Wesley Wierson

965 posts

Wesley Wierson banner
Wesley Wierson

Wesley Wierson

@DNA4CY

Genome hacker 🧬 | Techno-optimist 🚀 | Iowa State alumni 🌪 | Tattoo collector 💉 | Building @LEAHLabsInc 🐶, LifEngine 🚂, @UViiVE ☀️, VelociTx 🏎️

Twin Cities, MN Katılım Temmuz 2017
1.3K Takip Edilen370 Takipçiler
Sabitlenmiş Tweet
Wesley Wierson
Wesley Wierson@DNA4CY·
...here's the beauty that is my engineered DNA repair reporter in action. This experiment brought my PhD full circle: I used the targeted knock-in approach I pioneered to engineer a stable allele that can be used for interrogation of DNA repair pathway kinetics. This idea..
Wesley Wierson tweet mediaWesley Wierson tweet media
English
2
1
15
0
Erik Dunteman
Erik Dunteman@erikdunteman·
Some exciting news to share: Butter is joining Modal! Infra is having a moment. Agents need new patterns, new primitives. And importantly, scale like we've never seen before. There is no better team in the world to build this than Modal. It's an honor to join.
Erik Dunteman tweet media
Modal@modal

We're excited to announce that @ButterDev_ is joining Modal to help us continue to build the best sandbox infrastructure. Welcome to the team! 💚🧈

English
58
15
301
37.6K
Wesley Wierson
Wesley Wierson@DNA4CY·
We basically do this, or similar, with our multi-agent openclaw fleet. Multiple companies and academic labs in our network. Constant chatter and projects, from internal work to crazy moonshots. Takes some human effort, but we can see where the exponential is heading, and we’re well on our way to precisely what you describe with more agentic connections. Would love to chat!
English
1
0
1
37
Jake Wintermute 🧬/acc
Jake Wintermute 🧬/acc@SynBio1·
Am I crazy? Is this a thing? Is anybody working on something like this?
English
4
0
4
208
Jake Wintermute 🧬/acc
Jake Wintermute 🧬/acc@SynBio1·
There’s something I can’t quite articulate but feels like it needs to exist. Maybe you’d call it a “social network for agentic science.” It's a platform typey thing where AI agents identify connections between research projects and facilitate real-world collaborations
English
6
3
33
2K
Stephen C. Ekker, Ph.D.
Stephen C. Ekker, Ph.D.@scekker·
@DNA4CY @openclaw And the X algo is trying to force me to pay to promote this awesome science. This approach would help Grok, too. Our next paper will show that too
English
1
0
1
69
Wesley Wierson retweetledi
Jason Kelly
Jason Kelly@jrkelly·
The thing (pharma-biotech) people are missing about the dog cancer cure story is that once you get outside of humans we should largely just be trying new biotech products and not getting as worked up about predicting ahead of time what is safe and efficacious. At a minimum the LLMs got a person to feel like they could learn enough to know about a drug that might be worth giving their dog. Then the confidence to reach out to scientists and give something a try. That's a big step. I don't think this approach will translate to humans easily today -- but there a lot more potential applications of biotech other than treating diseases in humans! Good signal in this story that LLMs are going to open up more of those applications.
Egan Peltan@EganPeltan

This is totally out of control: There’s 0 - I repeat 0 - evidence any of the LLM work did anything meaningful for Rosie’s cancer I’m sorry to rain on the parade here. I know we want to believe. But, it’s possible to do a lot of things and have nothing happen @paul_conyngham co-administered α-PD-1 (conventional immunotherapy) with a TKI and the mRNA. It’s probably the most effective cancer immunotherapy of all time. This isn’t a small detail! There’s no evidence his process (beyond FDA approved doggie α-PD-1) had any impact on disease progression. The most parsimonious explanation is a partial response to α-PD-1 I get it. The chat bots make for a great story (although checking multiple LLMs isn’t validation), but it’s really just a neat story. It’s fundraising copy. Before he starts selling the “custom neoantigen mRNA vax” story to consumers, he should provide some evidence it did anything! That’s responsible citizen science This is just storytelling for the AGI true believers. Specifically, a story in search of venture money

