First drug developed using machine learning enters clinical trials

[Bubbajim]

What just happened? Of all the domains where machine learning is expected to be revolutionary, medicine is perhaps the most universal. In a major new milestone, a drug developed using machine learning is about to enter human trials.

Before a new medicine enters human trials, there is typically three to five years of work behind the scenes, researching causes for diseases and compounds that may help treat them. But working with British AI startup Exscientia, a Japanese drug development company called Sumitomo Dainippon Pharma Co. is about to start phase 1 clinical trials after only 12 months.

The drug in question is DSP-1181, a prospective treatment for obsessive-compulsive disorder (OCD). OCD affects millions of people worldwide, to varying degrees, and can be debilitating in its psychological effects.

Exscientia, based in Oxford, UK, operates an exciting machine learning platform called Centaur Chemist. The platform allegedly takes years off the time required to research new compounds, by combining A.I. techniques with existing knowledge of how medicines interact with the human body.

The benefit of machine learning is that it can happen virtually, and far quicker than scientists are able to work in the real world. The platform can analyze millions of molecular combinations and attempt to identify which may be the safest and most effective in treating a given disease.

Perhaps even more important is the potential savings associated with using machine learning to develop new medicines. Typically, it costs over $1 billion to bring a new drug through from conception to market, with a lot of those costs borne out during the research phases. But taking out years of painstaking research will save both time and money, speeding up development and freeing up resources to develop yet more medicines.

There’s a lot riding on Exscientia and Sumitomo Dainippon’s trial. The first phase is to check how the drug affects the body, and how the body metabolises the drug. So this will not prove the medication’s efficacy.

But if DSP-1181 is shown to be safe, phases two and three can proceed, to see whether the drug can help OCD patients in the real world. And if it does, we’ll witness the dawn of machine learning in medicine.

Permalink to story.

https://www.techspot.com/news/83827-first-drug-developed-using-machine-learning-enters-clinical.html

 

[Uncle Al]

The drug in question is DSP-1181, a prospective treatment for obsessive-compulsive disorder (OCD).

A drug created by a computer to treat an illness that is frequently associated with compulsive behavior like ... playing computer games. Imagine that!

 

[cliffordcooley]

OCD diagnosis in the majority of cases is not a disorder at all. The disorder is people thinking others not like them have disorders. People are different with a variety of passions. That does not mean they have a disorder because their passion is different. The disorder is our lack of ability to keep up.

 

[Evernessince]

OCD diagnosis in the majority of cases is not a disorder at all. The disorder is people thinking others not like them have disorders. People are different with a variety of passions. That does not mean they have a disorder because their passion is different. The disorder is our lack of ability to keep up.

You are thinking that someone who's obsessed with their passion has OCD but that would be categorically incorrect. If someone has OCD, they display specific mental ticks across the board, not just in a single area. There's another major difference as well, often times those with OCD display behavior patterns that seemingly make no sense and that which they themselves aren't even aware of. There is a very big difference between a passionate person and someone with OCD. In fact I'd call them completely different.

If you want an example (but no where near a full screening) check here: https://psychcentral.com/quizzes/ocd-quiz/

 

[umbala]

The drug in question is DSP-1181, a prospective treatment for obsessive-compulsive disorder (OCD).

A drug created by a computer to treat an illness that is frequently associated with compulsive behavior like ... playing computer games. Imagine that!

Why must you always comment on things you know nothing about? OCD has absolutely nothing to do with video game addiction. I know you're trying to be clever with "a computer is going to fix an illness a computer created" type of thinking, but it's offensive.

 

[umbala]

You are thinking that someone who's obsessed with their passion has OCD but that would be categorically incorrect. If someone has OCD, they display specific mental ticks across the board, not just in a single area. There's another major difference as well, often times those with OCD display behavior patterns that seemingly make no sense and that which they themselves aren't even aware of. There is a very big difference between a passionate person and someone with OCD. In fact I'd call them completely different.

