Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.00539 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908801730347008 |
|---|---|
| author | Jin, Xinmo Fan, Bowen Li, Xunkai Sun, Henan Zeng, YuXin Chen, Zekai Sun, Yuxuan Li, Jia Dai, Qiangqiang Qin, Hongchao Li, Rong-Hua Wang, Guoren |
| author_facet | Jin, Xinmo Fan, Bowen Li, Xunkai Sun, Henan Zeng, YuXin Chen, Zekai Sun, Yuxuan Li, Jia Dai, Qiangqiang Qin, Hongchao Li, Rong-Hua Wang, Guoren |
| contents | Drug-Drug Interactions (DDIs) significantly influence therapeutic efficacy and patient safety. As experimental discovery is resource-intensive and time-consuming, efficient computational methodologies have become essential. The predominant paradigm formulates DDI prediction as a drug graph-based link prediction task. However, further progress is hindered by two fundamental challenges: (1) lack of high-quality data: most studies rely on small-scale DDI datasets and single-modal drug representations; (2) lack of standardized evaluation: inconsistent scenarios, varied metrics, and diverse baselines. To address the above issues, we propose OpenDDI, a comprehensive benchmark for DDI prediction. Specifically, (1) from the data perspective, OpenDDI unifies 6 widely used DDI datasets and 2 existing forms of drug representation, while additionally contributing 3 new large-scale LLM-augmented datasets and a new multimodal drug representation covering 5 modalities. (2) From the evaluation perspective, OpenDDI unifies 20 SOTA model baselines across 3 downstream tasks, with standardized protocols for data quality, effectiveness, generalization, robustness, and efficiency. Based on OpenDDI, we conduct a comprehensive evaluation and derive 10 valuable insights for DDI prediction while exposing current limitations to provide critical guidance for this rapidly evolving field. Our code is available at https://github.com/xiaoriwuguang/OpenDDI |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00539 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | OpenDDI: A Comprehensive Benchmark for DDI Prediction Jin, Xinmo Fan, Bowen Li, Xunkai Sun, Henan Zeng, YuXin Chen, Zekai Sun, Yuxuan Li, Jia Dai, Qiangqiang Qin, Hongchao Li, Rong-Hua Wang, Guoren Machine Learning Drug-Drug Interactions (DDIs) significantly influence therapeutic efficacy and patient safety. As experimental discovery is resource-intensive and time-consuming, efficient computational methodologies have become essential. The predominant paradigm formulates DDI prediction as a drug graph-based link prediction task. However, further progress is hindered by two fundamental challenges: (1) lack of high-quality data: most studies rely on small-scale DDI datasets and single-modal drug representations; (2) lack of standardized evaluation: inconsistent scenarios, varied metrics, and diverse baselines. To address the above issues, we propose OpenDDI, a comprehensive benchmark for DDI prediction. Specifically, (1) from the data perspective, OpenDDI unifies 6 widely used DDI datasets and 2 existing forms of drug representation, while additionally contributing 3 new large-scale LLM-augmented datasets and a new multimodal drug representation covering 5 modalities. (2) From the evaluation perspective, OpenDDI unifies 20 SOTA model baselines across 3 downstream tasks, with standardized protocols for data quality, effectiveness, generalization, robustness, and efficiency. Based on OpenDDI, we conduct a comprehensive evaluation and derive 10 valuable insights for DDI prediction while exposing current limitations to provide critical guidance for this rapidly evolving field. Our code is available at https://github.com/xiaoriwuguang/OpenDDI |
| title | OpenDDI: A Comprehensive Benchmark for DDI Prediction |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.00539 |