Summary of Devil in the Tail: a Multi-modal Framework For Drug-drug Interaction Prediction in Long Tail Distinction, by Liangwei Nathan Zheng et al.
Devil in the Tail: A Multi-Modal Framework for Drug-Drug Interaction Prediction in Long Tail Distinction
by Liangwei Nathan Zheng, Chang George Dong, Wei Emma Zhang, Xin Chen, Lin Yue, Weitong Chen
First submitted to arxiv on: 16 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed framework, TFDM, is a novel multi-modal deep learning-based approach that leverages multiple properties of drugs to achieve drug-drug interaction (DDI) classification. The model fuses multimodal features, including graph-based, molecular structure, Target and Enzyme, for DDI identification. To tackle the distribution skewness challenge posed by long-tailed datasets, a novel loss function called Tailed Focal Loss is introduced. This framework outperforms recent SOTA methods in long-tailed DDI classification tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper introduces a new way to predict if two drugs will interact with each other. They create a special model that uses multiple types of information about the drugs, like their chemical structure and what they target in the body. This helps the model understand the complex relationships between drugs. The researchers also developed a new way to measure how well the model is doing, which is important when dealing with very long-tailed datasets. They tested their approach on four different datasets and found that it outperformed other recent methods. |
Keywords
» Artificial intelligence » Classification » Deep learning » Loss function » Multi modal
