Vertical distribution of Candidatus Methylomirabilis and Methanoperedens in agricultural soils.

Candidatus Methylomirabilis-related bacteria conduct anaerobic oxidation of methane (AOM) coupling with NO2- reduction, and Candidatus Methanoperedens-related archaea perform AOM coupling with reduction of diverse electron acceptors, including NO3-, Fe (III), Mn (IV) and SO42-. Application of nitrogen fertilization favors the growth of these methanotrophs in agricultural fields. Here, we explored the vertical variations in community structure and abundance of the two groups of methanotrophs in a nitrogen-rich vegetable field via using illumina MiSeq sequencing and quantitative PCR. The retrieved Methylomirabilis-related sequences had 91.12%-97.32% identity to the genomes of known Methylomirabilis species, and Methanoperedens-related sequences showed 85.49%-97.48% identity to the genomes of known Methanoperedens species which are capable of conducting AOM coupling with reduction of NO3- or Fe (III). The Methanoperedens-related archaeal diversity was significantly higher than Methylomirabilis-related bacteria, with totally 74 and 16 operational taxonomic units, respectively. In contrast, no significant difference in abundance between the bacteria (9.19 × 103-3.83 × 105 copies g-1 dry soil) and the archaea (1.55 × 104-3.24 × 105 copies g-1 dry soil) was observed. Furthermore, the abundance of both groups of methanotrophs exhibited a strong vertical variation, which peaked at 30-40 and 20-30 cm layers, respectively. Soil water content and pH were the key factors influencing Methylomirabilis-related bacterial diversity and abundance, respectively. For the Methanoperedens-related archaea, both soil pH and ammonium content contributed significantly to the changes of these archaeal diversity and abundance. Overall, we provide the first insights into the vertical distribution and regulation of Methylomirabilis-related bacteria and Methanoperedens-related archaea in vegetable soils. KEY POINTS: • The archaeal diversity was significantly higher than bacterial. • There was no significant difference in the abundance between bacteria and archaea. • The abundance of bacteria and archaea peaked at 30-40 and 20-30 cm, respectively.

Eggshell biometrics for individual egg identification based on convolutional neural networks.

Individual egg identification technology has potential applications in breeding, product tracking/tracing, and anti-counterfeit. This study developed a novel method for individual egg identification based on eggshell images. A convolutional neural network-based model, named Eggshell Biometric Identification (EBI) model, was proposed and evaluated. The main workflow included eggshell biometric feature extraction, egg information registration, and egg identification. The image dataset of individual eggshell was collected from the blunt-end region of 770 chicken eggs using an image acquisition platform. The ResNeXt network was then trained as a texture feature extraction module to obtain sufficient eggshell texture features. The EBI model was applied to a test set of 1,540 images. The testing results showed that when an appropriate Euclidean distance threshold for classification was set (17.18), the correct recognition rate and the equal error rate reached 99.96% and 0.02%. This new method provides an efficient and accurate solution for individual chicken egg identification, and can be extended to eggs of other poultry species for product tracking/tracing and anti-counterfeit.

Spatio-temporal variations of activity of nitrate-driven anaerobic oxidation of methane and community structure of Candidatus Methanoperedens-like archaea in sediment of Wuxijiang river.

Nitrate-driven anaerobic oxidation of methane (AOM), catalyzing by Candidatus Methanoperedens-like archaea, is a new addition in the global CH4 cycle. This AOM process acts as a novel pathway for CH4 emission reduction in freshwater aquatic ecosystems; however, its quantitative importance and regulatory factors in riverine ecosystems are nearly unknown. Here, we examined the spatio-temporal changes of the communities of Methanoperedens-like archaea and nitrate-driven AOM activity in sediment of Wuxijiang River, a mountainous river in China. These archaeal community composition varied significantly among reaches (upper, middle, and lower reaches) and between seasons (winter and summer), but their mcrA gene diversity showed no significant spatial or temporal variations. The copy numbers of Methanoperedens-like archaeal mcrA genes were 1.32 × 105-2.47 × 107 copies g-1 (dry weight), and the activity of nitrate-driven AOM was 0.25-1.73 nmol CH4 g-1 (dry weight) d-1, which could potentially reduce 10.3% of CH4 emissions from rivers. Significant spatio-temporal variations of mcrA gene abundance and nitrate-driven AOM activity were found. Both the gene abundance and activity increased significantly from upper to lower reaches in both seasons, and were significantly higher in sediment collected in summer than in winter. In addition, the variations of Methanoperedens-like archaeal communities and nitrate-driven AOM activity were largely impacted by the sediment temperature, NH4+ and organic carbon contents. Taken together, both time and space scales need to be considered for better evaluating the quantitative importance of nitrate-driven AOM in reducing CH4 emissions from riverine ecosystems.

