Research map / Probabilistic and scientific modeling / Molecules and proteins
Learning Adaptive Perturbation-Conditioned Contexts for Robust Transcriptional Response Prediction
Yinhua Piao, Hyomin Kim, Seonghwan Kim, Yunhak Oh, Junhyeok Jeon, Sang-Yeon Hwang, Jaechang Lim, Woo Youn Kim, Chanyoung Park, Sungsoo Ahn
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 |
|---|---|---|---|
| Replace TxPert with AdaPert adaptive subgraph context | TxPert · K562.Replogle | Pearson-Delta: 0.580 -> 0.619 | Improved |
| Replace TxPert with AdaPert | TxPert · K562.Replogle | PDS: 0.665 -> 0.711 | Improved |
| Replace TxPert with AdaPert | TxPert · RPE1.Replogle | PDS: 0.618 -> 0.663; MorPH 0.688 is higher | Mixed |
| Replace TxPert with AdaPert | TxPert · K562.Replogle | DES@50: 0.220 -> 0.263 | Improved |
| Replace TxPert with AdaPert on small-effect perturbations | TxPert · K562.Replogle small-effect | Pearson-Delta: 0.457 -> 0.462 | No clear effect |
| Replace TxPert with AdaPert on small-effect perturbations | TxPert · K562.Replogle small-effect | DES: 0.090 -> 0.115 | Improved |
| Replace TxPert with AdaPert on small-effect perturbations | TxPert · K562.Replogle small-effect | PDS: 0.740 -> 0.737 | No clear effect |
| Replace TxPert with AdaPert on medium-effect perturbations | TxPert · K562.Replogle medium-effect | PDS: 0.663 -> 0.740 | Improved |
| Replace TxPert with AdaPert on large-effect perturbations | TxPert · K562.Replogle large-effect | DES: 0.353 -> 0.420 | Improved |
| Remove perturbation-specific context z_context from AdaPert (ablation) | AdaPert · effect-size groups | all metrics | Improved |
| Remove non-DEG loss L_non from AdaPert on small and medium perturbations (ablation) | AdaPert · small and medium effect groups | all metrics | Improved |
| Remove non-DEG loss L_non on large perturbations (ablation) | AdaPert · large effect group (>10% DE genes) | all metrics | No clear effect |
Closest papers by meaning
- PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (NeurIPS 2025 · similarity 0.86)
- STRAND: Sequence-Conditioned Transport for Single-Cell Perturbations (NeurIPS 2026 · similarity 0.85)
- PRESCRIBE: Predicting Single-Cell Responses with Bayesian Estimation (NeurIPS 2025 · similarity 0.85)
- PerturbReason: A Knowledge-Grounded Benchmark and Framework for Cell-State–Conditioned Mechanistic Reasoning of Perturbation Effects (NeurIPS 2026 · similarity 0.85)
- Contextualizing biological perturbation experiments through language (ICLR 2025 · similarity 0.85)
- MapPFN: Learning Causal Perturbation Maps in Context (NeurIPS 2026 · 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.
