Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Imran S. Haque (@ihaque@{bsky,genomic}.social) Profile picture
Imran S. Haque (@ihaque@{bsky,genomic}.social)
@ImranSHaque
SVP AI and Digital Sciences @RecursionPharma. ex-Stanford(PhD), forever Cal 🐻. Find me at https://t.co/LPj0As6wOO if the alternative handles get banned.
May 1, 2023 • 12 tweets • 5 min read
Friday got away from me, but it was a beautiful weekend.

Today, the last tweetorial: how to debias the proximity bias we found @RecursionPharma widely confounding #CRISPR screens, and what it means for the field.

Preprint: biorxiv.org/content/10.110…

Image
Image Earlier tweetorials to understand the similarity maps we examined, what “proximity bias” means and its molec. origins in chrom. truncations, and how resources like @CancerDepMap are confounded by prox bias:





Apr 27, 2023 • 14 tweets • 7 min read
Tweetorial 3: how the “proximity bias” we found @RecursionPharma confounding #CRISPR screens affects widely used screening resources like the @CancerDepMap (spoiler: the image below!), and where it comes from.

Read along in the preprint: biorxiv.org/content/10.110…

Image
Image If you missed the first two tweetorials in the series, click here to understand the similarity maps we examine here, what “proximity bias” means, and its molecular origins in chromosomal truncations:




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… Image 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:
Apr 25, 2023 • 10 tweets • 5 min read
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. Image “But Imran,” you say, “I’d rather read your thrilling 41-page manuscript than read tweet threads!”

I can’t blame you, it’s great! (I may be a biased source.) Here ya go: biorxiv.org/content/10.110…
Aug 10, 2020 • 20 tweets • 8 min read
Happy Monday! In today's #tweetorial on our recent preprint describing @RecursionPharma's platform (biorxiv.org/content/10.110…), I'll explain the unusual 2-D drug response plots we use there and in our COVID-19 screen data at covid19.rxrx.ai..

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".
Apr 26, 2020 • 23 tweets • 11 min read
Very proud to be part of the team @RecursionPharma working on #Covid_19 and of our preprint today: biorxiv.org/content/10.110…. Brief #tweetorial :

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.