Forgot your password?
typodupeerror
Robotics Biotech Science

Robot Makes Scientific Discovery (Mostly) On Its Own 250

Posted by timothy
from the if-you-consider-that-on-its-own dept.
Hugh Pickens writes "A science-savvy robot called Adam has successfully developed and tested its first scientific hypothesis, discovering that certain genes in baker's yeast code for specific enzymes which encourage biochemical reactions in yeast, then ran an experiment with its lab hardware to test its predictions, and analyzed the results, all without human intervention. Adam was equipped with a database on genes that are known to be present in bacteria, mice and people, so it knew roughly where it should search in the genetic material for the lysine gene in baker's yeast, Saccharomyces cerevisiae. Ross King, a computer scientist and biologist at Aberystwyth University, first created a computer that could generate hypotheses and perform experiments five years ago. 'This is one of the first systems to get [artificial intelligence] to try and control laboratory automation,' King says. '[Current robots] tend to do one thing or a sequence of things. The complexity of Adam is that it has cycles.' Adam has cost roughly $1 million to develop and the software that drives Adam's thought process sits on three computers, allowing Adam to investigate a thousand experiments a day and still keep track of all the results better than humans can. King's group has also created another robot scientist called Eve dedicated to screening chemical compounds for new pharmaceutical drugs that could combat diseases such as malaria.
This discussion has been archived. No new comments can be posted.

Robot Makes Scientific Discovery (Mostly) On Its Own

Comments Filter:
  • by Toonol (1057698) on Thursday April 02, 2009 @11:42PM (#27440693)
    If I ever do cutting edge research on robot AI, please punch me if I try to name my new robots "Adam" or "Eve".
  • by Culture20 (968837) on Thursday April 02, 2009 @11:46PM (#27440713)
    ... it starts experimenting with inter-dimensional portal guns.
    • When weighed against the greatness of the songs those computers will write and sing, it's worth the loss of human and companion cube life. Besides, we don't know what the main character of Portal was doing there in the first place. After all, what are the chances that a woman who just HAPPENED to know how to fall infinitely far without damage would just HAPPEN to know how to operate the guns with perfect accuracy right after picking them up would just HAPPEN to be in the facility? Now, I'm not saying that s
    • by nospam007 (722110) * on Friday April 03, 2009 @04:55AM (#27442259)

      Call me when it begins faking results to get published.

      • Results won't need to be faked. Just like human researchers, it will be programmed to find certain results ahead of time. No faking involved.

      • When it develops its own hypothesis and after extensive testing and discovers it's wrong, will it feel bad?

    • We won't have to. The machines will call you with a calm message asking you to stay indoors.

  • Time for... (Score:3, Funny)

    by oldhack (1037484) on Friday April 03, 2009 @12:06AM (#27440823)

    the union of scientists. You thought Teamsters were nasty? You ain't seen jack squat. WE SPLICE GENES!!! WE SPLIT ATOMS!!! WE (probably) MAKE BLACKHOLES!!!

    Ross King, gutless traitor, you and your tin cans, your names will live in infamy.

  • But... (Score:5, Funny)

    by tsotha (720379) on Friday April 03, 2009 @12:07AM (#27440827)
    Oh, sure, it's neat-o. But you could probably afford hundreds of grad students to do the work for the same price.
    • Re:But... (Score:5, Informative)

      by wizardforce (1005805) on Friday April 03, 2009 @12:15AM (#27440871) Journal

      You joke but really undergrads are cheaper than graduate students... At least from my experience working in a biology lab in college. It was/is common practice to recruit undergrads to do free work for the labs. The undergrad gets some experience in the field and the lab gets free labor in exchange for dealing with the inexperience of the average undergrad.

      • Re:But... (Score:5, Insightful)

        by Saysys (976276) on Friday April 03, 2009 @12:20AM (#27440911)
        "in exchange for dealing with the inexperience of the average undergrad."

        THAT Sr. is an expensive proposition.
      • Re:But... (Score:4, Funny)

        by Anonymous Coward on Friday April 03, 2009 @12:22AM (#27440927)

        That's nothing, you could probably get some hobos to do the work for free and save some money by having them eat the hazardous biological waste rather than disposing of it.

