Slashdot Mirror


Programming Molecules To Let Chemicals Make Decisions

Nerval's Lobster writes "Computer scientists at Harvard University have come up with a way to convert algorithms that teach machines to learn into a form that would allow artificial intelligence to be programmed into complex chemical reactions. The ultimate result could be smart drugs programmed to react differently depending on which of several probable situations they might encounter – without the need to use nano-scale electronics to carry the instructions. 'This kind of chemical-based AI will be necessary for constructing therapies that sense and adapt to their environment,' according to Ryan P. Adams, assistant professor of computer science at Harvard's School of Engineering and Applied Sciences (SEAS), who co-wrote the paper explaining the technique (PDF). 'The hope is to eventually have drugs that can specialize themselves to your personal chemistry and can diagnose or treat a range of pathologies.' The techniques are part of a larger effort to program the behavior of molecules in manufacturing, decision-making and diagnostics, using both nano-scale electronics and the still-relatively-new study of bionanotechnology."

28 comments

  1. Bugs by Anonymous Coward · · Score: 0

    At least software bugs rarely kill people. It would be a very long time before I trust something like this for common treatments.

    1. Re:Bugs by pepty · · Score: 1

      Oddly enough the molecular programming part (polling the state of the cell, making a decision) will probably prove easier than the traditional part (crafting the drug that actually carries out the decision)

  2. First step by Rick+Zeman · · Score: 1

    Sounds like the first step to creating Orson Scott Card's "descadola" virus. When reality imitates fiction....

    1. Re:First step by Rick+Zeman · · Score: 1

      Errr, "descolada." Think I was dyslexic a bit there....

  3. Prior Art: Testosterone by Anonymous Coward · · Score: 5, Funny

    Come on. Men have been letting testosterone make decisions for them since the dawn of mankind.

    1. Re: Prior Art: Testosterone by Anonymous Coward · · Score: 0

      Estrogen is the other side of the coin.

  4. What could possibly go wrong? by Nkwe · · Score: 0

    Lots of stuff could go right as well, but it is a question worth asking.

  5. aka.. by houbou · · Score: 1

    a super-smart kryptonian white cell? :) lets' just make sure we stay under a yellow sun! :)

  6. Intresting idea by prefec2 · · Score: 1

    If I understand that correctly, it can work like a selection expression from XPath, aspect languages or graph search terms to match on the right "locations" in a lifeform body or any other complicated mixture, like soil.

    1. Re: Intresting idea by Electricity+Likes+Me · · Score: 1

      That eas my take from the paper - although this still seems very theoretical. The DNA computation implementation example isn't very useful because DNA is too unstable and too involved with regular biology to be used like that.

      The problem here is they're srill missing all the components to let you build something: you need a couple of molecules which can bind to useful cell receptors, change their state and unbind. Or you need a message carrier to bind to them and do the same. Then you need a whole family of drugs which can be selectively inhibited by your messengers.

      And then all of this needs to possibly avoid localization effects - i.e. your messengers need to avoid being concentrated in the body such that they might activate a whole bunch of drugs one-way, which then get absorbed faster then messengers elsewhere can deactivate them due to a positivs signal in one location.

  7. Queen City by Anonymous Coward · · Score: 0

    http://www.amazon.com/Queen-City-Doherty-Associates-Books/dp/0765307510

  8. This is the future folks by Anonymous Coward · · Score: 0

    While some countries think it's vital to re-create the space theater of half a century ago, the real breakthroughs will be understanding how matter organizes itself into life.

    1. Re:This is the future folks by mark-t · · Score: 2

      Both are important... for different reasons. Concentrating on one to the exclusion of the other is what is bad.

  9. w00t! by easyTree · · Score: 1

    Awesome - I can't wait until the script kiddies get hold of this and use it hack people and create armies of zombies.

    /me gets his shotgun and baseball bat and heads for the roof.

  10. Logic gates vs. AI by kruach+aum · · Score: 4, Interesting

    Rather than talking about these molecules in terms of Artificial Intelligence I think it would be more accurate to say that the molecules instead have some very rudimentary if-then logic designed into them. At this stage it doesn't sound *that* much more advanced than a reagent that turns blue in substance A and green in substance B.

