3D Spatial Learning for Adsorption Energy Prediction in Multi-Temporal Solution Systems: The MTSS Data Set and a GCN-Based Network.

Existing methods for adsorption energy prediction primarily focus on individual molecules or static molecular pairs, lacking the capabilities to model the diverse spatial configurations found in complex solution systems. While traditional data sets are static, dynamic systems explore a vast conformational space over time. This paper introduces the Multi-Temporal Solution System (MTSS) data set containing 500,000 temporally resolved configurations (3D atomic coordinates + adsorption energy labels) across five solvents.

Heterogeneity of diabetes and disease progression with a tree-like representation: findings from the China Cardiometabolic Disease and Cancer Cohort (4C) study.

Aims/hypothesis: Diabetes heterogeneity has been modelled as a continuum in European populations, but its phenotypes and long-term comorbidity risks remain unclear in Chinese individuals. This study aimed to identify distinct phenotypes and evaluate their links to future cardiometabolic risks in a large Chinese cohort.

Methods: The discriminative dimensionality reduction with trees (DDRTree) algorithm was used to develop a tree structure based on nine clinical variables.

Elucidating the heterogeneity of prediabetes through subphenotyping with a two-dimensional tree structure.

Prediabetes, an intermediate stage of developing diabetes, exhibits considerable phenotypic heterogeneity. Here, we apply the Discriminative Dimensionality Reduction Tree (DDRTree) algorithm to explore prediabetes heterogeneity in 55,777 participants from the China Cardiometabolic Disease and Cancer Cohort (4C) study. Based on 12 clinically available variables, we identify four distinct phenotypes and observe differential risks of type 2 diabetes mellitus (T2DM), chronic kidney disease (CKD), and cardiovascular disease (CVD).