Gordian Biotechnology (@GordianBio)

Pinned Post

@GordianBio

20 Nov 2024

The success of AI applied to drug discovery is being decided by a number of clinical trials. So far, the results are lackluster. Why? For AI to have a transformational effect in drug discovery, training data must come from living mammals. (🧵1/9)

6

28

60

14,834

Gordian Biotechnology

@GordianBio

Jul 1

AI made hypothesis generation and molecule design fast because the enabling data was ready. Now we're getting the data ready for what's still holding up drug discovery: causal validation. At BIO 2026's @IAmBiotech "AI x Nature" panel, our CEO Francisco LePort walked through what's real vs. what's hype in AIxBio. He pointed to causal target validation in vivo as the critical bottleneck in drug discovery, especially as AI makes the earlier steps faster. At Gordian, a single in vivo screen validates thousands of target hypotheses across cardio-renal-metabolic disease. We are building our internal pipeline on that screen, while also partnering externally with Pfizer and others to be announced soon.

1

5

467

Gordian Biotechnology reposted

Martin Borch Jensen

@MartinBJensen

Jun 24

Happy to see @GordianBio's Mosaic Screening paper among these. We took in vivo perturb-seq from observation to therapeutic assessment, from mice to horses. biorxiv.org/content/10.64898…

A Multispecies, Modality-Agnostic Scalable In Vivo Mosaic Screening Platform for Therapeutic Target...

Validating therapeutic targets for complex diseases requires investigating gene functions within native tissue architectures rather than reductionist in vitro models. Here we present a modality-agn...

biorxiv.org

Oded Rechavi

@OdedRechavi

Jun 24

Gloves are off! TODAY WE RELEASE THE 1% A list of the year’s very best papers. When we launched QED a little over half a year ago, I told you that our mission is to revolutionize scientific publishing. Revolutions don’t happen overnight… or maybe they do? When new technologies enable it? Time to put the power back in the scientists’ hands, not the journals’. Many scientists are depressed, and think journals will stay the same forever, no matter how dysfunctional, but no, it’s happening. Sooner than most people (or committees, or universities) can imagine. Check this out: When we released our AI review platform, it started a whole debate (and social media storm) on what it is that human reviewers can do that AI review still can’t. There are such things (and I’m happy about it), but the list is getting shorter and shorter. Numerous scientists already use QED to find gaps in their manuscripts and grants and to get constructive feedback that improves their experiments. And now, with your help, we take it to the next level. Today we release reviews and scores for all the experimental Life Science pre-prints that came out last year: 57,455 manuscripts!! If we are being conservative, and estimate that it takes a minimum of 8 hours to review a paper (it takes longer), and if we agree that 3 reviewers are typically required to review every submission, then reviewing this amount of manuscripts would take human experts >1 MILLION REVIEWER HOURS… Assuming you can find so many experts (not going to happen!), and assuming the experts who agree would have no conflict of interest (ha!!). QED did it. Then, we chose the best papers in every field (you can browse and search for key words), based on the originality and validity of the claims being made. We benchmarked our reviews not only using eventual journal selections but also by comparing our evaluations to those of human experts. When there were disagreements between the QED score and journal rank, we asked domain experts to judge who’s right (blindly), and they overwhelmingly sided with QED. No need to rely on glam journals anymore. No need to wait for two years to get their stamp of approval. No need to beg the reviewers, or worse, to write less ambitious papers, so no one would be upset. Want to find the most interesting papers in your field? Want to see where your paper stands? (“What’s your QED SCORE?”) Just visit qedscience.com! One last thing: We want good science to be seen (you can read the winners’ comments about their selection and the stories behind their discoveries on our website). We plan to organize a conference where the first authors (yes, the first authors, not the PIs) will present their work. We are not here to shame anyone (papers that got low scores). The reviews of the best papers that we selected explain why QED’s AI thought these papers are especially good - what’s unique about them, what their strengths are, which conceptual leaps were made, and what cutting-edge tools were developed. However, on the QED Science site you can analyze any paper in private, it’s fully transparent, and see if there are any gaps and what’s missing. Run your paper to see how it can improve, and maybe next time your paper will reach the top (if it’s not there already). Whether you’re on the 1% list of just have a good score that you want to share, on our website you can download the report and share it, for example with your tenure, promotion, or hiring committee, or with your university PR department. Forget about journal embargoes and waiting for it to be “accepted”. Improve your work until it’s good enough for YOU. You decide.

1

2

11

4,398

Gordian Biotechnology

@GordianBio

May 25

It's me!

