Accelerating drug discovery through systems-level understanding of diseases with in-vivo CRISPR and AI.
San Francisco, CA
Joined March 2026
- Tweets27
- Following36
- Followers1.1K
- Likes10
Perturb.ai retweeted
Rosalind for new drug discovery ideas:
GPT-Rosalind surfaced a new lead for drug discovery: could restoring cholesterol transport protect neurons from degeneration?
DCTN1 is a gene linked to Perry syndrome, a rare neurodegenerative disorder. In mouse-brain data, disrupting it increased expression of genes involved in making cholesterol. GPT-Rosalind suggested a possible explanation: cholesterol may not be reaching where neurons need it.
That gives scientists a specific mechanism to test and, if confirmed, a direction for developing new treatments for neurodegenerative disorders.
With @perturbai_tx and @scrippsresearch, a team of thousands of GPT-Rosalind agents worked in parallel, connecting gene-expression results from millions of mouse brain cells with scientific literature in just 32 minutes. We’re now expanding this collaboration to identify new drug targets.
openai.com/index/scaling-ai-…
8 million brain cells. 32 minutes. A new frontier in medicine.
In less than a year, PerturbAI built a proprietary AI-native drug discovery engine, created 6 genomic maps, revealing how genes influence health and disease in living systems.
Now, together with @OpenAI and @ScrippsResearch, we've uncovered 11,000 biological insights and ~100 promising leads using frontier AI in just 32 minutes.
We're expanding our partnership into drug-target discovery, bringing us closer to understanding disease and developing new medicines.
Better biology. Better targets. Better medicines.
Learn more: perturb.ai/news/perturbai-la…
Read the full blog here: openai.com/index/scaling-ai-…
Is AI making drug discovery more efficient?
According to a recently published paper in Nature Reviews Drug Discovery, not yet. And as @axios highlighted this week, a key reason is that today's AI is trained on data that does not translate into clinically successful targets.
This is why we founded PerturbAI. By generating large-scale causal data directly in living organs, we can identify targets more likely to translate and make better therapeutic decisions early, before years and millions are spent downstream.
Read the full Axios article here: finance.yahoo.com/healthcare…
Learn more about how PerturbAI is addressing this challenge: perturb.ai/
#AI #Biotech #DrugDiscovery #CRISPR #Genomics
It was great to hear former Akero Therapeutics CEO Andrew Cheng unpack their landmark deal with Novo Nordisk at #BIO2026.
From leading Akero through its $5.2B acquisition to his decades of clinical leadership at Gilead Sciences, Andrew's track record of scaling biotech innovation is unmatched.
We are incredibly fortunate to have Andrew bringing that caliber of industry foresight to PerturbAI as an advisor. His expertise is an invaluable asset as we work to build the next generation of AI-enabled therapeutics.
#Biotech #Innovation #DrugDiscovery #AI
PerturbAI is taking the stage at HardTech LIVE during San Francisco’s @deeptechweek on June 26!
Our co-founder and CEO, Grace Zheng, will share how PerturbAI is building biology's causal data engine, and using AI to turn insight into better medicines.
A few VIP spots are left for this event. Claim one here: deep-tech-week.com/sf-2026/e…
#DeepTechWeek #HardTech #AI #Genomics #DrugDiscovery
Last week, we wrote about our proprietary AI platform that powers therapeutic discovery at PerturbAI.
Today, we're sharing public tools and workflows we developed together with @NVIDIAHealth that make it easier to explore and analyze our Whole-Brain CRISPR Atlas, now downloaded more than 30,000 times since we released it in March.
perturb.ai/news-0623-public-…
🧠🧬✨
Read NVIDIA's announcement today at BIO about our BioNeMo collaboration here: nvda.ws/4vtsoxd
Perturb.ai retweeted
Yesterday at @OpenAI Forum Building the Future of AI, one takeaway stood out: closing the AI capability overhang takes more than better models. It requires the right biological data, rigorous evals, deployment, and tight feedback loops. That’s what we’re building at @perturbai_tx
(1/4) What if two genes in the same pathway suggest completely different therapeutic strategies?
