Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 



Forgot your password?
typodupeerror
×
Medicine Microsoft Biotech Communications Operating Systems Programming Software Windows News Science Technology

Microsoft Will 'Solve' Cancer Within The Next 10 Years By Treating It Like A Computer Virus, Says Company (independent.co.uk) 259

Microsoft is serious about finding a cure for cancer. In June, Microsoft researchers published a paper that shows how analyzing online activities can provide clues as to a person's chances of having cancer. They were able to identify internet users who had pancreatic cancer even before they'd been diagnosed, all from analyzing web query logs. Several months later, researchers on behalf of the company now say they will "solve" cancer within the next 10 years by treating it like a computer virus that invades and corrupts the body's cells. The goal is to monitor the bad cells and potentially reprogram them to be healthy again. The Independent reports: The company has built a "biological computation" unit that says its ultimate aim is to make cells into living computers. As such, they could be programmed and reprogrammed to treat any diseases, such as cancer. In the nearer term, the unit is using advanced computing research to try and set computers to work learning about drugs and diseases and suggesting new treatments to help cancer patients. The team hopes to be able to use machine learning technologies -- computers that can think and learn like humans -- to read through the huge amounts of cancer research and come to understand the disease and the drugs that treat it. At the moment, so much cancer research is published that it is impossible for any doctor to read it all. But since computers can read and understand so much more quickly, the systems will be able to read through all of the research and then put that to work on specific people's situations. It does that by bringing together biology, math and computing. Microsoft says the solution could be with us within the next five or ten years.
This discussion has been archived. No new comments can be posted.

Microsoft Will 'Solve' Cancer Within The Next 10 Years By Treating It Like A Computer Virus, Says Company

Comments Filter:
  • by ewhac ( 5844 ) on Tuesday September 20, 2016 @07:09PM (#52927895) Homepage Journal
    If there's one thing Microsoft has comprehensively and irrefutably established over the last 35 years of their existence, it's that they haven't the faintest clue how to identify or eradicate viruses.
    • Actually it's quite the opposite. Once identified, Windows is effectively immune to the same virus once patched. Sure you will still likely get other viruses, but that is not analogous to "solving" cancer (ie one type of virus like thing - whatever that actually means).
      • Windows is immune from the virus once it is patched, then the patch is patched. They fix the problems caused by the patch to the patch. Then finally actually fix the real original problem.

        It amazes me how many times the patch to fix the problem, doesn't fix the problem.
    • MS may have chance then, cancer is not caused by a virus.
      • should have said *usually* not caused by a virus (80%)
      • by saider ( 177166 )

        We'll probably see medical jargon appearing in our software now.

        "Windows has detected a malignant usb program. The prognosis is that you have a 85% chance that your personal data will be on a Russian server in 10 minutes. Immediate curative treatment in the form of Knowledge Base #A345-BB321 is required. Press Yes to accept the DNR and proceed with the treatment."

        Note that there will be no "Cancel" option.

      • Quite a few cancers are caused by virusses. See HPV for an example.

        It's possible the number is much larger -we're only just getting the ability to really study this stuff.

      • Comment removed based on user account deletion
    • Re: (Score:3, Insightful)

      by dargaud ( 518470 )

      Yeah, I read that title first thing in the morning and I very nearly spit orange juice all over the laptop.

      Seriously though, cancer is a very ancient disease. It comes from when the very first lonely cells decided to band together to increase survival, over 3 billion years ago. They figured out pretty quickly that group rules were necessary, like some cells go some places, others need to suicide at the right time, etc... And when a cell doesn't obey those ground rules and starts reproducing on its own, th

      • by Bongo ( 13261 )

        Hey I'm no oncologist but you make it sound like magic. Eradicate is the wrong word, as in , "destroy completely". What we have is an epidemic of cancer, and if we can figure out why that is, in the complex biochemistry, we'll go a long way to stopping that epidemic. As for why Microsoft would be any better at this than anyone else is beyond me. The answer may already be known, just unrecognised. Anyone read, "Tripping Over the Truth" by Christofferson ?

        • by silentcoder ( 1241496 ) on Wednesday September 21, 2016 @07:41AM (#52930337)

          > What we have is an epidemic of cancer

          Nope. We really don't. The increase in cancer cases over time tracks *exactly* the increases in human lifespan. We've always been equally prone to it (barring isolated and regionally limited edge-cases) - but until quite recently almost everybody got killed by something else first.
          Now that we survive most virusses, bacteria and parasites and have basically eradicated just about all our natural predators (with the exception of the mosquito) - we actually live long enough for cancer to happen, and the more people live long - the more get it.