If you want an example (but no where near a full screening) check here: https://psychcentral.com/quizzes/ocd-quiz/

Your description of OCD is also incorrect. You do not have to display specific mental ticks (or any ticks at all) across the board as you asserted. It's more of a spectrum similar to Autism. Any set of irrational thought patterns or personal "rituals" that consume a significant amount of time each day can be considered OCD behavior.

Your other assertion that the person themselves aren't aware of their OCD behavior is also incorrect. In fact, this is one of the worst sides of OCD in a way torturing your own mind. Because usually you're aware that what you're doing is compulsive or unusual, but you still can't stop doing it.

Some examples include walking up or down stairs and feeling the need to count them, or having to wash your hands after touching any foreign objects, or having things arranged a certain way on your desk, etc.

 

[cliffordcooley]

You are thinking that someone who's obsessed with their passion has OCD but that would be categorically incorrect.

I'm not the one diagnosing everyone with a disorder (not just OCD) to monitize on sales of medicine. Medicine of which makes the persons condition worse. But then why should they care as long as they can pay their bills. I'm not suggesting people don't have conditions. I'm saying way too many people are being diagnosed with conditions they don't have. My two sons was caught up in the crap. While their mother was pursuing state aid. It was the state pushing **** on us for no reason, other than to charge someone a bill.

 

[Evernessince]

Your description of OCD is also incorrect. You do not have to display specific mental ticks (or any ticks at all) across the board as you asserted. It's more of a spectrum similar to Autism. Any set of irrational thought patterns or personal "rituals" that consume a significant amount of time each day can be considered OCD behavior.

Your other assertion that the person themselves aren't aware of their OCD behavior is also incorrect. In fact, this is one of the worst sides of OCD in a way torturing your own mind. Because usually you're aware that what you're doing is compulsive or unusual, but you still can't stop doing it.

Some examples include walking up or down stairs and feeling the need to count them, or having to wash your hands after touching any foreign objects, or having things arranged a certain way on your desk, etc.

"Mental tics are thoughts that intrude into a person's mind "

mental tics - Google Search

This is a pointless argument of semantics where the end result is the same.

"Your other assertion that the person themselves aren't aware of their OCD behavior is also incorrect. In fact, this is one of the worst sides of OCD in a way torturing your own mind. "

And that's why I used quantifiers.

I highly doubt that either of us are qualified to speak with absolute confidence on this subject and given your terse response you yourself certainly are no psychiatrist.

 

[OortCloud]

There's a few people on here that could do with a healthy dose of DSP-1181...

 

[Unusual Kmc]

There's a few people on here that could do with a healthy dose of DSP-1181...

Such as yourself? Do you feel the need to post useless comments?

 

[captaincranky]

I think they should work on hybridizing a benzodiazipine with some form of psychedelic agent.

You know, something that when you're walking through a ghetto, that the buildings are made of gold, fluffy clouds appear at your feet, and the rap music turns into choirs of angels, all of this accompanied by an overwhelming sense of well being

 

[OortCloud]

Such as yourself? Do you feel the need to post useless comments?

It was just a lighthearted remark about us computer types being a little OCD - but if it upset you then I apologise...

 

[wiyosaya]

I'm not the one diagnosing everyone with a disorder (not just OCD) to monitize on sales of medicine. Medicine of which makes the persons condition worse. But then why should they care as long as they can pay their bills. I'm not suggesting people don't have conditions. I'm saying way too many people are being diagnosed with conditions they don't have. My two sons was caught up in the crap. While their mother was pursuing state aid. It was the state pushing **** on us for no reason, other than to charge someone a bill.

I agree that there are more than enough doctors/whatever who are out there trying to get you to spend more money on medicines that are not always needed, and I also see that medical advice changes from year to year.

I had a conversation with a RN a few years back about the fact that I do not get the flu shot because I have a bad reaction to it, and I also rarely get sick. She literally said to me "That sounds like an allergic reaction. You should get tested for allergies." I did not tell her this out loud, but I was thinking, "yeah, right. I should get tested for allergies because I should take a shot that I do not need and have a bad reaction to." ?

