Prediction of re-oxidation behaviour of ultra-low carbon steel by different slag series.

A kinetic model was developed using FactSage Macro Processing to simulate the re-oxidation of ultra-low carbon steel via different oxidising slags. The calculated results show good agreement with experimental laboratory thermal simulation data. Therefore, the model can be used to predict the change behaviour of slag-metal-inclusion in the re-oxidation reaction of liquid steel. It can provide prediction and guidance for an accurate secondary oxidation control process. During the slag re-oxidation process, when the oxygen in the steel is supersaturated and the slag is low in oxidation, it can easily form stick-like and dendritic shape inclusions of Al2O3 in steel. As the (FeO) content increases in slag, the oxygen transfer from slag to steel is evident, and the inclusion size increases, showing clusters and spherical shapes. In addition, supersaturated oxygen in steel easily forms unstable Al2O3-TiOx inclusions with [Ti]. As the components of liquid steel tend to be uniform, the Al2O3-TiOx inclusions will decompose and disappear, forming stable Al2O3 and TiO2 inclusions. The number of inclusions can be reduced by increasing the basicity and the ratio of CaO to Al2O3 in the initial slag.

Developing Computational Model to Predict Protein-Protein Interaction Sites Based on the XGBoost Algorithm.

The study of protein-protein interaction is of great biological significance, and the prediction of protein-protein interaction sites can promote the understanding of cell biological activity and will be helpful for drug development. However, uneven distribution between interaction and non-interaction sites is common because only a small number of protein interactions have been confirmed by experimental techniques, which greatly affects the predictive capability of computational methods. In this work, two imbalanced data processing strategies based on XGBoost algorithm were proposed to re-balance the original dataset from inherent relationship between positive and negative samples for the prediction of protein-protein interaction sites. Herein, a feature extraction method was applied to represent the protein interaction sites based on evolutionary conservatism of proteins, and the influence of overlapping regions of positive and negative samples was considered in prediction performance. Our method showed good prediction performance, such as prediction accuracy of 0.807 and MCC of 0.614, on an original dataset with 10,455 surface residues but only 2297 interface residues. Experimental results demonstrated the effectiveness of our XGBoost-based method.