Dataset Information

Prediction of human-virus protein-protein interactions through a sequence embedding-based machine learning method.

ABSTRACT: The identification of human-virus protein-protein interactions (PPIs) is an essential and challenging research topic, potentially providing a mechanistic understanding of viral infection. Given that the experimental determination of human-virus PPIs is time-consuming and labor-intensive, computational methods are playing an important role in providing testable hypotheses, complementing the determination of large-scale interactome between species. In this work, we applied an unsupervised sequence embedding technique (doc2vec) to represent protein sequences as rich feature vectors of low dimensionality. Training a Random Forest (RF) classifier through a training dataset that covers known PPIs between human and all viruses, we obtained excellent predictive accuracy outperforming various combinations of machine learning algorithms and commonly-used sequence encoding schemes. Rigorous comparison with three existing human-virus PPI prediction methods, our proposed computational framework further provided very competitive and promising performance, suggesting that the doc2vec encoding scheme effectively captures context information of protein sequences, pertaining to corresponding protein-protein interactions. Our approach is freely accessible through our web server as part of our host-pathogen PPI prediction platform (http://zzdlab.com/InterSPPI/). Taken together, we hope the current work not only contributes a useful predictor to accelerate the exploration of human-virus PPIs, but also provides some meaningful insights into human-virus relationships.

SUBMITTER: Yang X

PROVIDER: S-EPMC6961065 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction of human-virus protein-protein interactions through a sequence embedding-based machine learning method.

Yang Xiaodi X Yang Shiping S Li Qinmengge Q Wuchty Stefan S Zhang Ziding Z

Computational and structural biotechnology journal 20191226

The identification of human-virus protein-protein interactions (PPIs) is an essential and challenging research topic, potentially providing a mechanistic understanding of viral infection. Given that the experimental determination of human-virus PPIs is time-consuming and labor-intensive, computational methods are playing an important role in providing testable hypotheses, complementing the determination of large-scale interactome between species. In this work, we applied an unsupervised sequence ...[more]

PMID: 31969974

Similar Datasets

Project description:MotivationProtein structure prediction has been greatly improved by deep learning, but the contribution of different information is yet to be fully understood. This article studies the impacts of two kinds of information for structure prediction: template and multiple sequence alignment (MSA) embedding. Templates have been used by some methods before, such as AlphaFold2, RoseTTAFold and RaptorX. AlphaFold2 and RosetTTAFold only used templates detected by HHsearch, which may not perform very well on some targets. In addition, sequence embedding generated by pre-trained protein language models has not been fully explored for structure prediction. In this article, we study the impact of templates (including the number of templates, the template quality and how the templates are generated) on protein structure prediction accuracy, especially when the templates are detected by methods other than HHsearch. We also study the impact of sequence embedding (generated by MSATransformer and ESM-1b) on structure prediction.ResultsWe have implemented a deep learning method for protein structure prediction that may take templates and MSA embedding as extra inputs. We study the contribution of templates and MSA embedding to structure prediction accuracy. Our experimental results show that templates can improve structure prediction on 71 of 110 CASP13 (13th Critical Assessment of Structure Prediction) targets and 47 of 91 CASP14 targets, and templates are particularly useful for targets with similar templates. MSA embedding can improve structure prediction on 63 of 91 CASP14 (14th Critical Assessment of Structure Prediction) targets and 87 of 183 CAMEO targets and is particularly useful for proteins with shallow MSAs. When both templates and MSA embedding are used, our method can predict correct folds (TMscore > 0.5) for 16 of 23 CASP14 FM targets and 14 of 18 Continuous Automated Model Evaluation (CAMEO) targets, outperforming RoseTTAFold by 5% and 7%, respectively.Availability and implementationAvailable at https://github.com/xluo233/RaptorXFold.Supplementary informationSupplementary data are available at Bioinformatics online.

Project description:Background: Alzheimer's disease (AD) is the most common type of dementia. Scientists have discovered that the causes of AD may include a combination of genetic, lifestyle, and environmental factors, but the exact cause has not yet been elucidated. Effective strategies to prevent and treat AD therefore remain elusive. The identified genetic causes of AD mainly focus on individual genes, but growing evidence has shown that complex diseases are usually affected by the interaction of genes in a network. Few studies have focused on the interactions and correlations between genes and how they are gradually destroyed or disappear during AD progression. A differential network analysis has been recognized as an essential tool for identifying the underlying pathogenic mechanisms and significant genes for prediction analysis. We therefore aim to conduct a differential network analysis to reveal potential networks involved in the neuropathogenesis of AD and identify genes for AD prediction. Methods: In this paper, we selected 365 samples from the Religious Orders Study and the Rush Memory and Aging Project, including 193 clinically and neuropathologically confirmed AD subjects and 172 no cognitive impairment (NCI) controls. Then, we selected 158 genes belonging to the AD pathway (hsa05010) of the Kyoto Encyclopedia of Genes and Genomes. We employed a machine learning method, namely, joint density-based non-parametric differential interaction network analysis and classification (JDINAC), in the analysis of gene expression data (RNA-seq data). We searched for the differential networks in the RNA-seq data with a pathological diagnosis of AD. Finally, an optimal prediction model was built through cross-validation, which showed good discrimination and calibration for AD prediction. Results: We used JDINAC to derive a gene co-expression network and to explore the relationship between the interaction of gene pairs and AD, and the top 10 differential gene pairs were identified. We then compared the prediction performance between JDINAC and individual genes based on prediction methods. JDINAC provides better accuracy of classification than the latest methods, such as random forest and penalized logistic regression. Conclusions: The interaction between gene pairs is related to AD and can provide more insight than the individual genes in AD prediction.

Dataset Information

Prediction of human-virus protein-protein interactions through a sequence embedding-based machine learning method.

Publications

Prediction of human-virus protein-protein interactions through a sequence embedding-based machine learning method.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets