing Interests: The authors declare that they have no conflicts of interest., (Copyright © 2022 Yue Ji et al.)

With the rapid increase in crystal structures of protein-protein complexes deposited in the Protein Data Bank (PDB), more and more crystal contacts have been shown to have similar or even larger interface areas than biological interfaces. However, little attention has been paid to these large crystal packing contacts and their structural principles remain unknown. To address this issue, we used a comparative feature analysis to analyze the geometric and physicochemical properties of large crystal packing contacts by comparing two types of specific protein-protein interactions (PPIs), weak transient complexes and permanent homodimers. Our results show that although large crystal packing contacts have a similar interface area and contact size as permanent homodimers, they tend to be more planar, loosely packed and less hydrophobic than permanent homodimers and cannot form a central core region that is fully buried during interaction. However, the properties of large crystal packing contacts, except for the interface area and contact size, more closely resemble those of weak transient complexes. The large overlap between biological and large crystal packing contacts indicates that interface properties are not efficient indicators for classification of biological interfaces from large crystal packing contacts and finding other specific features urgently needed.

The prediction of protein domain region is an advantageous process on the study of protein structure and function. In this study, we proposed a new method, which is composed of fuzzy mean operator and region division, to predict the particular positions of domains in a target protein based on its sequence. The whole sequence is aligned and scored by using fuzzy mean operator, and the final determination of domain region position is realized by region division. A published benchmark is used for the comparison with previous researches. In addition, we generate two extra datasets to examine the stability of this method. Finally, the prediction accuracy of independent test dataset achieved by our method was up to 84.13%. We wish that this method could be useful for related researches., (© 2015 Wiley Periodicals, Inc.)

Protein-protein interactions (PPIs) play essential roles in many biological processes. In protein-protein interaction networks, hubs involve in numbers of PPIs and may constitute an important source of drug targets. The intrinsic disorder proteins (IDPs) with unstable structures can promote the promiscuity of hubs and also involve in many disease pathways, so they also could serve as potential drug targets. Moreover, proteins with similar functions measured by semantic similarity of gene ontology (GO) terms tend to interact with each other. Here, the relationship between hub proteins and drug targets based on GO terms and intrinsic disorder was explored. The semantic similarities of GO terms and genes between two proteins, and the rate of intrinsic disorder residues of each protein were extracted as features to characterize the functional similarity between two interacting proteins. Only using 8 feature variables, prediction models by support vector machine (SVM) were constructed to predict PPIs. The accuracy of the model on the PPI data from human hub proteins is as high as 83.72%, which is very promising compared with other PPI prediction models with hundreds or even thousands of features. Then, 118 of 142 PPIs between hubs are correctly predicted that the two interacting proteins are targets of the same drugs. The results indicate that only 8 functional features are fully efficient for representing PPIs. In order to identify new targets from IDP dataset, the PPIs between hubs and IDPs are predicted by the SVM model and the model yields a prediction accuracy of 75.84%. Further research proves that 3 of 5 PPIs between hubs and IDPs are correctly predicted that the two interacting proteins are targets of the same drugs. All results demonstrate that the model with only 8-dimensional features from GO terms and intrinsic disorder still gives a good performance in predicting PPIs and further identifying drug targets., (Copyright © 2015 Elsevier Ltd. All rights reserved.)

The assessment of binding affinity between ligands and the target proteins plays an essential role in drug discovery and design process. As an alternative to widely used scoring approaches, machine learning methods have also been proposed for fast prediction of the binding affinity with promising results, but most of them were developed as all-purpose models despite of the specific functions of different protein families, since proteins from different function families always have different structures and physicochemical features. In this study, we proposed a random forest method to predict the protein-ligand binding affinity based on a comprehensive feature set covering protein sequence, binding pocket, ligand structure and intermolecular interaction. Feature processing and compression was respectively implemented for different protein family datasets, which indicates that different features contribute to different models, so individual representation for each protein family is necessary. Three family-specific models were constructed for three important protein target families of HIV-1 protease, trypsin and carbonic anhydrase respectively. As a comparison, two generic models including diverse protein families were also built. The evaluation results show that models on family-specific datasets have the superior performance to those on the generic datasets and the Pearson and Spearman correlation coefficients (R p and Rs) on the test sets are 0.740, 0.874, 0.735 and 0.697, 0.853, 0.723 for HIV-1 protease, trypsin and carbonic anhydrase respectively. Comparisons with the other methods further demonstrate that individual representation and model construction for each protein family is a more reasonable way in predicting the affinity of one particular protein family.