Using our whole-brain CRISPR atlas, we found that two closely related NMDA receptor genes - GRIN2A and GRIN2B - produce markedly different effects across brain cell types and regions.
Some shared downstream genes even move in opposite directions.
A 🧵
(4/4) We walk through this example, additional insights from neurodegeneration-linked genes, and how PerturbAI uses organism-scale causal biology and AI to identify therapeutic opportunities in our latest blog post.
🔗perturb.ai/news-0618-proprie…
🧠🧬✨
Wrapping up a massive month for PerturbAI with some #BTS moments from the @OpenAI Forum!
We showcased our technology, unpacking how AI can help biology move from static maps toward predictive, causal models of living systems. We loved answering your thoughtful questions and were thrilled by the incredible interest our demo drummed up.
Our AI agents and models are designed to move biology from data to insight to therapeutic action, helping accelerate drug discovery from the ground up.
If you missed it, watch the replay of the Forum here: forum.openai.com/home/videos…
#AI #Biotech #DrugDiscovery #CRISPR #Genomics
Happening TODAY at 1:00 p.m. PT!
We are going live at the @OpenAI Forum, discussing PerturbAI’s platform and how AI is replacing complex, manual workflows with systems that allow researchers to accelerate drug discovery.
Don't miss out on:
•Our research presentation
•A fireside chat
•Live Q&A with the team
Register now and we'll see you in a few hours: bit.ly/41ANmgd
#CRISPR #Neuroscience #DrugDevelopment #Biotech #AI
Perturb.ai retweeted
Looking forward to it. Excited to share how large scale in vivo CRISPR atlas and AI reasoning models can help accelerate biology and medicine.
🔬 What if we could predict disease before it starts, tailor treatments to each person, and discover new medicines in a fraction of the time?
🧬 Join OpenAI Forum for a conversation on how AI is decoding biological intelligence with:
- @gracexyzheng, Co-Founder and CEO, @perturbai_tx
- @xinjin PhD, Co-Founder, PerturbAI and Professor at @scrippsresearch and Howard Hughes Medical Institute (HHMI)
- @joyjiao12, Researcher at OpenAI
Anyone in the world can attend this conversation ⬇️ forum.openai.com/public/even…
Perturb.ai retweeted
Look forward to sharing how causal in vivo data and AI reasoning models can work together to build better medicine. Excited for this conversation with @xinjin and @joyjiao12
Next Wednesday at the @OpenAI Forum, I’ll be joined by @perturbai_tx to talk about decoding biological intelligence with AI. GPT-Rosalind is an exciting lead-in to that discussion, and we’re especially excited about the data and the collaboration behind! forum.openai.com/public/even…
Perturb.ai retweeted
Excited for @OpenAI Forum on 4/22 @joyjiao12 @gracexyzheng!
One of the biggest opportunities in AI x bio is learning data from native physiology in vivo to decode complex disease: context matters. We’ll also be discussing the newly released GPT-Rosalind! Come hear what’s next 👇
Next Wednesday at the @OpenAI Forum, I’ll be joined by @perturbai_tx to talk about decoding biological intelligence with AI. GPT-Rosalind is an exciting lead-in to that discussion, and we’re especially excited about the data and the collaboration behind! forum.openai.com/public/even…
AI isn’t just a chatbot; it’s accelerating drug discovery!
Tune in next week for our presentation, Decoding Biological Intelligence: Building AI Agents for the Brain Genome, at the @OpenAI Forum.
Our collaboration with OpenAI has enabled us to build the world’s largest in vivo CRISPR atlas, representing a dataset of 8 million brain-wide cells.
PerturbAI co-founders Grace Zheng and Xin Jin, PhD will discuss how AI is fundamentally transforming scientific discovery, ushering in a new era of biology and medicine that is more predictive, more precise and far more effective.
Learn more about our presentation and save your spot here: bit.ly/41ANmgd
#AI #Genome #Neurology #CRISPR
Perturb.ai retweeted
Form follows function, or function dictates form?
📢Preprint: we build Perturb-CLEAR, in vivo screen of neuroanatomy! Disease perturbations produce selective morphology-RNA changes that RNA impact alone cannot predict. Was led by the invincible @BoliWu!
biorxiv.org/content/10.64898…
