VIDHOP, viral host prediction with deep learning

Building a pathway to One Health surveillance and response in Asian countries

To detect and respond to emerging diseases more effectively, an integrated surveillance strategy needs to be applied to both human and animal health. Current programs in Asian countries operate separately for the two sectors and are principally concerned with detection of events that represent a short-term disease threat. It is not realistic to either invest only in efforts to detect emerging diseases, or to rely solely on event-based surveillance. A comprehensive strategy is needed, concurrently investigating and managing endemic zoonoses, studying evolving diseases which change their character and importance due to influences such as demographic and climatic change, and enhancing understanding of factors which are likely to influence the emergence of new pathogens. This requires utilisation of additional investigation tools that have become available in recent years but are not yet being used to full effect. As yet there is no fully formed blueprint that can be applied in Asian countries. Hence a three-step pathway is proposed to move towards the goal of comprehensive One Health disease surveillance and response.

A microbial knowledge graph-based deep learning model for predicting candidate microbes for target hosts

Predicting interactions between microbes and hosts plays critical roles in microbiome population genetics and microbial ecology and evolution. How to systematically characterize the sophisticated mechanisms and signal interplay between microbes and hosts is a significant challenge for global health risks. Identifying microbe-host interactions (MHIs) can not only provide helpful insights into their fundamental regulatory mechanisms, but also facilitate the development of targeted therapies for microbial infections. In recent years, computational methods have become an appealing alternative due to the high risk and cost of wet-lab experiments. Therefore, in this study, we utilized rich microbial metagenomic information to construct a novel heterogeneous microbial network (HMN)-based model named KGVHI to predict candidate microbes for target hosts. Specifically, KGVHI first built a HMN by integrating human proteins, viruses and pathogenic bacteria with their biological attributes. Then KGVHI adopted a knowledge graph embedding strategy to capture the global topological structure information of the whole network. A natural language processing algorithm is used to extract the local biological attribute information from the nodes in HMN. Finally, we combined the local and global information and fed it into a blended deep neural network (DNN) for training and prediction. Compared to state-of-the-art methods, the comprehensive experimental results show that our model can obtain excellent results on the corresponding three MHI datasets. Furthermore, we also conducted two pathogenic bacteria case studies to further indicate that KGVHI has excellent predictive capabilities for potential MHI pairs.

IPEV: identification of prokaryotic and eukaryotic virus-derived sequences in virome using deep learning

BACKGROUND

The virome obtained through virus-like particle enrichment contains a mixture of prokaryotic and eukaryotic virus-derived fragments. Accurate identification and classification of these elements are crucial to understanding their roles and functions in microbial communities. However, the rapid mutation rates of viral genomes pose challenges in developing high-performance tools for classification, potentially limiting downstream analyses.

FINDINGS

We present IPEV, a novel method to distinguish prokaryotic and eukaryotic viruses in viromes, with a 2-dimensional convolutional neural network combining trinucleotide pair relative distance and frequency. Cross-validation assessments of IPEV demonstrate its state-of-the-art precision, significantly improving the F1-score by approximately 22% on an independent test set compared to existing methods when query viruses share less than 30% sequence similarity with known viruses. Furthermore, IPEV outperforms other methods in accuracy on marine and gut virome samples based on annotations by sequence alignments. IPEV reduces runtime by at most 1,225 times compared to existing methods under the same computing configuration. We also utilized IPEV to analyze longitudinal samples and found that the gut virome exhibits a higher degree of temporal stability than previously observed in persistent personal viromes, providing novel insights into the resilience of the gut virome in individuals.

CONCLUSIONS

IPEV is a high-performance, user-friendly tool that assists biologists in identifying and classifying prokaryotic and eukaryotic viruses within viromes. The tool is available at https://github.com/basehc/IPEV.

HostNet: improved sequence representation in deep neural networks for virus-host prediction

BACKGROUND

The escalation of viruses over the past decade has highlighted the need to determine their respective hosts, particularly for emerging ones that pose a potential menace to the welfare of both human and animal life. Yet, the traditional means of ascertaining the host range of viruses, which involves field surveillance and laboratory experiments, is a laborious and demanding undertaking. A computational tool with the capability to reliably predict host ranges for novel viruses can provide timely responses in the prevention and control of emerging infectious diseases. The intricate nature of viral-host prediction involves issues such as data imbalance and deficiency. Therefore, developing highly accurate computational tools capable of predicting virus-host associations is a challenging and pressing demand.