  11. Look up. by Anonymous Coward · · Score: 0

    This is ALL KINDS OF AWESOME! The power of science is truly amazing.

    Yes, things could go wrong. Things could *always* go wrong, with anything and everything. That is *no excuse whatsoever* to abstain from the development of technologies that will benefit humanity.

    My only concern is that too little effort is being spent researching and engineering means of surviving the next super volcano eruption. People like to brush this off because there hasn't been one in a long time....but that is precisely the problem....

    We are due.

    And when one of these volcanoes (there are 40 of them on the planet!) goes pop, it will be a planet wide extinction-level event. All human ambition will be buried under a thick blanket of ice for decades. If we don't have our self-sustaining underground bunkers ready by then, we are toast.

    Just sayin'

    1. Re:Look up. by Anonymous Coward · · Score: 0

      Sounds like someone's been watching a few too many disaster movies...sheesh

      PS "just sayin'" makes you look like a dick

  12. Scale issues by thisisauniqueid · · Score: 1

    Wait, use chemical reactions on the scale of femtometers to avoid using electronics on the scale of nanometers? Got it.

  13. BS by methano · · Score: 0

    I am an organic chemist. I'm not the smartest guy in the world but I do know a little bit about making molecules and their chances of doing useful things in the body. I've been doing this for 35 years and I have some credentials though I'm not a Harvard professor. My opinion is that this article is pure, extremely well crafted, bullshit. Throwing in all that math only makes it more so.

    1. Re:BS by Anonymous Coward · · Score: 1

      (I'm being entirely 100% serious here, not derogatory in any way.) Could you please expand a little bit on that, for those of us that aren't in the field? This is one of the reasons I read Slashdot--to get the opinions of people way smarter than me.

    2. Re:BS by Anonymous Coward · · Score: 0

      You're a stupid old man who can't let go of the past. Back when I was in college, they just discovered faster of light neutrinos and my physics professor just said that they were wrong without even giving it a moment's thought. We live in an age of precedented technological advancement where anything is possible. I bet you would have said that the internet was impossible too, right up until Google built it, you anachronism.

    3. Re:BS by Anonymous Coward · · Score: 0

      Most likely because the paper doesn't actually tell anyone how to do anything. It just asserts you can take a graph and craft a situation chemically whose final ratios are correlated with the graph. All of their results are simulated and show a scale of 3000 seconds, which seems unreasonably long. If you are talking about possibly non-organic species of chemicals such as drug delivery, can you really afford to have a state oscillate to extremes before converging on the correct value? I would be really interested in a professional response to this article.

    4. Re:BS by sjames · · Score: 1

      Not the best example there. I *DO* hope you were going for funny.

  14. We already have chemicals making decisions by maxwell+demon · · Score: 1

    We already have chemicals making decisions. There are chemicals storing the program (DNA), chemicals reading the program (ribosomes), and chemicals executing the program (enzymes). The systems running on such molecular logic are usually called "organisms".

    --
    The Tao of math: The numbers you can count are not the real numbers.
  15. saved by Msdose · · Score: 0

    Soon they can spray this over Washington to turn all those communists into capitalists.

  16. Comment removed by account_deleted · · Score: 1

    Comment removed based on user account deletion

  17. Designer drugs or chemical engineering? by Anonymous Coward · · Score: 0

    While the potential for chemical engineering is great (think self-adjusting reactions), and the potential for a combined lab tests-diagnosis-treatment is awesome (think rejection vs infection or emergency room treatments. (i.e. Patient has replacement operation, has what appears to be a strong rejection response, is treated with immune-suppressant which allows in-reality-infection to kill patient.) Where time is critical the treatment could test-and-treat in one application without waiting for lab results, diagnosis, prescription, and treatment.

    But I think the most popular use will be designer drugs. They can get you wasted but never kill you. Maybe even help. If you "OD" they could do the opposite, treating you for poisoning. In spite of thousands of drunk deaths every year in Russia and the U.S. I don't see these ever becoming cheap enough to become a required additive to booze.