And even though my Doctor knows about the fact that I have a bad reaction to the flu-shot, he keeps trying to get me to have it every year. ?

A few years back, I had a doctor tell me that I needed to be listed as a former smoker even though it was nearly 40-years since I smoked. I believe her reasoning was that the damage would never heal. Well, just recently, there was a study released that the lungs heal the damage from smoking after quitting. https://www.bbc.com/news/health-51279355 There's a laughable, IMO, quote in the article where some doctor says something like "we never would have thought that the lungs can heal." I kinda thought to myself, "yeah, no sh!t".

And I could go on and on about the things diabetics should not do or consume because, GASP, it will lower their blood sugar and their need for insulin.

As I see it, factors have made modern medicine a co-dependent relationship. Have an ache? Take a pill, etc., etc., etc. My approach is to take as little medicine as possible - in fact, the only medication that I take is insulin. In addition, I keep up on research pertaining to my health, and I think that it provides a better path for me.

Medical mistakes are a problem, and I think that there is a significant amount of just for profit motive that casts a pall over the entire industry - at least from my point of view. YMMV.

 

[BadThad]

People complain about drug prices all the time. They are expensive because the cost of bringing them to market is HUGE. Sometimes hundred of millions of dollars are spent only to flush everything down the drain when it doesn't work as expected, bad side effect or some other negative attribute is discovered.

I worked for in generic pharma R&D for 10 years. Even bringing a generic medicine to market can cost upwards of $100 million or more.

Bottom line, if this works, it would be helpful for all of mankind in the cost savings alone.

 

[captaincranky]

The drug in question is DSP-1181, a prospective treatment for obsessive-compulsive disorder (OCD).

A drug created by a computer to treat an illness that is frequently associated with compulsive behavior like ... playing computer games. Imagine that!

I kinda have to agree with the young 'uns on this point. Habitual gaming is more of an addictive disorder than OCD The same with checking Facebook every 10 minutes. Cell phones are particularly addictive as well.

There are two classes of addiction mental and physical. Obviously, physical addiction comes to mind first, as it is the most severe, witness the "opiod crisis". You can actually die from withdrawal.

When somebody takes your X-Box away from you, you'll just wish you were dead. But, as the song goes, "your heart will go on".

 

[captaincranky]

I worked for in generic pharma R&D for 10 years. Even bringing a generic medicine to market can cost upwards of $100 million or more.

How on earth can it take 100 million plus to bring a generic drug to market, when a company has been handed the formula due to patent expiry?

Hey, just asking.

 

[BadThad]

How on earth can it take 100 million plus to bring a generic drug to market, when a company has been handed the formula due to patent expiry?

Hey, just asking.

The formula is not "handed over" nor anything else given to the generic manufacturer. They only thing the generic mfg knows is the active ingredient level(s) and what any consumer can find about a drug. Additionally, generic manufacturers start work years before the patent expiration with the goal of bringing the product to market at or shortly after the patent expires. The R&D cost alone is huge since you're starting from ground-zero. You have to develop the product, perform hundreds of laboratory in-vitro tests and then, when you THINK it will work, run the in-vivo trials. Most often, the first trial will fail and then you get to start all over again.

 

[RebelFlag]

Such as yourself? Do you feel the need to post useless comments?

Apparently you do......

 

[Danny101]

That's nice! We're now being medicated by Skynet.

 

[Sir Sparkles]

The concept of connecting dots with known research and then making educated guestimations about compounds to try is a great revolution in bringing newer medicines to market. What may be lacking in this though is that if we fully turn this direction the database which we are referring to for these equations may stagnate. There has to be a balance between analytical science, exploratory science and accidental discovery. Some of our greatest leaps forwards in medicine were unintended discoveries. Think penicillin, insulin, quinine, paracetamol, viagra, valium, warfarin, LSD... the list goes on and on.