Research map / Probabilistic and scientific modeling / Molecules and proteins

CytoWave: Perturbation-Centric Pretraining for Single-Cell Response Prediction

NeurIPS 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Protein fitness and variant effect prediction

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes CytoWave, a perturbation-centric pretraining framework for predicting single-cell gene expression responses to perturbations that aims to generalize across datasets, protocols, contexts, and species.

Problem

Predicting gene expression under perturbations from single-cell data, where existing methods generalize poorly across datasets due to differences in experimental protocols, biological contexts, and species.

Approach

A perturbation-centric pretraining framework (CytoWave) intended to learn transferable representations of perturbation effects for single-cell response prediction; specific mechanism not stated in the available abstract.

Closest papers by meaning

• PRESCRIBE: Predicting Single-Cell Responses with Bayesian Estimation (NeurIPS 2025 · similarity 0.90)
• PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis (NeurIPS 2025 · similarity 0.90)
• STRAND: Sequence-Conditioned Transport for Single-Cell Perturbations (NeurIPS 2026 · similarity 0.89)
• PertEval-scFM: Benchmarking Single-Cell Foundation Models for Perturbation Effect Prediction (ICML 2025 · similarity 0.88)
• PerturbReason: A Knowledge-Grounded Benchmark and Framework for Cell-State–Conditioned Mechanistic Reasoning of Perturbation Effects (NeurIPS 2026 · similarity 0.87)
• A benchmark for prediction of transcriptomic responses to chemical perturbations across cell types (NeurIPS 2024 · similarity 0.87)