←
Mo Elzek1,567 posts
Mo Elzek avatar

Mo Elzek

@moelzek

physician scientist. founder @lonlongevity. Biochem PhD @cambridge_uni. science is not nonsense. first principle biology.

◷ Joined June 2009▧ 112 Photos and videos
Mo Elzek avatar
Mo Elzek@moelzek·Nov 17

great for the uk/eu bio ecosystem!!

For 26 years, every @FlagshipPioneer company has originated in our labs in Cambridge, Massachusetts. Today, that changes. We are launching a new Origination Lab in the UK, with an initial commitment of £100 million.  For the first time, we will conceive of and build new biotech start-ups outside of the 02142 zip code, turning unreasonable “what if?” questions into transformative companies across human and planetary health. This is a major step for Flagship, and a reflection of the confidence we have in the UK life sciences and AI ecosystems. Since first opening our London office three years ago, we’ve been impressed by the talent, imagination, and ambition that make the UK a leader in our field - and we are excited about the groundbreaking ventures that will come from combining our unique Flagship model with the UK's distinct strengths.  Thank you to all our partners in the UK and to the members of the Flagship team who have made this milestone possible. We are looking forward to building out our UK origination team and getting to work. You can read more about the announcement here: flagshippioneering.com/news/…

Pushmeet Kohli avatar
⟳ Mo Elzek retweeted
Pushmeet Kohli@pushmeet·Nov 11

I’m very pleased to introduce AlphaGenome 2, @GoogleDeepMind’s next-generation genomics model that deciphers how DNA changes affect cells. Cells are the basic units of life and key to our understanding of biology. It is an ongoing challenge to predict how DNA changes affect the functioning of different cells, such as for a heart muscle cell or an immune cell fighting an infection, and to uncover cellular drivers of disease. To make progress on this challenge, we needed to design the architecture of AlphaGenome 2 so its predictions were conditional on cell types and states. This new design enables AlphaGenome 2 to predict variant effects across hundreds of human cell types and adapt to unseen cell and disease states without retraining. When evaluated on the TenK10K immune cell dataset, AlphaGenome 2 demonstrated a major leap in accuracy over its predecessor. It reliably identified nearly twice as many causal variants (30% vs. 16%) and directional gene effects (43% vs. 23%) compared to the original AlphaGenome. This step-change improvement in precision helps researchers pinpoint previously overlooked disease-relevant variants with high confidence. Using analysis on retrospective case studies, we were able to show AG2’s real world utility in disease understanding. A landmark study had previously shown that a variant in a distant regulatory switch drives irritable bowel disease by overactivating the ETS2 gene in gut macrophages. When used to make predictions across various immune cell types in the gut, AlphaGenome 2 singled out the exact causal variant and showed that it selectively boosts the ETS2 gene in gut macrophages, leaving other cell types and genes largely unaffected. I would like to thank my colleagues Adam Gayoso @adamgayoso, Žiga Avsec @Avsecz, and our entire genomics team for their incredible contributions and dedication to bringing this model to life. We are making AlphaGenome 2 available for non-commercial academic research via the AlphaGenome API, and soon we will release AlphaGenome 2 Skills in Google Antigravity. I’m incredibly excited to see how scientists around the world use this model to make progress on biological understanding and treating disease. Read more on our blog here: deepmind.google/blog/alphage…

Nathan Skene avatar
⟳ Mo Elzek retweeted
Nathan Skene@n_skene·Nov 10

How do we work backwards from preventing and treating Alzheimer's? At @UKDRI, we want AI agents to help connect the evidence, identify what's missing and coordinate the science needed to get there. We're hiring 2 engineers to help build this. Roles below.

Mo Elzek avatar
Mo Elzek@moelzek·Nov 11

AI frontier labs are turning bio frontier labs!

NIK@ns123abcNov 10

Anthropic CEO predicts cancer, Alzheimer's, heart disease, mental illness will be cured in less than 10 years ACCELERATE

1:04
Mo Elzek avatar
Mo Elzek@moelzek·Nov 11

Reminds me of how Francisco Mojica kept CRISPR research alive in a small Spanish lab on a tiny grant in the 90s.

