1143 stories
·
1 follower

The End of Disease

1 Share

Last night the CEO of Google DeepMind, Demis Hassabis, appeared on 60 Minutes, and had this (among other things) to say:

Demis Hassabis: Proteins are the basic building blocks of life. So, everything in biology, everything in your body depends on proteins. You know, your neurons firing, your muscle fibers twitching, it's all mediated by proteins.

But 3D protein structures like this are so complex, less than 1% were known. Mapping each one used to take years. DeepMind's AI model did 200 million in one year. Now Hassabis has AI blazing through solutions to drug development. 

Demis Hassabis: So on average, it takes, you know, ten years and billions of dollars to design just one drug. We can maybe reduce that down from years to maybe months or maybe even weeks. Which sounds incredible today but that's also what people used to think about protein structures. And it would revolutionize human health, and I think one day maybe we can cure all disease with the help of AI.

Scott Pelley: The end of disease?

Demis Hassabis: I think that's within reach. Maybe within the next decade or so, I don't see why not.

So let me be one of the people to say Why Not. I'm not happy about doing this, or feeling as if I have to be doing this. I have written on this subject over and over for quite a few years now, and I sometimes worry that I'm getting pigeonholed as "That Dude That Says That AI Drug Discovery Isn't So Amazing". But at the risk of making that even more of a problem than ever, here we go.

If you want to see what I've written in the past about this, probably the original is 2007's "Andy Grove: Rich, Famous, Smart, and Wrong", in which I coined the phrase "The Andy Grove Fallacy" to describe the "why doesn't drug discovery get with the modern age and move as fast as software development" attitude. I expanded on this in 2010 and 2011 in commentaries ("Biology by the Numbers" and "Drugs, Airplane, and Radios") on the famous/infamous "Can a Biologist Fix a Radio" paper that appeared in 2002. These issues came up again in 2014 with "Google's Calico Moves Into Reality" and "Peter Thiel's Uncomplimentary View of Big Pharma".

If you're just going to read one of these earlier posts (at most) - and I can definitely understand the impulse - perhaps it should be 2015's "Silicon Valley Sunglasses". In 2018 I had pieces on nascent biotechs that were making what were (to me) grandiose claims for their computational powers in "The Case of Verge Genomics" and "Rewiring Plankton: And Reality". And the computational biology radio-fixing topic appeared again that year in "Engineering Biology, For Real?"

At this point, the AI hype really began to start taking over the world, and in 2019 I covered three announcements that companies had indeed discovered new drugs using such technology ("Has AI Discovered a Drug Now? Guess", "Another AI Drug Announcement", and "An AI-Generated Drug?". In recent years I've written some overviews of my thoughts on AI drug discovery in general (and tried to address what I think are some misconceptions about both topics) in "AI and Drug Discovery: Attacking the Right Problems" in 2021, "AI and the Hard Stuff" in 2023, and "AI Does Not Make It Easy" in 2024.

If you read through some of those, you will get about as much of my opinions on the subject as anyone can stand, and some of them you will receive several times from slightly different angles. And you'll also be well-equipped to see why Hassabis' statements above make me want to spend some time staring silently out the window, mouthing unintelligible words to myself. But let me lay down some of these thoughts again, interspersed with some new ones that I've been talking about recently.

First off, (1) the huge majority of what people are calling AI these days is in fact machine learning. Nothing wrong with that - machine learning can be great stuff, when you have a large enough and well-curated-enough data set to feed into such systems, and when the problems you're trying to work on have well-defined boundaries. But I would like to add that in my opinion (2) machine learning does not create any new knowledge. It rearranges information you have already obtained and combs through it looking for correlations and rules and patterns, and it can do a far, far better job at this than any human could. If the problem space you are working in has few enough degrees of freedom in it, it can use these patterns to make extremely useful analogies and predictions - the protein structure work that Hassabis references is a shining example of this. But (3) I strongly believe that all machine learning is done by looking for patterns in some sort of language (be it a native human language (or a coding language) as with chatbots, mathematical symbols, the language of protein sequence and structure as with AlphaFold et al., and so on. The analogies between letters, words, sentences, and grammar hold up quite well across such systems. And I believe that Wittgenstein was right when he said that in any language there are things that cannot be said.