        • Re: (Score:3, Interesting)

          by Bowling Moses (591924)
          That's not all that funny. I know someone who went on sabbatical to a Chinese university a couple years ago. They're building brand new high-tech bioscience labs but not the necessary infrastructure to support them properly. There were no facilities at that particular university, one of the top ten in China, for handling hazardous waste. Hazardous liquids are just poured down the drain, nothing for disposal was autoclaved. He saw a peasant (his term) poking through the trash and yes, eat the agar out of
      • ....and said undergrad becomes extremely disillusioned with the current state of affairs in scientific research, and decides to go into a different field instead.

        Tenured faculty do extremely little original research of their own, but are often paid 5 times in excess of what the graduate students are making.

        Where's the justice in THAT?

    • Re:But... (Score:5, Funny)

      by Profane MuthaFucka (574406) <busheatskok@gmail.com> on Friday April 03, 2009 @12:23AM (#27440931) Homepage Journal

      Yes, but there are no ethical rules against watching your two lab robots fuck each other.

    • Re:But... (Score:5, Informative)

      by fuzzyfuzzyfungus (1223518) on Friday April 03, 2009 @12:29AM (#27440963) Journal
      In terms of R&D, certainly, the status quo is cheaper. In terms of actually doing the work, though, I wouldn't be so sure. Much of science involves quite repetitive manipulation of samples, numerous instances of the same thing, tweaked variants in parallel, or both. Huge amounts of labor that is reasonably easy to characterize; but needs to be done precisely and without error.

      The case of electronics assembly is arguably analogous. Humans are cheap; but (quite expensive) pick and place machines are ubiquitous. Why? Because they are faster, more precise, and more consistent than humans.

      It is already starting. This piece [wired.com] describes a massive robot setup for processing brain samples(cue: whatcouldpossiblygowrong). In high volume gene sequencing, automated equipment is common enough to essentially be a stock photo cliche by now.
    • by RyoShin (610051)

      Grad students often move on or will eventually die. Sure, they're replaced, but each replacement has to start fresh. With something like Adam, it can continually go back to previous results and not miss a single detail. Future upgrades could give it better analysis methods so it can do better hypotheses, but still retain all previous data.

      Honestly, I'm not aware of the full scope, but for something like this $1MM seems like a bargain.

    • by znu (31198)

      It cost $1M to develop. It would probably be a lot cheaper if produced in thousand-lot quantities. Plus, it performs 1000 trials a day, keeping track of the results flawlessly; you'd need a lot of grad students to keep up with a facility with a few dozen of these. Or a few hundred. Or a few thousand.

      This sort of thing is going to be a very big deal over the coming decades. There is a very good chance that more than one person reading this post will have their life saved at some point by a cure that results

  • A bit of a stretch (Score:5, Insightful)

    by derGoldstein (1494129) on Friday April 03, 2009 @12:12AM (#27440859) Homepage
    '[Current robots] tend to do one thing or a sequence of things. The complexity of Adam is that it has cycles.'

    I think this is called "flow control". This was invented before electricity. It was around before the term "science" existed.

    So this is the first time it's applied to *this specific* operation. It's been around in robotics ever since there were "robots".

    Here's a good example [wikipedia.org].
  • Eh hehh... (Score:4, Insightful)

    by djupedal (584558) on Friday April 03, 2009 @12:16AM (#27440885)

    "...the software that drives Adam's thought process sits on three computers, allowing Adam to investigate a thousand experiments a day and still keep track of all the results better than humans can."

    There is no 'thought process'. 1's & 0's...that's it. Anthropomorphising the over priced little key-puncher isn't fooling anyone.

    Give me $1 mil and I'll put a scare into Adam that he won't soon forget. I can read 3k WPM as well as raw postscript, palms, tarot cards and bar codes with the naked eye. I can intuit nearly 30 spoken languages on body english alone and smell phony money at the bottom of a sweaty pocket. I don't need no stink'n badges and I know when to cross to the other side of the street. Adam might get better press, but until it can order at a drive thru and sort used car parts based on cross-over and eBay thru-put, I'm comfortable sleeping in.

    • by Bragador (1036480)
      Your neurons are also working in 1's & 0's. The difference is that our brain can reorganize itself while a computer chip can't adapt its circuits.
  • Personal (Score:4, Interesting)

    by mapkinase (958129) on Friday April 03, 2009 @12:21AM (#27440913) Homepage Journal

    I knew that Ross was up to something bigger than protein secondary structure prediction when I met him 15 years ago at ICRF. He was a great Prolog fan then. Now he has probably bunch of graduate students coding for him.

