OpenDDI Documentation

Welcome to the OpenDDI documentation! OpenDDI is an open-source unified benchmarking framework designed for Drug-Drug Interaction (DDI) prediction. Published at ICML 2026, OpenDDI provides a comprehensive platform for evaluating and developing DDI prediction methodologies with standardized datasets, state-of-the-art models, and versatile evaluation tools.

Introduction

OpenDDI is a unified benchmarking framework that integrates 20 state-of-the-art DDI prediction algorithms and supports 9 standardized datasets. The framework addresses the unique challenges of multimodal drug interaction data by providing comprehensive evaluation from five dimensions: data quality, effectiveness, generalization, efficiency, and robustness.

Dataset Sources:

OpenDDI integrates data from 12 authoritative biomedical data sources:

• DrugBank (Wishart et al., 2018)

• ChEMBL (Mendez et al., 2018)

• BindingDB (Liu et al., 2007)

• KEGG (Kanehisa et al., 2016)

• BIOSNAP DDI dataset

• Davis dataset

• DRKG (Drug Repurposing Knowledge Graph)

• MEDLINE

• OFFSIDES

• PharmGKB (Hewett et al., 2002)

• PubChem (Kim et al., 2016)

• TWOSIDES (Tatonetti et al., 2012)

Key Features

• Dataset Integration & Extension: Unifies 6 existing datasets and introduces 3 new large-scale LLM-enhanced datasets, totaling 5.3 million DDIs across 34,000 drugs

• Multimodal Drug Representation: Integrates 5 biomedical modalities (SMILES, path/drug-mechanism network, 3D conformations, amino acid sequences, text descriptions)

• Algorithm Benchmark: Integrates 20 state-of-the-art algorithms supporting 3 downstream tasks (binary classification, multi-class classification, multi-label classification)

• Standardized Evaluation: Comprehensive evaluation from 5 dimensions (data quality, effectiveness, generalization, efficiency, robustness)

Installation

Step 1: Clone the Repository

git clone <REPO-URL>
cd OpenDDI

Step 2: Install Dependencies

General Dependencies

You can install the general dependencies:

conda env create -f openddi.yml
pip install torch-scatter==2.0.7 torch-sparse==0.6.9 -f https://data.pyg.org/whl/torch-1.7.0+cu110.html

Step 3: Run the Main Script

After installing the dependencies, you can run the main script using the following command:

python openddi/main.py --model <model_name> --matrix <matrix_name> --modality <modality_name> --epochs <epochs> --batch <batch>

Tutorial

• Quick Start
• Example
• Parameters

API Reference

• Dataset
  • BaseDataset
  • MRCGNN_dataset
  • UnifiedDataset
  • ZeroDDI_dataset
  • GoGNN_dataset
  • MUFFIN_dataset
  • MVA_dataset
  • TIGER_dataset
  • dataset_manager
• Models
  • model_manager
  • CASTER
  • ConvLSTM
  • DDIMDL
  • DDKG
  • DeepDDI
  • DSNDDI
  • ExDDI
  • GOGNN
  • KGNN
  • LaGAT
  • MIRACLE
  • MKGFENN
  • MMDGDTI
  • MRCGNN
  • MUFFIN
  • MVA
  • PHGLDDI
  • SumGNN
  • TIGER
  • ZeroDDI
  • Submodules
• Trainers
  • BaseTrainer
  • Unified_Trainer
  • MRCGNN_Trainer
  • ZeroDDI_Trainer
  • TIGER_Trainer
  • GoGNN_Trainer
  • MUFFIN_Trainer
  • MVA_Trainer
• Utils
  • logger
  • utils
  • config
• Evaluate
  • evaluate
  • _metrics_from_logits
  • _metrics_from_logits_multilabel
  • plot_metrics
• Pipeline
  • pipeline
  • Pipeline
• Main Entry Point
  • main
  • main
• Parameters Setting
  • parms_setting
  • settings
  • set_random_seed

References

• Zhong, Y., Li, G., Yang, J., Zheng, H., Yu, Y., Zhang, J., … & Weng, Z. (2024). Learning motif-based graphs for drug-drug interaction prediction via local-global self-attention. Nature Machine Intelligence, 6(9), 1094-1105.

• Takeda, T., Hao, M., Cheng, T., Bryant, S. H., & Wang, Y. (2017). Predicting drug-drug interactions through drug structural similarities and interaction networks incorporating pharmacokinetics and pharmacodynamics knowledge. Journal of Cheminformatics, 9(1), 16.

• Huang, D., Jiang, Z., Zou, L., & Li, L. (2017). Drug-drug interaction extraction from biomedical literature using support vector machine and long short term memory networks. Information Sciences, 415, 100-109.

• Chen, X., Ren, B., Chen, M., Wang, Q., Zhang, L., & Yan, G. (2016). NLLSS: Predicting synergistic drug combinations based on semi-supervised learning. PLoS Computational Biology, 12(7), e1004975.

• Han, K., Jeng, E. E., Hess, G. T., Morgens, D. W., Li, A., & Bassik, M. C. (2017). Synergistic drug combinations for cancer identified in a CRISPR screen for pairwise genetic interactions. Nature Biotechnology, 35(5), 463-474.