RESULTS

To overcome the challenges of virus-host prediction, we present HostNet, a deep learning framework that utilizes a Transformer-CNN-BiGRU architecture and two enhanced sequence representation modules. The first module, k-mer to vector, pre-trains a background vector representation of k-mers from a broad range of virus sequences to address the issue of data deficiency. The second module, an adaptive sliding window, truncates virus sequences of various lengths to create a uniform number of informative and distinct samples for each sequence to address the issue of data imbalance. We assess HostNet's performance on a benchmark dataset of "Rabies lyssavirus" and an in-house dataset of "Flavivirus". Our results show that HostNet surpasses the state-of-the-art deep learning-based method in host-prediction accuracies and F1 score. The enhanced sequence representation modules, significantly improve HostNet's training generalization, performance in challenging classes, and stability.

CONCLUSION

HostNet is a promising framework for predicting virus hosts from genomic sequences, addressing challenges posed by sparse and varying-length virus sequence data. Our results demonstrate its potential as a valuable tool for virus-host prediction in various biological contexts. Virus-host prediction based on genomic sequences using deep neural networks is a promising approach to identifying their potential hosts accurately and efficiently, with significant impacts on public health, disease prevention, and vaccine development.

Misclassified: identification of zoonotic transition biomarker candidates for influenza A viruses using deep neural network

Introduction: Zoonotic transition of Influenza A viruses is the cause of epidemics with high rates of morbidity and mortality. Predicting which viral strains are likely to transition from their genetic sequence could help in the prevention and response against these zoonotic strains. We hypothesized that features predictive of viral hosts could be leveraged to identify biomarkers of zoonotic viral transition. Methods: We trained deep learning models to predict viral hosts based on the virus mRNA or protein sequences. Our multi-host dataset contained 848,630 unique nucleotide sequences obtained from the NCBI Influenza Virus and Influenza Research Databases. Each sequence, representing one gene from one viral strain, was classified into one of the three host categories: Avian, Human, and Swine. Trained models were analyzed using various neural network interpretation methods to identify interesting candidates for zoonotic transition biomarkers. Results: Using mRNA sequences as input led to higher prediction accuracies than amino acids, suggesting that the codon sequence contains information relevant to viral hosts that is lost during protein translation. UMAP visualization of the latent space of our classifiers showed that viral sequences clustered according to their host of origin. Interestingly, sequences from pandemic zoonotic viral strains localized at the margins between hosts, while zoonotic sequences incapable of Human-to-Human transmission localized with non-zoonotic viruses from the same host. In addition, host prediction for pandemic zoonotic sequences had low prediction accuracy, which was not the case for the other zoonotic strains. This supports our hypothesis that ambiguously predicted viral sequences bear features associated with cross-species infectivity. Finally, we compared misclassified sequences to well-classified ones to extract interesting candidates for zoonotic transition biomarkers. While features varied significantly between pairs of species and viral genes, several codons were conserved in Swine-to-Human and Avian-to-Human misclassified sequences, and in particular in the NA, HA, and NP genes, suggesting their importance for zoonosis in Humans. Discussion: Analysis of viral sequences using neural network interpretation approaches revealed important genetic differences between zoonotic viruses with pandemic potential, compared to non-zoonotic viral strains or zoonotic viruses incapable of Human-to-Human transmission.

GSPHI: A novel deep learning model for predicting phage-host interactions via multiple biological information

Emerging evidence suggests that due to the misuse of antibiotics, bacteriophage (phage) therapy has been recognized as one of the most promising strategies for treating human diseases infected by antibiotic-resistant bacteria. Identification of phage-host interactions (PHIs) can help to explore the mechanisms of bacterial response to phages and provide new insights into effective therapeutic approaches. Compared to conventional wet-lab experiments, computational models for predicting PHIs can not only save time and cost, but also be more efficient and economical. In this study, we developed a deep learning predictive framework called GSPHI to identify potential phage and target bacterium pairs through DNA and protein sequence information. More specifically, GSPHI first initialized the node representations of phages and target bacterial hosts via a natural language processing algorithm. Then a graph embedding algorithm structural deep network embedding (SDNE) was utilized to extract local and global information from the interaction network, and finally, a deep neural network (DNN) was applied to accurately detect the interactions between phages and their bacterial hosts. In the drug-resistant bacteria dataset ESKAPE, GSPHI achieved a prediction accuracy of 86.65 % and AUC of 0.9208 under the 5-fold cross-validation technique, significantly better than other methods. In addition, case studies in Gram-positive and negative bacterial species demonstrated that GSPHI is competent in detecting potential Phage-host interactions. Taken together, these results indicate that GSPHI can provide reasonable candidate sensitive bacteria to phages for biological experiments. The webserver of the GSPHI predictor is freely available at http://120.77.11.78/GSPHI/.

Using machine learning to detect coronaviruses potentially infectious to humans

Establishing the host range for novel viruses remains a challenge. Here, we address the challenge of identifying non-human animal coronaviruses that may infect humans by creating an artificial neural network model that learns from spike protein sequences of alpha and beta coronaviruses and their binding annotation to their host receptor. The proposed method produces a human-Binding Potential (h-BiP) score that distinguishes, with high accuracy, the binding potential among coronaviruses. Three viruses, previously unknown to bind human receptors, were identified: Bat coronavirus BtCoV/133/2005 and Pipistrellus abramus bat coronavirus HKU5-related (both MERS related viruses), and Rhinolophus affinis coronavirus isolate LYRa3 (a SARS related virus). We further analyze the binding properties of BtCoV/133/2005 and LYRa3 using molecular dynamics. To test whether this model can be used for surveillance of novel coronaviruses, we re-trained the model on a set that excludes SARS-CoV-2 and all viral sequences released after the SARS-CoV-2 was published. The results predict the binding of SARS-CoV-2 with a human receptor, indicating that machine learning methods are an excellent tool for the prediction of host expansion events.

Classification of Highly Divergent Viruses from DNA/RNA Sequence Using Transformer-Based Models

Viruses infect millions of people worldwide each year, and some can lead to cancer or increase the risk of cancer. As viruses have highly mutable genomes, new viruses may emerge in the future, such as COVID-19 and influenza. Traditional virology relies on predefined rules to identify viruses, but new viruses may be completely or partially divergent from the reference genome, rendering statistical methods and similarity calculations insufficient for all genome sequences. Identifying DNA/RNA-based viral sequences is a crucial step in differentiating different types of lethal pathogens, including their variants and strains. While various tools in bioinformatics can align them, expert biologists are required to interpret the results. Computational virology is a scientific field that studies viruses, their origins, and drug discovery, where machine learning plays a crucial role in extracting domain- and task-specific features to tackle this challenge. This paper proposes a genome analysis system that uses advanced deep learning to identify dozens of viruses. The system uses nucleotide sequences from the NCBI GenBank database and a BERT tokenizer to extract features from the sequences by breaking them down into tokens. We also generated synthetic data for viruses with small sample sizes. The proposed system has two components: a scratch BERT architecture specifically designed for DNA analysis, which is used to learn the next codons unsupervised, and a classifier that identifies important features and understands the relationship between genotype and phenotype. Our system achieved an accuracy of 97.69% in identifying viral sequences.

PREHOST: Host prediction of coronaviridae family using machine learning

Coronavirus, a zoonotic virus capable of transmitting infections from animals to humans, emerged as a pandemic recently. In such circumstances, it is essential to understand the virus's origin. In this study, we present a novel machine-learning pipeline PreHost for host prediction of the family, Coronaviridae. We leverage the complete viral genome and sequences at the protein level (spike protein, membrane protein, and nucleocapsid protein). Compared with the current state-of-the-art approaches, the random forest model attained high accuracy and recall scores of 99.91% and 0.98, respectively, for genome sequences. In addition to the spike protein sequences, our study shows membrane and nucleocapsid protein sequences can be utilized to predict the host of viruses. We also identified important sites in the viral sequences that help distinguish between different host classes. The host prediction pipeline PreHost will cater as a valuable tool to take effective measures to govern the transmission of future viruses.

Advances in the field of phage-based therapy with special emphasis on computational resources

In the current era, one of the major challenges is to manage the treatment of drug/antibiotic-resistant strains of bacteria. Phage therapy, a century-old technique, may serve as an alternative to antibiotics in treating bacterial infections caused by drug-resistant strains of bacteria. In this review, a systematic attempt has been made to summarize phage-based therapy in depth. This review has been divided into the following two sections: general information and computer-aided phage therapy (CAPT). In the case of general information, we cover the history of phage therapy, the mechanism of action, the status of phage-based products (approved and clinical trials) and the challenges. This review emphasizes CAPT, where we have covered primary phage-associated resources, phage prediction methods and pipelines. This review covers a wide range of databases and resources, including viral genomes and proteins, phage receptors, host genomes of phages, phage-host interactions and lytic proteins. In the post-genomic era, identifying the most suitable phage for lysing a drug-resistant strain of bacterium is crucial for developing alternate treatments for drug-resistant bacteria and this remains a challenging problem. Thus, we compile all phage-associated prediction methods that include the prediction of phages for a bacterial strain, the host for a phage and the identification of interacting phage-host pairs. Most of these methods have been developed using machine learning and deep learning techniques. This review also discussed recent advances in the field of CAPT, where we briefly describe computational tools available for predicting phage virions, the life cycle of phages and prophage identification. Finally, we describe phage-based therapy's advantages, challenges and opportunities.

Bioinformatics approaches for unveiling virus-host interactions

The coronavirus disease-2019 (COVID-19) pandemic has elucidated major limitations in the capacity of medical and research institutions to appropriately manage emerging infectious diseases. We can improve our understanding of infectious diseases by unveiling virus-host interactions through host range prediction and protein-protein interaction prediction. Although many algorithms have been developed to predict virus-host interactions, numerous issues remain to be solved, and the entire network remains veiled. In this review, we comprehensively surveyed algorithms used to predict virus-host interactions. We also discuss the current challenges, such as dataset biases toward highly pathogenic viruses, and the potential solutions. The complete prediction of virus-host interactions remains difficult; however, bioinformatics can contribute to progress in research on infectious diseases and human health.

In silico method for predicting infectious strains of influenza A virus from its genome and protein sequences

Influenza A is a contagious viral disease responsible for four pandemics in the past and a major public health concern. Being zoonotic in nature, the virus can cross the species barrier and transmit from wild aquatic bird reservoirs to humans via intermediate hosts. In this study, we have developed a computational method for the prediction of human-associated and non-human-associated influenza A virus sequences. The models were trained and validated on proteins and genome sequences of influenza A virus. Firstly, we have developed prediction models for 15 types of influenza A proteins using composition-based and one-hot-encoding features. We have achieved a highest AUC of 0.98 for HA protein on a validation dataset using dipeptide composition-based features. Of note, we obtained a maximum AUC of 0.99 using one-hot-encoding features for protein-based models on a validation dataset. Secondly, we built models using whole genome sequences which achieved an AUC of 0.98 on a validation dataset. In addition, we showed that our method outperforms a similarity-based approach (i.e., blast) on the same validation dataset. Finally, we integrated our best models into a user-friendly web server 'FluSPred' (https://webs.iiitd.edu.in/raghava/fluspred/index.html) and a standalone version (https://github.com/raghavagps/FluSPred) for the prediction of human-associated/non-human-associated influenza A virus strains.

Detecting DNA of novel fungal pathogens using ResNets and a curated fungi-hosts data collection

BACKGROUND

Emerging pathogens are a growing threat, but large data collections and approaches for predicting the risk associated with novel agents are limited to bacteria and viruses. Pathogenic fungi, which also pose a constant threat to public health, remain understudied. Relevant data remain comparatively scarce and scattered among many different sources, hindering the development of sequencing-based detection workflows for novel fungal pathogens. No prediction method working for agents across all three groups is available, even though the cause of an infection is often difficult to identify from symptoms alone.

RESULTS

We present a curated collection of fungal host range data, comprising records on human, animal and plant pathogens, as well as other plant-associated fungi, linked to publicly available genomes. We show that it can be used to predict the pathogenic potential of novel fungal species directly from DNA sequences with either sequence homology or deep learning. We develop learned, numerical representations of the collected genomes and visualize the landscape of fungal pathogenicity. Finally, we train multi-class models predicting if next-generation sequencing reads originate from novel fungal, bacterial or viral threats.

CONCLUSIONS

The neural networks trained using our data collection enable accurate detection of novel fungal pathogens. A curated set of over 1400 genomes with host and pathogenicity metadata supports training of machine-learning models and sequence comparison, not limited to the pathogen detection task.

AVAILABILITY AND IMPLEMENTATION

The data, models and code are hosted at https://zenodo.org/record/5846345, https://zenodo.org/record/5711877 and https://gitlab.com/dacs-hpi/deepac.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Convolutional Neural Network Applied to SARS-CoV-2 Sequence Classification

COVID-19, the illness caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus belonging to the Coronaviridade family, a single-strand positive-sense RNA genome, has been spreading around the world and has been declared a pandemic by the World Health Organization. On 17 January 2022, there were more than 329 million cases, with more than 5.5 million deaths. Although COVID-19 has a low mortality rate, its high capacities for contamination, spread, and mutation worry the authorities, especially after the emergence of the Omicron variant, which has a high transmission capacity and can more easily contaminate even vaccinated people. Such outbreaks require elucidation of the taxonomic classification and origin of the virus (SARS-CoV-2) from the genomic sequence for strategic planning, containment, and treatment of the disease. Thus, this work proposes a high-accuracy technique to classify viruses and other organisms from a genome sequence using a deep learning convolutional neural network (CNN). Unlike the other literature, the proposed approach does not limit the length of the genome sequence. The results show that the novel proposal accurately distinguishes SARS-CoV-2 from the sequences of other viruses. The results were obtained from 1557 instances of SARS-CoV-2 from the National Center for Biotechnology Information (NCBI) and 14,684 different viruses from the Virus-Host DB. As a CNN has several changeable parameters, the tests were performed with forty-eight different architectures; the best of these had an accuracy of 91.94 ± 2.62% in classifying viruses into their realms correctly, in addition to 100% accuracy in classifying SARS-CoV-2 into its respective realm, Riboviria. For the subsequent classifications (family, genera, and subgenus), this accuracy increased, which shows that the proposed architecture may be viable in the classification of the virus that causes COVID-19.

Women in the European Virus Bioinformatics Center

Viruses are the cause of a considerable burden to human, animal and plant health, while on the other hand playing an important role in regulating entire ecosystems. The power of new sequencing technologies combined with new tools for processing "Big Data" offers unprecedented opportunities to answer fundamental questions in virology. Virologists have an urgent need for virus-specific bioinformatics tools. These developments have led to the formation of the European Virus Bioinformatics Center, a network of experts in virology and bioinformatics who are joining forces to enable extensive exchange and collaboration between these research areas. The EVBC strives to provide talented researchers with a supportive environment free of gender bias, but the gender gap in science, especially in math-intensive fields such as computer science, persists. To bring more talented women into research and keep them there, we need to highlight role models to spark their interest, and we need to ensure that female scientists are not kept at lower levels but are given the opportunity to lead the field. Here we showcase the work of the EVBC and highlight the achievements of some outstanding women experts in virology and viral bioinformatics.

PHIAF: prediction of phage-host interactions with GAN-based data augmentation and sequence-based feature fusion

Phage therapy has become one of the most promising alternatives to antibiotics in the treatment of bacterial diseases, and identifying phage-host interactions (PHIs) helps to understand the possible mechanism through which a phage infects bacteria to guide the development of phage therapy. Compared with wet experiments, computational methods of identifying PHIs can reduce costs and save time and are more effective and economic. In this paper, we propose a PHI prediction method with a generative adversarial network (GAN)-based data augmentation and sequence-based feature fusion (PHIAF). First, PHIAF applies a GAN-based data augmentation module, which generates pseudo PHIs to alleviate the data scarcity. Second, PHIAF fuses the features originated from DNA and protein sequences for better performance. Third, PHIAF utilizes an attention mechanism to consider different contributions of DNA/protein sequence-derived features, which also provides interpretability of the prediction model. In computational experiments, PHIAF outperforms other state-of-the-art PHI prediction methods when evaluated via 5-fold cross-validation (AUC and AUPR are 0.88 and 0.86, respectively). An ablation study shows that data augmentation, feature fusion and an attention mechanism are all beneficial to improve the prediction performance of PHIAF. Additionally, four new PHIs with the highest PHIAF score in the case study were verified by recent literature. In conclusion, PHIAF is a promising tool to accelerate the exploration of phage therapy.

Predicting hosts based on early SARS-CoV-2 samples and analyzing the 2020 pandemic

The SARS-CoV-2 pandemic has raised concerns in the identification of the hosts of the virus since the early stages of the outbreak. To address this problem, we proposed a deep learning method, DeepHoF, based on extracting viral genomic features automatically, to predict the host likelihood scores on five host types, including plant, germ, invertebrate, non-human vertebrate and human, for novel viruses. DeepHoF made up for the lack of an accurate tool, reaching a satisfactory AUC of 0.975 in the five-classification, and could make a reliable prediction for the novel viruses without close neighbors in phylogeny. Additionally, to fill the gap in the efficient inference of host species for SARS-CoV-2 using existing tools, we conducted a deep analysis on the host likelihood profile calculated by DeepHoF. Using the isolates sequenced in the earliest stage of the COVID-19 pandemic, we inferred that minks, bats, dogs and cats were potential hosts of SARS-CoV-2, while minks might be one of the most noteworthy hosts. Several genes of SARS-CoV-2 demonstrated their significance in determining the host range. Furthermore, a large-scale genome analysis, based on DeepHoF's computation for the later pandemic in 2020, disclosed the uniformity of host range among SARS-CoV-2 samples and the strong association of SARS-CoV-2 between humans and minks.

Machine Learning and Artificial Intelligence for the Prediction of Host-Pathogen Interactions: A Viral Case

The research of interactions between the pathogens and their hosts is key for understanding the biology of infection. Commencing on the level of individual molecules, these interactions define the behavior of infectious agents and the outcomes they elicit. Discovery of host-pathogen interactions (HPIs) conventionally involves a stepwise laborious research process. Yet, amid the global pandemic the urge for rapid discovery acceleration through the novel computational methodologies has become ever so poignant. This review explores the challenges of HPI discovery and investigates the efforts currently undertaken to apply the latest machine learning (ML) and artificial intelligence (AI) methodologies to this field. This includes applications to molecular and genetic data, as well as image and language data. Furthermore, a number of breakthroughs, obstacles, along with prospects of AI for host-pathogen interactions (HPI), are discussed.

Global overview and major challenges of host prediction methods for uncultivated phages

Bacterial communities play critical roles across all of Earth's biomes, affecting human health and global ecosystem functioning. They do so under strong constraints exerted by viruses, that is, bacteriophages or 'phages'. Phages can reshape bacterial communities' structure, influence long-term evolution of bacterial populations, and alter host cell metabolism during infection. Metagenomics approaches, that is, shotgun sequencing of environmental DNA or RNA, recently enabled large-scale exploration of phage genomic diversity, yielding several millions of phage genomes now to be further analyzed and characterized. One major challenge however is the lack of direct host information for these phages. Several methods and tools have been proposed to bioinformatically predict the potential host(s) of uncultivated phages based only on genome sequence information. Here we review these different approaches and highlight their distinct strengths and limitations. We also outline complementary experimental assays which are being proposed to validate and refine these bioinformatic predictions.

Interpretable detection of novel human viruses from genome sequencing data

Viruses evolve extremely quickly, so reliable methods for viral host prediction are necessary to safeguard biosecurity and biosafety alike. Novel human-infecting viruses are difficult to detect with standard bioinformatics workflows. Here, we predict whether a virus can infect humans directly from next-generation sequencing reads. We show that deep neural architectures significantly outperform both shallow machine learning and standard, homology-based algorithms, cutting the error rates in half and generalizing to taxonomic units distant from those presented during training. Further, we develop a suite of interpretability tools and show that it can be applied also to other models beyond the host prediction task. We propose a new approach for convolutional filter visualization to disentangle the information content of each nucleotide from its contribution to the final classification decision. Nucleotide-resolution maps of the learned associations between pathogen genomes and the infectious phenotype can be used to detect regions of interest in novel agents, for example, the SARS-CoV-2 coronavirus, unknown before it caused a COVID-19 pandemic in 2020. All methods presented here are implemented as easy-to-install packages not only enabling analysis of NGS datasets without requiring any deep learning skills, but also allowing advanced users to easily train and explain new models for genomics.