Modelling future land use land cover changes and their impacts on urban heat island intensity in Guangzhou, China.

During rapid urbanization in developing countries, changes in land use and land cover (LULC) can significantly alter urban land surface temperatures (LST), exacerbating the urban heat island (UHI) effect and degrading the outdoor environment. In this study, taking Guangzhou, China, as an example, we used Landsat series satellite data from 1992 to 2022, classified the LULC of the study area by the Support Vector Machine (SVM) method, estimated the LST of the area by the mono-window algorithm, and classified the LST of the study area into five UHI intensity classes based on the normalized values of the LST, and explored the influence of the LULC on the distribution of the UHI intensity. The CA-ANN (cellular automata-artificial neural network) model in QGIS software was employed to forecast the distribution of LULC and UHI intensity in Guangzhou for 2032.

CDCS-TCM: A framework based on complex network theory to analyze the causality and dynamic correlation of substances in the metabolic process of traditional Chinese medicine.

Ethnopharmacological Relevance: Traditional Chinese medicine, with the feature of synergistic effects of multi-component, multi-pathway and multi-target, plays an important role in the treatment of cancer, cardiovascular and cerebrovascular diseases, etc. However, chemical components in traditional Chinese medicine are complex and most of the pharmacological mechanisms remain unclear, especially the relationships of chemical components change during the metabolic process.

Aim Of Study: Our aim is to provide a method based on complex network theory to analyze the causality and dynamic correlation of substances in the metabolic process of traditional Chinese medicine.

DeepPPThermo: A Deep Learning Framework for Predicting Protein Thermostability Combining Protein-Level and Amino Acid-Level Features.

Using wet experimental methods to discover new thermophilic proteins or improve protein thermostability is time-consuming and expensive. Machine learning methods have shown powerful performance in the study of protein thermostability in recent years. However, how to make full use of multiview sequence information to predict thermostability effectively is still a challenge.