          That said - cancer is not a disease and does not have a cause. Cancer is a collective noun for a whole host of diseases all with different causes, which just happen to have one, single tiny thing in common. The reason we haven't cured cancer is because nothing could possibly do that - no single treatment can deal with so many different diseases, all with different causes (many of which are unknown). Even the shotgun treatments of radiation and chemo are not useful on all of them.
          On the other hand we are making massive progress in curing and preventing specific cancers. In the last few years, for the first time in history, we actually developed a vaccine that can completely prevent several cancers (HPV vaccines grant effective immunity against cervical cancer and several types of throat and lip cancers). The reason is that we discovered that a specific virus causes these cancers - and could create a vaccine against that virus.

          Gene-targetted treatments are already greatly increasing life expectancy, survival rates and quality of life of many cancer patients - with far less negative side effects than the shotgun treatments. More experimental treatments using things like magnetofluids are being investigated which may offer new and uniquely safe types of surgical treatments which are viable on a much larger set of cancers.
          We are making progress - but this is a war against a massive army with a huge variety of different batallayons and there is no one attack to defeat it, not single battle will win this war. Lots of small victories that add up - that's the way to do it, and it won't happen quickly, but it is already happening much quicker than we could have hoped even a decade ago.

      • Well, they are probably just using the wrong words that everyone else uses ever since the 1970s when the "war on cancer" was started.

        Curing cancer is probably impossible, because as you say, you would need to monitor the activity of billions of cells to make sure each one is doing what it's supposed to.

        Making cancer a chronic condition that can be stabilized without the massive side effects of current treatments (chemo, radiation, surgery) would be a massive gain. Instead of feeling like shit for months wh

      • Not to mention there is a reason why evolution has not given us any defenses against it. It's part of the very structures evolution use in the first place, and furthermore it very rarely affects reproduction. Even things like testicular cancer usually happens late enough in life that you could have had kids already. Since so few cancers actually prevent you from first having kids - not only do genes with a propensity for cancer not get eradicated but there is also no evolutionary pressure be better at survi

    • Most users agree that Windows10 should be treated like a virus, so if M$ could rid the world of that one it would be a great service to humanity.

    • Microsoft as a company has gotten quite good at defending an imperfect host from a relentless barrage of clever bad stuff. If any tech company is well suited to finding a cure for Cancer, its Microsoft. The human body is the human body. You can't redesign it to make it cancer proof, much like Microsoft couldn't start over with Windows. Cancer is myriad and ever changing, much like the viruses, trojans, etc that are created to exploit Microsoft's products.
    • by v1 ( 525388 )

      Well I don't think it's fair to say they haven't been trying at all, but they didn't put nearly enough effort into it from the start. (their OS was originally marketed to businesses, and they operated for a long time under the assumption that somehow this made the network totally trustworthy) Unix came from an academic setting, and there you are full of geeky, talented, bored students looking for a challenge or a vent, and that makes your network more hostile than the internet of today.

      So they evolved in a

  • by ptaff ( 165113 ) on Tuesday September 20, 2016 @07:09PM (#52927899) Homepage

    The team hopes to be able to use machine learning technologies -- computers that can think and learn like humans

    If your definition of a human is a retarded 4-year-old that can be trained to name colors with 75% accuracy, yes.

    We're not there, we're not even close; "machine learning" is just the new buzzword in town, rising from the ashes of "big data".

    • The team hopes to be able to use machine learning technologies -- computers that can think and learn like humans

      If your definition of a human is a retarded 4-year-old that can be trained to name colors with 75% accuracy, yes.

      We're not there, we're not even close; "machine learning" is just the new buzzword in town, rising from the ashes of "big data".

      Big data itself was a phoenix from the ashes of AI.

    • Machine learning has been a thing much longer than big data. Don't believe me? Look at the age of the major ML journals. You'll see they predate big data by a while.

  • by pesho ( 843750 ) on Tuesday September 20, 2016 @07:17PM (#52927945)
    ... machine learning is the solution. And cancer is not "like a computer virus that invades and corrupts the body's cells". That is how an actual virus works, hence the analogy by which the "computer virus" term came to be. Cancer is more like when a bit randomly flips in RAM and then by pure coincidence this causes a memory leak within an infinite loop that spreads shit all over the place until everything comes crashing down.
    • by ewhac ( 5844 )

      Cancer is more like when a bit randomly flips in RAM and then by pure coincidence this causes a memory leak within an infinite loop that spreads shit all over the place until everything comes crashing down.

      So, Windows, then...