Protein-protein interactions (PPIs) are becoming highly attractive targets for drug discovery. Motivated by the rapid accumulation of PPI data in public database and the success stories concerning the targeting of PPIs, a machine-learning method based on sequence and structure properties was developed to access the druggability of PPIs. Here, a comprehensive non-redundant set of 34 druggable and 122 less druggable PPIs were firstly presented from the perspective of pockets. When tested by outer 5-fold cross-validation, the most representative model in discriminating the druggable PPIs from the less-druggable ones yielded an average accuracy of 88.24% (sensitivity of 82.38% and specificity of 92.00%). Moreover, a promising result was also obtained for the independent test set. Compared to other methods, the method gives a comparative performance, which is most likely due to the construction of a training set that encompasses less druggable PPIs and also the information of active pockets that have evolved to bind a natural ligand.

Structural domains in proteins are the basic units to form various proteins. In the protein's evolution and functioning, domains play important roles. But the definition of domain is not yet precisely given, and the update cycle of structural domain databases is long. The automatic algorithms identify domains slowly, while protein entities with great structural complexity are on the rise. Here, we present a method which recognizes the compact and modular segments of polypeptide chains to identify structural domains, and contrast some data sets to illuminate their effect. The method combines support vector machine (SVM) with K-means algorithm. It is faster and more stable than most current algorithms and performs better. It also indicates that when proteins are presented as some Alpha-carbon atoms in 3D space, it is feasible to identify structural domains by the spatially structural properties. We have developed a web-server, which would be helpful in identification of structural domains (http://vis.sculab.org/~huayongpan/cgi-bin/domainAssignment.cgi).

Protein-protein interactions (PPIs) play crucial roles in diverse cellular processes. There are different types of PPIs based on the composition, affinity and whether the association is permanent or transient. Analyzing the diversity of PPIs at the atomic level is crucial for uncovering the key features governing the interactions involved in PPI. A systematic physico-chemical and conformational studies were implemented on interfaces involved in different PPIs, including crystal packing, weak transient heterodimers, weak transient homodimers, strong transient heterodimers and homodimers. The comparative analysis shows that the interfaces tend to be larger, less planar, and more tightly packed with the increase of the interaction strength. Meanwhile the strong interactions undergo greater conformational changes than the weak ones involving main chains as well as side chains. Finally, using 18 features derived from our analysis, we developed a support vector regression model to predict the binding affinity with a promising result, which further demonstrate the reliability of our studies. We believe this study will provide great help in more thorough understanding the mechanism of diverse PPIs.

Domains are the structural basis of the physiological functions of proteins, and the prediction of which is an advantageous process on the study of protein structure and function. This article proposes a new complete automatic prediction method, PPM-Dom (Domain Position Prediction Method), for predicting the particular positions of domains in a target protein via its atomic coordinate. The presented method integrates complex networks, community division, and fuzzy mean operator (FMO). The whole sequences are divided into potential domain regions by the complex network and community division, and FMO allows the final determination for the domain position. This method will suffice to predict regions that will form a domain structure and those that are unstructured based on completely new atomic coordinate information of the query sequence, and be able to separate different domains in the same query sequence from each other. On evaluating the performance using an independent testing dataset, PPM-Dom reached 91.41% for prediction accuracy, 96.12% for sensitivity and 92.86% for specificity. The tool bag of PPM-Dom is freely available at http://cic.scu.edu.cn/bioinformatics/PPMDom.zip., (Copyright © 2013 The Authors. Published by Elsevier Ltd.. All rights reserved.)

The main objective of this study is to explore the contribution of complex network together with its different definitions of vertexes and edges to describe the structure of proteins. Protein folds into a specific conformation for its function depending on interactions between residues. Consequently, in many studies, a protein structure was treated as a complex system comprised of individual components residues, and edges were interactions between residues. What is the proper time for representing a protein structure as a network? To confirm the effect of different definitions of vertexes and edges in constructing the amino acid interaction networks, protein domains and the structural unit of proteins were described using this method. The identification performance of 2847 proteins with domain/domains proved that the structure of proteins was described well when R(C)(α) was around 5.0-7.5 Å, and the optimal cutoff value for constructing the protein structure networks was 5.0 Å (C(α) -C(α) distances) while the ideal community division method was community structure detection based on edge betweenness in this study.

