AI (artificial intelligence) discovers first new antibiotics in over 60 years!

[NewGuywithPD]

I believe that AI will CURE ALL DISEASES!

====================================

youtu.be/ahU5SO-j1A0?si=3I6...(Not working as expected?)

================================

[park_bear]

Just about any computer program can be regarded as a kind of "AI". Specialized computer programs for new drug discovery have been in use for many years and are constantly being improved. These sorts of AI have nothing to do with the large language model chatbots that have become a recent fad.

New antibiotics have been discovered all the time and many have been approved over the last 60 years. It is a long way from discovery of a new "class" of antibiotic to testing, human trial, and approval.

[NewGuywithPD in reply to park_bear]

it's obvious you never watched the video

[park_bear in reply to NewGuywithPD]

Okay, I have now watched the video. I reiterate my prior comment and will add that the video is wrong and uninformative. Many new antibiotics have been discovered and approved over the last 60 years. A couple of examples right off the top of my head are linezolid and its recently approved relative tedizolid. An entirely new class of antibiotic first approved in 2000.

The video fails to state what kind of AI helped with the new discovery, what antibiotic was discovered, and who discovered it. It wrongly implies that the cost of new antibiotic development was reduced from 1.5 billion to 50 million, which is wrong because most of the cost in drug development is in the human clinical trials.

Here is some proper reporting on the matter. No mention of AI being used:

arstechnica.com/science/202...

[Boscoejean]

the video does not exactly give you a wealth of information on how they used the AI to find this-

"In this case, the researchers designed their model to look for chemical features that make molecules effective at killing E. coli. To do so, they trained the model on about 2,500 molecules, including about 1,700 FDA-approved drugs and a set of 800 natural products with diverse structures and a wide range of bioactivities.

Once the model was trained, the researchers tested it on the Broad Institute’s Drug Repurposing Hub, a library of about 6,000 compounds

"The model picked out one molecule that was predicted to have strong antibacterial activity and had a chemical structure different from any existing antibiotics. Using a different machine-learning model, the researchers also showed that this molecule would likely have low toxicity to human cells"

"This molecule, which the researchers decided to call halicin, after the fictional artificial intelligence system from “2001: A Space Odyssey,” has been previously investigated as possible diabetes drug. The researchers tested it against dozens of bacterial strains isolated from patients and grown in lab dishes, and found that it was able to kill many that are resistant to treatment, including Clostridium difficile, Acinetobacter baumannii, and Mycobacterium tuberculosis. The drug worked against every species that they tested, with the exception of Pseudomonas aeruginosa, a difficult-to-treat lung pathogen."

news.mit.edu/2020/artificia....

[NewGuywithPD in reply to Boscoejean]

it was only a 15 minute video ... not a 'documentary'

the point i was trying to make ... is that quantum computers are about a BILLION x BILLION x BILLION .... fasssssssssssssster than our best super computer now ...

the point i was trying to make ... is that there have been tens of thousands of research papers and trials about Parkinson since the 1960s .

No 'human' could possibly read ... absorb ... and analyze that much data to project possible therapies.

But ... a quantum computer will be able to do this easily!

[Boscoejean in reply to NewGuywithPD]

and what I am saying is that it is often far easier to get a more complete picture by reading an article about the topic than watching a video that never really gives you much in the way of details