Devon Stork

By this time next year, either:

🏆 we'll have engineered PETase enzymes actually work industrially & recycle plastic

... or we'll know that AI-for-proteins is still a bit underbaked 😜

Excited to see what happens!!!! 😬

Spread the word ⬇️

Heads up: terraforming Mars isn’t just sci-fi, it’s a real possibility that’s possible with today’s technology.

Mars could be green in MY lifetime. 🚀 🌼

What’s stopping us? We need a lot more real research into how to do it right. Don’t nuke Mars!

👇

Can we do BETTER than evolution with the help of AI? It starts with data. 🧬 🔢

Check out @pioneerlabs.bsky.social's breakdown of how we get large-scale, high-fidelity data out of every engineering and evolution experiment!

I went to the 2025 Symposium on Biomaterials, Fuels and Chemicals with an invitation from @nils-averesch.bsky.social to speak about our work at @pioneerlabs.bsky.social engineering organisms for sustainable biomanufacturing on Mars! I took 80 pages of notes. docs.google.com/document/d/1...

🚀 New proposal from Align! The experimental platform aims to standardize #microbial #phenotyping & support predictive modeling. 🦠 Capturing data across 1k strains & 1k conditions; using BacterAI; generating high-quality datasets for ML @jensen_lab

Ever wonder how we’ll unlock Mars as a living world? 🌏 In our substack post we break down the 'red planet recipe'—the chemistry of mars soil — for growing life on another world. Dive into the science to find out more!

The next Alphafold2 will be a predictive model of protein expression. I think it's possible, and @alignbio.bsky.social is going for it! 🧬

Every single protein engineering project I have ever worked on at one point or another ran into expression issues. 😠 It can't come soon enough! 🙏

💡💥Here’s a modest proposal I’ve been pondering for a while on how to change the PEER REVIEW process and start more community-driven SCIENCE FUNDING. Lots of feedback/discussion welcomed! Other variants of the idea might exist already—not claiming originality. (a long 🧵) (1/9)

Sequence modeling and design from molecular to genome scale with Evo The genome is a sequence that completely encodes the DNA, RNA, and proteins that orchestrate the function of a whole organism. Advances in machine learning combined with massive datasets of whole geno...

PDF is available at www.biorxiv.org/content/10.1... and I'd be very curious to get takes from @hsalis.bsky.social, @akosnyerges.bsky.social the @cultivarium.bsky.social folks and anybody else!

My conclusion is that this is a cool model that nobody understands how to use yet. Genomes aren’t human-readable, and Evo gives us a hint how we might bridge that gap to start reading, designing and generally operating on the scale of organisms instead of single proteins/operons.

The generation of novel CRISPR systems & genomes doesn't seem very meaningful to me - I'm not convinced that those sequences do anything. In particular the genomes probably aren't even at the level of "colorless green ideas sleep furiously"

The part on zero-shot predictions on proteins & RNAs was neat, but doesn't seem revolutionary. They can match other predictive algorithms for fitness of protein/RNA. There's a ceiling on what these models can currently do and they've run into it by using a lot more data. Sure?

Figure 4E/S8 is exciting. Evo is good at predicting transposon boundaries with entropy, but I bet it encodes more data than that. Why is entropy high at the start of TnpA? What does it look like for bigger operons? Can we use this to explain biological functionality & essentiality at operon-scale?

Sequence modeling and design from molecular to genome scale with Evo The genome is a sequence that encodes the DNA, RNA, and proteins that orchestrate an organism’s function. We present Evo, a long-context genomic foundation model with a frontier architecture trained o...

I just read the Evo paper www.science.org/doi/10.1126/... from the @arcinstitute.org and have some thoughts. Tl;dr: I can see this being a fundamental part of the future of biology, but this paper is light on experimental data and I don’t think many of their demos are very interesting. 🧵

Yeah, I definitely applaud this effort despite the open-source sacrifice. Having a validated, verified & high-quality genome seq for a repository stock is worth a lot.

It's like when Addgene started doing whole-plasmid sequencing, except it's a lot harder to do organisms than plasmids!

Want to follow along as we engineer microbes for circular biomanufacturing in space? We're launching open science updates through our substack! ⬇️