For protein structure predictors like AlphaFold, examples of those things that cannot be said include all the larger, more important questions such as "Which of these proteins is more responsible for this particular disease?" and "Which of these proteins would be more likely to lead to a successful drug?" as well as "Which of these proteins should we avoid working on because such projects will have more potential pitfalls than the others?" Boy, those would be great questions to answer! But a machine learning program that knows protein structure cannot answer them, no matter how amazingly well it knows protein structure. You can extend that line of thinking, and you're going to have to extend it if you talk about "curing disease" in general - there are so, so many important questions that we don't even know how to get started on answering.

Now, at this point I have to briefly note Hassabis' protein-centricity, which ignores (poly)nucleotides, lipids, carbohydrates, small-molecule signaling ligands and all the rest of the incredible variety of biomolecules that make up a living system. His point of view comes naturally from someone who has been involved in such great advances in protein structure prediction, but no, "everything in your body depends on proteins" (or any one class of molecules!) is such a reductionist take that it really doesn't get you anywhere useful. It's like saying that everything in the Mona Lisa depends on the paint. We have systems built on top of systems that build up other systems past them, and our knowledge of such things is completely inadequate to cure disease within ten years. And unfortunately, it's going to be inadequate at the end of that ten years, too - I will put that marker down, although it doesn't make me happy to do it.

That's because we don't have enough pieces on the table to solve this puzzle. We don't even have enough in most of these areas to know quite what kind of puzzle we're even working on. Nowhere near. And AI/ML can be really, really good at rearranging the pieces we do have, in the limited little areas where we have some ground-truth knowledge about the real-world effects when you do that. But it will not just start filling in all those blank spots. That's up to us humans. My most optimistic take on these technologies is that if things go really, really well they might be able to help guide us towards more productive research than we might otherwise have been doing, but we are going to have a lot of data to gather, a lot of answers to run down, and a lot of twists and turns and utter surprises to deal with along the way. We're going to need a terrifying amount of new knowledge before we can actually turn to any AI/ML systems and ask them the kinds of big questions I mention above.

I realize that many on the AI side of the business are hoping for a breakthrough in Artificial General Intelligence to cut through all the sort of bleating I've been doing. But how is AGI going to suddenly reveal what is now hidden? The sum total of all the medical information in the world right now is not enough. And it's going to go on being Not Enough for quite some time to come. I hate to be like this, but I really have no other position I can take.

 

Read the whole story
tabithaclem
2 days ago
reply
Share this story
Delete

Thurston and theodora

1 Share

 A sweet rescue…..

In July 2013, we took in Cici and Harley. 
We were surprised when we found out puppies were coming-5 of them.  
When they were old enough, they were all adopted   

Papa Harley was stunning.  When Harley and Cici came to us, they were matted and has be shaved down.  But their hair grew back beautifully.  
 Papa Harley and mama Cici were adopted together. 

Two of the puppies were adopted by Pati. She named them Thurston and Theodora.  
Theodora was the tiny female she adopted. They both became stunning adult Pekes. 
Life has been wonderful for Theodora and Thurston. It’s hard to believe they are almost 12 years old.  The whole family, Harley, Cici, and all the puppies are still doing great.  What a sweet rescue that was. 🌺

Read the whole story
tabithaclem
16 days ago
reply
Share this story
Delete

POLEN IS HERE

1 Share


Kringle was helping his mom in the garden.  He looks so good.  His mom has done such a great job in helping him heal. 
She noticed he has a golden glow. It was pollen!  
Kris, now Eddie, has itches.  The pollen gets walked on. Then the dogs lick their paws and ingest the pollen. Ugh. Some dogs take 1/2 a Zyrtec.  Some take apoquel.  Some get a cytopoint shot to help w allergies.  (Of course, always consult w your vet.). 
Mistletoe (who is sitting on dog laundry) gets itchy w the spring things growing.  She hops around in the ivy and border grass.  And leaves. We have many trees and she brings them in on her tail. Yay. 
Gidget is peeking around the door. Are you hiding from pollen? 😜 I would if I could. 
Dickens skin is still healing and I hope the pollen doesn’t make it worse.   I’ll be glad when we get rain and it washes away.  The dogs will be glad, too.  

