Pinned Tweet
AI has two modes in drug discovery. Accelerate: moving faster through the existing playbook. Unlock: opening frontiers that weren't possible before.
Excited to announce Profluent is partnering with Eli Lilly, the global pharma powerhouse, to unlock breakthrough medicines for eal beyond the numbers ($2.25B + royalties): we’ll get to use our frontier AI models and foundational datasets to design proteins focused on large gene insertion, a therapeutic moonshot.
Proteins govern almost everything in biology. We've built a generalizable AI platform to design all proteins. Onward!
Excited to announce Profluent is partnering with Eli Lilly, the global pharma powerhouse, to unlock breakthrough medicines for eal beyond the numbers ($2.25B + royalties): we’ll get to use our frontier AI models and foundational datasets to design proteins focused on large gene insertion, a therapeutic moonshot.
Proteins govern almost everything in biology. We've built a generalizable AI platform to design all proteins. Onward!
21
25
321
46,214
Ali Madani retweeted
If I’m investing in frontier AI I would underwrite it mostly on new discovery and its applications like medicine because coding and most of knowledge work is quickly being saturated by sub-frontier models.
172
50
908
69,537
Boston biotech for ages: we don’t want to be seen as a CRO, that’s beneath us
Warp:
Warp:
While AI has advanced in mathematics, we believe there’s still a major gap in the physical sciences.
@warpsciences co-founders @kevinweil and Solomon Reisberg joined Lightspeed Partner @guruchahal to discuss how their labs could generate the experimental data needed to advance pany recently emerged from stealth and is building US chemistry labs to make research compounds for biotech and pharma companies.
“First be the hands, then build the nervous system, and then over time become the brain,” says Warp’s CEO Kevin.
The plan starts with expert chemists making molecules for customers. Cameras and sensors would record the work, helping Warp automate tasks and train models to improve how compounds are made.
More capable labs could let researchers pursue ideas for new medicines that time and cost currently put out of reach. The experiments could also produce more evidence for scientific AI to learn from.
Thank you to Kevin and Solomon for joining us!
Full episode below.
0:00 The Future Of Automated Labs
0:43 Introducing Warp Sciences And Founders
1:48 Kevin's Journey And Sol's Background
5:03 Building Warp's Founding Team
10:54 What Is A CRO And How Drug Discovery Works
13:24 The Pain Points: IP, Single Supplier And Geopolitical Risk
15:58 How Warp Is Taking On The Challenge
21:45 Threading The Needle On IP And Data Sharing
25:14 The Future Of Automated Labs, Business Plan And Funding
33:21 Closing Thoughts
4
1
100
10,361
Ali Madani retweeted
welcome to the 9th annual @stateofai report!
ai building better ai, world models, physical ai, geopolitics, cyber defense and 12-month predictions.
read it at stateof(dot)ai or watch my editor’s cut here.
a few of this year’s biggest findings follow:
ai building better ai, world models, physical ai, geopolitics, cyber defense and 12-month predictions.
read it at stateof(dot)ai or watch my editor’s cut here.
a few of this year’s biggest findings follow:
47
127
698
148,469
we build foundation models that span all protein modalities (ie not just one type of medicine). this partnership with @BioMarin pharma is one piece of evidence towards that.
we'll have even more announcements soon on this point
we'll have even more announcements soon on this point
We’re partnering with @BioMarin to use our AI models to design novel medicines.
Our foundation models unlock proteins with new and improved functions by drawing on the world's largest dataset of unique protein sequences (115B and counting): Profluent’s Protein Atlas
BioMarin generate and advance the strongest into preclinical testing. Looking forward to what AI can unlock for patients!
2
3
31
5,622
Finished off a great day, we secured a ton of GPUs to design proteins and craned a *literal ton* of laboratory equipment to test proteins.
Build, build, build. We don’t stop
Build, build, build. We don’t stop
4
3
144
6,403
Great to see Dario funding this. I may know a thing or two about enzyme discovery and AI. I liked the work and think highly of the researchers behind it all (yes you’ll eventually find a person behind all the AI)
You can have it all in biology right now. The well of opportunity is deep.
