Search

Timely and accurate prediction of winter wheat yields, which is crucial for optimizing production management, maintaining supply–demand balance, and ensuring food security, depends on interactions among numerous factors, such as climate, surface characteristics, and soil quality. Despite the extensive application of deep learning models in this field, few studies have analyzed the effect of the large-scale geospatial characteristics of neighboring regions on crop yields. Therefore, we present an attention-based spatio-temporal Graph Neural Network (ASTGNN) model coupled with geospatial characteristics and multi-source data for improved accuracy of winter wheat yield estimation. The datasets used in this study included multiple types of remote sensing, meteorological, soil, crop yield, and planting area data for Anhui, China, from 2005 to 2020. The results showed that multi-source data led to higher prediction performance than single-source data, and enabled accurate prediction of winter wheat yields three months prior to harvest. Furthermore, the ASTGNN model provided better prediction performance than two traditional crop yield prediction models (R2 = 0.70, RMSE = 0.21 t/ha, MAE = 0.17 t/ha). Therefore, ASTGNN enhances the accuracy of crop yield prediction by incorporating geospatial characteristics. This research has implications for improving agricultural production management, promoting the development of digital agriculture, and addressing climate change in agriculture. [ABSTRACT FROM AUTHOR]

We report new data on non-indigenous invertebrates from the Mediterranean Sea (four ostracods and 20 molluscs), including five new records for the basin: the ostracods Neomonoceratina iniqua, Neomonoceratina aff. mediterranea, Neomonoceratina cf. entomon, Loxoconcha cf. gisellae (Arthropoda: Crustacea)–the first records of non-indigenous ostracods in the Mediterranean–and the bivalve Striarca aff. symmetrica (Mollusca). Additionally, we report for the first time Electroma vexillum from Israel, and Euthymella colzumensis, Joculator problematicus, Hemiliostraca clandestina, Pyrgulina nana, Pyrgulina microtuber, Turbonilla cangeyrani, Musculus aff. viridulus and Isognomon bicolor from Cyprus. We also report the second record of Fossarus sp. and of Cerithiopsis sp. cf. pulvis in the Mediterranean Sea, the first live collected specimens of Oscilla galilae from Cyprus and the northernmost record of Gari pallida in Israel (and the Mediterranean). Moreover, we report the earliest records of Rugalucina angela, Ervilia scaliola and Alveinus miliaceus in the Mediterranean Sea, backdating their first occurrence in the basin by 3, 5 and 7 years, respectively. We provide new data on the presence of Spondylus nicobaricus and Nudiscintilla aff. glabra in Israel. Finally, yet importantly, we use both morphological and molecular approaches to revise the systematics of the non-indigenous genus Isognomon in the Mediterranean Sea, showing that two species currently co-occur in the basin: the Caribbean I. bicolor, distributed in the central and eastern Mediterranean, and the Indo-Pacific I. aff. legumen, at present reported only from the eastern Mediterranean and whose identity requires a more in-depth taxonomic study. Our work shows the need of taxonomic expertise and investigation, the necessity to avoid the unfounded sense of confidence given by names in closed nomenclature when the NIS belong to taxa that have not enjoyed ample taxonomic work, and the necessity to continue collecting samples–rather than relying on visual censuses and bio-blitzes–to enable accurate detection of non-indigenous species. [ABSTRACT FROM AUTHOR]

Background: DNA‐based next‐generation sequencing has been widely used in the selection of target therapies for patients with nonsmall cell lung cancer (NSCLC). RNA‐based next‐generation sequencing has been proven to be valuable in detecting fusion and exon‐skipping mutations and is recommended by National Comprehensive Cancer Network guidelines for these mutation types. Methods: The authors developed an RNA‐based hybridization panel targeting actionable driver oncogenes in solid tumors. Experimental and bioinformatics pipelines were optimized for the detection of fusions, single‐nucleotide variants (SNVs), and insertion/deletion (indels). In total, 1253 formalin‐fixed, paraffin‐embedded samples from patients with NSCLC were analyzed by DNA and RNA panel sequencing in parallel to assess the performance of the RNA panel in detecting multiple types of mutations. Results: In analytical validation, the RNA panel achieved a limit of detection of 1.45–3.15 copies per nanogram for SNVs and 0.21–6.48 copies per nanogram for fusions. In 1253 formalin‐fixed, paraffin‐embedded NSCLC samples, the RNA panel identified a total of 124 fusion events and 26 MET exon 14‐skipping events, in which 14 fusions and six MET exon 14‐skipping mutations were missed by DNA panel sequencing. By using the DNA panel as the reference, the positive percent agreement and the positive predictive value of the RNA panel were 98.08% and 98.62%, respectively, for detecting targetable SNVs and 98.15% and 99.38%, respectively, for detecting targetable indels. Conclusions: Parallel DNA and RNA sequencing analyses demonstrated the accuracy and robustness of the RNA sequencing panel in detecting multiple types of clinically actionable mutations. The simplified experimental workflow and low sample consumption will make RNA panel sequencing a potentially effective method in clinical testing. RNA panel sequencing was capable of detecting multiple types of clinically actionable mutations with high accuracy. This simplified experimental method was proven in 1253 formalin‐fixed, paraffin‐embedded non–small cell lung cancer samples. [ABSTRACT FROM AUTHOR]