# Case study: Cell Painting: hits that were well positions
URL: https://omicsquest.com/case-studies/cell-painting-plate-effects/

Most 'active' compounds sat in outer wells, and replicate compounds failed to find each other. The phenotypes were mostly position effects.

Problem: The team's in-house analysis normalized features to the whole plate and called 300 hits. Medicinal chemists could not find any structure-activity relationship, and repeat plates gave different hits.

Findings:
- Hits were enriched about fourfold in edge wells. Evaporation changed cell density and morphology.
- Compound layout was not randomized across plates, so position and compound identity were linked.
- Replicate retrieval was near random (mAP close to baseline) for most hits, which meant the profiles were not reproducible.

Rescue:
- Normalized to on-plate DMSO controls, corrected well-position effects, and sphered profiles across plates.
- Selected features with pycytominer and removed density-confounded features.
- Scored phenotypic activity and replicate mAP with permutation testing, and kept only reproducible compounds.
- Mapped mechanism-of-action similarity against annotated reference compounds.

Result: The reproducible hit list shrank to 64 compounds that formed coherent clusters. Two clusters matched tubulin and HDAC reference phenotypes and lined up with chemistry series. We also designed a randomized plate layout for the next screen.

---
Source: https://omicsquest.com/case-studies/cell-painting-plate-effects/ | OmicsQuest, contact@omicsquest.com