Field Builders make the fields that make the future. More people should consider the role. We’re backing at least 50 Field Builders to launch grant programs in emerging scientific fields. Each Field Builder will award $70,000 to researchers they recruit and receive a $5,000 honorarium for leading the work. Applications for the Field Building Accelerator are open now through December 15, 2026: fieldbuilding.org/

0:13
Chenru Duan avatar
⟳ Mo Elzek retweeted
Chenru Duan@chenru_duan·Nov 2

We’re introducing Hydrogen-1.0, our first open-weight model for scientific research. We post-trained GLM-5.3 (@Zai_org) on our internal scientific data, lab records, and discovery trajectories. It scores 38.3% on FrontierScience-Research vs GPT-6-Astra’s 33.3% and scores 93.0% on GPQA-Diamonds. We believe science should be open, collaborative, and democratized, rather than proprietary. Only open weights let researchers inspect, adapt and build on the unprecedented speed of AI growth. There are many recent models named by chemical elements, but we believe Hydrogen-1.0 is the first aiming towards and open scientific superintelligence for discovery. 🧵

0:44
Mo Elzek avatar
Mo Elzek@moelzek·Nov 3

At our 3rd AI x Bio Roundtables, we asked how we measure success in AI for biotech, and how that success reaches patients. Our latest newsletter has some answers, and more questions to explore. Thank you to @MarkKotter, Jordan Abdi MD, @n_skene, @cnesheva and Chris McMurran for leading those conversations. @LonLongevity is delighted to continue the discussion at our next AI x Bio Roundtables, exploring five questions: 1. Making our own medicines: could we instruct the body's immune system to produce a treatment? Joshua Blight, @baseimmune 2. Biosecurity without slowing innovation: what practical steps should UK bio AI startups take to evaluate and reduce risks? @HannahMadan, @PrimaMente 3. Drugging disordered proteins: how can AI and experimental biophysics turn these proteins into credible drug targets? @KamilTamiola, @PeptoneLtd 4. The future of clinical trials: what can AI tell us before a therapy first enters humans, and what could trials look like by 2035? Ed Dixon, Bayezian 5. Humans and AI doing science together: how should peer review, credit and verification evolve? @getFilip, Curie Thank you to our five chairs, and to Stephanie Avraamides and @fiftyyears 5050 for hosting us. Kudos to Ket Mhatre, PhD for helping me capture the notes. 📅 Wednesday 4 November, 17:30–21:00 📍 Fifty Years, 2 Soho Square, London Article: londonlongevity.substack.com… RSVP: luma.com/blqp9myt

Post attachment
Mo Elzek avatar
Mo Elzek@moelzek·Nov 2

Super excited about this!!! The future is already here so let’s evenly distribute it! @FraMoira and @unrulyvc put something super!!

What technologies will rewrite our institutions? What institutions will govern technology? 48h to Unruly Futures 2026. Stacked lineup: - post-agi economics / future of markets: @izakaminska @JulianDJacobs - AI and institutional architecture: @sebkrier @ObadiaAlex @leoquattrucci @jujulemons - what’s rot and what’s not: @curtis_yarvin @tomough @stefanobernardi - new technoscientific institutions: @jamiec_24 @AndriesKerp - after the biosingularity: @julian_englert @moelzek and more in frontier real estate, post-UN humanitarian response, agri and food sovereignty etc Thanks to our sponsors @RenPhilanthropy @RonitKanwar, @cartainc

Mo Elzek avatar
Mo Elzek@moelzek·Oct 9

Imagine telling the parents of a child with a chronic disease, “Our goal is to improve your child's health, but not to help them live longer”!! Medicine gets more unethical issues as people get older!

Should aging research focus on lifespan or healthspan? What is the ultimate goal of the field? Delighted that our paper, led by David Gems, is finally out @GeroScienceAGE ! We argue that extending healthspan rather than lifespan is a misguided cliché. link.springer.com/article/10…

Mo Elzek avatar
Mo Elzek@moelzek·Aug 12

4/ It has been a GREAT two years for London Longevity. We have organised over 30 events, learnt so much and met many brilliant people building the science and technology to slow the evil forces of ageing. We are super ready for the next phase: shifting from a community that learns to a community that builds. Get in touch if you want to build with us

Mo Elzek avatar
Mo Elzek@moelzek·Aug 12

3/ Not all wellness products are created equal. There is a lot of hope and hype because of the industry’s reliance on influencer marketing. But this momentum will turn into frustration if the high expectations do not materialise. We should avoid that by being supervigilant about scientific evidence and quality control of all wellness we consume. We need to stay healthy until biotech picks up

Mo Elzek avatar
Mo Elzek@moelzek·Aug 12

2/ AI companies are going all-in on biology. They will build, invest in and acquire more biotech startups. This is completely different from the Calico era. They need biological data to train new models and will have to develop biology know-how to build biosecurity guardrails