From Detection to Mechanism: Cross-Attention Graph Neural Networks Enable Drug-Drug Interaction Type Prediction An Ablation Study with Acetylsalicylic Acid Validation

• URL: http://arxiv.org/abs/2605.27861v1
• Date: Wed, 27 May 2026 02:22:44 GMT
• Title: From Detection to Mechanism: Cross-Attention Graph Neural Networks Enable Drug-Drug Interaction Type Prediction An Ablation Study with Acetylsalicylic Acid Validation
• Abstract summary: This study presents a systematic ablation study of three Graph Neural Network (GNN) architectures for drug-drug interaction (DDI) prediction.<n>Three architectures are compared under identical training conditions.<n>CrossAtt improves multi-class F1-macro by +0.186 absolute (+45%) over Concat, while improving binary AUC by only +0.012 (+1.3%)<n>The ternary architecture underperforms despite equivalent training data, with its failure consistent with a training instability hypothesis.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Predicting whether two drugs interact (binary detection) is a substantially dif- ferent task from predicting the mechanism type of that interaction (multi-class classification). This study presents a systematic ablation study of three Graph Neural Network (GNN) architectures for drug-drug interaction (DDI) prediction on a publicly available benchmark dataset comprising 38,337 positive pairs across 86 interaction types. Three architectures are compared under identical training conditions (n = 61,339 pairs): a siamese dual Message Passing Neural Network (MPNN) with concatenation (Concat), a dual MPNN with four-head cross-attention (CrossAtt), and a ternary MPNN incorporating an interaction graph (Ternary). CrossAtt improves multi-class F1-macro by +0.186 absolute (+45%) over Concat, while improving binary AUC by only +0.012 (+1.3%) - confirming that atom-level inter-molecular communication specifically enables mechanism-type classification. The ternary architecture underperforms despite equivalent training data, with its failure consistent with a training instability hypothesis. Validation on ten acetylsali- cylic acid (ASA) drug pairs, held out prior to training, demonstrates 10/10 correct DDI-type predictions for CrossAtt versus 0/10 for Ternary. Two consistent failure cases are identified across all architectures, linking to structural limits established in a companion toxicity study.

