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

Scientists use ML to find an antibiotic able to kill superbugs in mice

statnews.com

Post reply on HN
Print view View original

31–40 of 93 posts

Re: Scientists use ML to find an antibiotic able to kill superbugs in mice

#31

Post by refurb »

koolba wrote: post #3

> That is an especially pressing challenge in the development of new antibiotics, because a lack of economic incentives has caused pharmaceutical companies to pull back from the search for badly needed treatments. Each year in the U.S., drug-resistant bacteria and fungi cause more than 2.8 million infections and 35,000 deaths, with more than a third of fatalities attributable to C. diff, according to the the Centers…

In terms of your numbers, 2.8M is all drug resistant infections - even the best drug would only work for a fraction of those..

Re: Scientists use ML to find an antibiotic able to kill superbugs in mice

#32

Post by refurb »

throwGuardian wrote: post #26
DoreenMichele wrote: post #9

...in mice. It would be nice if we spent as much time, money and attention on figuring out prevention. Inadequate hygiene infrastructure (like toilets) in developing areas is part of the problem here. But addressing that isn't as exciting to people as finding a cure for a super bug. If we really want to fix this, that needs to change.

Super bugs are a mostly first world problem, rampant in top tier hospitals providing cutting edge treatments, despite following safety precautions meant to deter secondary bacterial infections during or post hospitalization

Super bugs are a mostly first world problem

Not true at all. There are several known resistant strains that have come out of developing countries.

Why? Antibiotic use can be rampant - in many countries you can buy them without a prescription.

Re: Scientists use ML to find an antibiotic able to kill superbugs in mice

#33

Post by IAmEveryone »

spitfire wrote: post #10
entee wrote: post #2

This paper shows what can be done when you carefully run an ML program alongside a wet lab experimental program tailored to feed back into the ML program. The results end up far more interesting than some recent "ML aided drug discovery" papers in that they actually discovered a drug that functions very differently than known antibiotics (AB). Even though the structures that came out look AB-like, they work different…

Not just in drug discovery but in most interesting industries. Using ML as either a human/cyborg aid or ML+real world ground truth is a secret superpower that I'm surprised more people don't know about. I'm glad they don't.

As a less cynical observation than a sister comment, I think this is partly due to how current tools work, or possibly even inherent to the technology. Just look at the number of ML examples where you never even get to see a single example of the data you are working with. Interactivity is even rarer, certainly because it doesn’t scale, but maybe also for the somewhat pedestrian reason that interactive UIs doesn’t come natural for either the tools and/or the people using them.

Then, there’s this issue of “explainability”: if you want to direct some generator you need to find out how the concepts you want to work with are encoded in intermediary layers.

To be fair, all this isn’t much of a secret, and there are quite a few projects doing interesting things. Magenta comes to mind, or GANBreeder.

Re: Scientists use ML to find an antibiotic able to kill superbugs in mice

#34

Post by IAmEveryone »

entee wrote: post #25
naresh_xai wrote: post #20

Earlier quoted context omitted.

Exactly why we need causal reasoning/causal proof alongwith ML

In this case I’m not sure if the reasoning for what molecules work would make sense even if we had an “oracle” to explain it. Why a molecule works is a complicated interplay of fundamental physics and emergent properties. The explanation is likely not human interpretable without a ton of equations in the first place. That said in broader medical cases of ML where particular symptoms and measurements drive a diagnosis…

I’m not sure about the exact mechanisms of drug efficiency. But there are well-known patterns in molecular biology, auch as specific sequences in proteins reliably forming specific 3D structures.

If these models produce novel but (somewhat) effective structures, it must be because they pick up on less obvious patterns in the data. To be able to describe these would seem to super effective.

Re: Scientists use ML to find an antibiotic able to kill superbugs in mice

#35

Post by logifail »

Decades ago when I worked in a lab, "high-throughput screening" was definitely on the list of buzzwords.

Given what I saw back then, I'm struggling to understand how there could possibly be "a library [..] of 6,111 molecules at various stages of investigation for human diseases" (a.k.a. "Drug Repurposing Hub") which hasn't already been partially or fully screened for interesting antibiotic activity.

Could it be there's more fame (and funding) in a project where you can publish a paper and get headlines about "ML" and "superbugs", than in actually testing a library of existing compounds to see if any of them kill E. coli?

Re: Scientists use ML to find an antibiotic able to kill superbugs in mice

#36

Post by lazyasciiart »

DoreenMichele wrote: post #13
bravoetch wrote: post #11

Earlier quoted context omitted.

We do.

I can't think of the last time I saw a headline on the front page of HN about the importance of solving open defecation. I see headlines about creating new treatments for super bugs pretty regularly. Open defecation costs $US260b globally https://www.news.com.au/world/breaking-news/open-defecation-... Price to pay: Antibiotic-resistant infections cost $2 billion a year http://www.cidrap.umn.edu/news-perspective/2018/…

I think those links look interesting, can't speak for the rest of HN. If you don't want to post them, can I? (specifically that last one?)

Re: Scientists use ML to find an antibiotic able to kill superbugs in mice

#37

Post by DoreenMichele »

lazyasciiart wrote: post #36
DoreenMichele wrote: post #13

Earlier quoted context omitted.

I can't think of the last time I saw a headline on the front page of HN about the importance of solving open defecation. I see headlines about creating new treatments for super bugs pretty regularly. Open defecation costs $US260b globally https://www.news.com.au/world/breaking-news/open-defecation-... Price to pay: Antibiotic-resistant infections cost $2 billion a year http://www.cidrap.umn.edu/news-perspective/2018/…

I think those links look interesting, can't speak for the rest of HN. If you don't want to post them, can I? (specifically that last one?)

Have at it.

Re: Scientists use ML to find an antibiotic able to kill superbugs in mice

#39

Post by headmelted »

xzel wrote: post #18
entee wrote: post #2

This paper shows what can be done when you carefully run an ML program alongside a wet lab experimental program tailored to feed back into the ML program. The results end up far more interesting than some recent "ML aided drug discovery" papers in that they actually discovered a drug that functions very differently than known antibiotics (AB). Even though the structures that came out look AB-like, they work different…

People have been doing this exact thing for two decades at least but obviously with less computing power. There's literally nothing new about the idea. The real trick is being incredibly lucky and finding something that actually works in humans after multiple trials. I'm sure you know this based on your comment and this isn't really directed at you (truly wish you best of luck, I really hope the computing power and s…

I’m usually also skeptical of getting excited about successful animal trials for new medications, but with this I’m actually leaning more on the side of optimism.

With cancer treatments and antivirals in mice, we’re not so much targeting the pathogen as targeting the host immune system in the hopes it ends up nerfing the intended target (tumor/virus/whatever).

Given that the compound seems effective against C. Difficile (even if it’s in mice), I’d expect it to work elsewhere.

Of course, I’m not a doctor and have no idea what I’m talking about so grain of salt required.

Post reply on HN