# CASTER: Predicting Drug Interactions with Chemical Substructure Representation

arXiv: https://arxiv.org/abs/1911.06446 · HTML: https://mlsanity.com/paper/1911.06446/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2019.

## Built on by (most cited first, 24 of 24)

- [SafeDrug: Dual Molecular Graph Encoders for Recommending Effective and Safe Drug Combinations](https://mlsanity.com/paper/2105.02711/) (2021)
- [Molformer: Motif-based Transformer on 3D Heterogeneous Molecular Graphs](https://mlsanity.com/paper/2110.01191/) (2021)
- [HyGNN: Drug-Drug Interaction Prediction via Hypergraph Neural Network](https://mlsanity.com/paper/2206.12747/) (2022)
- [ChemicalX: A Deep Learning Library for Drug Pair Scoring](https://mlsanity.com/paper/2202.05240/) (2022)
- [Comprehensive evaluation of deep and graph learning on drug-drug interactions prediction](https://mlsanity.com/paper/2306.05257/) (2023)
- [A Unified View of Relational Deep Learning for Drug Pair Scoring](https://mlsanity.com/paper/2111.02916/) (2021)
- [STNN-DDI: A Substructure-aware Tensor Neural Network to Predict Drug-Drug Interactions](https://mlsanity.com/paper/2111.05708/) (2021)
- [Relation Matters in Sampling: A Scalable Multi-Relational Graph Neural Network for Drug-Drug Interaction Prediction](https://mlsanity.com/paper/2105.13975/) (2021)
- [BatmanNet: Bi-branch Masked Graph Transformer Autoencoder for Molecular Representation](https://mlsanity.com/paper/2211.13979/) (2022)
- [Natural Language-Assisted Multi-modal Medication Recommendation](https://mlsanity.com/paper/2501.07166/) (2025)
- [Knowledge-informed Molecular Learning: A Survey on Paradigm Transfer](https://mlsanity.com/paper/2202.10587/) (2022)
- [Graph neural networks and attention-based CNN-LSTM for protein classification](https://mlsanity.com/paper/2204.09486/) (2022)
- [Review of Natural Language Processing in Pharmacology](https://mlsanity.com/paper/2208.10228/) (2022)
- [Towards Interpretable Drug-Drug Interaction Prediction: A Graph-Based Approach with Molecular and Network-Level Explanations](https://mlsanity.com/paper/2507.09173/) (2025)
- [OpenDDI: A Comprehensive Benchmark for DDI Prediction](https://mlsanity.com/paper/2602.00539/) (2026)
- [DDI Prediction via Heterogeneous Graph Attention Networks](https://mlsanity.com/paper/2207.05672/) (2022)
- [Predicting Drug-Drug Interactions from Heterogeneous Data: An Embedding Approach](https://mlsanity.com/paper/2103.10916/) (2021)
- [Multi-View Substructure Learning for Drug-Drug Interaction Prediction](https://mlsanity.com/paper/2203.14513/) (2022)
- [ADEP: A Novel Approach Based on Discriminator-Enhanced Encoder-Decoder Architecture for Accurate Prediction of Adverse Effects in Polypharmacy](https://mlsanity.com/paper/2406.00118/) (2024)
- [Molecular Graph Representation Learning via Structural Similarity Information](https://mlsanity.com/paper/2409.08580/) (2024)
- [ImageDDI: Image-enhanced Molecular Motif Sequence Representation for Drug-Drug Interaction Prediction](https://mlsanity.com/paper/2508.08338/) (2025)
- [Functional Groups are All you Need for Chemically Interpretable Molecular Property Prediction](https://mlsanity.com/paper/2509.09619/) (2025)
- [CoFEND: A Cross-Modal Fusion End-to-End Network for Cold-Start Drug-Drug Interaction Prediction](https://mlsanity.com/paper/2607.02928/) (2026)
- [Asymmetric Focal Loss Improves Graph Neural Network Prediction of Drug-Drug Interactions](https://mlsanity.com/paper/2607.07611/) (2026)

## Abstract (arXiv)

Adverse drug-drug interactions (DDIs) remain a leading cause of morbidity and mortality. Identifying potential DDIs during the drug design process is critical for patients and society. Although several computational models have been proposed for DDI prediction, there are still limitations: (1) specialized design of drug representation for DDI predictions is lacking; (2) predictions are based on limited labelled data and do not generalize well to unseen drugs or DDIs; and (3) models are characterized by a large number of parameters, thus are hard to interpret. In this work, we develop a ChemicAl SubstrucTurE Representation (CASTER) framework that predicts DDIs given chemical structures of drugs.CASTER aims to mitigate these limitations via (1) a sequential pattern mining module rooted in the DDI mechanism to efficiently characterize functional sub-structures of drugs; (2) an auto-encoding module that leverages both labelled and unlabelled chemical structure data to improve predictive accuracy and generalizability; and (3) a dictionary learning module that explains the prediction via a small set of coefficients which measure the relevance of each input sub-structures to the DDI outcome. We evaluated CASTER on two real-world DDI datasets and showed that it performed better than state-of-the-art baselines and provided interpretable predictions.