You can have it all in biology right now. The well of opportunity is deep.
Claude has discovered a previously unknown enzyme system hidden in the DNA of bacteriophages. Beside the enzyme’s gene sits a long array of repeating DNA—a structure that looks somewhat similar to CRISPR.
We don’t yet understand what this system does, but only a handful of known systems share its features, and all of them are able to cut, copy, and paste DNA. Historically, the discovery of such programmable systems has helped revolutionize medicine. CRISPR, for instance, is now the foundation of genetic medicines. But it will take much more work to learn what this system does, and whether it can be put to similar use.
Read more: anthropic.com/news/claude-di…
4
1
55
4,613
Unbelievable momentum, unstoppable founder @OmarKunbargi
Peace is possible. We're building it @Asymmlabs.
We've raised $51M toward that goal.
More announcements to come.
2
0
10
2,700
The government is backing us for a moonshot to design *personalized curative* medicines. Excited to be partnering with GemmaBio and be in the elite company of the best medical centers in the world.
Each word has significance.
Personalized = bespoke to each patient [this is ogy with AI can directly play a role]
Curative = lasting solutions that cure not just manage disease. This is what we at Profluent live for, real cures to disease.
Let's go build!
Each word has significance.
Personalized = bespoke to each patient [this is ogy with AI can directly play a role]
Curative = lasting solutions that cure not just manage disease. This is what we at Profluent live for, real cures to disease.
Let's go build!
12
10
113
16,920
come chat with jeff and team in one of the coolest cities in the world!
I’m heading to ICML in Seoul with the @ProfluentBio team. If you want to talk protein design, generative models, or anything BioML, come find me!
And if you want to meet the Profluent team, we're hosting dinners and doing coffee chats throughout the week. Sign up below.
1
1
19
4,538
first time agreeing to do a podcast b/c (1) @nathanbenaich is legend and (2) there's so much happening in the field [modeling paradigms, effect of scale, big deals, clinical readouts]
it's a builder's future, now.
it's a builder's future, now.
it's been a huge few weeks for ai in bio: a $2.25b @ProfluentBio x @EliLillyandCo deal on ai-designed gene editors, verve's base-editing data, new scaling results on protein models from @czbiohub, @IsomorphicLabs' haul.
@thisismadani and i recorded a pod diving into all of it
logy from discovery to design, sequence-first vs structure-first, and why he calls this the "gpt-1.5 era" of biology...
enjoy!
3
4
26
8,258
Ali Madani retweeted
This has quietly been a miracle month in medicine.
In the last 5 weeks we’ve got news on:
- retatrutide, the triple agonist GLP-1 from Lilly, basically melting fat and body-wide inflammation at record levels
- RevMed’s new pancreatic cancer drug showing unprecedented abilities to extend life
- small trial of a one-and-done PCSK9 gene editing therapy for slashing LDL cholesterol
- Mayo’s AI-assisted radiology showing vastly improved cancer detection
- this new therapy for metastatic solid tumors
This stuff is at varying levels of evidence. Retatrutide is ~100% on its way, other stuff needs more clinical trial data. But put it together and we’re maybe on the verge of majorly reducing the mortality of heart disease and cancer, the two leading causes of death in America.
In the last 5 weeks we’ve got news on:
- retatrutide, the triple agonist GLP-1 from Lilly, basically melting fat and body-wide inflammation at record levels
- RevMed’s new pancreatic cancer drug showing unprecedented abilities to extend life
- small trial of a one-and-done PCSK9 gene editing therapy for slashing LDL cholesterol
- Mayo’s AI-assisted radiology showing vastly improved cancer detection
- this new therapy for metastatic solid tumors
This stuff is at varying levels of evidence. Retatrutide is ~100% on its way, other stuff needs more clinical trial data. But put it together and we’re maybe on the verge of majorly reducing the mortality of heart disease and cancer, the two leading causes of death in America.
This is actually insane.
97% of people taking the standard of care for metastatic solid tumor got worse by seven years.
But with lorlatinib, that number was only 45% in the same time!
This is an ENORMOUS jump in the quality of cancer care.