      • by pesho ( 843750 )
        You mean to say that Microsoft has had cancer solved for years? Why didn't hey tell us? That's cruel.
    • by wierd_w ( 1375923 ) on Tuesday September 20, 2016 @07:25PM (#52928017)

      personally, i would say cancer is much more like wallstreet fatcats.

      a mutation in the rules governing proper behavior causes them to consume all available resources, send ssignals to the regulatory system that they are essential and need protection, while earnestly believing they are the most important part of the system while destroying it from the inside, due to the removal of a system to terminate that behavior early.

      • by j-beda ( 85386 )

        personally, i would say cancer is much more like wallstreet fatcats.

        a mutation in the rules governing proper behavior causes them to consume all available resources, send ssignals to the regulatory system that they are essential and need protection, while earnestly believing they are the most important part of the system while destroying it from the inside, due to the removal of a system to terminate that behavior early.

        Hey, that's pretty good. I'll have to remember that.

    • by ColdWetDog ( 752185 ) on Tuesday September 20, 2016 @07:30PM (#52928045) Homepage

      NoNoNoNo. The underlying assumption that computers and humans are fundamentally similar is completely incorrect. The term 'computer virus' is a reasonable analogy but you can't push it so far that you impute that the mechanisms are the same. Cancer is way more complex that 'reprogramming a cell'. It involves cell homeostasis mechanisms that have no analogous function in hardware or software.

      "It’s not just an analogy, it’s a deep mathematical insight. Biology and computing are disciplines which seem like chalk and cheese but which have very deep connections on the most fundamental level.”

      (FTFA) Oh yeah. Prove it. Or even give us something other than executive level bullshit.

      Perhaps when you have computers that can handle errors more gracefully than "PC LOAD LETTER" I might think about taking him seriously. But we've barely moved past that level at present.

      • NoNoNoNo. The underlying assumption that computers and humans are fundamentally similar is completely incorrect. The term 'computer virus' is a reasonable analogy but you can't push it so far that you impute that the mechanisms are the same. Cancer is way more complex that 'reprogramming a cell'. It involves cell homeostasis mechanisms that have no analogous function in hardware or software.

        I agree with your statement here wholeheartedly, which is why I'm struggling to understand how the fuck Microsoft could even make this statement with a straight face, much less offer any evidence to back it up:

        "They were able to identify internet users who had pancreatic cancer even before they'd been diagnosed, all from analyzing web query logs."

        I mean seriously, they can't even protect or prevent a computer running Windows from getting infected, so I fail to see how we should give them any credibility w

      • In the same deeply unhelpful sense that you can argue that all areas of science are in principle reducible to physics there might be such deep connections. It's just that they will probably end up being about as useful. There's a whole genre of nerd-mysticism to be found in areas where claims of fundamental unity can be plausibly advanced; but cannot be made to yield anything of interest or utility. Mystics love transcendent unity that dissolves all mundane apparent complexity; and going a little overboard
  • by fuzzyfuzzyfungus ( 1223518 ) on Tuesday September 20, 2016 @07:19PM (#52927957) Journal
    What could possibly go wrong? After all, it's proven totally trivial to eradicate bugs in software(that's why nobody uses systems that haven't been formally verified; it's such an easy step that you'd be crazy to skip it!); so it should be easy enough to extend our victories in that field to vastly more complex biological systems that lack many of the convenient mathematical properties built into the abstractions we use for computing.

    Seriously guys; I'm glad you care about curing cancer and all; but what flavor of insanity drives this level of optimism about your chances?
  • Oblig xkcd. (Score:4, Informative)

    by sims 2 ( 994794 ) on Tuesday September 20, 2016 @07:24PM (#52928009)

    Researcher Translation.
    https://xkcd.com/678/ [xkcd.com]

  • Bill Gates and SPAM (Score:5, Informative)

    by Anonymous Coward on Tuesday September 20, 2016 @07:28PM (#52928037)

    In 2004 Bill claimed SPAM would be eradicated in 2 years. http://www.informationweek.com/spam-will-be-solved-in-2-years--gates/d/d-id/1022817?

    That went very well....

    • Re: (Score:2, Insightful)

      by Anonymous Coward

      He was right. It was effectively eradicated, at least as far as users were concerned, by 2006. Though the credit for that goes to Google, not Microsoft.

  • Solved like they solved computer viruses? So then, we'll have a few incidents where almost every possible target in the world is infected within a 10 minute window such that they'll need to be scratched. Then shortly after all newborns will have to be outfitted with 3rd party counter measures within 10 minutes of birth?
  • by Bruce Perens ( 3872 ) <bruce@perens.com> on Tuesday September 20, 2016 @07:37PM (#52928071) Homepage Journal

    If we can solve the problem of cancer within 10 years by treating it as a computer virus, why not treat gravity as a computer virus and come up with practical, cheap antigravity? Or that pesky light-speed limit, we need to beat that, and 10 years sounds about right

  • ... is to force any cell divisions that occur in the organism in question to *always* perform a 100% identical copy, with no error.... ever.