Martin Borch Jensen

@MartinBJensen

May 25

Memorial day is for progress

3

247

Gordian Biotechnology reposted

Martin Borch Jensen

@MartinBJensen

May 20

On AI for bio: AI has advanced the most in domains where outputs could be verified quickly. Games have winners, code and math can be formally validated, and chatbot conversations have continuous user feedback. Pubmed cannot provide the same function for biology, because it’s very spotty documentation even of what we think we know. The verifiable outcomes need to be experimentally generated ground truths.

7

4

31

2,553

Gordian Biotechnology reposted

Martin Borch Jensen

@MartinBJensen

May 19

The “data for AI in bio” discourse is shifting from “we need data” to “what's the right data for this problem?”, and then how to produce it. Right now there's a key gap between stated goals of curing disease and ongoing data generation efforts. We gravitate towards rapid and scalable experiments, even when those will never tell us how to treat Alzheimer's or aging. The default path is that intelligence will explode, and cures will be stuck waiting for data that can't be accelerated. There is work we should start today if we want to avoid that. I wrote out thoughts on how we can identify data that will/won't let us cure disease, and how to overcome the technical and physical barriers to making it.

7

25

93

10,726

Gordian Biotechnology reposted

BiotechTV

@BiotechTV

Apr 23

𝐔𝐧𝐥𝐨𝐜𝐤𝟐𝟎𝟐𝟔: @GordianBio Co-Founder & CSO @MartinBJensen discusses the company's large-scale in vivo screening work. #UNLOCK2026

2:55

1

7

26

5,037

Gordian Biotechnology reposted

Seth Bannon

@sethbannon

Apr 13

Multiplexed in vivo screening is the future of drug development. @ManifoldBio is multiplexing protein therapies in vivo. @GordianBio is multiplexing gene therapies in vivo. @waypointbio is multiplexing cell therapies in vivo. GT Bio is multiplexing LNPs in vivo. 50Y portcos all

7

19

187

37,560

Gordian Biotechnology reposted

Martin Borch Jensen

@MartinBJensen

Apr 13

We're multiplexing target validation in vivo, for any modality :) Our first small molecules are looking promising, in addition to AAV therapy we're having FDA meetings about.

1

12

1,051

Gordian Biotechnology reposted

Norn Group

@NornGroup

Apr 6

Something is bottlenecking AI from increasing the number of treatments that make it to patients… @MartinBJensen: “Today, [hypothesis generation, making the drugs, and clinical trials] are being greatly accelerated by AI... But what about the causal validation? Right now, we are still going into the lab and running experiments. Every pharma company is still testing their drug in animal studies. We're not doing things differently than we were when ChatGPT2 came out.” - @PMWCintl 2026

2:03

3

13

3,589

Gordian Biotechnology reposted

Norn Group

@NornGroup

Mar 30

Aging is the #1 risk factor for so many of the diseases NIH funds billions to, but gets ~5% of the funding those diseases get individually. "For those who are entrepreneurs: if I told you your company is failing, you don't have enough sales, it's like ‘let's optimize the font on our website.’" - @MartinBJensen, @NornGroup founder & @GordianBio CSO

1:51

3

19

1,868

Gordian Biotechnology reposted

Martin Borch Jensen

@MartinBJensen

Apr 1

I'll be at UNLOCK talking about what I think is the most underappreciated bottleneck in AI for drug discovery: the "right data for your question" problem. There is a lot of excitement about AI for drug discovery, and rightly so. But how much it will help tell us HOW to cure disease, is limited by not having enough data that encompasses diseases at work. 'Disease' happens in organs and organisms, with all their feedback loops and emergent complexity, not in individual cells. And for age-related diseases, such data will take years to generate. As models get smarter and cheaper, the cost of not having started collecting the right data rise. This is solvable if we become deliberate and strategic about which datasets to build and how. I'll get into how Gordian is tackling this through large-scale drug discovery in living animals developing age-related disease and generating organism-level data. I'll also be sharing the next focus for @ImpetusGrants/@NornGroup, on building the datasets that will make AI maximally useful for longevity.

