MIBPred: Ensemble Learning-Based Metal Ion-Binding Protein Classifier.

In biological organisms, metal ion-binding proteins participate in numerous metabolic activities and are closely associated with various diseases. To accurately predict whether a protein binds to metal ions and the type of metal ion-binding protein, this study proposed a classifier named MIBPred. The classifier incorporated advanced Word2Vec technology from the field of natural language processing to extract semantic features of the protein sequence language and combined them with position-specific score matrix (PSSM) features. Furthermore, an ensemble learning model was employed for the metal ion-binding protein classification task. In the model, we independently trained XGBoost, LightGBM, and CatBoost algorithms and integrated the output results through an SVM voting mechanism. This innovative combination has led to a significant breakthrough in the predictive performance of our model. As a result, we achieved accuracies of 95.13% and 85.19%, respectively, in predicting metal ion-binding proteins and their types. Our research not only confirms the effectiveness of Word2Vec technology in extracting semantic information from protein sequences but also highlights the outstanding performance of the MIBPred classifier in the problem of metal ion-binding protein types. This study provides a reliable tool and method for the in-depth exploration of the structure and function of metal ion-binding proteins.

[Effects of organic manure on the profile distribution of soil nitrate-N in a peach orchard].

In 2004 and 2005, a field experiment was conducted in a peach orchard in Pinggu District of Beijing to study the effects of organic manure on the profile distribution of nitrate-N in soil. Four treatments were installed, i.e., applying 6.75 x 10(4) kg x hm(-2) of organic manure both in 2004 and in 2005 (T1), no fertilization in 2004 but applying 13.5 x 10(4) kg x hm(-2) of organic manure in 2005 (T2), no fertilization in 2004 but applying 6.75 x 10(4) kg x hm(-2) of organic manure in 2005 (CK), and no fertilization both in 2004 and in 2005 (CK). In 2006, soil samples at the depth of 0-120 cm were collected from the treatments and analyzed. The results showed that soil nitrate-N had a relatively uniform distribution in the profile in CK, accumulated more at the depth of 0-60 cm and decreased gradually at 60-120 cm in T1 and T3, and increased with increasing depth, with the peak at the depth of 100-120 cm in T2. The soil nitrate-N content below 60 cm in T2 was the highest among all the treatments, indicating that applying excessive amount of organic manure could induce nitrate-N leaching. The profile distribution of soil nitrate-N had significant correlations with the total amount of applied organic manure, the amount of organic manure applied in the nearest year, and the distance of sampling sites from peach tree. A correlation model of organic manure treatments and soil nitrate-N distribution was established.