PREDAC-CNN: predicting antigenic clusters of seasonal influenza A viruses with convolutional neural network.

Vaccination stands as the most effective and economical strategy for prevention and control of influenza. The primary target of neutralizing antibodies is the surface antigen hemagglutinin (HA). However, ongoing mutations in the HA sequence result in antigenic drift. The success of a vaccine is contingent on its antigenic congruence with circulating strains. Thus, predicting antigenic variants and deducing antigenic clusters of influenza viruses are pivotal for recommendation of vaccine strains. The antigenicity of influenza A viruses is determined by the interplay of amino acids in the HA1 sequence. In this study, we exploit the ability of convolutional neural networks (CNNs) to extract spatial feature representations in the convolutional layers, which can discern interactions between amino acid sites. We introduce PREDAC-CNN, a model designed to track antigenic evolution of seasonal influenza A viruses. Accessible at http://predac-cnn.cloudna.cn, PREDAC-CNN formulates a spatially oriented representation of the HA1 sequence, optimized for the convolutional framework. It effectively probes interactions among amino acid sites in the HA1 sequence. Also, PREDAC-CNN focuses exclusively on physicochemical attributes crucial for the antigenicity of influenza viruses, thereby eliminating unnecessary amino acid embeddings. Together, PREDAC-CNN is adept at capturing interactions of amino acid sites within the HA1 sequence and examining the collective impact of point mutations on antigenic variation. Through 5-fold cross-validation and retrospective testing, PREDAC-CNN has shown superior performance in predicting antigenic variants compared to its counterparts. Additionally, PREDAC-CNN has been instrumental in identifying predominant antigenic clusters for A/H3N2 (1968-2023) and A/H1N1 (1977-2023) viruses, significantly aiding in vaccine strain recommendation.

Characterizing the antigenic evolution of pandemic influenza A (H1N1) pdm09 from 2009 to 2023.

The H1N1pdm09 virus has been a persistent threat to public health since the 2009 pandemic. Particularly, since the relaxation of COVID-19 pandemic mitigation measures, the influenza virus and SARS-CoV-2 have been concurrently prevalent worldwide. To determine the antigenic evolution pattern of H1N1pdm09 and develop preventive countermeasures, we collected influenza sequence data and immunological data to establish a new antigenic evolution analysis framework. A machine learning model (XGBoost, accuracy = 0.86, area under the receiver operating characteristic curve = 0.89) was constructed using epitopes, physicochemical properties, receptor binding sites, and glycosylation sites as features to predict the antigenic similarity relationships between influenza strains. An antigenic correlation network was constructed, and the Markov clustering algorithm was used to identify antigenic clusters. Subsequently, the antigenic evolution pattern of H1N1pdm09 was analyzed at the global and regional scales across three continents. We found that H1N1pdm09 evolved into around five antigenic clusters between 2009 and 2023 and that their antigenic evolution trajectories were characterized by cocirculation of multiple clusters, low-level persistence of former dominant clusters, and local heterogeneity of cluster circulations. Furthermore, compared with the seasonal H1N1 virus, the potential cluster-transition determining sites of H1N1pdm09 were restricted to epitopes Sa and Sb. This study demonstrated the effectiveness of machine learning methods for characterizing antigenic evolution of viruses, developed a specific model to rapidly identify H1N1pdm09 antigenic variants, and elucidated their evolutionary patterns. Our findings may provide valuable support for the implementation of effective surveillance strategies and targeted prevention efforts to mitigate the impact of H1N1pdm09.

Transmission restriction and genomic evolution co-shape the genetic diversity patterns of influenza A virus.

Influenza A virus (IAV) shows an extensive host range and rapid genomic variations, leading to continuous emergence of novel viruses with significant antigenic variations and the potential for cross-species transmission. This causes global pandemics and seasonal flu outbreaks, posing sustained threats worldwide. Thus, studying all IAVs' evolutionary patterns and underlying mechanisms is crucial for effective prevention and control. We developed FluTyping to identify IAV genotypes, to explore overall genetic diversity patterns and their restriction factors. FluTyping groups isolates based on genetic distance and phylogenetic relationships using entire genomes, enabling identification of each isolate's genotype. Three distinct genetic diversity patterns were observed: one genotype domination pattern comprising only H1N1 and H3N2 seasonal influenza subtypes, multi-genotypes co-circulation pattern including majority avian influenza subtypes and swine influenza H1N2, and hybrid-circulation pattern involving H7N9 and three H5 subtypes of influenza viruses. Furthermore, the IAVs in multi-genotypes co-circulation pattern showed region-specific dominant genotypes, implying the restriction of virus transmission is a key factor contributing to distinct genetic diversity patterns, and the genomic evolution underlying different patterns showed more influenced by host-specific factors. In summary, a comprehensive picture of the evolutionary patterns of overall IAVs is provided by the FluTyping's identified genotypes, offering important theoretical foundations for future prevention and control of these viruses.

