Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AlphaGenome Atlas: a high-resolution map of human DNA

blog.google

Post reply on HN
Print view View original

131–140 of 140 posts

Re: AlphaGenome Atlas: a high-resolution map of human DNA

#131

Post by idiotsecant »

John7878781 wrote: post #91
adrian_b wrote: post #77

In another HN thread about this AlphaGenome Atlas, someone has posted a link to: https://www.science.org/content/blog-post/mutate-em-all-and-... which comments the results of this study: https://www.biorxiv.org/content/10.64898/2026.07.25.740675v1 That study has done in reality what the AlphaGenome Atlas does in fiction, but instead for a human they have done it for one of the simplest viruses. So they have fuzzed th…

Yep. Sequence-to-function models are still very limited. AlphaGenome Atlas, despite the flashy branding, is unlikely to provide significant benefit to researchers.

And it makes a lot of sense why they are limited. DNA is not an instruction set. It's more like a heavily encrypted dataset where the encryption key is the totality of physics and biology. The interactions with the physical world that result in the end product of life are enormously (it would seem hopelessly) complex.

For a machine intelligence to turn DNA sequences into organisim phenotype prediction requires modelling all that in latent space.

I imagine that is going to take a monumental amount of example data

Re: AlphaGenome Atlas: a high-resolution map of human DNA

#132

Post by bonsai_spool »

r0ze-at-hn wrote: post #129
Stevvo wrote: post #106

Don't be put off by the box asking for your "affiliation". I wrote "None", clicked submit and it took me straight to the Atlas.

The agreement does pretty much state you can't use this for anything useful. As someone who regularly investigates whole genomes I would love to use this as a tool on novel mutations. These folks are the edge cases no one else could figure out that I get a crack at. Beyond the DNA we have the symptoms and lab work and I can usually narrow it down to a handful of guesses, but it sure would be nice to use this to help…

> Beyond the DNA we have the symptoms and lab work and I can usually narrow it down to a handful of guesses, but it sure would be nice to use this to help rank where to invest efforts.

This is exactly what the various DeepMind products have been for, and this simply aggregates them. Why are you unable to use this for candidate discovery when that's exactly what it's for? Is this because you do gene discovery in a commercial setting?

Re: AlphaGenome Atlas: a high-resolution map of human DNA

#133

Post by gdhkgdhkvff »

adrian_b wrote: post #77

In another HN thread about this AlphaGenome Atlas, someone has posted a link to: https://www.science.org/content/blog-post/mutate-em-all-and-... which comments the results of this study: https://www.biorxiv.org/content/10.64898/2026.07.25.740675v1 That study has done in reality what the AlphaGenome Atlas does in fiction, but instead for a human they have done it for one of the simplest viruses. So they have fuzzed th…

Why should we discount this model just because other models that are already thought to be worse weren’t very accurate? I’m not in this field at all, so curious if I’m missing something here.

Re: AlphaGenome Atlas: a high-resolution map of human DNA

#134

Post by dekhn »

idiotsecant wrote: post #131
John7878781 wrote: post #91

Earlier quoted context omitted.

Yep. Sequence-to-function models are still very limited. AlphaGenome Atlas, despite the flashy branding, is unlikely to provide significant benefit to researchers.

And it makes a lot of sense why they are limited. DNA is not an instruction set. It's more like a heavily encrypted dataset where the encryption key is the totality of physics and biology . The interactions with the physical world that result in the end product of life are enormously (it would seem hopelessly) complex. For a machine intelligence to turn DNA sequences into organisim phenotype prediction requires model…

It seems like we can skip much of the expensive modelling and use evolutionary conservation data to shortcut building a full latent space that captures all salient interactions. It's unclear to me whether we truly need to model the entire latent space. And given that biology develops in a generative way with feedback, it may be that attempting to model this using a static latent space is unproductive.

Re: AlphaGenome Atlas: a high-resolution map of human DNA

#135

Post by smorf »

adrian_b wrote: post #77

In another HN thread about this AlphaGenome Atlas, someone has posted a link to: https://www.science.org/content/blog-post/mutate-em-all-and-... which comments the results of this study: https://www.biorxiv.org/content/10.64898/2026.07.25.740675v1 That study has done in reality what the AlphaGenome Atlas does in fiction, but instead for a human they have done it for one of the simplest viruses. So they have fuzzed th…

Just because a virus genome is small doesn't make it simple, actually quite the opposite (think of it as an obfuscated, compressed package, that is hugely variable with no checksum). In the case of this virus there are even overlapping open reading frames, which is something you would never find in a eukaryotic genome, and almost the entire genome is protein coding, whereas only 2% of the human genome is protein coding.

The real value of AlphaGenome is not the effect of SNPs on protein coding regions (there are other tools for that, like AlphaFold), but rather identifying regulatory elements, such as promoters or alternative splicing patterns or microRNAs, within the ~98% of the genome that hasn't been well characterised yet.

That 98% is vastly underexplored, so a tool like this could help researchers interested in expression profiles or alternative splicing patterns of a protein, identify the source. Obviously not every "important" SNP will be consequential, but it helps narrow the search for that needle in a haystack.

