Prediction of protein secondary structure by the improved TCN-BiLSTM-MHA model with knowledge distillation.

Secondary structure prediction is a key step in understanding protein function and biological properties and is highly important in the fields of new drug development, disease treatment, bioengineering, etc. Accurately predicting the secondary structure of proteins helps to reveal how proteins are folded and how they function in cells. The application of deep learning models in protein structure prediction is particularly important because of their ability to process complex sequence information and extract meaningful patterns and features, thus significantly improving the accuracy and efficiency of prediction. In this study, a combined model integrating an improved temporal convolutional network (TCN), bidirectional long short-term memory (BiLSTM), and a multi-head attention (MHA) mechanism is proposed to enhance the accuracy of protein prediction in both eight-state and three-state structures. One-hot encoding features and word vector representations of physicochemical properties are incorporated. A significant emphasis is placed on knowledge distillation techniques utilizing the ProtT5 pretrained model, leading to performance improvements. The improved TCN, achieved through multiscale fusion and bidirectional operations, allows for better extraction of amino acid sequence features than traditional TCN models. The model demonstrated excellent prediction performance on multiple datasets. For the TS115, CB513 and PDB (2018-2020) datasets, the prediction accuracy of the eight-state structure of the six datasets in this paper reached 88.2%, 84.9%, and 95.3%, respectively, and the prediction accuracy of the three-state structure reached 91.3%, 90.3%, and 96.8%, respectively. This study not only improves the accuracy of protein secondary structure prediction but also provides an important tool for understanding protein structure and function, which is particularly applicable to resource-constrained contexts and provides a valuable tool for understanding protein structure and function.

Functional analyses of the NRT2 family of nitrate transporters in Arabidopsis.

Nitrogen is an essential macronutrient for plant growth and development. Nitrate is the major form of nitrogen acquired by most crops and also serves as a vital signaling molecule. Nitrate is absorbed from the soil into root cells usually by the low-affinity NRT1 NO3 - transporters and high-affinity NRT2 NO3 - transporters, with NRT2s serving to absorb NO3 - under NO3 -limiting conditions. Seven NRT2 members have been identified in Arabidopsis, and they have been shown to be involved in various biological processes. In this review, we summarize the spatiotemporal expression patterns, localization, and biotic and abiotic responses of these transporters with a focus on recent advances in the current understanding of the functions of the seven AtNRT2 genes. This review offers beneficial insight into the mechanisms by which plants adapt to changing environmental conditions and provides a theoretical basis for crop research in the near future.

Prediction of soil moisture using BiGRU-LSTM model with STL decomposition in Qinghai-Tibet Plateau.

Ali Network data based on the Qinghai-Tibetan Plateau (QTP) can provide representative coverage of the climate and surface hydrometeorological conditions in the cold and arid region of the QTP. Among them, the plateau soil moisture can effectively quantify the uncertainty of coarse resolution satellite and soil moisture models. With the objective of constructing an "end-to-end" soil moisture prediction model for the Tibetan Plateau, a combined prediction model based on time series decomposition and a deep neural network is proposed in this article. The model first performs data preprocessing and seasonal-trend decomposition using loess (STL) to obtain the trend component, seasonal component and random residual component of the original time series in an additive way. Subsequently, the bidirectional gated recurrent unit (BiGRU) is used for the trend component, and the long short-term memory (LSTM) is used for the seasonal and residual components to extract the time series information. The experiments based on the measured data demonstrate that the use of STL decomposition and the combination model can effectively extract the information in soil moisture series using its concise and clear structure. The proposed model in this article has a stable performance improvement of 5-30% over a single model and existing prediction models in different prediction time domains. In long-range prediction, the proposed model also achieves the best accuracy in the shape and temporal domains described by using dynamic time warping (DTW) index and temporal distortion index (TDI). In addition, the generalization performance experiments show that the combined method proposed in this article has strong reference value for time series prediction of natural complex systems.

The Arabidopsis eIF4E1 regulates NRT1.1-mediated nitrate signaling at both translational and transcriptional levels.

Identifying new nitrate regulatory genes and illustrating their mechanisms in modulating nitrate signaling are of great significance for achieving the high yield and nitrogen use efficiency (NUE) of crops. Here, we screened a mutant with defects in nitrate response and mapped the mutation to the gene eIF4E1 in Arabidopsis. Our results showed that eIF4E1 regulated nitrate signaling and metabolism. Ribo-seq and polysome profiling analysis revealed that eIF4E1 modulated the amount of some nitrogen (N)-related mRNAs being translated, especially the mRNA of NRT1.1 was reduced in the eif4e1 mutant. RNA-Seq results enriched some N-related genes, supporting that eIF4E1 is involved in nitrate regulation. The genetic analysis indicated that eIF4E1 worked upstream of NRT1.1 in nitrate signaling. In addition, an eIF4E1-interacting protein GEMIN2 was identified and found to be involved in nitrate signaling. Further investigation showed that overexpression of eIF4E1 promoted plant growth and enhanced yield and NUE. These results demonstrate that eIF4E1 regulates nitrate signaling by modulating NRT1.1 at both translational and transcriptional levels, laying the foundation for future research on the regulation of mineral nutrition at the translational level.