Owing to their potential for systematic analysis, complex networks have been widely used in proteomics. Representing a protein structure as a topology network provides novel insight into understanding protein folding mechanisms, stability and function. Here, we develop a new feature to reveal correlations between residues using a protein structure network. In an original attempt to quantify the effects of several key residues on catalytic residues, a power function was used to model interactions between residues. The results indicate that focusing on a few residues is a feasible approach to identifying catalytic residues. The spatial environment surrounding a catalytic residue was analyzed in a layered manner. We present evidence that correlation between residues is related to their distance apart most environmental parameters of the outer layer make a smaller contribution to prediction and ii catalytic residues tend to be located near key positions in enzyme folds. Feature analysis revealed satisfactory performance for our features, which were combined with several conventional features in a prediction model for catalytic residues using a comprehensive data set from the Catalytic Site Atlas. Values of 88.6 for sensitivity and 88.4 for specificity were obtained by 10-fold cross-validation. These results suggest that these features reveal the mutual dependence of residues and are promising for further study of structure-function relationship.

A three-stage support vector machine (SVM) was constructed to predict the state of cysteines by fusing sequence information, evolution information and annotation information of protein sequences. The first and second stages were for predicting whether the protein sequences contain disulfide bonds and whether all of the cysteines are involved in disulfide bonds. In the last stage, one SVM was constructed for predicting which cysteines are involved in disulfide bonds, among all these cysteines in proteins. The three SVMs give a good performance and the overall prediction accuracy are 90.05%, 96.36% and 80.00%, respectively, which indicates that the features selected in this work are effective for predicting the state of cysteines. In addition, current methods only paid too much attention to the prediction performance and never showed us how much important the roles of these features played in the prediction. As a result a feature importance measurement designated as F-score function was used to evaluate these features. The result shows that among these protein descriptors; evolution information is the most important feature for representing the disulfide-containing proteins. The prediction software and data sets used in this article are freely available at http://cic.scu.edu.cn/bioinformatics/Predict_Cys.zip., (Copyright © 2010 Elsevier Ltd. All rights reserved.)

Lipid-protein interactions play a vital role in various biological processes, which are involved in cellular functions and can affect the stability, folding and the function of peptides and proteins. In this study, a sequence-based method by using support vector machine and position specific scoring matrix (PSSM) was proposed to predict lipid-binding sites. Considering the influence of surrounding residues of one amino acid, a sliding window was chosen to encode the PSSM profiles. By incorporating the evolutionary information and the local features of residues surrounding one lipid-binding site, the method yielded a high accuracy of 80.86% and the Matthew's Correlation Coefficient of 0.58 by using fivefold cross validation test. The good result indicates the applicability of the method.

In contrast to a large number of classically secreted proteins (CSPs) and non-secreted proteins (NSPs), only a few proteins have been experimentally proved to enter non-classical secretory pathways. So it is difficult to identify non-classically secreted proteins (NCSPs), and no methods are available for distinguishing the three types of proteins simultaneously. In order to solve this problem, a data mining has been taken firstly, and mammalian proteins exported via ER-Golgi-independent pathways are collected through extensive literature searches. In this paper, a support vector machine (SVM)-based ternary classifier named SecretP is proposed to predict mammalian secreted proteins by using pseudo-amino acid composition (PseAA) and five additional features. When distinguishing the three types of proteins, SecretP yielded an accuracy of 88.79%. Evaluating the performance of our method by an independent test set of 92 human proteins, 76 of them are correctly predicted as NCSPs. When performed on another public independent data set, the prediction result of SecretP is comparable to those of other existing computational methods. Therefore, SecretP can be a useful supplementary tool for future secretome studies. The web server SecretP and all supplementary tables listed in this paper are freely available at http://cic.scu.edu.cn/bioinformatics/secretp/index.htm., (Copyright (c) 2010 Elsevier Inc. All rights reserved.)

Beta-turn is a secondary protein structure type that plays an important role in protein configuration and function. Here, we introduced an approach of beta-turn prediction that used the support vector machine (SVM) algorithm combined with predicted secondary structure information. The secondary structure information was obtained by using E-SSpred, a new secondary protein structure prediction method. A 7-fold cross validation based on the benchmark dataset of 426 non-homologous protein chains was used to evaluate the performance of our method. The prediction results broke the 80% Q (total) barrier and achieved Q (total) = 80.9%, MCC = 0.44, and Q (predicted) higher 0.9% when compared with the best method. The results in our research are coincident with the conclusion that beta-turn prediction accuracy can be improved by inclusion of secondary structure information.

There are approximately 10(9) proteins in a cell. A hotspot in bioinformatics is how to identify a protein subcellular localization, if its sequence is known. In this paper, a method using fast Fourier transform-based support vector machine is developed to predict the subcellular localization of proteins from their physicochemical properties and structural parameters. The prediction accuracies reached 83% in prokaryotic organisms and 84% in eukaryotic organisms with the substitution model of the c-p-v matrix (c, composition; p, polarity; and v, molecular volume). The overall prediction accuracy was also evaluated using the "leave-one-out" jackknife procedure. The influence of the substitution model on prediction accuracy has also been discussed in the work. The source code of the new program is available on request from the authors.

