MorphoHELM is a new benchmark for Cell Painting morphology representations that tests methods across increasing batch effect levels and finds classic computer vision strategies remain the strongest general-purpose performers.
Machine learning and image-ba sed profil- ing in drug discovery
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
DINO-based ViT models pretrained on HPA FOV achieve macro F1 of 0.822 zero-shot and 0.860 after fine-tuning for protein localization on OpenCell, demonstrating effective transfer from SSL pretraining.
citing papers explorer
-
MorphoHELM: A Comprehensive Benchmark for Evaluating Representations for Microscopy-Based Morphology Assays
MorphoHELM is a new benchmark for Cell Painting morphology representations that tests methods across increasing batch effect levels and finds classic computer vision strategies remain the strongest general-purpose performers.
-
Using Deep Learning Models Pretrained by Self-Supervised Learning for Protein Localization
DINO-based ViT models pretrained on HPA FOV achieve macro F1 of 0.822 zero-shot and 0.860 after fine-tuning for protein localization on OpenCell, demonstrating effective transfer from SSL pretraining.