 

Read the whole story
tabithaclem
21 days ago
reply
Share this story
Delete

GIDGET -- MOMMY'S GIRL

1 Share

Gidget is Amee's special girl.   I fostered Gidget in 2020-2021.   I went on vacation and asked my daughter to watch out dogs, but Amee watched Gidget.  Gidget never came back home with me.  She was home with Amee.
Gidget came into rescue with her brother, Rocky in December 2020.   She was 9 at the time,  She had white eyelashes which gave her a distinct look.  
Gidget welcomed Autumn to her home recently.  She knows what it is like to be the new one.  
Gidget also thinks she's the queen bee, so she lets them know she is in charge.  
Autumn is so glad that Gidget let her stay.  
Gidget had a bath the other day.  Her mom messaged me to see if I could hear her screaming--and I'm almost 100 miles away.  LOL   Gidget CAN SING!!
Gidget is now 13.  It's hard to believe.  As she had gotten older, she has decided that she enjoys fruit.  Her mom said mango is her favorite.  I love mango, too.   
Gidget may be a little older now, but she will always be her mommy's girl.  💜


 

Read the whole story
tabithaclem
27 days ago
reply
Share this story
Delete

PIPER AND PADDINGTON—BIRTHDAY!

1 Share

Piper and Paddington came into rescue 6 years ago last month.  
Their owner was in the hospital and couldn’t take of them anymore.  Paddington looks at Piper as his father figure. 
They had all their medical completed.  My husband had never asked to keep any of the dogs I fostered.  But he asked if we could keep them. ❤️❤️ 
Paddington has grown long beautiful ears. He is a stunning red Peke.  
Piper has become my shadow.  Where I go, he goes.  I was told he was a Malti-Poo.  When I did a DNA test on him, he wasn’t a Malti-Poo.  He was a Shih Tzu/Maltese.  And he even has 2% Pekingese!  
Paddington is a big mush.  You can hold him on his back like a baby.  I can trim his nails and he doesn’t budge. 
They found the Pekingese pathway in the yard right after they came.  
Paddington has the nickname “Bad Pad.”  He has been known to be a pistol w male foster dogs.  😩
But how could I stay mad at this face.  Nope.  Can’t do it. 
When Cinnamon came into rescue, Paddington became her protector.  He has never fussed at her!  
Now they celebrated another birthday here.  Paddington turned 9 and Piper turned 10. 

Happy birthday Piper and Paddington. 🎂❤️🎂❤️
Let’s all celebrate! 🥳🎉




Read the whole story
tabithaclem
31 days ago
reply
Share this story
Delete

Metamorphine, An Unwelcome Product

1 Share

Now this is one that I wouldn't have seen coming. In hospital settings it's common to use patient-controlled analgesia (PCA) pumps for management of severe pain. These infuse a solution containing morphine together with nonopioid analgesics directly into a patient's intravenous connection, and allow them to deal with their own experience of pain and their own tolerance for it. This system actually tends to result in lower analgesic doses than would otherwise be administered and improves the patient experience in general.

But a couple of years ago questions were raised about one commonly used mixture. There have naturally been IV solution stability studies of the main analgesics used (morphine, hydromorphone, esketamine, and metamizole), but it turned out that the morphine/metamizole combination was not as stable in solution (an effect first noted in doctoral work in 2009). Hydromorphone/esktamine mixtures were completely stable at 22C and at 37C, but while a morphine/metamizole mix held up at 22C, it showed significant ongoing loss of both components at 37 degrees. 

This turns out to be due to the formation of a Mannich condensation adduct between metamizole and morphine (shown at right) which has been given the name "metamorphine". Metamizole itself can decompose to provide the formaldehyde needed. This new paper characterizes it thoroughly and looks into its pharmacology, and it turns out to still be a nanomolar ligand at the mu-opioid receptor. That's 8- to 10-fold weaker than morphine, but still very much in the pharmacological activity range (remember, morphine is the standard by which opioid agonists are judged!) This was unexpected, since that's a pretty large group to hang off the morphine backbone. But there are some changes on the metamizole - metamorphine seems to have lost all of metamizole's anti-inflammatory activity.

As long as PCA pumps are kept at room temperature, this shouldn't be a problem. But if they are too close to the patient's body, left on or near warm equipment, or exposed to sunlight, you could see some problems. Never assume without checking that your chemicals are going to do what they're supposed to or remain what they say they are on the label - particularly in solution!

Read the whole story
tabithaclem
31 days ago
reply
Share this story
Delete
Next Page of Stories