Seth Howes

🩺 doctor defected to tech 👨🏼‍💻
prev engineer @exolabs | medicine @uniofoxford | ML @imperialcollege

[Seth Howes @SethSHowes]

I’ve wanted to do this for a decade.

But I never did - I refuse to give any company my DNA.

It is me.

So this week I sequenced my genome entirely at home. Literally on my kitchen table.

I never exposed my DNA sequence to the internet. Not at any point.

I used a MinION to do the sequencing (it’s smaller + weighs less than an iPhone).

I used open-source DNA models for the analysis (Evo2 and AlphaGenome) running locally on a DGX Spark and Mac Studio.

I traced mechanisms behind my family’s multigenerational autoimmune conditions that no clinician has been able to understand.

When I set out to do this I didn’t know if it would actually work. It does.

Your genome is the most private data you will ever have. You probably shouldn’t let it leave your house.

[Patrick Collison @patrickc]

I'm lucky enough to have a great doctor and access to excellent Bay Area medical care. I've taken lots of standard screening tests over the years and have tried lots of "health tech" devices and tools.

With all this said, by far the most useful preventative medical advice that I've ever received has come from unleashing coding agents on my genome, having them investigate my specific mutations, and having them recommend specific follow-on tests and treatments.

Population averages are population averages, but we ourselves are not averages. For example, it turns out that I probably have a 30x(!) higher-than-average predisposition to melanoma. Fortunately, there are both specific supplements that help counteract the particular mutations I have, and of course I can significantly dial up my screening frequency. So, this is very useful to know.

I don't know exactly how much the analysis cost, but probably less than $100. Sequencing my genome cost a few hundred dollars.

(One often sees papers and articles claiming that models aren't very good at medical reasoning. These analyses are usually based on employing several-year-old models, which is a kind of ludicrous malpractice. It is true that you still have to carefully monitor the agents' reasoning, and they do on occasion jump to conclusions or skip steps, requiring some nudging and re-steering. But, overall, they are almost literally infinitely better for this kind of work than what one can otherwise obtain today.)

There are still lots of questions about how this will diffuse and get adopted, but it seems very clear that medical practice is about to improve enormously. Exciting times!

[Arda Göreci @ArdaGoreci]

Today, we are launching our research blog!

We’ll use it for technical notes from our work building tools for enzyme and biomolecular design.

Our first post is about The Unreasonable Redundancy of Nature's Protein Folds.

TLDR: Please don't fold more sequences (1/n)

[Seth Howes @SethSHowes]

yes.

[Crémieux @cremieuxrecueil]

My latest article is about how the longevity movement should not be about wellness tips and tricks and lifestyle improvements, but rather, true, biotech-enabled life extension and life improvement.

We should be able to live exciting lives, without restriction. Forever.

[Seth Howes @SethSHowes]

This is a great point. I spent $180 on compute alone for base + variant calling. If I were saving the data in the cloud I would also be paying $70 per sequence per month. You could probably charge a 30% margin on this.

My guess is that they haven’t done this as they believe it’s hard to build this product well.

According to people I’ve spoken to at nanopore, they have to service a lot of technical issues from people that have P2 Solos. Usually root issue is lack of onboard compute, with poor product UX to ameliorate potential failure modes.

Plenty that can go wrong when a flow cell produces 900 gb of data per flow cell & you have such variability in internet upload speeds / reliability.

This isn’t to say it’s not possible - I think it definitely is.

You could have a robust system for uploads that is tolerant to interruptions. If you consistently face internet reliability issues as a user then you could be prompted in MinKNOW to buy a compute module instead.

[Seth Howes @SethSHowes]

Checked out of my hotel room but no worries - I can keep sequencing.

I’m eking out that final 5% data yield in the hotel lobby before my flight in 3 hours.

This is truly sequencing anywhere.

Maybe i should keep sequencing at 30,000 feet…

[Seth Howes @SethSHowes]

@billytcl Not if you upload to R2 as the object store - they don’t charge egress fees whereas S3 does

[Seth Howes @SethSHowes]

@billytcl stream pod5 files to GPU box on runpod!

[Seth Howes @SethSHowes]

@The__Taybor now a sequencer sequencing in space is seriously cool

[Seth Howes @SethSHowes]

@kirk3gaard @The__Taybor @ollama @exolabs @__tinygrad__ this too

[Seth Howes @SethSHowes]

@The__Taybor @kirk3gaard @ollama This is what @exolabs are working on (where I used to work)

[Seth Howes @SethSHowes]

@kirk3gaard @brad_woolf @TheODINInc I built a relay agent + remote gpu worker that makes it super easy to offload basecalling. If this is useful for community then happy to share

[Seth Howes @SethSHowes]

@KianSadeghi5 @mattzieger @Gencove @nucleusgenomics reasonable

[Seth Howes @SethSHowes]

I just sequenced a human genome to 30× coverage entirely at home.

As far as I know, this is the first time this has been done.

I didn’t step foot in a lab once. Every step - from saliva collection, to running the sequencer - took place in a single room with a dining table + kitchenette.

Six weeks ago, I had never done wet lab biology before.

I used an Oxford Nanopore P2 Solo - the only commercially available sequencing device portable enough to do 30x human genome sequencing at home.

Biggest takeaway - I could build something that combined software, hardware, and molecular biology far faster than I thought was possible.

I can name >100 specific instances where AI helped me solve a technical problem that would previously have blocked me because I lacked access to a domain expert.

For example: how do I save my sequencing run when my DNA extraction yield is 4x lower than I need it to be, and I have this limited set of reagents to hand?

To make this work, I had to navigate multiple disciplines:

- writing software to monitor sequencing runs and orchestrate remote GPU infra for basecalling
- learning + executing 5 hour long molecular biology protocols
- building a hardware device to quantify DNA concentration

Apologies for the hyperbole, but I feel super lucky to be living in 2026.

A few weeks ago I decided to sequence a human genome to 30x at home.

Then I actually did it. And I did it really quickly.

[Seth Howes @SethSHowes]

@Scobleizer now at 5 full sequences in 3 days - all in single hotel room

[Seth Howes @SethSHowes]

@KianSadeghi5 @mattzieger @Gencove @nucleusgenomics How much do you charge for 30x WGS?

[Seth Howes @SethSHowes]

@danbri $1.2k per run

[Seth Howes @SethSHowes]

@lvwerra i would like to, but i have yet to find a way for them to be useful for personal genome variant interpretation. i would love to hear any ideas you have on how they might be

[Seth Howes @SethSHowes]

@paul_conyngham high agency bio 👊

[Seth Howes @SethSHowes]

@antinertia may livestream a sequencing run start to finish later this week if people want

[Seth Howes @SethSHowes]

@antinertia claude & brain is all you need

[Seth Howes @SethSHowes]

@WillThings @YimbyGeorge SAVE THE P2 SOLO

[Seth Howes @SethSHowes]

@Keivansamani no flames were made when producing the sequences