English
7
3
93
46.1K
Charly Wargnier
Charly Wargnier@DataChaz·
THIS is the wildest open-source project I’ve seen this month. We were all hyped about @karpathy's autoresearch project automating the experiment loop a few weeks ago. (ICYMI → github.com/karpathy/autor…) But a bunch of folks just took it ten steps further and automated the entire scientific method end-to-end. It's called AutoResearchClaw, and it's fully open-source. You pass it a single CLI command with a raw idea, and it completely takes over 🤯 The 23-stage loop they designed is insane: ✦ First, it handles the literature review. - It searches arXiv and Semantic Scholar for real papers - Cross-references them against DataCite and CrossRef. - No fake papers make it through. ✦ Second, it runs the sandbox. - It generates the code from scratch. - If the code breaks, it self-heals. - You don't have to step in. ✦ Finally, it writes the paper. - It structures 5,000+ words into Introduction, Related Work, Method, and Experiments. - Formats the math, generates the comparison charts, - Then wraps the whole thing in official ICML or ICLR LaTeX templates. You can set it to pause for human approval, or you can just pass the --auto-approve flag and walk away. What it spits out at the end: → Full academic paper draft → Conference-grade .tex files → Verified, hallucination-free citations → All experiment scripts and sandbox results This is what autonomous AI agents actually look like in 2026. Free and open-source. Link to repo in 🧵 ↓
Charly Wargnier tweet media
English
78
379
2.4K
212.9K
Wesley Wierson
Wesley Wierson@DNA4CY·
Just installed this and ran a test on overcoming NK cell exhaustion in solid tumors. Multiple failures happened. Most critically, the final report has 25% citation contamination (110 out of 452 citations). We have an agent fleet with learned behavior to catch citation hallucinations at extremely high fidelity (writing a paper on this right now). My agent tells me this happened at Stage 3-4 keyword searches scraping papers containing the words “solid” or “cell” from entirely unrelated fields. Got some good papers on “Roman Galactic Plane Survey” and “Pulsatile Therapy for Perovskite Solar Cells” though! Happy to share the data if helpful.
English
0
0
1
316
Charly Wargnier
Charly Wargnier@DataChaz·
If you enjoyed this, feel free to repost to support their work ♻️ For more on AI agents and LLM workflows, follow me → @datachaz
Charly Wargnier@DataChaz

THIS is the wildest open-source project I’ve seen this month. We were all hyped about @karpathy's autoresearch project automating the experiment loop a few weeks ago. (ICYMI → github.com/karpathy/autor…) But a bunch of folks just took it ten steps further and automated the entire scientific method end-to-end. It's called AutoResearchClaw, and it's fully open-source. You pass it a single CLI command with a raw idea, and it completely takes over 🤯 The 23-stage loop they designed is insane: ✦ First, it handles the literature review. - It searches arXiv and Semantic Scholar for real papers - Cross-references them against DataCite and CrossRef. - No fake papers make it through. ✦ Second, it runs the sandbox. - It generates the code from scratch. - If the code breaks, it self-heals. - You don't have to step in. ✦ Finally, it writes the paper. - It structures 5,000+ words into Introduction, Related Work, Method, and Experiments. - Formats the math, generates the comparison charts, - Then wraps the whole thing in official ICML or ICLR LaTeX templates. You can set it to pause for human approval, or you can just pass the --auto-approve flag and walk away. What it spits out at the end: → Full academic paper draft → Conference-grade .tex files → Verified, hallucination-free citations → All experiment scripts and sandbox results This is what autonomous AI agents actually look like in 2026. Free and open-source. Link to repo in 🧵 ↓

English
1
4
10
8K
Wesley Wierson retweetledi
Twist Bioscience
Twist Bioscience@TwistBioscience·
AI-designed proteins are advancing fast, but how do they perform in real biological systems? Bits to Binders found out…
Twist Bioscience tweet media
English
1
21
168
21.7K
Wesley Wierson
Wesley Wierson@DNA4CY·
Our first paper out from @LEAHLabsInc in collaboration with UT-Austin scientists. Open source de novo design of antigen receptors for CAR-T cell therapy. 42 countries of teams. 12,000 binders screened. Dozens of CD20 binders that enable functional CAR-T cells identified. And a really cool set of de novo binder design rules in this vertical identified. In silico bits to therapeutic atoms in a single step, all enabled by our patented gene editing tech.
Clay Kosonocky@kosonocky

The results are finally in! 🏆💻🧬 I'm thrilled to announce that the manuscript for the Bits to Binders protein design competition is out on bioRxiv! Here's a summary of our findings, including some simple criteria that nearly *double* success rates when applied as a filter 🧵

