Search

The prediction of future data using existing data is an effective tool for regional planning and watershed management. The back propagation neural network （BPNN） and convolutional neural network （CNN） were used to construct a prediction model based on the water quality index of Hengyang in Xiangjiang River Basin from April to May 2022 and the results of permanganate index prediction by different models were compared. The prediction results displayed by BPNN could predict the water quality； however, overfitting occurred during the prediction. BPNN modified by particle swarm optimization （PSO） could avoid overfitting, which improved the parameter selection method of the BPNN mode. The CNN model had a better prediction effect, which had a more complex structure and a more scientific fitting method to avoid the model falling into the local extreme value during the fitting process and improve the accuracy of the model prediction results. The evaluation parameters including root-mean-square error （RMSE）, coefficient of determination （ R 2 ）, and mean absolute error （MAE） were used to predict the accuracy of the network. Compared with that of the traditional BPNN model, PSO-BPNN reduced the RESM of the test set from 0.278 2 mg·L -1 to 0.210 9 mg·L -1 , reduced the MAE of the test set from 0.222 3 mg·L -1 to 0.153 7 mg·L -1 and increased the R 2 of the test set from 0.864 0 to 0.921 8, which indicated that PSO-BPNN had more stable fitting ability. RMSE, MAE, and R 2 of the test set in the CNN model were 0.122 0 mg·L -1 , 0.092 7 mg·L -1 , and 0.970 5, respectively, which showed that CNN had a better fitting and prediction effect than that of BPNN.

Chinese cordyceps (GL) is a traditional medicinal fungus, with Ophiocordyceps sinensis ( O. sinensis , BL) and Paecilomyces hepiali ( P. hepiali , JSB) being fungi isolated from wild Chinese cordyceps. These three species share similar chemical composition and pharmacological effects. Existing studies have primarily compared the metabolites of Chinese cordyceps and O. sinensis , overlooking the assessment of antioxidant capacity in Chinese cordyceps, P. hepiali , and O. sinensis . In this study, LC-MS/MS was employed to analyze metabolites in GL, JSB, and BL. Utilizing principal component analysis (PCA), supervised orthogonal partial least squares discriminant analysis (OPLS-DA), and hierarchical cluster analysis (HCA), it was observed that the majority of differential metabolites (DMs) primarily accumulated in organic acids and derivatives, lipids and lipid-like molecules, and organoheterocyclic compounds. Antioxidant activity analysis indicated that GL exhibited the higher 2,2-diphenyl-1-picrylhydrazyl radical scavenging ability (DPPH•, scavenging rate is 81.87 ± 0.97%), hydroxyl free radical scavenging capacity (•OH, scavenging rate is 98.10 ± 0.60%), and superoxide anion radical scavenging capacity (O 2 •- , scavenging rate is 69.74 ± 4.36%), while JSB demonstrated the higher FRAP total antioxidant capacity of 8.26 μmol Trolox/g ( p < 0.05). Correlation analysis revealed a positive correlation between DMs (fatty acyls and amino acids) and DPPH•, FRAP, •OH, and O 2 •- ( p < 0.05). Additionally, glycerophospholipid DMs were found to be positively correlated with FRAP ( p < 0.05). Through KEGG pathway analysis, it was determined that the accumulation of DMs in pathways such as cutin, suberine and wax biosynthesis has a higher impact on influencing the antioxidant activity of the samples. These results shed light on the antioxidant capacity and metabolic characteristics of Chinese cordyceps and its substitutes and offer valuable insights into how different DMs impact the strength of antioxidant activity, aiding in the advancement and application of Chinese cordyceps and its substitutes.

Sexual reproduction in ascomycetes is controlled by the mating-type (MAT) locus. (Pseudo)homothallic reproduction has been hypothesized on the basis of genetic data from Hirsutella sinensis (Genotype #1 of Ophiocordyceps sinensis ). However, the differential occurrence and differential transcription of mating-type genes in the MAT1-1 and MAT1-2 idiomorphs were found in the genome and transcriptome assemblies of H. sinensis , and the introns of the MAT1-2-1 transcript were alternatively spliced with an unspliced intron I that contains stop codons. These findings reveal that O. sinensis reproduction is controlled at the genetic, transcriptional, and coupled transcriptional-translational levels. This study revealed that mutant mating proteins could potentially have various secondary structures. Differential occurrence and transcription of the a-/α-pheromone receptor genes were also found in H. sinensis . The data were inconsistent with self-fertilization under (pseudo)homothallism but suggest the self-sterility of H. sinensis and the requirement of mating partners to achieve O. sinensis sexual outcrossing under heterothallism or hybridization. Although consistent occurrence and transcription of the mating-type genes of both the MAT1-1 and MAT1-2 idiomorphs have been reported in natural and cultivated Cordyceps sinensis insect-fungi complexes, the mutant MAT1-1-1 and α-pheromone receptor transcripts in natural C. sinensis result in N-terminal or middle-truncated proteins with significantly altered overall hydrophobicity and secondary structures of the proteins, suggesting heterogeneous fungal source(s) of the proteins and hybridization reproduction because of the co-occurrence of multiple genomically independent genotypes of O. sinensis and >90 fungal species in natural C. sinensis .

Background: Due to similar clinical manifestations and imaging signs, differential diagnosis of primary intestinal lymphoma (PIL) and Crohn's disease (CD) is a challenge in clinical practice., Aim: To investigate the ability of radiomics combined with machine learning methods to differentiate PIL from CD., Methods: We collected contrast-enhanced computed tomography (CECT) and clinical data from 120 patients form center 1. A total of 944 features were extracted single-phase images of CECT scans. Using the last absolute shrinkage and selection operator model, the best predictive radiographic features and clinical indications were screened. Data from 54 patients were collected at center 2 as an external validation set to verify the robustness of the model. The area under the receiver operating characteristic curve, accuracy, sensitivity and specificity were used for evaluation., Results: A total of five machine learning models were built to distinguish PIL from CD. Based on the results from the test group, most models performed well with a large area under the curve (AUC) (> 0.850) and high accuracy (> 0.900). The combined clinical and radiomics model (AUC = 1.000, accuracy = 1.000) was the best model among all models., Conclusion: Based on machine learning, a model combining clinical data with radiologic features was constructed that can effectively differentiate PIL from CD., Competing Interests: Conflict-of-interest statement: We have no financial relationships to disclose., (©The Author(s) 2024. Published by Baishideng Publishing Group Inc. All rights reserved.)