UNLOCK AI x Science

@unlockscience26

Mar 30

Most drug discovery for aging diseases starts in a plastic dish with young cells. @MartinBJensen and his team at @GordianBio test hundreds of therapies simultaneously in living animals instead. Speaking at UNLOCK 2026. April 22 in SF. unlockscience.ai

2

10

1,920

Gordian Biotechnology reposted

Martin Borch Jensen

@MartinBJensen

Mar 10

AI is mind-blowing, and yet it’s not on track to give us many more new medicines for aging and disease, because so much of our data is about molecules and cells rather than organs and organisms. If we want AI to make progress here, we have to be deliberate about the datasets we build today. As the QT describes, “biology” really refers to different layers of organization (molecular, cellular, physiological). A reaction working x-fold faster is not x-fold progress in “biology” - useful answers have to work at the level where your problem is. We can’t simulate one from the former because of emergent behavior and a scale that can’t be simulated (you may have seen today’s paper on simulating the simplest possible cell. A human cell, let alone organ, is orders of magnitude more). This means that we cannot predict aging and complex disease (which emerges from the physiological layer) using AI purely trained on datasets lower layers. How should we think about the datasets we’ll need to cure disease? We can think of an experiment across six dimensions. Those are: how relevant it is to disease, how comprehensive its answer, how scalable, how costly, how fast to iterate, and how precise. Experiments on each layer score differently across these six dimensions. Work at the molecular level score high on speed, scale, and cost, but low on relevance to disease (knowing the structure of a protein may explain Huntington’s, but not most diseases). Living patients are of course most relevant, but most $ and time. Cells and model organisms are in between. The first rule I follow for AI-enabling datasets is that our data should span 1) the layer where answers lie (i.e. if we’re studying aging we must involve a living organism), and 2) a layer where we can causally test hypotheses at scale. In a perfect world these are the same model system, but that’s not always possible. If not, we need paired datasets that maps states and responses across those layers. New technology can change the tradeoffs. For example, at @GordianBio we screen hundreds of targets simultaneously inside living organs with naturally progressing disease, such as horses with spontaneous osteoarthritis. So the experiment happens in the physiological layer, but experimental set up, but with scale of perturbation testing more akin to what people do at the cellular layer.

Norn Group

@NornGroup

Mar 10

We build datacenters to meet anticipated compute demand. We should also build biological datasets to meet anticipated demand from abundant intelligence. AI is quickly getting good at drug design and hypothesis generation, which means more hypotheses in line to be tested. But target validation hasn’t kept pace. It is still hard, slow, and expensive, so drug discovery has crowded around the same already de-risked targets while most of the genome stays unexplored. Like our founder @MartinBJensen mentioned at @PMWCintl, to break out of that and achieve real target abundance, causal validation of targets needs to work at high throughput. AI hasn’t been able to tell us what targets to go after because we don’t have the right data. Biology operates at three layers: molecular, cellular, and physiological. Each layer has emergent properties which cannot be predicted by just looking at the layer below it. Most diseases are organ-level phenomena, and we don't yet have the in vivo datasets to predict them from cellular data alone. This is where we are focusing next for Impetus Grants @impetusgrants: building the datasets that will give us more and better targets for aging drugs. Contact us in the link below if you want to support this round.

2

5

24

3,537

Gordian Biotechnology reposted

UNLOCK AI x Science

@unlockscience26

Mar 30

Most drug discovery for aging diseases starts in a plastic dish with young cells. @MartinBJensen and his team at @GordianBio test hundreds of therapies simultaneously in living animals instead. Speaking at UNLOCK 2026. April 22 in SF. unlockscience.ai

1

5

12

1,840

Gordian Biotechnology reposted

Martin Borch Jensen

@MartinBJensen

Mar 4

Finding new medicines is getting more and more expensive, and AI won't help much unless we can generate physiological data at scale. In our new preprint, @GordianBio extends the progress of the functional genomics community to run pooled in vivo screens at scale, in a way that answers questions about physiology and therapeutic potential. We show screens in mice and horses, fibrotic and degenerative disease, with a framework for physiological predictions validated in human ex vivo tissues. Very proud of @v_sontake, @vkartha88, Neety and the rest of the team. Tweetorial follows:

9

58

203

38,784

Gordian Biotechnology reposted

Martin Borch Jensen

@MartinBJensen

Feb 19

Within a year, @Gordianbio went from not working in obesity to running in vivo screens in visceral adipose tissue and signing a collaboration with Pfizer. @BradLoncar stopped by the lab to hear about it. There are thousands of GWAS hits that correlate with body weight and other targets with human evidence, but the bottleneck is figuring out which of those are interesting as drug targets, with causal potential, in a relevant biological environment. Gordian solves that. We use AAV to deliver different payloads into a tissue so you get a mosaic where individual cells are perturbed by different targets. Then we read it out with single-cell transcriptomics to assess what changed after treatment. Does targeting this gene do what you'd expect, or does it get overruled by inflammatory signaling or systemic metabolism? You can rank hundreds of targets for causal signal in one experiment. Brad asked great questions about where in vivo models still matter and where they don't. Worth a watch if you're thinking about the next wave of obesity target discovery beyond GLP-1s.

