graph neural networks

Machine Learning-Aided Voltage Stability-Constrained Optimal Power Flow Dataset and Source Code

This repository contains the dataset and source code developed for machine learning-aided voltage stability-constrained optimal power flow (ML-VSCOPF) studies on a modified IEEE 118-bus power system. The dataset contains operating conditions, network topology information, renewable-generation dispatch, load conditions,...

REAPS: An All-Atom Receptor-Aware Geometric Deep Learning Framework for De Novo Design of Linear and Macrocyclic Peptide Binders

The REceptor-Aware Peptide Sequence Designer (REAPS), a geometric graph neural network that reframes sequence design for peptide binders by treating the receptor as a fully observable all-atom context, is introduced.

MalXGraph-ViT: A Hybrid Transformer-graph Neural Network Framework with Explainable AI for Robust Malware Detection and Classification on Emerging Public Benchmarks

The exponential growth of malware variants, propelled by automated obfuscation, polymorphism, and AIassisted code generation, has rendered signature-based and heuristic detection ineffective.This paper proposes MalXGraph-ViT, a multi-stage framework integrating grayscale visual feature extraction, Global Context Vision...

Bridging Nature, Data, and Artificial Intelligence: An Interdisciplinary Approach for Natural Products Discovery

Natural products (NPs) continue to serve as a foundational source for drug leads, owing to their unique chemical architectures, evolutionary optimisation, and structural diversity. Nevertheless, conventional natural product discovery is slow, resource-intensive, and constrained by rediscovery, dereplication inefficienc...

Drug-conditioned Residue Gating with Bidirectional Cross-attention for Drug-target Binding Affinity Prediction

Drug-target affinity (DTA) prediction remains challenging because drug and protein representations are frequently compressed before fine-grained atom-residue relationships and drug-specific residue relevance can be adequately modeled.In this study, a multimodal DTA framework is proposed in which molecular graphs are en...

GT-Muzero: SQL Query Plan Optimization via Graph Transformers and Model-Based Reinforcement Learning

Learning-based Structured Query Language (SQL) optimizers often face low sample efficiency and high training costs. To address these challenges, this study proposes a query optimization framework, GT- MuZero, which integrates a Graph Transformer (GT) with the model-based reinforcement learning (RL) algorithm MuZero. Th...

Bipartite Synchronization of T-S Fuzzy Coupled Delayed Neural Networks with Signed Graphs Under Fast Fixed-Time Control

Hzw-ZuttoZutto/Revisiting-Locally-Differentially-Private-Graph-Neural-Networks: AEC artifact v1.1.0

No description provided.

Approximate graph-fibration symmetry in connectome-constrained neural networks: code and results

Analysis and simulation code (loaders for the Janelia male CNS v1.0 and FlyWire v783 connectomes, an independent leaky integrate-and-fire implementation with Shiu et al. 2024 constants, mirror-symmetrisation and shuffle interventions, static mirror-defect analyses, quotient-network simulation, a teacher-student tying-g...

Approximate graph-fibration symmetry in connectome-constrained neural networks: code and results

Analysis and simulation code (loaders for the Janelia male CNS v1.0 and FlyWire v783 connectomes, an independent leaky integrate-and-fire implementation with Shiu et al. 2024 constants, mirror-symmetrisation and shuffle interventions, static mirror-defect analyses, quotient-network simulation, a teacher-student tying-g...

Accurate RNA-Ligand Binding Site Prediction Based on a Multi-Channel Graph Neural Network.

Edge-to-Cloud Computations-as-a-Service in Software-Defined Energy Networks for Smart Grids

Modern electricity grids run latency-sensitive functions, protection relays, fault isolation, and microgrid control, that demand millisecond analytics at the edge, while energy-hungry analytics workloads sit in distant clouds, causing missed realtime deadlines and wasted power. We formulate the placement of these grid...