Analysis of Emerging Variants of Turkey Reovirus using Machine Learning.

Avian reoviruses continue to cause disease in turkeys with varied pathogenicity and tissue tropism. Turkey enteric reovirus has been identified as a causative agent of enteritis or inapparent infections in turkeys. The new emerging variants of turkey reovirus, tentatively named turkey arthritis reovirus (TARV) and turkey hepatitis reovirus (THRV), are linked to tenosynovitis/arthritis and hepatitis, respectively. Turkey arthritis and hepatitis reoviruses are causing significant economic losses to the turkey industry. These infections can lead to poor weight gain, uneven growth, poor feed conversion, increased morbidity and mortality and reduced marketability of commercial turkeys. To combat these issues, detecting and classifying the types of reoviruses in turkey populations is essential. This research aims to employ clustering methods, specifically K-means and Hierarchical clustering, to differentiate three types of turkey reoviruses and identify novel emerging variants. Additionally, it focuses on classifying variants of turkey reoviruses by leveraging various machine learning algorithms such as Support Vector Machines, Naive Bayes, Random Forest, Decision Tree, and deep learning algorithms, including convolutional neural networks (CNNs). The experiments use real turkey reovirus sequence data, allowing for robust analysis and evaluation of the proposed methods. The results indicate that machine learning methods achieve an average accuracy of 92%, F1-Macro of 93% and F1-Weighted of 92% scores in classifying reovirus types. In contrast, the CNN model demonstrates an average accuracy of 85%, F1-Macro of 71% and F1-Weighted of 84% scores in the same classification task. The superior performance of the machine learning classifiers provides valuable insights into reovirus evolution and mutation, aiding in detecting emerging variants of pathogenic TARVs and THRVs.

Embolic necrosuppurative pneumonia in domestic cats induced by a novel Neisseria species.

Three cats, aged 2 to 11 years, presented to the University of Minnesota Veterinary Diagnostic Laboratory over a 3-year period following euthanasia or death due to respiratory distress. Thoracic radiographs revealed nodular, soft tissue opacities throughout the lung fields in all cases. On postmortem examination, approximately 60% to 80% of the lung parenchyma were expanded by multifocal to coalescing, well-demarcated, beige, semi-firm nodules. Histologically, large numbers of neutrophils, fewer macrophages, fibrin, and cellular and karyorrhectic debris effaced the pulmonary parenchyma. The inflammatory foci contained aggregates of gram-negative cocci. 16s rRNA Sanger sequencing and whole-genome sequencing identified the bacteria isolated from the lung of all cats under aerobic conditions as a novel Neisseria spp. Based on whole-genome sequence analysis, all 3 sequences shared 92.71% and 92.67% average nucleotide identity with closely related Neisseria animaloris NZ LR134440T and Neisseria animaloris GCA 002108605T, respectively. The in silico DNA-DNA hybridization identity compared to our isolates was 46.6% and 33.8% with strain DSM Neisseria zoodegmatis 21642 and strain DSM 21643, respectively. All 3 sequences have less than 95% average nucleotide identity and less than 70% DNA-DNA hybridization identity, suggesting that the 3 isolates are a novel species of the genus Neisseria. Infection with Neisseria spp. induces an embolic pneumonia in cats that radiographically and pathologically resembles a metastatic neoplastic process and should be considered among the etiologic differential diagnoses in cases of infectious pulmonary disease with a disseminated, nodular lung pattern.