VP DataSci @RecursionPharma;ex-Freenome(CSO), Counsyl(VP Sci Aff), Stanford(PhD), forever Cal 🐻.
Tweets my own, except when RTs; those prob someone else's!
Apr 26, 2023 • 10 tweets • 8 min read
More tweetorial! Let’s dig into the “proximity bias” we found @RecursionPharma confounding #CRISPR screens, what it means, and where it comes from.
You can always read along in the preprint here: biorxiv.org/content/10.110…
If you missed the first tweetorial in the series, click here to understand what the red-and-blue heatmaps here mean, and how we use them to map the functions of genes at a genome-wide level:
Tweetorial time! We @RecursionPharma mapped consequences of #CRISPR screening of >17K human genes, found a systematic bias confounding all CRISPR screens, traced its molecular cause, and propose a debiasing algorithm.
“But Imran,” you say, “I’d rather read your thrilling 41-page manuscript than read tweet threads!”
in terms of jumping cat gifs.
A primer: the @RecursionPharma platform takes images of cells under different conditions (disease agent, disease+drug, control, etc.), and feeds the images through a custom deep network to derive a high-dimensional (128-1024D) "embedding".
We developed a human cell model of SARS-CoV-2 infection, compared it to the field-standard monkey cell model, and screened ~1700 drugs.
Also: the entire cellular image dataset (~450GB of 5-channel microscopy) is available at rxrx.ai/rxrx19. 305,520 5-ch pics @ 1Mpx licensed CC-BY. Want some big image data for ML to help with the pandemic? Here it is. We've also released the DL image embeddings.