    I imagine that this might be theoretically possible, but I don't expect that our sun will still be burning if or when it is achieved.

    • I don't see how you can "force" cells in an organism to perform 100% identical copies, unless you genetically alter its DNA and put in place a new and better cell division mechanism. Which seems pretty far-fetched, in the same ballpark as creating Dyson spheres and Ringworlds.

      You could probably treat cancer with a 100% success rate when they occur (which isn't quite the same as eliminating it, but close enough) with millions of advanced nanobots that swim around in your body and kill (or render impotent) ca

      • Just specially tailor some cytoplasmic parasites to need cancer cells as hosts. Do to cancer what wolbachia does to insect cells.

        • There probably isn't enough uniqueness about cancer lines for that... if cancer were easy to differentiate from regular cells your own T cells would be sufficient to self-cure cancer already.
    • by mysidia ( 191772 )

      I imagine that this might be theoretically possible, but I don't expect that our sun will still be burning if or when it is achieved.

      What if we replaced every single cell in your body one by one with a synthetic one controlled by nanomachines designed to execute every cellular process the same way that a biological cell would, however, the nanomachines controlling the cell would have a software program, instead of being controlled by the DNA, and during cell division, the clone would be a Digital cop

    • No-one said "eliminate", they said "solve. I'm not even sure what that means in this context, but if if means new methods for easier early diagnosis that saves lots of lives or extends quality of life then maybe we should not be so cynical.
      eg AIDS could be called "solved" since you can now live a long and relatively normal life while infected.
    • The DNA damage that leads to cancer doesn't exclusively happen during copying. Sometimes free radicals just damage your DNA, or radiation does, or just heat, or other chemical action. You not only have to copy 100% correct but correctly repair errors 100% of the time.

      In order to fix both issues to extremely high probability, we'd need to have SIX strands of DNA. In case of damage to one, the repair happens according to the majority opinion of the correct sequence. If there's no majority opinion, (all th

    • by ooloorie ( 4394035 ) on Tuesday September 20, 2016 @11:15PM (#52928955)

      ... is to force any cell divisions that occur in the organism in question to *always* perform a 100% identical copy, with no error.... ever.

      Not at all. Cancerous and pre-cancerous cells arise in the body all the time. It's the body's ability to eliminate such cells that protects you from cancer, but sometimes those mechanisms fail.

  • ...the "blue screen of death" will have a whole new meaning.
  • False positives are a major problem with computer antivirus

    At least when the computer AV goes haywire, though, and renders the machine unbootable, you can always restore from backup and start over again.

    You can't exactly do that with a human, if the antivirus accidentally kills off important parts of a vital system such as the brain.

    Also..... it sounds like snakeoil. The human immune system is a highly-advanced highly-intelligent defense system with memory that learns much like the human mind does, and

    • And it's surprisingly simple. And they need it, because they have so many more cells than people do they would have a high risk of cancer without some sort of defense.

      http://www.nature.com/news/how... [nature.com]

      To summarize the contents of the link, elephants just have 20 copies of the p53 gene. To incite cancer, all the copies would have to be disabled, via the most common cancer generating mutation mechanism.

      If you want to engineer people to be cancer resistant, it might be as simple as introducing more copies of the p53 gene into our genome.

      • And it's surprisingly simple. And they need it, because they have so many more cells than people do they would have a high risk of cancer without some sort of defense.

        http://www.nature.com/news/how... [nature.com]

        To summarize the contents of the link, elephants just have 20 copies of the p53 gene. To incite cancer, all the copies would have to be disabled, via the most common cancer generating mutation mechanism.

        If you want to engineer people to be cancer resistant, it might be as simple as introducing more copies of the p53 gene into our genome.

        the p16 and p27 genes of the naked mole rat perform a similar function and we human have just the p16 and a crappier version too.

  • There's a longstanding history of that kind of thing. Marketers having been data mining to detect when women are pregnant for years now and their methods are creepily accurate.

    The thing is, though, that pregnancy is one thing. Pancreatic cancer is one thing. Cancer *in general* is more like a mixed bag of similar phenomena. We've pretty much converted many individual types of cancers that were a death sentence twenty years ago into curable illnesses. But others remain intractable. So saying "curing cancer" is a bit like saying "curing infection". Curing *the whole category* will require a truly fundamental progress in biology.