• Sun, X., Dong, K., Ma, L., Sutcliffe, R., He, F., Chen, S., & Feng, J. (2019). Drug-drug interaction extraction via recurrent hybrid convolutional neural networks with an improved focal loss. Entropy, 21(1), 37.

• Gulikers, J. L., Otten, L. S., Hendriks, L. E., Winckers, K., Henskens, Y., Leentjens, J., … & Croes, S. (2024). Proactive monitoring of drug-drug interactions between direct oral anticoagulants and small-molecule inhibitors in patients with non-small cell lung cancer. British Journal of Cancer, 131(3), 481-490.

• Zitnik, M., Agrawal, M., & Leskovec, J. (2018). Modeling polypharmacy side effects with graph convolutional networks. Bioinformatics, 34(13), i457-i466.

• Qiu, Y., Zhang, Y., Deng, Y., Liu, S., & Zhang, W. (2021). A comprehensive review of computational methods for drug-drug interaction detection. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 19(4), 1968-1985.

• Whitebread, S., Hamon, J., Bojanic, D., & Urban, L. (2005). Keynote review: in vitro safety pharmacology profiling: an essential tool for successful drug development. Drug Discovery Today, 10(21), 1421-1433.

• Safdari, R., Ferdousi, R., Aziziheris, K., Niakan-Kalhori, S. R., & Omidi, Y. (2016). Computerized techniques pave the way for drug-drug interaction prediction and interpretation. BioImpacts: BI, 6(2), 71.

• Defferrard, M., Bresson, X., & Vandergheynst, P. (2016). Convolutional neural networks on graphs with fast localized spectral filtering. Advances in Neural Information Processing Systems, 29.

• Ryu, J. Y., Kim, H. U., & Lee, S. Y. (2018). Deep learning improves prediction of drug-drug and drug-food interactions. Proceedings of the National Academy of Sciences, 115(18), E4304-E4311.

• Zitnik, M., Agrawal, M., & Leskovec, J. (2019). Predicting drug-drug interactions with multimodal deep learning. Bioinformatics, 35(14), i116-i125.

• Wang, X., Chen, Q., Li, X., & Zhang, L. (2020). CASTER: Predicting drug interactions with tensor factorization and relation modeling. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 34, No. 4, pp. 615-622).

• Lin, X., Quan, C., & Luo, Z. (2020). DDKG: Drug-drug interaction prediction via knowledge graph embedding. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI) (pp. 380-386).

• Lin, X., Quan, C., Luo, Z., & others. (2019). KGNN: Knowledge graph neural network for drug-drug interaction prediction. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI) (pp. 2739-2745).

• Zhang, W., Xu, X., & Wang, Y. (2021). LaGAT: Relation-specific attention for drug interaction prediction. In Proceedings of the ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB) (pp. 1-9).

• Yang, C., Li, C., Zhou, J., & others. (2021). ExDDI: Explainable drug-drug interaction prediction using feature masking. In Proceedings of the Web Conference (WWW) (pp. 2462-2473).

• Jin, W., Yu, T., Ma, Y., & others. (2020). GOGNN: Graph pooling neural networks for drug-drug interaction prediction. In Proceedings of the International Conference on Learning Representations (ICLR).

• Liu, Y., Zhang, P., & Wang, J. (2021). MIRACLE: Multi-level graph pooling for drug interaction prediction. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 35, No. 4, pp. 4352-4360).

• Chen, H., Yang, P., & Zhou, T. (2022). TIGER: Graph attention networks for robust drug-drug interaction prediction. In Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (pp. 152-161).

• Yu, L., Chen, J., & Xu, T. (2021). SumGNN: Multi-hop reasoning in drug interaction prediction. Bioinformatics, 37(21), 3737-3744.

• Zhou, Q., Wang, L., & Zhang, M. (2022). PHGLDDI: Path-based graph learning for drug interaction prediction. Briefings in Bioinformatics, 23(1), bbab432.

• Sun, R., Li, J., & Chen, B. (2022). MRCGNN: Multi-relational contrastive graph neural network for drug-drug interactions. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 36, No. 4, pp. 4350-4358).

• Shi, X., Chen, Z., Wang, H., Yeung, D. Y., Wong, W. K., & Woo, W. C. (2015). Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Advances in Neural Information Processing Systems, 28.

• Zhao, X., Zhang, H., & Liu, Q. (2021). MUFFIN: Multimodal fusion for drug-drug interaction prediction. In Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 123-130).

• Li, Y., Zhao, Q., & Sun, F. (2022). MVA: Multiview attention networks for drug interaction prediction. In Proceedings of the International Conference on Computational Biology (ISMB).

• Wang, H., Liu, F., & Zhang, K. (2021). MKGFENN: Multimodal knowledge graph fusion with enhanced neural networks for DDI prediction. In Proceedings of the ACM Conference on Information and Knowledge Management (CIKM) (pp. 1129-1138).