Molecular Regulation of Nitrate Responses in Plants.

Nitrogen is an essential macronutrient that affects plant growth and development. Improving the nitrogen use efficiency of crops is of great importance for the economic and environmental sustainability of agriculture. Nitrate (NO3-) is a major form of nitrogen absorbed by most crops and also serves as a vital signaling molecule. Research has identified key molecular components in nitrate signaling mainly by employing forward and reverse genetics as well as systems biology. In this review, we focus on advances in the characterization of genes involved in primary nitrate responses as well as the long-term effects of nitrate, especially in terms of how nitrate regulates root development.

The Arabidopsis NLP7 gene regulates nitrate signaling via NRT1.1-dependent pathway in the presence of ammonium.

Nitrate is not only an important nutrient but also a signaling molecule for plants. A few of key molecular components involved in primary nitrate responses have been identified mainly by forward and reverse genetics as well as systems biology, however, many underlining mechanisms of nitrate regulation remain unclear. In this study, we show that the expression of NRT1.1, which encodes a nitrate sensor and transporter (also known as CHL1 and NPF6.3), is modulated by NIN-like protein 7 (NLP7). Genetic and molecular analyses indicate that NLP7 works upstream of NRT1.1 in nitrate regulation when NH4+ is present, while in absence of NH4+, it functions in nitrate signaling independently of NRT1.1. Ectopic expression of NRT1.1 in nlp7 resulted in partial or complete restoration of nitrate signaling (expression from nitrate-regulated promoter NRP), nitrate content and nitrate reductase activity in the transgenic lines. Transcriptome analysis revealed that four nitrogen-related clusters including amino acid synthesis-related genes and members of NRT1/PTR family were modulated by both NLP7 and NRT1.1. In addition, ChIP and EMSA assays results indicated that NLP7 may bind to specific regions of the NRT1.1 promoter. Thus, NLP7 acts as an important factor in nitrate signaling via regulating NRT1.1 under NH4+ conditions.

The Arabidopsis CPSF30-L gene plays an essential role in nitrate signaling and regulates the nitrate transceptor gene NRT1.1.

Plants have evolved sophisticated mechanisms to adapt to fluctuating environmental nitrogen availability. However, more underlying genes regulating the response to nitrate have yet to be characterized. We report here the identification of a nitrate regulatory mutant whose mutation mapped to the Cleavage and Polyadenylation Specificity Factor 30 gene (CPSF30-L). In the mutant, induction of nitrate-responsive genes was inhibited independent of the ammonium conditions and was restored by expression of the wild-type 65 kDa encoded by CPSF30-L. Molecular and genetic evidence suggests that CPSF30-L works upstream of NRT1.1 and independently of NLP7 in response to nitrate. Analysis of the 3'-UTR of NRT1.1 showed that the pattern of polyadenylation sites was altered in the cpsf30 mutant. Transcriptome analysis revealed that four nitrogen-related clusters were enriched in the differentially expressed genes of the cpsf30 mutant. Nitrate uptake was decreased in the mutant along with reduced expression of the nitrate transporter/sensor gene NRT1.1, while nitrate reduction and amino acid content were enhanced in roots along with increased expression of several nitrate assimilatory genes. These findings indicate that the 65 kDa protein encoded by CPSF30-L mediates nitrate signaling in part by regulating NRT1.1 expression, thus adding an important component to the nitrate signaling network.

Nitrate Assay for Plant Tissues.

Nitrogen is an essential macronutrient for plant growth and nitrate content in plants can reflect the nitrogen supply of soil. Here, we provide the salicylic acid method to evaluate the nitrate content in plant tissues. The method is reliable and stable, thus it can be a good choice for measurement of nitrate in plant tissues.

The Arabidopsis NRG2 Protein Mediates Nitrate Signaling and Interacts with and Regulates Key Nitrate Regulators.

We show that NITRATE REGULATORY GENE2 (NRG2), which we identified using forward genetics, mediates nitrate signaling in Arabidopsis thaliana. A mutation in NRG2 disrupted the induction of nitrate-responsive genes after nitrate treatment by an ammonium-independent mechanism. The nitrate content in roots was lower in the mutants than in the wild type, which may have resulted from reduced expression of NRT1.1 (also called NPF6.3, encoding a nitrate transporter/receptor) and upregulation of NRT1.8 (also called NPF7.2, encoding a xylem nitrate transporter). Genetic and molecular data suggest that NRG2 functions upstream of NRT1.1 in nitrate signaling. Furthermore, NRG2 directly interacts with the nitrate regulator NLP7 in the nucleus, but nuclear retention of NLP7 in response to nitrate is not dependent on NRG2. Transcriptomic analysis revealed that genes involved in four nitrogen-related clusters including nitrate transport and response to nitrate were differentially expressed in the nrg2 mutants. A nitrogen compound transport cluster containing some members of the NRT/PTR family was regulated by both NRG2 and NRT1.1, while no nitrogen-related clusters showed regulation by both NRG2 and NLP7. Thus, NRG2 plays a key role in nitrate regulation in part through modulating NRT1.1 expression and may function with NLP7 via their physical interaction.