Slashdot Mirror
Software Beats Animal Tests at Predicting Toxicity of Chemicals (nature.com)
Machine-learning software trained on masses of chemical-safety data is so good at predicting some kinds of toxicity that it now rivals -- and sometimes outperforms -- expensive animal studies, researchers report. From a report: Computer models could replace some standard safety studies conducted on millions of animals each year, such as dropping compounds into rabbits' eyes to check if they are irritants, or feeding chemicals to rats to work out lethal doses, says Thomas Hartung, a toxicologist at Johns Hopkins University in Baltimore, Maryland. "The power of big data means we can produce a tool more predictive than many animal tests."
In a paper published in Toxicological Sciences on 11 July, Hartung's team reports that its algorithm can accurately predict toxicity for tens of thousands of chemicals -- a range much broader than other published models achieve -- across nine kinds of test, from inhalation damage to harm to aquatic ecosystems. The paper "draws attention to the new possibilities of big data," says Bennard van Ravenzwaay, a toxicologist at the chemicals firm BASF in Ludwigshafen, Germany. "I am 100% convinced this will be a pillar of toxicology in the future." Still, it could be many years before government regulators accept computer results in place of animal studies, he adds. And animal tests are harder to replace when it comes to assessing more complex harms, such as whether a chemical will cause cancer or interfere with fertility."
In a paper published in Toxicological Sciences on 11 July, Hartung's team reports that its algorithm can accurately predict toxicity for tens of thousands of chemicals -- a range much broader than other published models achieve -- across nine kinds of test, from inhalation damage to harm to aquatic ecosystems. The paper "draws attention to the new possibilities of big data," says Bennard van Ravenzwaay, a toxicologist at the chemicals firm BASF in Ludwigshafen, Germany. "I am 100% convinced this will be a pillar of toxicology in the future." Still, it could be many years before government regulators accept computer results in place of animal studies, he adds. And animal tests are harder to replace when it comes to assessing more complex harms, such as whether a chemical will cause cancer or interfere with fertility."
Further proof that machine learning and AI has real world use. This is replacing the suffering of millions of animals today. Truly useful.
Yeah, but the SOFTWARE said it DIDN'T cause cancer!
If we take a toxin that kills us, but had passed Animal Testing, then it is just God playing trick on us. But if it is something that an algorithm didn't realize to check then it is the fault of man. And some poor grad student will get hit with a multi-billion dollar lawsuit for not realizing such a chemical is harmful.
This is actually with my Tongue in Cheek response. But also a reflection of our culture and its intolerance for mistakes, to a point where we are being held back on progressing, because there could be new mistakes made, even though overall it is a much better solution.
If something is so important that you feel the need to post it on the internet... It probably isn't that important.
1) The model is not overfit.
2) The new compound is within or similar to something within the training set.
As drugs can be novel chemistry, there is a risk of (2). All models have a risk of (1).
Maybe I'm old-fashioned but it seems to me that confirming that a substance is not toxic and predicting how toxic it may be are two very different things.
At some point someone will fill in for a patent on this technology. The end result will be rather sad - 1 group of people will be earning billions; the rest of the world will continue breeding lab rats.
I say, rather than torture the animals, let us get rid of these government regulations and let the people who want these stupid products test them out.
This posting is provided 'AS IS' without warranty of any kind, implied or otherwise.
Animal testing.
Where's the source data going to come from if we were to stop all animal tests (which you know, sociologically speaking, is where this is leading)?
The software predicts toxicity based on existing data, right?
I'm not particularly familiar with the industry, but I was presuming this could be first line of defense, with a smaller round of animal testing as the last line of defense to confirm the safety of the chemicals as attested by the predictions. Trust when the model says it's toxic/irritant, but verify when the model proclaim something to be safe.
If the models work, then the animal testing should be relatively humane (they should just be getting safe doses at that point) and cheaper/quicker (fewer animals made non-viable through the 'error' part of trial and error, fewer iterations that have to wait for biological processes to run the full course). However if the models are wrong, then the animal testing may bear that out.
XML is like violence. If it doesn't solve the problem, use more.
with out any text, or data? i am reminded of the invention of a battery found in a mesopotamian ruin. is this another great discovery buried in the sands of time?
There is one thing you a forgetting... this is also putting millions of animals out of a job! ;)
Funny but the ironic bit is how that is the EXACT same argument people use when we replace jobs that involve handling or emitting chemicals that kill people. We can't stop mining coal despite it killing people because people might lose their jobs! We can't use autonomous vehicles because truck drivers might lose their jobs.
You'd think that the software beats animal tests every time, but even the summary says, "it now rivals -- and sometimes outperforms -- expensive animal studies".
"Sometimes outperforms" is not the same thing as beating every time. "Rivals" implies that the two are about evenly matched.
You take the drugs and chemicals the software says are good. I'll stick with animal tested drugs.
The "prediction" the algorithm this hypes does not distinguish between "Fatal in contact with skin" and "Harmful in contact with skin". Wouldn't you think that the difference matters? The algorithm uses GHS hazard statements (see wikipedia) but ignores things like carcinogens (!!) and reproductive effects (!!!). I know, I know, "it's better to light a single candle...". But still, this is no where near a replacement for Animal Tests. At what point do can you confidently stop animal testing and use this? Well, never. But who knows, the approach may lead to something useful someday.
No, you're not old-fashioned, because the old-fashioned people were well aware of the phrase: "The poison is in the dose." :)
--
.nosig
can now be looked up by computer.
Domestic spying is now "Benign Information Gathering"
That's not how life science works. When biological or environmental differences lead to variations in test results, those variations are not "errors," they are data. Averaging them out, or presenting a number that implies that variation is not there is incorrect and misleading. Stating that your prediction of animal toxicity (that's what the study is predicting) is more reliable than an animal test because animal tests show wider variance than your prediction model does is pretty dumb.
Still need to keep testing the animals to make sure AI keeps beating animal experiments.