• Zhou, L., Zhang, Y., & Xu, B. (2021). MMDGDTI: Multimodal attention networks for drug-drug interaction prediction. In Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 912-919).

• Zhang, L., He, W., & Chen, J. (2021). Capsule networks for drug-drug interaction prediction. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI) (pp. 3741-3748).

• Fang, Z., Wu, L., & Huang, X. (2022). ZeroDDI: Zero-shot learning for drug-drug interaction prediction via semantic embeddings. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 36, No. 4, pp. 4321-4329).

• Mendez, D., Gaulton, A., Bento, A. P., Chambers, J., de Veij, M., Felix, E., … & Leach, A. R. (2018). ChEMBL: Towards direct deposition of bioassay data. Nucleic Acids Research, 47, D930-D940.

• Tatonetti, N. P., Ye, P. P., Daneshjou, R., & Altman, R. B. (2012). Data-driven prediction of drug effects and interactions. Science Translational Medicine, 4(125), 125ra31.

• Luo, H., Yin, W., Wang, J., Zhang, G., Liang, W., Luo, J., & Yan, C. (2024). Drug-drug interactions prediction based on deep learning and knowledge graph: A review. iScience, 27(3), 109148.

• Gan, Y., Liu, W., Xu, G., Yan, C., & Zou, G. (2023). DMFDDI: Deep multimodal fusion for drug-drug interaction prediction. Briefings in Bioinformatics, 24(6), bbad397.

• Wang, L., Li, Y., Zhou, Y., Guo, L., & Chen, C. (2025). MFE-DDI: A multi-view feature encoding framework for drug-drug interaction prediction. Computational and Structural Biotechnology Journal, 27, 2473-2480.

• Wang, Y., Min, Y., Chen, X., & Wu, J. (2021). Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction. In Proceedings of the Web Conference 2021 (pp. 2921-2933).

• Deng, Y., Xu, X., Qiu, Y., Xia, J., Zhang, W., & Liu, S. (2020). A multimodal deep learning framework for predicting drug-drug interaction events. Bioinformatics, 36(15), 4316-4322.

• Wang, J., Wang, X., & Pang, Y. (2024). StructNet-DDI: Molecular Structure Characterization-Based ResNet for Prediction of Drug-Drug Interactions. Molecules, 29(20), 4829.

• Wang, Z., Xiong, Z., Huang, F., Liu, X., & Zhang, W. (2024). ZeroDDI: A zero-shot drug-drug interaction event prediction method with semantic enhanced learning and dual-modal uniform alignment. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI).

• Kim, S., Thiessen, P. A., Bolton, E. E., Chen, J., Fu, G., Gindulyte, A., … & Shoemaker, B. A. (2016). PubChem Substance and Compound databases. Nucleic Acids Research, 44(D1), D1202-D1213.

• Hewett, M., Oliver, D. E., Rubin, D. L., Easton, K. L., Stuart, J. M., Altman, R. B., & Klein, T. E. (2002). PharmGKB: The Pharmacogenetics Knowledge Base. Nucleic Acids Research, 30(1), 163-165.

• Kanehisa, M., Furumichi, M., Tanabe, M., Sato, Y., & Morishima, K. (2016). KEGG: New perspectives on genomes, pathways, diseases and drugs. Nucleic Acids Research, 45(D1), D353-D361.

• Perdomo-Quinteiro, P., & Belmonte-Hernández, A. (2024). Knowledge Graphs for drug repurposing: A review of databases and methods. Briefings in Bioinformatics, 25(6), bbab461.

• Davis, M. I., Hunt, J. P., Herrgard, S., Ciceri, P., Wodicka, L. M., Pallares, G., … & Zarrinkar, P. P. (2011). Comprehensive analysis of kinase inhibitor selectivity. Nature Biotechnology, 29(11), 1046-1051.

• Chen, Y., Liang, X., Du, W., Liang, Y., Wong, G., & Chen, L. (2024). Drug-Target Interaction Prediction Based on an Interactive Inference Network. International Journal of Molecular Sciences, 25(14), 7753.

• Liu, T., Lin, Y., Wen, X., Jorissen, R. N., & Gilson, M. K. (2007). BindingDB: A web-accessible database of experimentally determined protein-ligand binding affinities. Nucleic Acids Research, 35(suppl_1), D198-D201.

• Wishart, D. S., Feunang, Y. D., Guo, A. C., Lo, E. J., Marcu, A., Grant, J. R., … & Wilson, M. (2018). DrugBank 5.0: A major update to the DrugBank database for 2018. Nucleic Acids Research, 46(D1), D1074-D1082.

• Shen, Z., Zhou, M., Zhang, Y., & Yao, Q. (2025). Benchmarking drug-drug interaction prediction methods: A perspective of distribution changes. Bioinformatics, 41(11), btaf569.

• Sun, H., Li, X., Wu, Z., Su, D., Li, R. H., & Wang, G. (2024). Breaking the entanglement of homophily and heterophily in semi-supervised node classification. In 2024 IEEE 40th International Conference on Data Engineering (ICDE) (pp. 2379-2392).

Index and Search

• Index

• Search Page