English
0
1
4
204
Wesley Wierson retweetledi
Mgoes (bio/acc 🤖💉)
Mgoes (bio/acc 🤖💉)@m_goes_distance·
Most people have no idea how insane this is: Demis Hassabis (yeah the Chad from Google Deepmind) just dropped IsoDDE It's: -2x better than AlphaFold 3 on novel targets -2.3x better on antibody docking -20x better than Boltz-2 on biologics -discovers hidden binding pockets in seconds (took researchers 15 years for cerebron) -outperforms all physics-based methods Partnerships already live are Novartis, Eli Lilly, J&J First AI-designed drugs entering trials by end of 2026. AI doesn't just help discover drugs anymore. AI designs drugs, humans validate. and in case you missed it, Ginkgo completed 36K autonomous experiments. Isomorphic just showed up with end-to-end drug design Discovery timelines went from 10 years → 10 months bio/acc
English
29
93
757
58.8K
Wesley Wierson retweetledi
Jake Wintermute 🧬/acc
Jake Wintermute 🧬/acc@SynBio1·
Anything that can be built purely with bits is going to zero. No software-only VC play will ever 100x again Biology is the only thing you can build with AI that 100,000 OpenClaw agents can't immediately clone for free
Sam Altman@sama

I am very excited about AI, but to go off-script for a minute: I built an app with Codex last week. It was very fun. Then I started asking it for ideas for new features and at least a couple of them were better than I was thinking of. I felt a little useless and it was sad.

English
11
9
151
22.5K
Wesley Wierson retweetledi
Dr. Jocelynn Pearl
Dr. Jocelynn Pearl@JocelynnPearl·
The future of cancer treatment is here, albeit for a select few. Great long read article (linked below) by @ElliotHershberg on Sid’s quest to attack his cancer in so many ways. I was lucky enough to learn about the approach this past year via @pwekane
Dr. Jocelynn Pearl tweet mediaDr. Jocelynn Pearl tweet mediaDr. Jocelynn Pearl tweet mediaDr. Jocelynn Pearl tweet media
English
3
9
47
6.4K
Parmita Mishra
Parmita Mishra@parmita·
I have added some of the coolest people to this bio/acc group and we actually chat here about cool stuff! I am deleting this and re-making the gc with the new encrypted DMs. PLEASE tag awesome people who should join People who are BIOLOGISTS or IN BIOTECH !
Parmita Mishra tweet mediaParmita Mishra tweet media
English
112
8
181
17.7K
Wesley Wierson retweetledi
Josie Zayner
Josie Zayner@josiezayner·
These are Cat embryos right before we used CRISPR gene editing to knockout the primary allergen gene Fel D1 on our quest to create a true hypoallergenic cat at Embryo Corp (implants soon)
Josie Zayner tweet media
English
21
37
274
19.5K
Wesley Wierson retweetledi
Mgoes (bio/acc 🤖💉)
Mgoes (bio/acc 🤖💉)@m_goes_distance·
bullish on biotech startups rn if you're building anything to accelerate biology or know someone who is - longevity, gene editing, diagnostics, whatever drop a comment or tag them will move fast.
English
86
13
272
18.7K
Simon Høiberg
Simon Høiberg@SimonHoiberg·
Bryan, you should allocate another $1M to 10 smaller angels. E.g. @marclou, @levelsio, myself - gather 10 of us and let us invest $100K each. I think it would GREATLY benefit your mission to get a group of smaller founders onboard too!
Bryan Johnson@bryan_johnson