Related papers

• Pharmacogenomic Knowledge Graph Augmentation for Graph Neural Network-Based Drug-Drug Interaction Prediction [0.0]
  Graph neural networks (GNNs) applied to drug-drug interaction (DDI) prediction rely exclusively on molecular structure encoded as SMILES-derived graphs.<n>The present study investigates whether pharmacogenomic prior knowledge partially closes this gap.<n>Experiments are conducted under both pair-level and drug-level data splits to quantify generalization to unseen drugs.
  arXiv  Detail & Related papers  (2026-06-05T07:47:32Z)
• Drug Synergy Prediction via Residual Graph Isomorphism Networks and Attention Mechanisms [3.073484266148604]
  We introduce a novel model named the Residual Graph Isomorphism Network integrated with an Attention mechanism (ResGIN-Att)<n>The model first extracts multi scale topological features of drug molecules using a residual graph isomorphism network, where residual connections help mitigate over-smoothing in deep layers. Subsequently, an adaptive Long Short-Term Memory (LSTM) module fuses structural information from local to global scales. Finally, a cross-attention module is designed to explicitly model drug-drug interactions and identify key chemical substructures.
  arXiv  Detail & Related papers  (2026-04-23T09:31:51Z)
• Multi-Objective Reinforcement Learning for Generating Covalent Inhibitor Candidates [0.0]
  We present a machine learning pipeline for generating covalent inhibitor candidates.<n>It is applied to two targets: epidermal growth factor receptor (EGFR) and acetylcholinesterase (ACHE)<n>The pipeline rediscovers known covalent inhibitors at rates of up to 0.50% (EGFR) and 0.74% (ACHE) in 10,000-structure runs.
  arXiv  Detail & Related papers  (2026-04-21T21:54:53Z)
• Design and Validation of a Lightweight 1D CNN for Affective Touch Classification in Soft Plush Companions [59.49967357689445]
  Soft, sensorized companions offer a physically safe and emotionally intuitive interface for socially assistive technologies.<n>This study presents a complete open-source dilated real-based framework for the development and validation of deep learning models for affective touch recognition in soft interactive companions.
  arXiv  Detail & Related papers  (2026-04-16T10:20:05Z)
• Tensor-DTI: Enhancing Biomolecular Interaction Prediction with Contrastive Embedding Learning [0.015229507502478598]
  We propose a contrastive learning framework that integrates multimodal embeddings from molecular graphs, protein language models, and binding-site predictions to improve interaction modeling.<n>Our findings highlight the benefits of integrating multimodal information with contrastive objectives to enhance interaction-prediction accuracy and to provide more interpretable and reliability-aware models for virtual screening splits.
  arXiv  Detail & Related papers  (2026-01-09T13:39:49Z)
• MMM: Quantum-Chemical Molecular Representation Learning for Combinatorial Drug Recommendation [5.017879531498458]
  Drug-drug interactions (DDI) between co-prescribed medications remain a significant challenge.<n>We propose Multimodal DDI Prediction with Molecular Electron Localization Function (ELF) Maps (MMM)<n>MMM combines ELF-derived features that encode global electronic properties with a bipartite graph encoder that models local substructure interactions.<n>These results demonstrate the potential complementary ELF-based 3D representations to enhance prediction accuracy and support safer drug prescribing in clinical practice.
  arXiv  Detail & Related papers  (2025-10-09T08:03:14Z)
• Aligned Manifold Property and Topology Point Clouds for Learning Molecular Properties [55.2480439325792]
  This work introduces AMPTCR, a molecular surface representation that combines local quantum-derived scalar fields and custom topological descriptors within an aligned point cloud format.<n>For molecular weight, results confirm that AMPTCR encodes physically meaningful data, with a validation R2 of 0.87.<n>In the bacterial inhibition task, AMPTCR enables both classification and direct regression of E. coli inhibition values.
  arXiv  Detail & Related papers  (2025-07-22T04:35:50Z)
• HCAF-DTA: drug-target binding affinity prediction with cross-attention fused hypergraph neural networks [0.6906005491572401]
  We propose a drug-target association prediction model based on cross-attention fusion hypergraph neural network.<n>In the prediction stage, a bidirectional multi-head cross-attention mechanism is designed to model intermolecular interactions.<n>Experiments on benchmark datasets show that HCAF-DTA outperforms state of the arts in all three performance evaluation metrics.
  arXiv  Detail & Related papers  (2025-04-02T06:46:28Z)
• A Cross-Field Fusion Strategy for Drug-Target Interaction Prediction [85.2792480737546]
  Existing methods fail to utilize global protein information during DTI prediction. Cross-field information fusion strategy is employed to acquire local and global protein information. Siamese drug-target interaction SiamDTI prediction method achieves higher accuracy levels than other state-of-the-art (SOTA) methods on novel drugs and targets.
  arXiv  Detail & Related papers  (2024-05-23T13:25:20Z)
• Improved Drug-target Interaction Prediction with Intermolecular Graph Transformer [98.8319016075089]
  We propose a novel approach to model intermolecular information with a three-way Transformer-based architecture. Intermolecular Graph Transformer (IGT) outperforms state-of-the-art approaches by 9.1% and 20.5% over the second best for binding activity and binding pose prediction respectively. IGT exhibits promising drug screening ability against SARS-CoV-2 by identifying 83.1% active drugs that have been validated by wet-lab experiments with near-native predicted binding poses.
  arXiv  Detail & Related papers  (2021-10-14T13:28:02Z)
• CovidDeep: SARS-CoV-2/COVID-19 Test Based on Wearable Medical Sensors and Efficient Neural Networks [51.589769497681175]
  The novel coronavirus (SARS-CoV-2) has led to a pandemic. The current testing regime based on Reverse Transcription-Polymerase Chain Reaction for SARS-CoV-2 has been unable to keep up with testing demands. We propose a framework called CovidDeep that combines efficient DNNs with commercially available WMSs for pervasive testing of the virus.
  arXiv  Detail & Related papers  (2020-07-20T21:47:28Z)
• Ensemble Transfer Learning for the Prediction of Anti-Cancer Drug Response [49.86828302591469]
  In this paper, we apply transfer learning to the prediction of anti-cancer drug response. We apply the classic transfer learning framework that trains a prediction model on the source dataset and refines it on the target dataset. The ensemble transfer learning pipeline is implemented using LightGBM and two deep neural network (DNN) models with different architectures.
  arXiv  Detail & Related papers  (2020-05-13T20:29:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.