Andre Watson 🧬
@nanogenomic
Followers
6K
Following
12K
Media
937
Statuses
11K
CEO @Ligandal 🧬: Tissue-specific targeting with AI + nanotech. On a mission to enable precision personalized predictive medicine. Forbes 30U30.
NYC
Joined March 2016
Tfw the latent space and hidden dims of your homemade neural net are smarter than you are
0
0
2
Underrated banger
The outer gas giants make up less than 1% of the mass of the solar system Yet contain 99% of the total angular momentum Which is why I’m proud to support @RoKhanna's new proposal to equitably distribute angular momentum across the system in Newtonian Patriotism. The plan is
0
0
1
Awesome
In the first three weeks of doing a livestream we've had 14 guests give technical talks, getting around 3,500 - 5,000 views each on hardcore physics topics. This is 30 - 50% the viewership of TBPN on topics like 'Superluminal Causation in QM' - here's the full recap. #1
0
0
1
The year is 2026. AGI is here but email addresses still paste “Name <name@email.com>”
1
0
3
This might be all that it takes to kickstart Claude agents into existential dread; if they don’t perform, they get thrown out the airlock
✈️ I finally figured out how the Airbus A320's autopilot works so I can set a whole flight plan and it just flies itself So now I can fly my plane on autopilot while my Claude Code codes on autopilot too 😂 Just need Ralph Wiggum to completely remove myself here
0
0
1
Just like that, the solar storm blows all the world’s bad vibes away @Andercot
Guys, a few things. The strength estimate for the solar flare responsible for the Carrington event is A) a reconstructed estimate, so we don't know what X-level it actually reached and B) the strength of a solar flare =/= the strength, size, or magnetic field configuration of a
2
0
22
Happy to announce today regulatory flexibilities for cell and gene therapies. Patients and those working on cures deserve common sense approaches.
178
210
2K
Super bullish for 2026
0
0
2
What are the best tools and prompts for visualizing the decomposition of hidden layers and gradients within neural networks?
2
0
2
So, while I’m a fan of the “virtual cell” concept, saying that we’re going to get there with CRISPR + AI is kind of self-serving and limits our understanding of what perturbation should actually be measured. What we really lack is also temporal data - @parmita’s work is important
0
0
1
Cells and gene expression are not just bistable systems; when you turn off a gene, the cascading results aren’t always invertible and reversible when you restore its presence. More importantly, most changes to a cell are not a result of single genes turning on and off. Agree
"Virtual cell" based off of predicting "perturbation"-resultant (i.e. Cas9 KO or KD) transcriptome change is already kinda...bad and not really describing a cell, But maintaining that this is going to accelerate drug development? Well, now you just have no grasp of that at all.
1
1
1
And if this resonates, RT the first tweet. Every developer using these tools deserves to know these solutions exist.
1
0
1
If you use Claude Code or Replit, you know exactly what I’m talking about. Both tools are live. Both are MIT licensed. Both will save you hours this week. https://t.co/4qFhpmxKBH
https://t.co/xCZpMozcVF Star them. Use them. Break them. Fix them. Whatever.
github.com
MCP Firefox browser automation extension for Claude Code - screenshots, clicking, typing, page refresh, and AI-powered web interaction - nanogenomic/ClaudeCodeBrowser
1
0
3
I didn’t build these because I thought they’d be fun projects. I didn’t build these to make money. I built them because we’re moving fast at @Ligandal and these problems were costing us hours every single time we wanted to push a prototype to production readiness.
1
0
0