BiotechTV

@BiotechTV

Feb 18

𝐅𝐫𝐨𝐦 𝐭𝐡𝐞 𝐁𝐚𝐲 𝐀𝐫𝐞𝐚: @GordianBio announced that it will be using its unique large-scale in vivo screening process to help Pfizer look for new targets against obesity. Co Founder & CSO @MartinBJensen explains how it works. Full video: biotechtv.com/post/gordian-b…

2:57

3

6

27

4,165

Gordian Biotechnology reposted

Norn Group

@NornGroup

Feb 25

Heart failure, fibrosis, neurodegeneration are organ-level problems. Studying cells in isolation, as it is common in biology, tells you about cells, not about the complex diseases their dysfunction contributes to. At @GordianBio, Martin approaches this differently. The thesis is that to get useful answers, you need to interrogate cells inside a living organ that has developed the disease naturally, sometimes over years, to understand whether a therapy would work in that environment.

1

6

203

Gordian Biotechnology reposted

BiotechTV

@BiotechTV

Feb 18

𝐅𝐫𝐨𝐦 𝐭𝐡𝐞 𝐁𝐚𝐲 𝐀𝐫𝐞𝐚: @GordianBio announced that it will be using its unique large-scale in vivo screening process to help Pfizer look for new targets against obesity. Co Founder & CSO @MartinBJensen explains how it works. Full video: biotechtv.com/post/gordian-b…

2:57

1

7

25

13,253

Gordian Biotechnology reposted

Martin Borch Jensen

@MartinBJensen

Feb 18

February is the best month because I get to celebrate the anniversaries of the original Gors. Seven years in, they're still with us 🇲🇰

1

13

806

Gordian Biotechnology reposted

Dr. Shelby

@shelbynewsad

Feb 16

One of our obsessions over the last year @CompoundVC has been in hyper-specific and curated Research Days. So far we’ve run these for: - Biohacking 2x - Biosecurity - Wearables - Autonomous Science And next week we’re running a research day on Rapid in vivo Evidence. We have an all-star line up from the only public human challenge trial company, hVIVO, @GordianBio that uses animal models that closely mimic human disease biology, @PheironAI that aggregates national scale biobank data, @ManifoldBio that uses barcoded antibody screens in mice, rare disease leader @eperlste, @alexsaraki who’s talking about what he’s building, and others.

1

8

50

3,476

Gordian Biotechnology reposted

Daniel Shur

@teleodaniel

Feb 17

So excited to host @MartinBJensen on this week's episode the Free Radicals podcast! As the co-founder and CSO of @GordianBio, Martin has raised over $60M from top investors like @foundersfund , @HorizonsHK , @fiftyyears and The Longevity Fund, to revolutionize testing of therapeutics and targets at scale. Gordian also recently announced a partnership with @pfizer! Martin is also a prominent voice in longevity, and as the founder of @NornGroup he has also made countless contributions to the field more broadly, including through @impetusgrants. In this episode, Martin shares his insightful thoughts on the longevity field broadly, and also deep dives into Gordian's technology. This was a fun, wide ranging episode. Be sure to follow me and @EricDai_BioE to stay up to date on the latest news in longevity biotech! And special thank you to @NFX & @omri_drory for lending us their beautiful podcasting studio! 0:00 Intro 03:27 Where is the longevity field today and are we on track to cure aging in our lifetimes? 14:25 Is longevity truly different from other areas of biotechnology? 16:07 What is aging? 22:13 An aging body is like a company that’s developed toxic bureacracy 26:46 Gordian’s approach to tackling aging 45:09 Will scale alone solve biology? 49:08 What data would superintelligent AI need to cure aging? 54:00 Unified theory of aging or biology 59:26 What understudied areas in aging deserve more attention? 1:02:23 How does loss of cellular identity relate to aging and disease? 1:10:07 Why are there no trillion-dollar biotechs and what would it take to create one? 1:17:32 What are the key components needed for a biotech flywheel? 1:21:43 How can biotech companies de-risk clinical development? 1:37:02 What is Norn Group and what problems does it address? 1:43:58 What opportunities exist for individuals to impact the aging field?

1:46:14

5

29

5,872