AI tool designs mRNA vaccines that are more potent and stable | Hacker News Reader

AI tool designs mRNA vaccines that are more potent and stable

nature.com

146 pointsvoisin58 comments

The scientific article seems to be open access [1].

Before people draw links to recent large language model breakthroughs: Although they do use techniques from computational linguistics, there are no neural networks involved. This is more like old-school AI.

They have essentially a giant optimization problem, and they (approximately) model it as a lattice parsing problem, with a stochastic context-free grammar. They can solve that to optimality in O(n^3), which is too slow for some applications. So they propose a O(n) heuristic (hence no optimality guarantees, but the model was approximate to begin with anyways, and the heuristic is a lot faster), which is the reason for the name of their code: "LinearDesign".

[1] https://www.nature.com/articles/s41586-023-06127-z

Much appreciated! Do you have a good source on what a lattice parsing problem is?

"The lattice parsing problem refers to the task of parsing a word lattice, which is a graph structure that represents multiple possible sequences of words that could have generated a given speech signal [1]. The word lattice is a weighted directed acyclic graph, where each node represents a word hypothesis and each edge represents a transition between two words. The weights on the edges represent the likelihood of the transition. The goal of lattice parsing is to find the most likely sequence of words that generated the speech signal, given the word lattice [1]. Lattice parsing is a challenging problem because the word lattice can be very large and contain many alternative paths, making it difficult to find the most likely path efficiently [1]. Several techniques have been proposed to address this problem, including bi-directional LR parsing from an anchor word, augmented chart data structure, and attention shifting for parsing speech [2][3][4]."

1. https://doi.org/10.21437/interspeech.2016-1583

2. https://doi.org/10.3115/997939.997950

3. https://dl.acm.org/doi/10.3115/991146.991188

4. https://doi.org/10.21236/ada105028

----

(full disclosure this might not be correct, I tried this with an LLM approach we're beta testing at my job called scite Assistant that answers with real references - no hallucinations, just curious how the response is against someone that knows the field a bit more..!)

This linear-time approximation algorithm for mRNA design (LinearDesign) was inspired a lot from their previous work on a linear-time RNA folding algorithm (LinearFold).

We re-wrote their C implementation[0] of LinearFold in Go and added comments to explain how the algorithm worked: https://github.com/allyourbasepair/rbscalculator/blob/main/l...

[0] - https://github.com/LinearFold/LinearFold

Hopefully these ones will be tested longer than the last batch of mRNA designs, so that risks like the doubling of retinal vascular occlusion risk are identified before they go into production: https://www.nature.com/articles/s41541-023-00661-7

Statistically, based on the paper you linked longer testing to pick up this side effect would have been the wrong decision. It seems to me that longer testing would have caused more deaths than would have prevented RVO. From your paper:

Based on the official COVID-19 death reports, it is estimated that vaccinations have prevented 14.4 million excess COVID-19 deaths worldwide between December 2020 and December 202139. Thus, vaccination is the most effective method for preventing the spread of SARS-CoV-2.

The number of reported ophthalmic complications has remained low, and vaccine-related retinal vascular occlusion is very rare, although the number of COVID-19 vaccinations is enormous.

That paragraph is a logical fallacy. To compute a cost/benefit analysis for something you have to include all the costs, not just one. There are many papers like that one covering many different side effects.

Note that there was an attempted discussion of that paper on HN but it was immediately flagged to death. It always happens for every such paper. People still aren't ready to do a full and honest accounting. Probably they never will be.

I want to comment on this because you are phrasing it as if people who got the vaccine are in denial and not wanting to talk about it. Topics like this are hard to discuss because they are immediately polarizing and everyone who has a strong opinion but very little understanding of the science feels the to get their quip in about how right they are and how wrong the other people are. You can especially since it in threads relating celebrity deaths with comments like "well we know what REALLY killed them wink wink"

How else do you interpret insta-flagging any research papers that discuss vaccine injuries, other than people who got it not wanting to talk about it?

People flag conspiratorial antivax comments, news at 11.

Personally, I already spent two years dealing with physical threats and violence from antimask/antivax crazies, I'm not about to give them the time of day when they crawl out of the woodwork on the internet.

Like everyone else, you're not reading what you don't want to see.

I said people flag stories that are research papers. As in, published by doctors. Not comments, not conspiracies, just collected data. Doesn't matter. People (like you?) flag them anyway to try and keep everyone else at the same intellectual darkness.

Dr Oz and Jordan Peterson are doctors too, but that doesn't mean I'm not going to flag their quackery and words-shaped toxic waste every time I see it. The ability to receive a doctorate and publish a paper does not preclude a person from being an acidic blockhead or from receiving a thusly befitting amount of attention.

Art and text generated by AI are not eligible for copyright. I wonder if the same would apply to medicine.

Not sure why this would matter, generally medication is incredibly expensive because of the research that needs to go into it not scaling well to the amount of people that might need it for rare disease. If drug discovery costs go down to almost nothing, and trialling is greatly assisted with AI driven protein folding, it would almost become trivial to cure most diseases.

In some jurisdictions - I would argue that will blatantly be overturned, as it's a limit on economic activity, and we know what happens to those.

Where are you seeing this? Everything I saw is that they are eligible for copyright, and the copyright is owned by the person who ran the tool and selected the output.

The news was dumb media bait where people tried to claim the AI itself owned the copyright which makes no sense since AI is not a legal entity able to own things.

Judge declared it about a month ago. Positon was the human edited parts were but machine generated parts were not. Sorry don’t have the reference at hand.

Seems almost impossible to enforce. Say I generate an image, then go in photoshop and play with the levels/colors. Every single pixel was modified by me. And the only way you could use it without infringing on my copyright is to work out what the original image was, which is impossible.

We’ll if I then copied your work, onus would be on you to explain what you did beyond just promoting the engine with ‘astronaut on horse’.

You wouldn’t copyright an RNA sequence like this. While it is novel, I’m not sure you’d be able to get a copyright on it, as it’s a set sequence.

Instead, you’d patent it. And I’m not aware that that question has yet been asked. Especially when computationally driven drug design has a rich history, I’d expect for AI generated work to be patentable.

Is Monte Carlo an AI? I'm asking for a friend.

Of course it is. It's artificial and makes intelligent decisions. So is a pile of if sentences if they encode logical reasoning that applies some knowledge.

If one had a database of all answers to every question in the universe, making AGI would be as simple as fetch call.

This is an optimization "AI", like a computer chess program, right? It's not determining in advance which kinds of structures are going to be most stable and generating them, it's working toward pre-determined structural optima?

AI is usually a marketing term. They used machine learning to learn the topology of a prediction space related to desirable properties of mRNA vaccines.

I could be wrong, but that makes it sound algorithmically similar to AlphaFold 1 where they used ML to learn properties of the folded protein and then optimized the final structure to fit those properties

Reply on news.ycombinator.com