DeepViral: prediction of novel virus-host interactions from protein sequences and infectious disease phenotypes.
TL;DR: DeepViral as discussed by the authors embeds human proteins and viruses in a shared space using their associated phenotypes and functions, supported by formalized background knowledge from biomedical ontologies, and predicts protein-protein interactions (PPI) between humans and viruses.
Abstract: Motivation Infectious diseases caused by novel viruses have become a major public health concern. Rapid identification of virus-host interactions can reveal mechanistic insights into infectious diseases and shed light on potential treatments. Current computational prediction methods for novel viruses are based mainly on protein sequences. However, it is not clear to what extent other important features, such as the symptoms caused by the viruses, could contribute to a predictor. Disease phenotypes (i.e., signs and symptoms) are readily accessible from clinical diagnosis and we hypothesize that they may act as a potential proxy and an additional source of information for the underlying molecular interactions between the pathogens and hosts. Results We developed DeepViral, a deep learning based method that predicts protein-protein interactions (PPI) between humans and viruses. Motivated by the potential utility of infectious disease phenotypes, we first embedded human proteins and viruses in a shared space using their associated phenotypes and functions, supported by formalized background knowledge from biomedical ontologies. By jointly learning from protein sequences and phenotype features, DeepViral significantly improves over existing sequence-based methods for intra- and inter-species PPI prediction. Availability Code and datasets for reproduction and customization are available at https://github.com/bio-ontology-research-group/DeepViral. Prediction results for 14 virus families are available at https://doi.org/10.5281/zenodo.4429824.
Citations
More filters
Georgetown University Medical Center1, University of Toronto2, Institute of Ecosystem Studies3, University of Glasgow4, Georgetown University5, International Livestock Research Institute6, University of Nebraska Medical Center7, Icahn School of Medicine at Mount Sinai8, Louisiana State University9, Pacific Lutheran University10, Colorado State University11, University of Arkansas12, University of London13, Georgetown University Law Center14, University of Cambridge15, University of Manitoba16, Massey University17, Tufts University18, University of Nairobi19, EcoHealth Alliance20, Griffith University21, University of Florida22, Washington State University23, University of Helsinki24, Carnegie Mellon University25, University of Pretoria26, Maasai Mara University27
TL;DR: In the light of the urgency raised by the COVID-19 pandemic, global investment in wildlife virology is likely to increase, and new surveillance programs will identify hundreds of novel viruses that might someday pose a threat to humans.
Abstract: In the light of the urgency raised by the COVID-19 pandemic, global investment in wildlife virology is likely to increase, and new surveillance programmes will identify hundreds of novel viruses that might someday pose a threat to humans. To support the extensive task of laboratory characterization, scientists may increasingly rely on data-driven rubrics or machine learning models that learn from known zoonoses to identify which animal pathogens could someday pose a threat to global health. We synthesize the findings of an interdisciplinary workshop on zoonotic risk technologies to answer the following questions. What are the prerequisites, in terms of open data, equity and interdisciplinary collaboration, to the development and application of those tools? What effect could the technology have on global health? Who would control that technology, who would have access to it and who would benefit from it? Would it improve pandemic prevention? Could it create new challenges? This article is part of the theme issue 'Infectious disease macroecology: parasite diversity and dynamics across the globe'.
33 citations
TL;DR: In this article, a Siamese convolutional neural network (CNN) architecture and a multi-layer perceptron were used to predict human-virus protein-protein interactions.
Abstract: Motivation To complement experimental efforts, machine learning-based computational methods are playing an increasingly important role to predict human-virus protein-protein interactions (PPIs). Furthermore, transfer learning can effectively apply prior knowledge obtained from a large source dataset/task to a small target dataset/task, improving prediction performance. Results To predict interactions between human and viral proteins, we combine evolutionary sequence profile features with a Siamese convolutional neural network (CNN) architecture and a multi-layer perceptron. Our architecture outperforms various feature encodings-based machine learning and state-of-the-art prediction methods. As our main contribution, we introduce two transfer learning methods (i.e., 'frozen' type and 'fine-tuning' type) that reliably predict interactions in a target human-virus domain based on training in a source human-virus domain, by retraining CNN layers. Finally, we utilize the 'frozen' type transfer learning approach to predict human-SARS-CoV-2 PPIs, indicating that our predictions are topologically and functionally similar to experimentally known interactions. Supplementary information Supplementary data are available at Bioinformatics online.
