abhishaike

LLMs probably wont change how likely that is :)

Thank you for the kind words :)

Very fair! We're working on a preprint right now

Somewhat, we are assuming that a model trained on human data entirely is able to 'project' mouse data into a human transcriptomic space. It feels like something that should obviously fail (isn't it out of distribution?), but it works surprisingly well according to the perturbation controls we had! Morphology of tissue may simply be a rather universal substrate.

And yes, it is trained on 18,963-plex spatial transcriptomics :)

(I work at Noetik and wrote this article)

Thanks for posting this here! And surprising its attracting attention, I have to imagine that the TAM for 2-hour-long biologics-manufacturing podcasts is small :)

If you're more interested in this person's work, his website is here: https://www.iku.bio/

I'm going to be honest: I have absolutely no idea what this comment means

I will investigate these other locations!

Apologies, I do kinda auto-repost my articles here without thinking whether they are paywalled (nearly everything I’ve written isn’t)

here is an unpaywalled link that anyone can access: https://www.owlposting.com/p/8157b515-56ce-40a4-a7f0-da6d46f...

edit: please subscribe if you enjoyed this! lots of really crazy articles + podcasts in this subfield are planned for the upcoming month :) all free!

I don't disagree!

Thanks for posting this here! Sent this HN link to the founders, so they may be able to answer any Q's that people have

>molecules get screened against tox targets

sure! i cover this in the essay, the purpose of this dataset is not just toxicity, but repurposing also

>toxicity of major metabolites

this is planned (and also explicitly mentioned in the article)

>no need to worry about CYP’s

again, this is about more than just toxicity

>volume of distribution

i suppose, but this feels like a strange point to raise. this dataset doesnt account for a lot of things, no biological dataset does

>advertisement

to some degree: it is! but it is also one that is free for academic usage and the only one of its kind accessible to smaller biopharmas

<3 high praise, appreciate the kind words

I completely agree, but I also think there is some truth to the related statement: 'cancer research often isn't conducted in a way that is actually useful'!

For example, in-vivo tumor experiments in mice can yield completely different results depending on exactly where the tumor was implanted. E.g. a 'lung cancer mouse model' may have the lung cancer injected just under the skin, also known as subcutaneous tumor models, instead of in the lung! Entirely because it's a lot more efficient + yields more trustable data, but the results are often deeply disconnected from how the tumor would naturally grow + respond to drugs within its host organ.

thanks for posting this here!

Fixed!

I think it has very limited therapeutic applications with what we know about RNA structure today! But there's a great deal of completely unknown RNA biology (some of which I touch on in the essay) that may greatly benefit from RNA structure. The bit I mention about Arrakis Therapeutics preclinical work in drugging the (structured) RNA version of the MYC protein points to that being a very real possibility. All interesting biotech startups are built on bets on where the future is going, and I'm very happy that someone (AtomicAI and others) is betting on this, because clearly the answer of 'is RNA structure useful' isn't super open-and-shut

oh yeah, I didn’t mean to say that they did claim that, that was just my (mis)conception

This is in the article!

+1 to this!

I've also written a potentially helpful coverage piece on extracting conformations from cryo-EM data: https://www.owlposting.com/p/a-primer-on-ml-in-cryo-electron...

Author here, I wish I added a section on coarse graining as well :) hope you write a post about it!

Writer of the article here: randomization fixes most of this, but the other commenters are correct in that doesnt fully account for the clinic performance (e.g. nurse performance, which does dip during the night according to the literature). I previously thought it wasn't a major issue for clinical trials, since a separate team independent from the main ward are giving the drugs, but there isn't super strong evidence to support that. I will update the article to admit this!

This said, I am inclined to believe that this isn't a major concern for chronotherapy studies, since I haven't yet seen it being raised in any paper yet as a concern and the results seem far too strong to blame entirely on 'night nurses make more mistakes'. Fully possible that that is the case! I just am on the other side of it

<3

I mention this in the article :)

Fixed!

dumb wording on my part! fixed :)

Ah i wrote this! Thank you for posting it here :)

A biology/machine-learning blog!

https://www.owlposting.com/

Rediscovering an old love for writing that I thought had left me after highschool, now applied in the field I work in! Recommend starting your own blog if you're on the fence + being consistent about posting, it's extremely worth it

this is super interesting, had no idea this was happening! i assumed things were tending towards cheaper given sequencing prices were dropping, why are things rising elsewhere?

<3

apologies will do better