  • by Mr_Icon (124425) on Friday April 03, 2009 @12:25AM (#27440941) Homepage

    The complexity of Adam is that it has cycles.

    No, no, no -- the complexity of *Eve* is that it has cycles.

  • Next thing you know, the robot will abduct a pretty female lab assistant to experiment on. [imdb.com]

  • by Eil (82413) on Friday April 03, 2009 @12:44AM (#27441021) Homepage Journal

    Well, we're boned.

  • Are we ..? (Score:2, Insightful)

    by louzer (1006689)
    I get a feeling we are already generating & testing hypothesises for someone/something bigger than us like in Asimov's The Last Answer.
  • by moderatorrater (1095745) on Friday April 03, 2009 @01:06AM (#27441157)
    Isn't the first requirement for a singularity be that it's able to improve itself, thus leading to an accelerating growth that ends in the subjugation of humanity? If so, wouldn't it be prudent to withhold knowledge of the scientific method as long as possible?
    • Re: (Score:3, Interesting)

      by Kjella (173770)

      Isn't the first requirement for a singularity be that it's able to improve itself, thus leading to an accelerating growth that ends in the subjugation of humanity?

      We've had that for years with simple statistics keeping, neural networks, evolutionary algorithms and other ways of limited learning. You can have a learning chess computer that'll run circles around me yet it's completely harmless because it's not self-aware - it does not understand what it means to be turned off.

      I'd be much more fascinated by a robot that given access to its own schematics etc. was to implement its own survivability routine like avoiding excess heat, cold, pressure, electrical jolts, wate

      • Re: (Score:3, Insightful)

        by Chris Burke (6130)

        I'd be much more fascinated by a robot that given access to its own schematics etc. was to implement its own survivability routine like avoiding excess heat, cold, pressure, electrical jolts, water damage, corrosion, metal fatigue and so on and found pressing the "off" button as one of the identified threats to its survival. Not self-awareness in a human sense but enough logic to recognize the puppeteer.

        I would like to think that the robot would be rational about it and realize that "Off" was an orderly shu

    • by feepness (543479)
      Sure, make it angry.
    • by dodobh (65811)

      Just remember to build morality into the AI. Culture Minds FTW.

      • Re: (Score:2, Funny)

        by Anonymous Coward

        Why? So it can feel bad after it's killed us all?

        • by MadKeithV (102058)
          No, so that it can smugly continue to claim that it was all about "freedom" and "principles" and "doing the right thing" after it has killed us all.
    • by sorak (246725)

      Isn't the first requirement for a singularity be that it's able to improve itself, thus leading to an accelerating growth that ends in the subjugation of humanity? If so, wouldn't it be prudent to withhold knowledge of the scientific method as long as possible?

      No. If a machine is going to run the world, then we don't want it to be a creationist.

  • by f2x (1168695) <flush2x AT gmail DOT com> on Friday April 03, 2009 @01:09AM (#27441189) Homepage
    This probably isn't the most helpful commentary, but it's a slight rant on semantics.

    I used to work with Motoman K6's a few years back. Using these robots, we performed plasma cutting, arc welding, material handling, etc... Just looking at the K6, you knew it was a robot. Watching a robot work in a cell after you've trained it to do it's job is a very rewarding experience. Of course we also had other machines that were also very complex in their tasks, but we didn't consider them robots. CNC mills and lathes, pipe benders, other machines that ran autonomously that also had to be programmed and synchronized with the flow of production. Sometimes the line resembled a kind of demented Rube Goldberg contraption, but we were somewhat strict to define only the articulated manipulators themselves as robots.

    So when I saw this pile of servos in a glass cleanroom set to the over-dramatic theme of "Bonanza Reloaded", I thought, "Yeah, that's nice, but... It just doesn't strike me as a 'robot' so much as it does an automated bio lab."

    And yes, I realize there were clearly robots within the cell, but calling the unit as a whole a "robot" just irks me a little.

    Of course in the spirit of all the other bad jokes I've seen posted, do you think this "robot" will use it's genetic findings with the yeast cells to perfect the most delicious and moist cake recipe ever?
  • by camperdave (969942) on Friday April 03, 2009 @01:38AM (#27441319) Journal
    This reminds me of the Automated Mathematician (AM) program I read about in an AI course (or was it an old Byte magazine?). This program was programmed with a bunch of axioms, and basic strategies. It looked for "interesting things", like what happens when you apply identical arguments to a two argument function. As I recall, it discovered for itself the concept of prime numbers. It applied what it learned and came up with the theorem that all angles can be expressed as the sum of two prime angles (or something like that).

