Summary of Towards Generalization Of Drug Response Prediction to Single Cells and Patients Utilizing Importance-aware Multi-source Domain Transfer Learning, by Hui Liu et al.
Towards generalization of drug response prediction to single cells and patients utilizing importance-aware multi-source domain transfer learning
by Hui Liu, Wei Duan, Judong Luo
First submitted to arxiv on: 8 Mar 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- 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 scAdaDrug model is a multi-source domain adaptation tool that predicts individual cell drug response using adaptive importance-aware representation learning. The model uses a shared encoder to extract features related to drug response from multiple source domains and adaptively modulates the latent representation of each sample between source and target domains. Experimental results show state-of-the-art performance on various datasets, including single-cell data derived from cell lines, PDX models, and clinical tumor patient cohorts. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The scAdaDrug model is a new tool that helps predict how well medicine will work for individual cells in cancer tumors. This is important because right now we don’t do very well at predicting which cells will be affected by treatment. The model uses data from different sources to learn what makes some cells resistant to drugs, and then it uses this information to make better predictions about which cells will respond to treatment. |
Keywords
» Artificial intelligence » Domain adaptation » Encoder » Representation learning