Global antigenic landscape and vaccine recommendation strategy for low pathogenic avian influenza A (H9N2) viruses.

The sustained circulation of H9N2 avian influenza viruses (AIVs) poses a significant threat for contributing to a new pandemic. Given the temporal and spatial uncertainty in the antigenicity of H9N2 AIVs, the immune protection efficiency of vaccines remains challenging. By developing an antigenicity prediction method for H9N2 AIVs, named PREDAC-H9, the global antigenic landscape of H9N2 AIVs was mapped. PREDAC-H9 utilizes the XGBoost model with 14 well-designed features. The XGBoost model was built and evaluated to predict the antigenic relationship between any two viruses with high values of 81.1 %, 81.4 %, 81.3 %, 81.1 %, and 89.4 % in accuracy, precision, recall, F1 value, and area under curve (AUC), respectively. Then the antigenic correlation network (ACnet) was constructed based on the predicted antigenic relationship for H9N2 AIVs from 1966 to 2022, and ten major antigenic clusters were identified. Of these, four novel clusters were generated in China in the past decade, demonstrating the unique complex situation there. To help tackle this situation, we applied PREDAC-H9 to calculate the cluster-transition determining sites and screen out virus strains with the high cross-protective spectrum, thus providing an in silico reference for vaccine recommendation. The proposed model will reduce the clinical monitoring workload and provide a useful tool for surveillance and control of H9N2 AIVs.

A Cullin 5-based complex serves as an essential modulator of ORF9b stability in SARS-CoV-2 replication.

The ORF9b protein, derived from the nucleocapsid's open-reading frame in both SARS-CoV and SARS-CoV-2, serves as an accessory protein crucial for viral immune evasion by inhibiting the innate immune response. Despite its significance, the precise regulatory mechanisms underlying its function remain elusive. In the present study, we unveil that the ORF9b protein of SARS-CoV-2, including emerging mutant strains like Delta and Omicron, can undergo ubiquitination at the K67 site and subsequent degradation via the proteasome pathway, despite certain mutations present among these strains. Moreover, our investigation further uncovers the pivotal role of the translocase of the outer mitochondrial membrane 70 (TOM70) as a substrate receptor, bridging ORF9b with heat shock protein 90 alpha (HSP90α) and Cullin 5 (CUL5) to form a complex. Within this complex, CUL5 triggers the ubiquitination and degradation of ORF9b, acting as a host antiviral factor, while HSP90α functions to stabilize it. Notably, treatment with HSP90 inhibitors such as GA or 17-AAG accelerates the degradation of ORF9b, leading to a pronounced inhibition of SARS-CoV-2 replication. Single-cell sequencing data revealed an up-regulation of HSP90α in lung epithelial cells from COVID-19 patients, suggesting a potential mechanism by which SARS-CoV-2 may exploit HSP90α to evade the host immunity. Our study identifies the CUL5-TOM70-HSP90α complex as a critical regulator of ORF9b protein stability, shedding light on the intricate host-virus immune response dynamics and offering promising avenues for drug development against SARS-CoV-2 in clinical settings.

Mapping Chinese Medical Entities to the Unified Medical Language System.

Background: Chinese medical entities have not been organized comprehensively due to the lack of well-developed terminology systems, which poses a challenge to processing Chinese medical texts for fine-grained medical knowledge representation. To unify Chinese medical terminologies, mapping Chinese medical entities to their English counterparts in the Unified Medical Language System (UMLS) is an efficient solution. However, their mappings have not been investigated sufficiently in former research. In this study, we explore strategies for mapping Chinese medical entities to the UMLS and systematically evaluate the mapping performance. Methods: First, Chinese medical entities are translated to English using multiple web-based translation engines. Then, 3 mapping strategies are investigated: (a) string-based, (b) semantic-based, and (c) string and semantic similarity combined. In addition, cross-lingual pretrained language models are applied to map Chinese medical entities to UMLS concepts without translation. All of these strategies are evaluated on the ICD10-CN, Chinese Human Phenotype Ontology (CHPO), and RealWorld datasets. Results: The linear combination method based on the SapBERT and term frequency-inverse document frequency bag-of-words models perform the best on all evaluation datasets, with 91.85%, 82.44%, and 78.43% of the top 5 accuracies on the ICD10-CN, CHPO, and RealWorld datasets, respectively. Conclusions: In our study, we explore strategies for mapping Chinese medical entities to the UMLS and identify a satisfactory linear combination method. Our investigation will facilitate Chinese medical entity normalization and inspire research that focuses on Chinese medical ontology development.