17 citations
TL;DR: DeepTrio as mentioned in this paper uses mask multiple parallel convolutional neural networks for protein-protein interaction (PPI) prediction and achieves a better performance over several state-of-the-art methods in terms of various quality metrics.
Abstract: MOTIVATION Protein-protein interaction (PPI), as a relative property, is determined by two binding proteins, which brings a great challenge to design an expert model with an unbiased learning architecture and a superior generalization performance. Additionally, few efforts have been made to allow PPI predictors to discriminate between relative properties and intrinsic properties. RESULTS We present a sequence-based approach, DeepTrio, for PPI prediction using mask multiple parallel convolutional neural networks. Experimental evaluations show that DeepTrio achieves a better performance over several state-of-the-art methods in terms of various quality metrics. Besides, DeepTrio is extended to provide additional insights into the contribution of each input neuron to the prediction results. AVAILABILITY We provide an online application at http://bis.zju.edu.cn/deeptrio. The DeepTrio models and training data are deposited at https://github.com/huxiaoti/deeptrio.git. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
13 citations
TL;DR: In this article , a comprehensive introduction of deep learning in protein-protein interactions (PPIs) prediction, including the diverse learning architectures, benchmarks and extended applications, is presented, and readers are referred to the references therein.
Abstract: Protein-protein interactions (PPIs) play key roles in a broad range of biological processes. The disorder of PPIs often causes various physical and mental diseases, which makes PPIs become the focus of the research on disease mechanism and clinical treatment. Since a large number of PPIs have been identified by in vivo and in vitro experimental techniques, the increasing scale of PPI data with the inherent complexity of interacting mechanisms has encouraged a growing use of computational methods to predict PPIs. Until recently, deep learning plays an increasingly important role in the machine learning field due to its remarkable non-linear transformation ability. In this article, we aim to present readers with a comprehensive introduction of deep learning in PPI prediction, including the diverse learning architectures, benchmarks and extended applications.
10 citations
TL;DR: Dong et al. as discussed by the authors developed a multitask transfer learning approach that exploits the information of around 24 million protein sequences and the interaction patterns from the human interactome to counter the problem of small training datasets.
Abstract: Viral infections are causing significant morbidity and mortality worldwide. Understanding the interaction patterns between a particular virus and human proteins plays a crucial role in unveiling the underlying mechanism of viral infection and pathogenesis. This could further help in prevention and treatment of virus-related diseases. However, the task of predicting protein–protein interactions between a new virus and human cells is extremely challenging due to scarce data on virus-human interactions and fast mutation rates of most viruses. We developed a multitask transfer learning approach that exploits the information of around 24 million protein sequences and the interaction patterns from the human interactome to counter the problem of small training datasets. Instead of using hand-crafted protein features, we utilize statistically rich protein representations learned by a deep language modeling approach from a massive source of protein sequences. Additionally, we employ an additional objective which aims to maximize the probability of observing human protein–protein interactions. This additional task objective acts as a regularizer and also allows to incorporate domain knowledge to inform the virus-human protein–protein interaction prediction model. Our approach achieved competitive results on 13 benchmark datasets and the case study for the SARS-CoV-2 virus receptor. Experimental results show that our proposed model works effectively for both virus-human and bacteria-human protein–protein interaction prediction tasks. We share our code for reproducibility and future research at https://git.l3s.uni-hannover.de/dong/multitask-transfer
.
10 citations
References
More filters
TL;DR: The goal of the Gene Ontology Consortium is to produce a dynamic, controlled vocabulary that can be applied to all eukaryotes even as knowledge of gene and protein roles in cells is accumulating and changing.