A reliable and low-cost deep learning model integrating convolutional neural network and transformer structure for fine-grained classification of chicken Eimeria species.

Chicken coccidiosis is a disease caused by Eimeria spp. and costs the broiler industry more than 14 billion dollars per year globally. Different chicken Eimeria species vary significantly in pathogenicity and virulence, so the classification of different chicken Eimeria species is of great significance for the epidemiological survey and related prevention and control. The microscopic morphological examination for their classification was widely used in clinical applications, but it is a time-consuming task and needs expertise. To increase the classification efficiency and accuracy, a novel model integrating transformer and convolutional neural network (CNN), named Residual-Transformer-Fine-Grained (ResTFG), was proposed and evaluated for fine-grained classification of microscopic images of seven chicken Eimeria species. The results showed that ResTFG achieved the best performance with high accuracy and low cost compared with traditional models. Specifically, the parameters, inference speed and overall accuracy of ResTFG are 1.95M, 256 FPS and 96.9%, respectively, which are 10.9 times lighter, 1.5 times faster and 2.7% higher in accuracy than the benchmark model. In addition, ResTFG showed better performance on the classification of the more virulent species. The results of ablation experiments showed that CNN or Transformer alone had model accuracies of only 89.8% and 87.0%, which proved that the improved performance of ResTFG was benefit from the complementary effect of CNN's local feature extraction and transformer's global receptive field. This study invented a reliable, low-cost, and promising deep learning model for the automatic fine-grain classification of chicken Eimeria species, which could potentially be embedded in microscopic devices to improve the work efficiency of researchers and extended to other parasite ova, and applied to other agricultural tasks as a backbone.

In vivo prediction of abdominal fat and breast muscle in broiler chicken using live body measurements based on machine learning.

The purpose of this study was to predict the carcass characteristics of broilers using support vector regression (SVR) and artificial neural network (ANN) model methods. Data were obtained from 176 yellow feather broilers aged 100-day-old (90 males and 86 females). The input variables were live body measurements, including external measurements and B-ultrasound measurements. The predictors of the model were the weight of abdominal fat and breast muscle in male and female broilers, respectively. After descriptive statistics and correlation analysis, the datasets were randomly divided into train set and test set according to the ratio of 7:3 to establish the model. The results of this study demonstrated that it is feasible to use machine learning methods to predict carcass characteristics of broilers based on live body measurements. Compared with the ANN method, the SVR method achieved better prediction results, for predicting breast muscle (male: R2 = 0.950; female: R2 = 0.955) and abdominal fat (male: R2 = 0.802; female: R2 = 0.944) in the test set. Consequently, the SVR method can be considered to predict breast muscle and abdominal fat of broiler chickens, except for abdominal fat in male broilers. However, further revaluation of the SVR method is suggested.

Spatial variations of activity and community structure of nitrite-dependent anaerobic methanotrophs in river sediment.

Rivers are an important site for methane emissions and reactive nitrogen removal. The process of nitrite-dependent anaerobic methane oxidation (n-damo) links the global carbon cycle and the nitrogen cycle, but its role in methane mitigation and nitrogen removal in rivers is poorly known. In the present study, we investigated the activity, abundance, and community composition of n-damo bacteria in sediment of the upper, middle, and lower reaches of Wuxijiang River (Zhejiang Province, China). The 13CH4 stable isotope experiments showed that the methane oxidation activity of n-damo was 0.11-1.88 nmol CO2 g-1 (dry sediment) d-1, and the activity measured from the middle reaches was significantly higher than that from the remaining regions. It was estimated that 3.27 g CH4 m-2 year-1 and 8.72 g N m-2 year-1 could be consumed via n-damo. Quantitative PCR confirmed the presence of n-damo bacteria, and their 16S rRNA gene abundance varied between 5.45 × 105 and 5.86 × 106 copies g-1 dry sediment. Similarly, the abundance of n-damo bacteria was significantly higher in the middle reaches. High-throughput sequencing showed a high n-damo bacterial diversity, with totally 152 operational taxonomic units being detected at 97 % sequence similarity cut-off. In addition, the n-damo bacterial community composition also varied spatially. The inorganic nitrogen (NH4+, NO2-, NO3-) level was found to be the key environmental factor controlling the n-damo activity and bacterial community composition. Overall, our results showed the spatial variations and environmental regulation of the activity and community structure of n-damo bacteria in river sediment, which expanded our understanding of the quantitative importance of n-damo in both methane oxidation and reactive nitrogen removal in riverine systems.