    In fact it may require multidisciplinary breakthroughs. There's lots of things that kill tumor cells, but don't work on tumors.

    • by Nemyst ( 1383049 )

      Curing *the whole category* will require a truly fundamental progress in biology.

      Why, though? At this point it seems just as likely that we'll find a miracle cure to cure all cancers as it is that we'll just figure out treatments for every kind one by one.

  • ... its ultimate aim is to make cells into living computers.

    Adding a new edition to the Windows line up: Enterprise, Professional, Home, Body

    (Notice: Do not engage in activities, like driving, while the mandatory updates are being applied as there have been reports of CPU utilization rates of 100% for extended periods of time. We expect this issue to be resolved in a future update.)

  • that sends a signal if there's cancer?
  • "Machine learning" is apparently the new nanotech.

  • by eyepeepackets ( 33477 ) on Tuesday September 20, 2016 @09:12PM (#52928537)

    Such hubris from a corporation that can't even get its flagship OS to keep time properly: Windows 10 will have a time-related brainfart if not connected to the internet when it tries to update system time and change the system time to some arbitrary time in the immediate past, usually several hours at a minimum. Such crap.

  • Ambient Authority is the root cause of most of the woes of modern computing. Your OS of choice doesn't know how to even ask "which files should this program have access to, for this instance", and just gives programs free run to do as they please... until this is fixed, we're going to have virii.

    Cancer on the other hand is a situation where a cell already has resources it's supposed to have, but doesn't get rate limited in the use of them, allow it to grow, divide, and multiply.

    Two fundamentally different p

    • First fundamental problem: It's viruses. In English at least. In Latin, it would not be viri either because virus is neuter and only masculine nouns on -us become -i in the second declination. Virus is of the third declination (neuter). Another example is opus. It becomes opera. Not opi. Opi may put you to sleep similar to many Opera, but it is still something different.

      The Latin plural of virus is vira, by the way. Viri would be the genitive singular. Virii is ... probably a problem with your keyboard, I d

  • ... to an entirely new level.

  • "Two years from now, spam will be solved," -- Bill Gates, 2004 http://www.informationweek.com... [informationweek.com]?
  • In other words, ignore it long enough 'til some other companies come along to do it for them, then buy one randomly?

  • by Greyfox ( 87712 )
    There's going to be a lot more cancer, then? I guess if everyone dies of cancer, that could technically be considered a "solution"...
  • What, they will set up a profitable business model around it making sure it is never extinguished so that they can sell subscriptions forever, and ocassionally coming up with a new strain of cancer when business gets slow? I can totally see Microsoft doing just that...
  • All my lifetime there have been news every few years about how this company or that is just about to find a cure for cancer and then nothing ever happens. I can assure you that the cure for cancer will not be found in the next 100 years. Of course there will be advances in how cancer is treated but a full blown cure is not going to happen.

  • by jandersen ( 462034 ) on Wednesday September 21, 2016 @04:55AM (#52929757)

    The language is deliberately vague, because of course this is mostly a marketing stunt for Microsoft; after all, what does 'solve cancer' mean? But to be fair, we are in fact beginning to understand many of the factors that make up several cancer diseases, and sometimes it is beneficial to focus on a far away goal, even if it isn't entirely realistic in the timeframe.

    Cancer, I think, will always be with us - in a snes it always IS; some would say that all of us have cancer, all the time, because there is always a certain proportion of new cells that have genetic faults, and some of them have the potential to become cancerous - what saves us is a good immune system. It makes intuitive sense, I think, because as we get older, our immune system becomes less efficient, and then we are less likely to stop all cancer cells, which explains why cancer is much more common in older people.

    There is, however, reasons to hope that we can at some point find a single or a few common traits that unite all types of cancer and make them curable; I have certainly seen articles that hint at something that could give us that. But in 10 years? I don't know.

  • I see tonnes of scepticism above (which is healthy and fine) and tonnes of sarcasm (which is fine, too). But you know what? I hope they succeed. Good luck to them. We need a cure for cancer, other than cutting it out if it's found early enough.

    The difference between Microsoft and many other places trying to cure cancer is Microsoft actually have money. I doubt this will work but why not hope it does?
  • Comment removed based on user account deletion
  • ...turns out they are ;-} (reminiscent of the Gates icon /. used to have): 'The company has built a "biological computation" unit that says its ultimate aim is to make cells into living computers. As such, they could be programmed and reprogrammed to treat any diseases'
  • Death certificate reads: STOP: 0xDEADBEEF00000000 (ATGCCGCGAATrojan-IM.....)

So you think that money is the root of all evil. Have you ever asked what is the root of money? -- Ayn Rand

Working...