Machine Learning Takes On Antibiotic Resistance (quantamagazine.org) 13
To combat resistant bacteria and refill the trickling antibiotic pipeline, scientists are getting help from deep learning networks. From a report: Once-powerful antibiotics are losing their efficacy at a disconcerting pace as bacteria evolve immunity to our drugs. At least 700,000 people around the world now die each year from infections that could formerly be treated with antibiotics. A report last year from the United Nations Interagency Coordination Group on Antimicrobial Resistance warned that if no new major advances are made by 2050, mortality could leap to 10 million deaths a year. What makes this prognosis all the more dire is that the antibiotic pipeline has slowed to a trickle. In the past two decades, only a few new antibiotics have been found that kill bacteria in novel ways, and rising resistance is a problem for all of them. Meanwhile, traditional methods of identifying antibiotics by screening natural compounds continue to come up short. Because of this, some researchers are now turning from the wet lab to silicon power in hopes of finding an answer.
In the February 20 issue of Cell, one team of scientists announced that they -- and a powerful deep learning algorithm -- had found a totally new antibiotic, one with an unconventional mechanism of action that allows it to fight infections that are resistant to multiple drugs. The compound was hiding in plain sight (as a possible diabetes treatment) because humans didn't know what to look for. But the computer did. Using computers and machine learning to make sense of mountains of biomedical data is nothing new. But the team at the Massachusetts Institute of Technology, led by James Collins, who studies applications of systems biology to antibiotic resistance, and Regina Barzilay, an artificial intelligence researcher, achieved success by developing a neural network that avoids scientists' potentially limiting preconceptions about what to look for. Instead, the computer develops its own expertise.
In the February 20 issue of Cell, one team of scientists announced that they -- and a powerful deep learning algorithm -- had found a totally new antibiotic, one with an unconventional mechanism of action that allows it to fight infections that are resistant to multiple drugs. The compound was hiding in plain sight (as a possible diabetes treatment) because humans didn't know what to look for. But the computer did. Using computers and machine learning to make sense of mountains of biomedical data is nothing new. But the team at the Massachusetts Institute of Technology, led by James Collins, who studies applications of systems biology to antibiotic resistance, and Regina Barzilay, an artificial intelligence researcher, achieved success by developing a neural network that avoids scientists' potentially limiting preconceptions about what to look for. Instead, the computer develops its own expertise.
Is this a dupe or not? (Score:3)
On the one hand, they're referring to the same February 20th issue of Cell. On the other, this story is from Quanta, not The Guardian.
https://science.slashdot.org/s... [slashdot.org]
Does change of scenery warrant a new slashdot post? In general, Quanta's science coverage is better and more interesting than The Guardian.
Re: (Score:2)
Does change of scenery warrant a new slashdot post? In general, Quanta's science coverage is better and more interesting than The Guardian.
IMHO in this case it definitely does.
The Guardian's article just talks about the drugs and mentioned that A.I. was used to find them.
The Quanta article goes deep into the nerd-interesting guts of the search and how it was accomplished.
In particular it brought to light the Drug-repurposing database and how it allows the discovery of new uses for already approved drugs - w
It should come as no surprise (Score:1)
Phages? (Score:2)
Re: (Score:2)
"The Deadliest Being on Planet Earth - The Bacteriophage" [youtube.com]
.
Re: (Score:1)
That's the second phage.
Comment removed (Score:4, Informative)
Re: (Score:1)
Re: (Score:2)
Re: (Score:2)
Here is #4:
3. For every new hospital being built, instead build 2, separated by 100 meters or so. Use one building for 6 months, then move everything to the other for the next 6 months. Killer bacteria are also bred in hospitals - moving them around and allowing the building to lie 'fallow' for a time should kill off all the resistant bugs and keep the hospital from breeding drug resistant bacteria.
Anyone else ever propose something like this?
Application of the methodology to COVID-19 (Score:2)
(Some of this is a repeat from above, but in a different context.)
The article brought to light the Drug-repurposing database and how it allows the discovery of new uses for already approved drugs. These can be immediately used off-label and have an abbreviated set of tests run for putting the new use on-label, rather than having to go through the whole multi-year safety-and-effectiveness obstacle course.
It would be nice to see the database (and perhaps also this methodology) applied to the search for anti-
Re: (Score:2)
Re: (Score:2)