Abstract: Genomic sequencing has made it clear that a large fraction of the genes specifying the core biological functions are shared by all eukaryotes. Knowledge of the biological role of such shared proteins in one organism can often be transferred to other organisms. The goal of the Gene Ontology Consortium is to produce a dynamic, controlled vocabulary that can be applied to all eukaryotes even as knowledge of gene and protein roles in cells is accumulating and changing. To this end, three independent ontologies accessible on the World-Wide Web (http://www.geneontology.org) are being constructed: biological process, molecular function and cellular component.
35,225 citations
Journal Article•
TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
Abstract: Deep neural nets with a large number of parameters are very powerful machine learning systems. However, overfitting is a serious problem in such networks. Large networks are also slow to use, making it difficult to deal with overfitting by combining the predictions of many different large neural nets at test time. Dropout is a technique for addressing this problem. The key idea is to randomly drop units (along with their connections) from the neural network during training. This prevents units from co-adapting too much. During training, dropout samples from an exponential number of different "thinned" networks. At test time, it is easy to approximate the effect of averaging the predictions of all these thinned networks by simply using a single unthinned network that has smaller weights. This significantly reduces overfitting and gives major improvements over other regularization methods. We show that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
33,597 citations
TL;DR: The purpose of this article is to serve as an introduction to ROC graphs and as a guide for using them in research.
17,017 citations
TL;DR: The latest version of STRING more than doubles the number of organisms it covers, and offers an option to upload entire, genome-wide datasets as input, allowing users to visualize subsets as interaction networks and to perform gene-set enrichment analysis on the entire input.
Abstract: Proteins and their functional interactions form the backbone of the cellular machinery. Their connectivity network needs to be considered for the full understanding of biological phenomena, but the available information on protein-protein associations is incomplete and exhibits varying levels of annotation granularity and reliability. The STRING database aims to collect, score and integrate all publicly available sources of protein-protein interaction information, and to complement these with computational predictions. Its goal is to achieve a comprehensive and objective global network, including direct (physical) as well as indirect (functional) interactions. The latest version of STRING (11.0) more than doubles the number of organisms it covers, to 5090. The most important new feature is an option to upload entire, genome-wide datasets as input, allowing users to visualize subsets as interaction networks and to perform gene-set enrichment analysis on the entire input. For the enrichment analysis, STRING implements well-known classification systems such as Gene Ontology and KEGG, but also offers additional, new classification systems based on high-throughput text-mining as well as on a hierarchical clustering of the association network itself. The STRING resource is available online at https://string-db.org/.
10,584 citations
TL;DR: In addition to maintaining the GenBank(R) nucleic acid sequence database, the National Center for Biotechnology Information (NCBI) provides data analysis and retrieval resources for the data in GenBank and other biological data made available through NCBI’s website.
Abstract: In addition to maintaining the GenBank(R) nucleic acid sequence database, the National Center for Biotechnology Information (NCBI) provides data analysis and retrieval resources for the data in GenBank and other biological data made available through NCBI's website. NCBI resources include Entrez, PubMed, PubMed Central, LocusLink, the NCBI Taxonomy Browser, BLAST, BLAST Link (BLink), Electronic PCR, OrfFinder, Spidey, RefSeq, UniGene, HomoloGene, ProtEST, dbMHC, dbSNP, Cancer Chromosome Aberration Project (CCAP), Entrez Genomes and related tools, the Map Viewer, Model Maker, Evidence Viewer, Clusters of Orthologous Groups (COGs) database, Retroviral Genotyping Tools, SARS Coronavirus Resource, SAGEmap, Gene Expression Omnibus (GEO), Online Mendelian Inheritance in Man (OMIM), the Molecular Modeling Database (MMDB), the Conserved Domain Database (CDD) and the Conserved Domain Architecture Retrieval Tool (CDART). Augmenting many of the web applications are custom implementations of the BLAST program optimized to search specialized data sets. All of the resources can be accessed through the NCBI home page at: http://www.ncbi.nlm.nih.gov.
9,604 citations