Research map / Label-efficient and robust learning / Recognition and long-tail
DeepSADR: Deep Transfer Learning with Subsequence Interaction and Adaptive Readout for Cancer Drug Response Prediction
Yuanpeng Zhang, Zhijian Huang, Ziyu Fan, Siyuan Shen, Yahan Li, Shangqian Wu, Min Wu, Lei Deng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add adaptive Set-Transformer readout instead of sum/max/mean (ablation) | DeepSADR · TCGA patients (average of 5 drugs) | AUC: 0.662 -> 0.856 | Improved |
| add adaptive Set-Transformer readout instead of sum/max/mean (ablation) | DeepSADR · TCGA patients (average of 5 drugs) | AUPR: 0.675 -> 0.862 | Improved |
| add subsequence interaction graph module (ablation) | DeepSADR · TCGA patients (average of 5 drugs) | AUC: 0.698 -> 0.856 | Improved |
| add subsequence interaction graph module (ablation) | DeepSADR · TCGA patients (average of 5 drugs) | AUPR: 0.710 -> 0.862 | Improved |
| add threshold selection to prune weak interaction edges (ablation) | DeepSADR · TCGA patients (average of 5 drugs) | AUC: 0.775 -> 0.856 | Improved |
| add threshold selection to prune weak interaction edges (ablation) | DeepSADR · TCGA patients (average of 5 drugs) | AUPR: 0.749 -> 0.862 | Improved |
| feed pre-trained drug response features as extra input to fine-tuning (ablation) | DeepSADR · TCGA patients (average of 5 drugs) | AUC: 0.781 -> 0.856 | Improved |
| feed pre-trained drug response features as extra input to fine-tuning (ablation) | DeepSADR · TCGA patients (average of 5 drugs) | AUPR: 0.787 -> 0.862 | Improved |
| use GNP drug subsequence encoder instead of simplest GNN (ablation) | DeepSADR · TCGA patients, Sorafenib | AUC: 0.907/0.016 -> 0.957/0.037 | Improved |
| fine-tune on patient data after pre-training on cell lines | DeepSADR · TCGA patients, Cisplatin | AUC: 0.585 -> 0.927 | Improved |
| fine-tune on patient data after pre-training on cell lines | DeepSADR · TCGA patients, Fluorouracil | AUC: 0.534 -> 0.806 | Improved |
| use DeepSADR instead of GANDALF on Fluorouracil | GANDALF · TCGA patients, Fluorouracil | AUC: 0.793/0.031 -> 0.805/0.056 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- WISER — WISER: Weak Supervision and Supervised Representation Learning to Improve Drug Response Prediction in Cancer (ICML 2024) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Knowledge-Guided Domain Adaptation Model for Transferring Drug Response Prediction from Cell Lines to Patients (AAAI 2025 · similarity 0.89)
- WISER: Weak Supervision and Supervised Representation Learning to Improve Drug Response Prediction in Cancer (ICML 2024 · similarity 0.87)
- Predicting Dose-Response Curves with Deep Neural Networks (ICML 2024 · similarity 0.86)
- GeSubNet: Gene Interaction Inference for Disease Subtype Network Generation (ICLR 2025 · similarity 0.85)
- Learning Cross-Domain Representations for Transferable Drug Perturbations on Single-Cell Transcriptional Responses (AAAI 2025 · similarity 0.84)
- Learning Identifiable Factorized Causal Representations of Cellular Responses (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