    This seems to be doing the same thing: mixing and matching patterns, looking for interesting coincidences, and then testing for them. The only difference is that this is doing it with real world biological samples, and not abstract mathematical constructs.
    • by foobsr (693224)
      This reminds me of the Automated Mathematician (AM) program

      Me too, and there still is an earlier ancestor, namely the Logic Theorist [wikipedia.org] (1955). Looking at how far AI has come since then, I meanwhile wonder if basically logic based pattern matching will cut it.

      And yes, this thing is not a robot at all (which/who(?), IMHO, should have a considerable repository of 'senses' to get a grasp of what is going on in the real world (an interesting observation is that this repository gradually gets lost from humans
  • Yeah, cute. I'd be more impressed if there was a link to the code that showed how it worked. The Scientific American article was particularly disappointing. I remember when SA gave you enough information to learn something.

  • The end of science (Score:4, Insightful)

    by eskayp (597995) on Friday April 03, 2009 @01:58AM (#27441433)

    This is terrible.
    No experimenter bias to worry about.
    Programmable for effective randomization.
    Truly double blind capable.
    Can counteract the Placebo effect.
    No ego to bruise.
    It's the end of science as we know it.

    • by foobsr (693224)
      No experimenter bias to worry about.
      No built in heuristics which where thought up by the developer who was totally isolated from social influences (probably some kind of condition along the autistic spectrum).

      Programmable for effective randomization.
      Perfectly 'well-definedness' of "effective"; amen.

      Truly double blind capable.
      Yes, one hand not knowing what the other is doing.

      Can counteract the Placebo effect.
      Is free to ignore hard to explain observations.

      No ego to bruise.
      A frozen, muted
  • Lysine? (Score:5, Funny)

    by Anenome (1250374) on Friday April 03, 2009 @02:06AM (#27441473)

    So, our future AI overlords begin their research with the Lysine Contingency? Should we be worried?

    • Re: (Score:3, Funny)

      by juhaz (110830)

      So, our future AI overlords begin their research with the Lysine Contingency? Should we be worried?

      Of course we should. Next thing you know, they'll be cloning dinosaur shock troops.

  • damn! i got this phd for nothing now! D:
  • So the robot accomplished 1 experiment by how?

    allowing Adam to investigate a thousand experiments a day and still keep track of all the results better than humans can.

    Throwing darts... and eventually hitting something.

    Woop woop!

  • by Henkc (991475) on Friday April 03, 2009 @02:29AM (#27441565)
    Academics have been poking away on software AI for decades (also ANN [wikipedia.org]) - I can't help feeling that this is a dead-end in the same way that cold fusion is, even though it's intellectually (hacking) fascinating.

    What's far more fascinating and promising is the development of hardware neural nets [physorg.com]. To put it into perspective:

    Since the neurons are so small, the system runs 100,000 times faster than the biological equivalent and 10 million times faster than a software simulation. "We can simulate a day in one second," Meier notes.

    10 million times faster than software? That's like jumping from an abacus to a Pentium.

    I just hope these folks continue to receive the funding they need.

    • by foobsr (693224)
      We can simulate a day in one second

      The question here (which from time to time plagues me since decades) is whether, given these conditions, a day is still a day? IMHO, hard to decide.

      CC.
  • by Ed Avis (5917)
    The BBC news article [bbc.co.uk] about this breaks new ground by including not one, but two car-based analogies, both of which fail to reach the (admittedly high) benchmark of bad analogies set here on Slashdot.

    The robot was able to work out the role of the genes by observing yeast cells as they grew. It used existing information about the function of known genes to make predictions about the role an unknown gene might play in the cell's growth. It then tested this by looking at a strain of yeast from which that gene

  • From the Science article: "In the future, he says, scientists, in order to carry out their work, might have to learn how to program computers and express knowledge about the world the way people in artificial intelligence have done."

    Huh? Weird. Scientists might have to learn how to program computers? Who would have expected it?

  • If it can't publish it will never get tenure, will be fired, and then hired by Rumsfield who is still looking for WMD.

  • Long term if it does take off I can see industry going for it big time. It would mean the possibility of having less skilled staff (ie smaller wage outgoing) to come up with new ideas. I feel its no coincidence they throw the C.elegans genome at it to see what sticks, rather than problems from the world of physics.

What this country needs is a good five cent microcomputer.

Working...