Dataset Information

Supervised learning and prediction of physical interactions between human and HIV proteins.

ABSTRACT: Infectious diseases result in millions of deaths each year. Physical interactions between pathogen and host proteins often form the basis of such infections. While a number of methods have been proposed for predicting protein-protein interactions (PPIs), they have primarily focused on intra-species protein-protein interactions.We present an application of a supervised learning method for predicting physical interactions between host and pathogen proteins, using the human-HIV system. Using a Support Vector Machine with a linear kernel, we explore the use of a number of features including domain profiles, protein sequence k-mers, and properties of human proteins in a human PPI network. We achieve the best cross-validation performance when we use a combination of all three of these features. At a precision value of 70% we obtain recall values greater than 40%, depending on the ratio of positive examples to negative examples used during training. We use a classifier trained using these features to predict new PPIs between human and HIV proteins. We focus our discussion on those predicted interactions that involve human proteins known to be critical for HIV replication and propagation. Examples of predicted interactions with support in the literature include those necessary for viral attachment to the host membrane and subsequent invasion of the host cell.Unlike intra-species PPIs, host-pathogen PPIs have not yet been experimentally detected on a large scale, though they are likely to play important roles in pathogenesis and disease outcomes. Computational methods that can robustly and accurately predict host-pathogen PPIs hold the promise of guiding future experiments and gaining insights into potential mechanisms of pathogenesis.

SUBMITTER: Dyer MD

PROVIDER: S-EPMC3134873 | biostudies-literature | 2011 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Supervised learning and prediction of physical interactions between human and HIV proteins.

Dyer Matthew D MD Murali T M TM Sobral Bruno W BW

Infection, genetics and evolution : journal of molecular epidemiology and evolutionary genetics in infectious diseases 20110305 5

<h4>Background</h4>Infectious diseases result in millions of deaths each year. Physical interactions between pathogen and host proteins often form the basis of such infections. While a number of methods have been proposed for predicting protein-protein interactions (PPIs), they have primarily focused on intra-species protein-protein interactions.<h4>Methodology</h4>We present an application of a supervised learning method for predicting physical interactions between host and pathogen proteins, u ...[more]

PMID: 21382517

Similar Datasets

Project description:BackgroundViral-host protein-protein interaction plays a vital role in pathogenesis, since it defines viral infection of the host and regulation of the host proteins. Identification of key viral-host protein-protein interactions (PPIs) has great implication for therapeutics.MethodsIn this study, a systematic attempt has been made to predict viral-host PPIs by integrating different features, including domain-domain association, network topology and sequence information using viral-host PPIs from VirusMINT. The three well-known supervised machine learning methods, such as SVM, Naïve Bayes and Random Forest, which are commonly used in the prediction of PPIs, were employed to evaluate the performance measure based on five-fold cross validation techniques.ResultsOut of 44 descriptors, best features were found to be domain-domain association and methionine, serine and valine amino acid composition of viral proteins. In this study, SVM-based method achieved better sensitivity of 67% over Naïve Bayes (37.49%) and Random Forest (55.66%). However the specificity of Naïve Bayes was the highest (99.52%) as compared with SVM (74%) and Random Forest (89.08%). Overall, the SVM and Random Forest achieved accuracy of 71% and 72.41%, respectively. The proposed SVM-based method was evaluated on blind dataset and attained a sensitivity of 64%, specificity of 83%, and accuracy of 74%. In addition, unknown potential targets of hepatitis B virus-human and hepatitis E virus-human PPIs have been predicted through proposed SVM model and validated by gene ontology enrichment analysis. Our proposed model shows that, hepatitis B virus "C protein" binds to membrane docking protein, while "X protein" and "P protein" interacts with cell-killing and metabolic process proteins, respectively.ConclusionThe proposed method can predict large scale interspecies viral-human PPIs. The nature and function of unknown viral proteins (HBV and HEV), interacting partners of host protein were identified using optimised SVM model.

Project description:The role of three-dimensional genome organization as a critical regulator of gene expression has become increasingly clear over the last decade. Most of our understanding of this association comes from the study of long range chromatin interaction maps provided by Chromatin Conformation Capture-based techniques, which have greatly improved in recent years. Since these procedures are experimentally laborious and expensive, in silico prediction has emerged as an alternative strategy to generate virtual maps in cell types and conditions for which experimental data of chromatin interactions is not available. Several methods have been based on predictive models trained on one-dimensional (1D) sequencing features, yielding promising results. However, different approaches vary both in the way they model chromatin interactions and in the machine learning-based strategy they rely on, making it challenging to carry out performance comparison of existing methods. In this study, we use publicly available 1D sequencing signals to model cohesin-mediated chromatin interactions in two human cell lines and evaluate the prediction performance of six popular machine learning algorithms: decision trees, random forests, gradient boosting, support vector machines, multi-layer perceptron and deep learning. Our approach accurately predicts long-range interactions and reveals that gradient boosting significantly outperforms the other five methods, yielding accuracies of about 95%. We show that chromatin features in close genomic proximity to the anchors cover most of the predictive information, as has been previously reported. Moreover, we demonstrate that gradient boosting models trained with different subsets of chromatin features, unlike the other methods tested, are able to produce accurate predictions. In this regard, and besides architectural proteins, transcription factors are shown to be highly informative. Our study provides a framework for the systematic prediction of long-range chromatin interactions, identifies gradient boosting as the best suited algorithm for this task and highlights cell-type specific binding of transcription factors at the anchors as important determinants of chromatin wiring mediated by cohesin.

Dataset Information

Supervised learning and prediction of physical interactions between human and HIV proteins.

Publications

Supervised learning and prediction of physical interactions between human and HIV proteins.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets