Improving influenza surveillance based on multi-granularity deep spatiotemporal neural network

Genotypes and Phylogenetic Analysis of Human Adenovirus in Hospitalized Pneumonia and Influenza-Like Illness Patients in Jiangsu Province, China (2013-2021)

Background

Human adenovirus (HAdV) is common pathogens that cause various respiratory diseases. The genetic diversity of viruses caused by recombination is considered to be the main source of emerging outbreaks. The aim of this study is to explore the evolutionary relationship and recombination events of HAdV genome in respiratory tract infections in Jiangsu Province.

Methods

Whole-genome sequencing (WGS) technology was used to sequence 66 patients with HAdV infection (37 patients with influenza-like illness (ILI) and 29 hospitalized patients with pneumonia) from Jiangsu Province. Epidemiological analysis was performed on hospitalized pneumonia and ILI patients infected with HAdV. Subsequently, phylogenetic, recombination, and nucleotide and amino acid identity analyses were performed.

Results

Epidemiological analysis of patients undergoing WGS showed that 75.7% of ILI patients were infected with the HAdVB strain and 69.0% of hospitalized pneumonia patients were infected with the HAdVC strain. Moreover, the hospitalized pneumonia and ILI patients infected with HAdV were different in region and time. The strains of HAdVB3 and HAdVB7 genotypes were mainly infected in 2015 and 2017, and the strains of HAdVC1 and HAdVC2 genotypes were mainly infected in 2020. The results of histogram analysis showed that the HAdV strain mainly infected children under 5 years old. In addition, 36 novel recombinant strains were identified. The discovery of these recombinant strains may contribute to understanding the epidemiology of HAdV and research on related vaccines. Furthermore, the percentage of nucleotide and amino acid identities revealed a high level of genetic conservation within isolates from HAdVB3, HAdVB7, HAdVC1, HAdVC2 and HAdVC5 genotypes.

Conclusion

The WGS analysis reveals the evolutionary relationships and recombination events of HAdV strains in Jiangsu Province, which is helpful to deepen the understanding of HAdV epidemiology and evolution. In addition, it provides a basis for the formulation of public health strategies in Jiangsu Province.

The epidemic forest reveals the spatial pattern of the spread of acute respiratory infections in Jakarta, Indonesia

Acute respiratory infection (ARI) is a communicable disease of the respiratory tract that implies impaired breathing. The infection can expand from one to the neighboring areas at a region-scale level through a human mobility network. Specific to this study, we leverage a record of ARI incidences in four periods of outbreaks for 42 regions in Jakarta to study its spatio-temporal spread using the concept of the epidemic forest. This framework generates a forest-like graph representing an explicit spread of disease that takes the onset time, spatio-temporal distance, and case prevalence into account. To support this framework, we use logistic curves to infer the onset time of the outbreak for each region. The result shows that regions with earlier onset dates tend to have a higher burden of cases, leading to the idea that the culprits of the disease spread are those with a high load of cases. To justify this, we generate the epidemic forest for the four periods of ARI outbreaks and identify the implied dominant trees (that with the most children cases). We find that the primary infected city of the dominant tree has a relatively higher burden of cases than other trees. In addition, we can investigate the timely ( R t ) and spatial reproduction number ( R c ) by directly evaluating them from the inferred graphs. We find that R t for dominant trees are significantly higher than non-dominant trees across all periods, with regions in western Jakarta tend to have higher values of R c . Lastly, we provide simulated-implied graphs by suppressing 50% load of cases of the primary infected city in the dominant tree that results in a reduced R c , suggesting a potential target of intervention to depress the overall ARI spread.

Graph Polish: A Novel Graph Generation Paradigm for Molecular Optimization

Molecular optimization, which transforms a given input molecule X into another Y with desired properties, is essential in molecular drug discovery. The traditional approaches either suffer from sample-inefficient learning or ignore information that can be captured with the supervised learning of optimized molecule pairs. In this study, we present a novel molecular optimization paradigm, Graph Polish. In this paradigm, with the guidance of the source and target molecule pairs of the desired properties, a heuristic optimization solution can be derived: given an input molecule, we first predict which atom can be viewed as the optimization center, and then the nearby regions are optimized around this center. We then propose an effective and efficient learning framework, Teacher and Student polish, to capture the dependencies in the optimization steps. A teacher component automatically identifies and annotates the optimization centers and the preservation, removal, and addition of some parts of the molecules; a student component learns these knowledges and applies them to a new molecule. The proposed paradigm can offer an intuitive interpretation for the molecular optimization result. Experiments with multiple optimization tasks are conducted on several benchmark datasets. The proposed approach achieves a significant advantage over the six state-of-the-art baseline methods. Also, extensive studies are conducted to validate the effectiveness, explainability, and time savings of the novel optimization paradigm.

Influenza surveillance with Baidu index and attention-based long short-term memory model

BACKGROUND

The prediction and prevention of influenza is a public health issue of great concern, and the study of timely acquisition of influenza transmission trend has become an important research topic. For achieving more quicker and accurate detection and prediction, the data recorded on the Internet, especially on the search engine from Google or Baidu are widely introduced into this field. Moreover, with the development of intelligent technology and machine learning algorithm, many updated and advanced trend tracking and forecasting methods are also being used in this research problem.

METHODS

In this paper, a new recurrent neural network architecture, attention-based long short-term memory model is proposed for influenza surveillance. This is a kind of deep learning model which is trained by processing from Baidu Index series so as to fit the real influenza survey time series. Previous studies on influenza surveillance by Baidu Index mostly used traditional autoregressive moving average model or classical machine learning models such as logarithmic linear regression, support vector regression or multi-layer perception model to fit influenza like illness data, which less considered the deep learning structure. Meanwhile, some new model that considered the deep learning structure did not take into account the application of Baidu index data. This study considers introducing the recurrent neural network with long short-term memory combined with attention mechanism into the influenza surveillance research model, which not only fits the research problems well in model structure, but also provides research methods based on Baidu index.

RESULTS

The actual survey data and Baidu Index data are used to train and test the proposed attention-based long short-term memory model and the other comparison models, so as to iterate the value of the model parameters, and to describe and predict the influenza epidemic situation. The experimental results show that our proposed model has better performance in the mean absolute error, mean absolute percentage error, index of agreement and other indicators than the other comparison models.

CONCLUSION

Our proposed attention-based long short-term memory model vividly verifies the ability of this attention-based long short-term memory structure for better surveillance and prediction the trend of influenza. In comparison with some of the latest models and methods in this research field, the model we proposed is also excellent in effect, even more lightweight and robust. Future research direction can consider fusing multimodal data based on this model and developing more application scenarios.

Deep Neural Networks for Optimal Selection of Features Related to Flu

In recent times, humans who have been exposed to influenza A viruses (IAV) may not become hostile. Despite the fact that KLRD1 has been discovered as an influenza susceptibility biomarker, it remains to be seen if pre-exposure host gene expression can predict flu symptoms. In this paper, we enable the examination of flu using deep neural networks from input human gene expression datasets with various subtype viruses. This study enables the utilization of these datasets to forecast the spread of flu and can provide the necessary steps to eradicate the flu. The simulation is conducted to test the efficiency of the model in predicting the spread against various input datasets. The results of the simulation show that the proposed method offers a better prediction ability of 2.98% more than other existing methods in finding the spread of flu.

Self-attention-based Deep Learning Network for Regional Influenza Forecasting

Early prediction of influenza plays an important role in minimizing the damage caused, as it provides the resources and time needed to formulate preventive measures. Compared to traditional mechanistic approach, deep/machine learning-based models have demonstrated excellent forecasting performance by efficiently handling various data such as weather and internet data. However, due to the limited availability and reliability of such data, many forecasting models use only historical occurrence data and formulate the influenza forecasting as a multivariate time-series task. Recently, attention mechanisms have been exploited to deal with this issue by selecting valuable data in the input data and giving them high weights. Particularly, self-attention has shown its potential in various forecasting tasks by utilizing the predictive relationship between objects from the input data describing target objects. Hence, in this study, we propose a forecasting model based on self-attention for regional influenza forecasting, called SAIFlu-Net. The model exploits a long short-term memory network for extracting time-series patterns of each region and the self-attention mechanism to find the similarities between the occurrence patterns. To evaluate its performance, we conducted extensive experiments with existing forecasting models using weekly regional influenza datasets. The results show that the proposed model outperforms other models in terms of root mean square error and Pearson correlation coefficient.