Research map / Probabilistic and scientific modeling / Molecules and proteins
Predicting Cellular Responses to Novel Drug Perturbations at a Single-Cell Resolution
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| pretrain on L1000 bulk data (ablation) | chemCPA · sci-Plex3 unseen drugs, shared genes, 10uM | mean r2 DEGs: 0.32 -> 0.54 | Helped |
| pretrain on L1000 bulk data (ablation) | chemCPA · sci-Plex3 unseen drugs, extended 2000 genes, 10uM | mean r2 DEGs: 0.22 -> 0.47 | Helped |
| pretrain on L1000 bulk data (ablation) | chemCPA · sci-Plex3 unseen drug-cell line combos, 10uM | mean r2 DEGs: 0.58 -> 0.68 | Helped |
| add perturbation network (no pretraining) vs CPA | CPA · sci-Plex3 combos, 10uM | mean r2 DEGs: 0.34 -> 0.58 | Helped |
| chemCPA without pretraining vs baseline on extended gene set (ablation) | chemCPA · sci-Plex3 extended genes | median r2 DEGs: 0.00 -> 0.00 | No clear effect |
| use GROVER encoder instead of RDKit (pretrained) (ablation) | chemCPA pretrained · sci-Plex3 shared genes, 10uM | mean r2 DEGs: 0.54 -> 0.47 | Hurt |
| use JT-VAE encoder instead of RDKit (pretrained) (ablation) | chemCPA pretrained · sci-Plex3 shared genes, 10uM | mean r2 DEGs: 0.54 -> 0.35 | Hurt |
| pretrain JT-VAE-encoder chemCPA on L1000 (ablation) | chemCPA (JT-VAE) · sci-Plex3 shared genes, 10uM | mean r2 DEGs: 0.39 -> 0.35 | Hurt |
| pretrain GROVER-encoder chemCPA on L1000 (ablation) | chemCPA (GROVER) · sci-Plex3 shared genes, 10uM | mean r2 DEGs: 0.32 -> 0.47 | Helped |
Closest papers by meaning
- A benchmark for prediction of transcriptomic responses to chemical perturbations across cell types (NeurIPS 2024 · similarity 0.89)
- Learning Cross-Domain Representations for Transferable Drug Perturbations on Single-Cell Transcriptional Responses (AAAI 2025 · similarity 0.88)
- Learning Identifiable Factorized Causal Representations of Cellular Responses (NeurIPS 2024 · similarity 0.87)
- Chem-PerturBridge: a harmonized compendium of small molecule perturbation transcriptomic effects (NeurIPS 2026 · similarity 0.87)
- PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (NeurIPS 2025 · similarity 0.86)
- PRESCRIBE: Predicting Single-Cell Responses with Bayesian Estimation (NeurIPS 2025 · similarity 0.85)
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.