Identifying protein-RNA binding residues is essential for understanding the mechanism of protein-RNA interactions. So far, rigid distance thresholds are commonly used to define protein-RNA binding residues. However, after investigating 182 non-redundant protein-RNA complexes, we find that it would be unsuitable for a certain amount of complexes since the distances between proteins and RNAs vary widely. In this work, a novel definition method was proposed based on a flexible distance cutoff. This method can fully consider the individual differences among complexes by setting a variable tolerance limit of protein-RNA interactions, i.e. the double minimum-distance by which different distance thresholds are achieved for different complexes. In order to validate our method, a comprehensive comparison between our flexible method and traditional rigid methods was implemented in terms of interface structure, amino acid composition, interface area and interaction force, etc. The results indicate that this method is more reasonable because it incorporates the specificity of different complexes by extracting the important residues lost by rigid distance methods and discarding some redundant residues. Finally, to further test our double minimum-distance definition strategy, we developed a classifier to predict those binding sites derived from our new method by using structural features and a random forest machine learning algorithm. The model achieved a satisfactory prediction performance and the accuracy on independent data sets reaches to 85.0%. To the best of our knowledge, it is the first prediction model to define positive and negative samples using a flexible cutoff. So the comparison analysis and modeling results have demonstrated that our method would be a very promising strategy for more precisely defining protein-RNA binding sites. [ABSTRACT FROM AUTHOR]

The human papillomavirus 16 (HPV16) has high risk to lead various cancers and afflictions, especially, the cervical cancer. Therefore, investigating the pathogenesis of HPV16 is very important for public health. Protein-protein interaction (PPI) network between HPV16 and human was used as a measure to improve our understanding of its pathogenesis. By adopting sequence and topological features, a support vector machine (SVM) model was built to predict new interactions between HPV16 and human proteins. All interactions were comprehensively investigated and analyzed. The analysis indicated that HPV16 enlarged its scope of influence by interacting with human proteins as much as possible. These interactions alter a broad array of cell cycle progression. Furthermore, not only was HPV16 highly prone to interact with hub proteins and bottleneck proteins, but also it could effectively affect a breadth of signaling pathways. In addition, we found that the HPV16 evolved into high carcinogenicity on the condition that its own reproduction had been ensured. Meanwhile, this work will contribute to providing potential new targets for antiviral therapeutics and help experimental research in the future. [ABSTRACT FROM AUTHOR]

Protein methylation plays vital roles in many biological processes and has been implicated in various human diseases. To fully understand the mechanisms underlying methylation for use in drug design and work in methylation-related diseases, an initial but crucial step is to identify methylation sites. The use of high-throughput bioinformatics methods has become imperative to predict methylation sites. In this study, we developed a novel method that is based only on sequence conservation to predict protein methylation sites. Conservation difference profiles between methylated and non-methylated peptides were constructed by the information entropy (IE) in a wider neighbor interval around the methylation sites that fully incorporated all of the environmental information. Then, the distinctive neighbor residues were identified by the importance scores of information gain (IG). The most representative model was constructed by support vector machine (SVM) for Arginine and Lysine methylation, respectively. This model yielded a promising result on both the benchmark dataset and independent test set. The model was used to screen the entire human proteome, and many unknown substrates were identified. These results indicate that our method can serve as a useful supplement to elucidate the mechanism of protein methylation and facilitate hypothesis-driven experimental design and validation. [ABSTRACT FROM AUTHOR]

Abstract: Signal peptide has a pivotal role in the translocation of secretory protein. Some models have been designed to predict its cleavage site. It is reported that the cleavage site has relationship with the neighboring sequence environment, i.e., hydrophobic core h-region, and the specific patterns in c-region. In some studies, this finding does facilitate the prediction of cleavage site. However, in these models, sequence environment information is merely taken account of as model inputs and no detailed investigation into its effect on the prediction of cleavage site has been made. In this work, we analyze the constraint on cleave site placed by the hydrophobic core of signal peptide and then use it to improve the performance of the signal peptide cleavage site prediction. Our model is designed as follows: firstly, a sliding window is used to scan sample and artificial neural network (ANN) is employed to give cleavage site/non-cleavage site scores. Then, based on an estimated hydrophobic h-region a correcting function is proposed to improve the prediction result, in which the sequence environment is taken into account. A trend of cleavage site is indicated by our analysis for each position, which is consistent with experimental findings. Through this correcting step, the improvement of prediction accuracy is over 7%. It therefore demonstrates the neighboring sequence environment is helpful for determination of cleavage site. Program written in Matlab can be downloaded from http://www.scucic.cn/combined model/source code.html. [Copyright &y& Elsevier]