graph neural networks

AChE Molecular Machine Learning: Structure-Aware Prediction of Acetylcholinesterase Inhibitory Potency

A structure-aware molecular machine-learning pipeline for continuous prediction of acetylcholinesterase inhibitory potency from molecular structure. The project includes ChEMBL activity retrieval and curation, IC50 normalization and pIC50 transformation, Morgan fingerprints, RDKit molecular descriptors, scaffold-aware...

AChE Molecular Machine Learning: Structure-Aware Prediction of Acetylcholinesterase Inhibitory Potency

A structure-aware molecular machine-learning pipeline for continuous prediction of acetylcholinesterase inhibitory potency from molecular structure. The project includes ChEMBL activity retrieval and curation, IC50 normalization and pIC50 transformation, Morgan fingerprints, RDKit molecular descriptors, scaffold-aware...

Gated-Slot Linear Attention Graph Neural Networks for Session-based Recommendation.

Session-based Recommendation (SBR) systems aim to predict the next item which a user is likely to interact with, based on behavior sequence within the current session. Recent approaches leveraging the Transformer attention mechanism (e.g.,GC-SAN) have demonstrated superior performance over traditional methods; however,...

Expressivity of quantum graph neural networks with variable-dimension edge qudits

A Graph Neural Network for Global Daily Fire Radiative Power Prediction at Medium-Range Lead Times

The model is a lightweight graph neural network. It treats each spatial patch as a grid graph, applies residual graph convolutions to each day of input history, and then aggregates the history with temporal convolutions. A two-part (hurdle) output head predicts both the probability of occurrence and the conditional int...

AI applications in drug discovery and personalized medicine

The era of artificial intelligence (AI) in drug discovery and personalized medicine is bringing a new twist to the healthcare field, enhancing the ability to identify the target, develop drugs, and design personal treatment regimens when taking into account the profile of a particular patient. They allow for incorporat...

Graph-Based Fault Localization in Microservices Using Static Code Metrics

AChE Molecular Machine Learning: Structure-Aware Prediction of Acetylcholinesterase Inhibitory Potency

A structure-aware molecular machine-learning pipeline for continuous prediction of acetylcholinesterase inhibitory potency from molecular structure. The project includes ChEMBL activity retrieval and curation, IC50 normalization and pIC50 transformation, Morgan fingerprints, RDKit molecular descriptors, scaffold-aware...

Energy-reserve coordinated scheduling of cascade hydro-photovoltaic-pumped storage systems based on physics-constrained graph neural networks

Intraday scheduling of cascade hydro-photovoltaic-pumped storage systems requires joint coordination of energy dispatch, photovoltaic accommodation, reserve security, and physical feasibility under photovoltaic fluctuation, load variation, inflow uncertainty, and limited storage capacity. Existing optimization methods...

Recognition Method for Road Grid Pattern By Integrating GraphSAGE Model and Gating Mechanism

Grid pattern recognition is of great significance for spatial pattern cognition, cartographic generalization, and multi-scale representation. To address the issues that existing methods rarely consider multi-level features and insufficiently utilize the learning and mining capabilities of intelligent models, this paper...

Toward a Transferable Representation of Protein Dynamics for Functional Prediction and Mechanistic Discovery

Protein function is determined not only by the static structure of molecules, but also by coordinated conformational fluctuations that occur across various spatial and temporal scales. Molecular dynamics simulations, elastic network models, principal component analysis, and related approaches offer useful descriptions...

Tractable and Thermodynamically Consistent pKa Prediction via First-Dissociation Aggregation

Ionization governs molecular behavior, yet predicting aqueous pKa accurately and tractably remains a fundamental challenge. Rigorous ensemble methods require enumerating a protonation-state space that grows exponentially with the number of ionizable sites, while fast graph predictors return numbers without thermodynami...