Semi-supervised contrastive learning for bioactivity prediction using Cell Painting data

This repo contains the code to train SemiSupCon models and extract features from cell painting data for bioactivity prediction. We used the loss function from the Supervised Contrastive learning paper.

Baseline comparisson

Statistical report

Data

SemiSupCon(BBBC022) Embeddings

Baseline embeddings for the BBBC022 dataset

SemiSupCon(BBBC036) Embeddings

BBBC022 images processed with ImageJ