Rethinking Drug-Drug Interaction Modeling as Generalizable Relation Learning

• URL: http://arxiv.org/abs/2601.15771v1
• Date: Thu, 22 Jan 2026 09:00:30 GMT
• Title: Rethinking Drug-Drug Interaction Modeling as Generalizable Relation Learning
• Authors: Dong Xu, Jiantao Wu, Qihua Pan, Sisi Yuan, Zexuan Zhu, Junkai Ji,
• Abstract summary: Drug-drug interaction (DDI) prediction is central to drug discovery and clinical development.<n>We propose GenRel-DDI, a relation-centric learning framework that reformulates DDI prediction as a relation-centric learning problem.<n>Experiments show that GenRel-DDI consistently and significantly outperforms state-of-the-art methods.
• Score: 14.217488560342135
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Drug-drug interaction (DDI) prediction is central to drug discovery and clinical development, particularly in the context of increasingly prevalent polypharmacy. Although existing computational methods achieve strong performance on standard benchmarks, they often fail to generalize to realistic deployment scenarios, where most candidate drug pairs involve previously unseen drugs and validated interactions are scarce. We demonstrate that proximity in the embedding spaces of prevailing molecule-centric DDI models does not reliably correspond to interaction labels, and that simply scaling up model capacity therefore fails to improve generalization. To address these limitations, we propose GenRel-DDI, a generalizable relation learning framework that reformulates DDI prediction as a relation-centric learning problem, in which interaction representations are learned independently of drug identities. This relation-level abstraction enables the capture of transferable interaction patterns that generalize to unseen drugs and novel drug pairs. Extensive experiments across multiple benchmark demonstrate that GenRel-DDI consistently and significantly outperforms state-of-the-art methods, with particularly large gains on strict entity-disjoint evaluations, highlighting the effectiveness and practical utility of relation learning for robust DDI prediction. The code is available at https://github.com/SZU-ADDG/GenRel-DDI.

Related papers

• A Multi-Scale Graph Neural Process with Cross-Drug Co-Attention for Drug-Drug Interactions Prediction [16.181492817294743]
  We propose MPNP-DDI, a novel Multi-scale Graph Neural Process framework.<n>The core of MPNP-DDI is a unique message-passing scheme that learns a hierarchy of graph representations at multiple scales.<n>MPNP-DDI significantly outperforms state-of-the-art baselines on benchmark datasets.
  arXiv  Detail & Related papers  (2025-09-18T07:48:10Z)
• Predicting Drug-Drug Interactions Using Heterogeneous Graph Neural Networks: HGNN-DDI [8.48967497162918]
  Drug-drug interactions (DDIs) can lead to reduced therapeutic efficacy or severe adverse effects.<n>We propose HGNN-DDI, a graph neural network model designed to predict potential DDIs by integrating multiple drug-related data sources.<n> Experimental results on benchmark DDI datasets demonstrate that HGNN-DDI outperforms state-of-the-art baselines in prediction accuracy and robustness.
  arXiv  Detail & Related papers  (2025-08-26T07:50:47Z)
• Robust Molecular Property Prediction via Densifying Scarce Labeled Data [53.24886143129006]
  In drug discovery, compounds most critical for advancing research often lie beyond the training set.<n>We propose a novel bilevel optimization approach that leverages unlabeled data to interpolate between in-distribution (ID) and out-of-distribution (OOD) data.
  arXiv  Detail & Related papers  (2025-06-13T15:27:40Z)
• RGDA-DDI: Residual graph attention network and dual-attention based framework for drug-drug interaction prediction [4.044376666671973]
  We propose RGDA-DDI, a residual graph attention network (residual-GAT) and dual-attention based framework for drug-drug interaction prediction. A series of evaluation metrics demonstrate that the RGDA-DDI significantly improved DDI prediction performance on two public benchmark datasets.
  arXiv  Detail & Related papers  (2024-08-27T17:13:56Z)
• Learning to Describe for Predicting Zero-shot Drug-Drug Interactions [54.172575323610175]
  Adverse drug-drug interactions can compromise the effectiveness of concurrent drug administration. Traditional computational methods for DDI prediction may fail to capture interactions for new drugs due to the lack of knowledge. We propose TextDDI with a language model-based DDI predictor and a reinforcement learning(RL)-based information selector.
  arXiv  Detail & Related papers  (2024-03-13T09:42:46Z)
• DDIPrompt: Drug-Drug Interaction Event Prediction based on Graph Prompt Learning [15.69547371747469]
  DDIPrompt is an innovative solution inspired by the recent advancements in graph prompt learning. Our framework aims to address these issues by leveraging intrinsic the knowledge from pre-trained models. Extensive experiments on two benchmark datasets demonstrate DDIPrompt's SOTA performance.
  arXiv  Detail & Related papers  (2024-02-18T06:22:01Z)
• ADRNet: A Generalized Collaborative Filtering Framework Combining Clinical and Non-Clinical Data for Adverse Drug Reaction Prediction [49.56476929112382]
  Adverse drug reaction (ADR) prediction plays a crucial role in both health care and drug discovery. We propose ADRNet, a generalized collaborative filtering framework combining clinical and non-clinical data for drug-ADR prediction.
  arXiv  Detail & Related papers  (2023-08-03T11:28:12Z)
• How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval [80.54532535622988]
  We show that a generalizable dense retriever can be trained to achieve high accuracy in both supervised and zero-shot retrieval. DRAGON, our dense retriever trained with diverse augmentation, is the first BERT-base-sized DR to achieve state-of-the-art effectiveness in both supervised and zero-shot evaluations.
  arXiv  Detail & Related papers  (2023-02-15T03:53:26Z)
• SSM-DTA: Breaking the Barriers of Data Scarcity in Drug-Target Affinity Prediction [127.43571146741984]
  Drug-Target Affinity (DTA) is of vital importance in early-stage drug discovery. wet experiments remain the most reliable method, but they are time-consuming and resource-intensive. Existing methods have primarily focused on developing techniques based on the available DTA data, without adequately addressing the data scarcity issue. We present the SSM-DTA framework, which incorporates three simple yet highly effective strategies.
  arXiv  Detail & Related papers  (2022-06-20T14:53:25Z)
• Multi-View Substructure Learning for Drug-Drug Interaction Prediction [69.34322811160912]
  We propose a novel multi- view drug substructure network for DDI prediction (MSN-DDI) MSN-DDI learns chemical substructures from both the representations of the single drug (intra-view) and the drug pair (inter-view) simultaneously and utilizes the substructures to update the drug representation iteratively. Comprehensive evaluations demonstrate that MSN-DDI has almost solved DDI prediction for existing drugs by achieving a relatively improved accuracy of 19.32% and an over 99% accuracy under the transductive setting.
  arXiv  Detail & Related papers  (2022-03-28T05:44:29Z)
• AttentionDDI: Siamese Attention-based Deep Learning method for drug-drug interaction predictions [0.9176056742068811]
  Drug-drug interactions (DDIs) refer to processes triggered by the administration of two or more drugs leading to side effects beyond those observed when drugs are administered by themselves. Due to the massive number of possible drug pairs, it is nearly impossible to experimentally test all combinations and discover previously unobserved side effects. We propose a Siamese self-attention multi-modal neural network for DDI prediction that integrates multiple drug similarity measures.
  arXiv  Detail & Related papers  (2020-12-24T13:33:07Z)

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.