Cell Painting predictions improve by weighing and reasoning on evidence
From Retrieval to Reasoning: Agentic Mechanism Prediction from Cell Painting Profiles
Artificial Intelligence
Summary
Predicting how drugs work using cell images can be tricky because similar-looking cells don’t always mean the same drug effect. The authors show that instead of just matching similar profiles, it’s better to carefully consider and weigh different pieces of evidence before deciding. They built a system called PhenoAIR that judges how reliable each piece of evidence is and uses that to make better predictions. This approach worked better than methods that only compare cell profiles or use language models.
What this means in practice
- •For pharmaceutical development teams: Improve drug mechanism predictions from cell imaging by using reliability-weighted evidence evaluation.
- •For computational biology engineers: Build more accurate phenotype-based inference tools by integrating evidence calibration and multi-agent reasoning.
Authors
Jiayuan Chen, Botao Yu, Tianyu Liu, Thai-Hoang Pham, Meng Wu, Ping Zhang
Abstract
Cell Painting is a high-content morphological profiling assay widely used for phenotype-based biological inference, with mechanism of action (MOA) prediction as a central application. Existing approaches largely formulate Cell Painting-based inference as representation matching, assigning predictions from nearby reference perturbations in morphological feature space. However, retrieved neighbors are often noisy and partially misleading evidence due to batch effects, non-specific cytotoxicity, phenotypic convergence, and source-dependent variability. We reformulate Cell Painting-based MOA prediction as a calibrated evidence reasoning problem, where retrieved neighbors are treated as uncertain observations that must be evaluated, compared, and sometimes rejected before supporting a mechanistic conclusion. We propose PhenoAIR, a reliability-aware multi-agent framework that maintains a candidate-centric evidence memory and performs controller-guided refinement over phenotype- and mechanism-side evidence. PhenoAIR uses offline reference-set calibration to weight evidence by source reliability, phenotype stability, and mechanism-level confusion. We evaluate PhenoAIR on a benchmark constructed from JUMP Cell Painting profiles and annotations, covering controlled, realistic, and discovery-oriented open-world MOA prediction settings. PhenoAIR outperforms representation-matching and LLM-based baselines across all settings.