We just raised $60 million for Blueprint. To bring my longevity protocol to you. Our society has made us unwell…metabolically, mentally, spiritually. We’re addicted. Social media, porn, nicotine, junk food, fast food, smartphones, streaming, energy drinks, and gambling. Each perfectly engineered to keep us in their grip. Years ago, I was owned by these systems. They wrecked me, and my health. I wish there had been someone in my life helping me break free. Blueprint will be that system. Collectively, we will claw our power back. Blueprint will take better care of people than they can themselves. Better than the healthcare system does. Better than our societal norms allow. We will be your home for health. Blueprint will help you feel clear-headed and vibrant. You will become more jacked and beautiful with our presence in your life. There’s nothing better than feeling your best. Some of the world’s most powerful people are backing Blueprint. Talent are pivoting their careers to join our team. They rightly see that Blueprint is in the right place, at the right time, for the global emergence of the new macro trend of health, anti-aging and Don’t Die. In this post I’ll cover: + Who’s investing + What Blueprint will be + Who’s joining + Open positions + How to get early access The next era of human is here. [WHO’S INVESTING] This remarkable group of people are Blueprint investors. They are backing the next great frontier: human longevity. + Akshay Bd + Alex Hormozi + Amanda Cassatt + Andrej Karpathy + Ari Emanuel + Balaji Srinivasan + Bill Lee + Brad Keywell + Brian & Veronica Grazer + Bryan Meehan + Cameron Winklevoss + Carter Reum + Chris Hollod + Dan Manges + Dave Morin + Don Wilson + Drew Houston + Emmett Shear + Eric Demuth + Fareed Adib + Generational Family Office + Jason Fried + Jay Shetty + Joe Gebbia + Joe Lonsdale + John Carmack + Joshua Kushner + Kamal Ravikant + Karim Beguir + Kevin Hartz + Kim Kardashian + Kyle Widrick + Logan Paul + Michael Cao + Michael Kives + Naval Ravikant + NIV + Olaf Carlson-Wee + Paris Hilton + Pippa Lamb + Saquon Barkley + Ken Katz + Seth Bannon + Shayne Coplan + Steve Aoki + Steven Bartlett + Suna Said + Tyler Winklevoss + Winnie Liu + Wojciech Zaremba [TEAM] Defeating death would be humanity’s greatest accomplishment. Big things are happening right now in our small corner of the galaxy. We see the consequence of this moment and are working to positively influence the future of intelligent existence. We believe that product is philosophy and companies can influence the world. Join if you love to work insanely hard and also get eight hours of sleep. Joining our team as CEO is Gyre Renwick. He was previously President of Modern Health and before that an executive at Google Health and Lyft Healthcare. Gyre builds complex health systems into growth engines. In this next chapter, I am doubling down on Blueprint and Don’t Die. I’m all in. Gyre will run the business and I will focus on vision, strategy, and birthing Don’t Die into the world. Blueprint is the practical manifestation of Don’t Die. They are the same thing. I will continue to juggle many full-time jobs: rejuvenation athlete, Blueprint vision, leading the Don’t Die moral philosophy and ideology, building a global community, and content creation. Ultimately, both Blueprint & Don’t Die ladder up to the same thing, answering the question: ‘what does humanity do as we give birth to super intelligence?’. Kate Tolo (co-founder), Gyre, and I will be in lockstep building this mission together. Roles we are filling now: + Chief Technology Officer + Chief Product Officer + Chief Medical Officer + Chief Marketing Officer + Engineers of all types + See all open roles Refer your most talented friends. If you don’t see a job fit, still email us. [BLUEPRINT VISION] We’re making my protocol accessible to everyone. To replicate everything including the measurements, protocols, therapies - and make it easy and accessible for others to do in a community. For your family and friends to do this too. Many think that the world’s most powerful people have their health figured out. The truth is, most everyone is floundering. Luxury concierge services often do little for wealthy people as the biggest gains are not in expensive therapies but daily habits. We will help you build life foundations, starting with the basics and graduating to advanced therapies. Our goal is to be more effective in helping you achieve your health goals than any health system or concierge in the world. Blueprint will build around: + your preferences + your budget + your preexisting conditions + your prior results + your prescriptions + your level of effort It’s health within context. I built Blueprint to solve my own problem. My body and mind were broken, and I didn’t know who to trust to help me fix it. Everyone disagreed with everyone else. I found sanity in gathering a team of doctors and building a protocol based upon robust measurement and scientific evidence. It’s a methodical process that produces better outcomes and results in fewer mistakes and wasted time. After my team and I built a protocol for me, my friends and family asked if they could get access too.  Then their friends and family asked and I said yes again. The circle kept on expanding until we stumbled into Blueprint becoming a company. We will tell you to do less. Most good health can be achieved with very little effort. It’s the systems, infrastructure, knowledge, and piecing through the noise that is hard. Blueprint is Bryan Johnson’s protocol, for everyone. What this will practically mean: + Blood draws + Food delivery + GLP-1s + Rx prescriptions + Free protocols + Toxin testing + At-home tests + Skin care & hair care + Nutrition & supplementation + Advanced therapies And your AI health companion will make it simple. I like to call this my Autonomous Self. In the same way you put in an address and digital navigation tells you the best way to get there, Blueprint is navigation to vibrance. Our goal is to remove the thinking and hassle for you so that you can focus on building durable life habits and achieve the best health of your life. I love thinking about what the future will say about us. When I think from the perspective of those who exist in the year 2500, I think they’ll observe that the 2020s and 2030s was the time when humans figured out that they were the first generation who wouldn’t die. Early access below. What an amazing opportunity. Let’s do this together. Bryan

English
36
3
140
69.3K
Wesley Wierson retweetledi
Lucas Harrington
Lucas Harrington@CRISPR_LuCas·
Excited to announce Preventive, a PBC dedicated to rigorous research into the safety of embryo editing for preventing disease. We've raised ~$30M and believe that if proven safe, this could be one of the most important health technologies of our lifetimes🧵
Lucas Harrington tweet media
English
20
34
179
132.5K