Generating Joint Transcriptomic and Morphological Responses to Drug Perturbations via Rectified Flow
Verma, S.; Wang, M.; Wang, L.; Sola, M.; Kazemian, M.; Grama, A.; Lanman, N. A.
Show abstract
MotivationPredicting cellular responses to drug perturbations requires capturing complex dependencies between transcriptomic and morphological changes. Existing approaches model these modalities in isolation, missing critical molecular-phenotypic relationships that occur simultaneously during drug treatment. No current method jointly predicts gene expression profiles and cellular morphology from chemical perturbations. ResultsWe introduce PertFlow, a unified computational frame-work that simultaneously predicts treatment gene expression (bulk RNA-seq) and generates cellular morphology (Cell Painting images) from control cellular states, conditioned on drug metadata. Evaluated on paired RNA-seq and imaging data from 3 cell lines and 40 compounds (17,242 samples), PertFlow achieves Pearson correlation of 0.780{+/-}0.264 for transcriptomic prediction and FID of 24.06 for morphological generation. Board-certified pathologists rated generated images with median similarity scores of 7.11-7.89/10. The model successfully recovers known drug mechanisms including microtubule disruption, DNA damage, and MAPK pathway inhibition, with gene enrichment analysis confirming activation of expected biological pathways (EMT, p53, apoptosis). AvailabilityCode and pretrained models will be available at https://github.com/wangmengbo/PertFlow.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Capturing cell heterogeneity in representations of cell populations for image-based profiling using contrastive learning 96%
- Predicting drug polypharmacology from cell morphology readouts using variational autoencoder latent space arithmetic 95%
- A deep generative model of 3D single-cell organization 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.