Re: AlphaGenome Atlas: a high-resolution map of human DNA

#136

Post by r0ze-at-hn »

bonsai_spool wrote: post #132
r0ze-at-hn wrote: post #129

Earlier quoted context omitted.

The agreement does pretty much state you can't use this for anything useful. As someone who regularly investigates whole genomes I would love to use this as a tool on novel mutations. These folks are the edge cases no one else could figure out that I get a crack at. Beyond the DNA we have the symptoms and lab work and I can usually narrow it down to a handful of guesses, but it sure would be nice to use this to help…

> Beyond the DNA we have the symptoms and lab work and I can usually narrow it down to a handful of guesses, but it sure would be nice to use this to help rank where to invest efforts. This is exactly what the various DeepMind products have been for, and this simply aggregates them. Why are you unable to use this for candidate discovery when that's exactly what it's for? Is this because you do gene discovery in a com…

Because the agreement explicitly lists out what it can't be used for and this is included in that list.

Re: AlphaGenome Atlas: a high-resolution map of human DNA

#137

Post by bonsai_spool »

r0ze-at-hn wrote: post #136
bonsai_spool wrote: post #132

Earlier quoted context omitted.

> Beyond the DNA we have the symptoms and lab work and I can usually narrow it down to a handful of guesses, but it sure would be nice to use this to help rank where to invest efforts. This is exactly what the various DeepMind products have been for, and this simply aggregates them. Why are you unable to use this for candidate discovery when that's exactly what it's for? Is this because you do gene discovery in a com…

Because the agreement explicitly lists out what it can't be used for and this is included in that list.

What does the agreement say? Again, this is exactly what these products are designed for and what they’re used to do in publications

Re: AlphaGenome Atlas: a high-resolution map of human DNA

#138

Post by epistasis »

atorodius wrote: post #88
John7878781 wrote: post #84

People are upvoting this because it has the “Alpha______” prefix. Meanwhile, everyone in the field of genomics knows that AlphaGenome provides essentially zero improvements over the previous SOTA, Borzoi…

> a database that predicts the effects of every possible single nucleotide variant in the human genome. We used the AlphaGenome AI model to pre-calculate the regulatory impact of all 9 billion single-letter genetic changes, resulting in a massive, 1-petabyte dataset. This is for a database, no? While Borzoi is a model? > Here, we introduce Borzoi, a model that learns to predict cell-type-specific and tissue-specific…

This type of model, of which there are many, either directly releases their results as a precomputed database right away, or others release that database, or the method gets ignored.

Check out VIPdb for the broad category of methods/databases

https://genomeinterpretation.org/vipdb.html

These are predictors for "pathogenicity". Which is the vague concept of "does it cause genetic disease in humans" where "disease" itself is defined as the broad set of things that "brings patients into the doctor to figure out what's wrong."

The "regulatory impact" part of this is what differs from other predictors, in that it predicts the internal states as measured by several different assays, such as transcription regulating proteins are bound where in the genome, etc. Those predictions may or may not be usefel to people trying to reason about things going on in the cell, but my guess is that it's not going to get much use my molecular biologists, because the way the paper was described is pretty bad, and there are no experimental results I saw towards validating that.

But then, I'm not super interested in this paper. It's my field, but if there's something interesting I'm sure I'll hear about it from colleagues. Google is a fantastic advertising company that sometimes also does a bit of science, but this PR push is just an advertisement. A standard work-a-day paper gets covered as if it were ground breaking, and it will get enough eyes that I feel like I can safely ignore it until somebody in the field points out something interesting.

Re: AlphaGenome Atlas: a high-resolution map of human DNA

#139

Post by r0ze-at-hn »

bonsai_spool wrote: post #137
r0ze-at-hn wrote: post #136

Earlier quoted context omitted.

Because the agreement explicitly lists out what it can't be used for and this is included in that list.

What does the agreement say? Again, this is exactly what these products are designed for and what they’re used to do in publications

https://deepmind.google.com/science/alphagenome/terms

The set of who can actually use this is pretty much null as it is. You cannot use it in a publication, nor for any clinical purposes.

Re: AlphaGenome Atlas: a high-resolution map of human DNA

#140

Post by bonsai_spool »

r0ze-at-hn wrote: post #139
bonsai_spool wrote: post #137

Earlier quoted context omitted.

What does the agreement say? Again, this is exactly what these products are designed for and what they’re used to do in publications

https://deepmind.google.com/science/alphagenome/terms The set of who can actually use this is pretty much null as it is. You cannot use it in a publication, nor for any clinical purposes.

> The set of who can actually use this is pretty much null as it is. You cannot use it in a publication [...]

"You can *publish*, share and adapt output in accordance with the Terms, including the requirement to provide clear notice that (with the exception of the AVI Score) use is subject to AlphaGenome Output Terms of Use and of any modifications you make."

> , nor for any clinical purposes.

Of course they'll write this, there's no scoring tool that would advertise clinical utility unless they're charging you money

---

Your concern about publication is incorrect; they simply want you to cite them appropriately if you are indeed a researcher: https://deepmind.google.com/science/alphagenome/output-terms

Post reply on HN