212
1,916
11,734
2,935,391
Ali Madani retweeted
We pre-train LLMs on the whole of the internet. You might think this explains how they learn so many emergent capabilities: the knowledge is implicit in the training data.
But in fact models can do things that were never demonstrated anywhere in training!
@svlevine argues that gent capabilities is compositionality:
But in fact models can do things that were never demonstrated anywhere in training!
@svlevine argues that gent capabilities is compositionality:
47
98
1,393
152,517
This release is huge.
So many impressive results, descriptive methods, and all around open science.
Really refreshing. Congrats to the team. Your papers are basically textbooks at this point
So many impressive results, descriptive methods, and all around open science.
Really refreshing. Congrats to the team. Your papers are basically textbooks at this point
I'm so excited to show the world what we've been working on the for the past months!! I'm going to highlight some of the fun results from this paper that I find particularly exciting.
3
1
67
6,179
the verve story line has always been inspiring to me. wishing them continued success as they trail blaze through.
these are the bets worth making. once it pans out, there will be a rush toward these modalities and opportunities.
glad our future doesn’t get locked away and shelved bc of short sightedness or risk aversion
these are the bets worth making. once it pans out, there will be a rush toward these modalities and opportunities.
glad our future doesn’t get locked away and shelved bc of short sightedness or risk aversion
Every non-biotech person I describe Verve to is floored. They can't believe this is a future we get to live in - permanent solution for high cholesterol and strokes - even after I tell them it means editing their genes.
At the same time more than 90% of the biotech VCs I've talked to are bearish on exactly this direction.
"Why cure a disease if you can do monthly injections"
"Insurance would never cover cures"
I am excited for those people to not make any money when they are proven wrong. Its striking that no one sees that cures have been out of vogue for very silly reasons - we equated one-and-done to viral vectors, rare disease TAMs, and rare disease prices. None of those are relevant assumptions, and Lilly has multiple bets in this space to prove everyone wrong.
0
0
22
3,234
can AI scale it?
at ASGCT this month, we showed AI can ~10x the addressable coverage when designing base editors (the molecules behind the Verve/Lilly announcement), among other benefits.
that translates to an unlock for patients by dramatically expanding addressable targets iting
we don't want a world where this is a one off breakthrough. we want a repeatable engine.
at ASGCT this month, we showed AI can ~10x the addressable coverage when designing base editors (the molecules behind the Verve/Lilly announcement), among other benefits.
that translates to an unlock for patients by dramatically expanding addressable targets iting
we don't want a world where this is a one off breakthrough. we want a repeatable engine.
Eli Lilly has done it.
They've gone and made what seems to be a powerful, permanent gene therapy for LDL cholesterol.
That means they'll be able to effectively prevent most heart disease with a single infusion!
3
3
28
10,096
for more: x.com/ProfluentBio/s…
We're at @ASGCTherapy today sharing something we've been heads down building: using our AI models to scale base editing for personalized medicine.
The gap between what's theoretically correctable and what we can actually fix today is huge. We think AI can close that gap.
Not ur SVP of Gene Editing, breaks it down here. Interested in learning more? Shoot us a DM.
0
0
1
734
cool to see 3 nature papers published in one day on AI for science.
contrary to AI replacement doomerism, i firmly see the future being defined by the scientist. incredible time to build
previous decades focused builder energy on social media or enterprise SaaS. this is insanely more exciting and impactful.
drug discovery clearly is one of the largest impact areas. i hope it will extend beyond that as well
contrary to AI replacement doomerism, i firmly see the future being defined by the scientist. incredible time to build
previous decades focused builder energy on social media or enterprise SaaS. this is insanely more exciting and impactful.
drug discovery clearly is one of the largest impact areas. i hope it will extend beyond that as well
3
10
79
9,971
Papers:
nature.com/articles/s4158…
nature.com/articles/s4158…
nature.com/articles/s4158…
Congrats @SGRodriques @andrewwhite01 @vivnat michael brenner and respective teams!
nature.com/articles/s4158…
nature.com/articles/s4158…
nature.com/articles/s4158…
Congrats @SGRodriques @andrewwhite01 @vivnat michael brenner and respective teams!
0
0
13
1,231
