Slashdot Mirror


Researchers Use Google's Search Algorithms To Fight Cancer

MatthewVD writes "German scientists have modified Google's PageRank algorithm to scan tumors and learn more about how cancers progress. PageRank orders results based on how other web pages are connected to them via hyperlinks; the modified algorithm, NetRank, scans how genes and proteins in a cell are similarly connected through a network of interactions with their neighbors. This approach could also yield new therapies to help combat tumors."

52 comments

  1. Oh Geez by StylishGuy · · Score: 0

    This is nothing more than some twisting to make it "nerdy" article. The original pagerank algorithm is just about relations between different pages. Gee, how did not anyone think about there being relation between different body parts when cancer spreads??

    1. Re:Oh Geez by Theophany · · Score: 5, Funny

      Your tumor's linked to you thyroid, your thyroid's linked to your larynx, Google's gonna steal all your data...

      Serious question: will their be an AdSense-style scheme for recurring cancer-sufferers to accrue referral income?

    2. Re:Oh Geez by Jakeula · · Score: 0

      I assume the news is more about the fact that researchers are actually using a modified Google algorithm. It doesn't say anywhere that it's a new idea to look at how your body is connected to combat disease. All this information can be found simply from the title, and the Google icon next to it. I could be wrong however, and maybe this entire article went over my head.

    3. Re:Oh Geez by martin-boundary · · Score: 2, Insightful

      It's not a "google" algorithm. Google's contribution to science isn't the ranking algorithm, it's the _scale_ of application on the order of billions of nodes. People have been doing calculations using "PageRank" for about a century before Google was founded (by hand obviously).

    4. Re:Oh Geez by Kergan · · Score: 2

      Gee, how did not anyone think about there being relation between different body parts when cancer spreads??

      Well yeah, that's how science research works. The bloody obvious must be consensually established before it gets considered a valid work hypothesis or argument. And once a consensus takes hold on the wrong conclusion, it takes an impressive amount of contrarian data to shift opinions.

      http://en.wikipedia.org/wiki/Falsifiable#Kuhn_and_Lakatos

    5. Re:Oh Geez by Anonymous Coward · · Score: 2, Interesting

      It has nothing to do with anatomical connection between body parts. That's a naive assumption. People have known that cancer spreads from the original tumor to a metastatic site via blood and lymph vessels for a long time. The article is about identifying correlations between changes in expression of genes and proteins, and how these are linked to cancer progression and metastasis. Believe it or not, but every cell in your body is a machine with millions, if not billions, of working parts. One small change in one gene can have dramatic consequences on a number of molecular signaling pathways. Biological, and specifically cancer biological, research has long been focused on deciphering these molecular pathways and identifying the connections between them. So there's already a wealth of data, the key is making sense of it, generating hypotheses, and then testing the hypotheses. So, any additional tools in the arsenal are more than welcome.

      Granted, I have no clue if the new application of Google's algorithm is useful or just something flashy to get a publication. But to dismiss the idea behind it as trivial is misguided.

    6. Re:Oh Geez by s_p_oneil · · Score: 1

      Google can steal all my cancer. I wouldn't mind one bit. I wouldn't even mind the ads, in that case. ;-)

    7. Re:Oh Geez by goombah99 · · Score: 1

      This is nothing more than some twisting to make it "nerdy" article. The original pagerank algorithm is just about relations between different pages. Gee, how did not anyone think about there being relation between different body parts when cancer spreads??

      Amen. This is EXACLTY how every does it, and always has. Where do you think google got it's idea from?

      --
      Some drink at the fountain of knowledge. Others just gargle.
    8. Re:Oh Geez by Anonymous Coward · · Score: 0

      Go back to bed, bonch.

    9. Re:Oh Geez by evilRhino · · Score: 1

      There are a few extra layers of abstraction here. They are analyzing genes, which express themselves on a cellular level, which aggregate to form body parts.

    10. Re:Oh Geez by mcgrew · · Score: 1

      This is nothing more than some twisting to make it "nerdy" article.

      You don't consider biochemists to be nerds? Not geeky maybe but definitely nerdy.

  2. Markov? by Anonymous Coward · · Score: 1

    This is just another markov model, just like PageRank. Move along people, nothing to see here.

    1. Re:Markov? by StylishGuy · · Score: 1

      Exactly. The funny thing is, markov model is also one of the basic things used to game Google's algorithm itself, with the autogeneration of content.

      Which makes me wonder, on the all things that interest geeks, why do they ignore things like communication? Why is there no comprehensive research done towards generation human readable text by automation?

    2. Re:Markov? by Anonymous Coward · · Score: 1

      Which makes me wonder, on the all things that interest geeks, why do they ignore things like communication? Why is there no comprehensive research done towards generation human readable text by automation?

      Yourself make seem generation almost readable text by automation. Will you confirmation Turing test on the soon?

    3. Re:Markov? by Anonymous Coward · · Score: 1

      Why is there no comprehensive research done towards generation human readable text by automation?

      There is. It's just very difficult to generate useful text, moreso automatically. Markov chains give you good results (considering the little effort required) but the text is gibberish. I don't think there's a "killer application" for this, though. Find a way to kill people with it and sure enough we'll have it in a few years.

    4. Re:Markov? by Anonymous Coward · · Score: 1

      Economics mostly. It's still cheaper to hire a bunch of people from China/India/Alabama or other third-world location. Generating text by automation seems to require a pretty strong AI, and that's hard to get.

    5. Re:Markov? by Anonymous Coward · · Score: 0

      Find a way to make money with it and sure enough we'll have it in a few years.

      Here, FTFY. Markov chains already have money-making use - generating plausible text-like garbage to fool spam filters. When anti-spam gets smart enough to identify them (that's not soon), someone will make a better algorithm.

      Or maybe just use random snippets from books. Works too.

    6. Re:Markov? by Anonymous Coward · · Score: 0

      Find a way to kill people with it and sure enough we'll have it in a few years.

      Oh, aren't you the worldly, cynical hipster?
      Can you kill people with e-mail? No.
      Can you kill people with instant messaging? No.
      Can you kill people with an electronic spreadsheet, document, or database? No, no, and (wait for it) no.
      Yet, each one of these applications is nearly ubiquitous.
      Next time, ease off on the sarcastic karma-whoring; you had a decent post until that last sentence.

    7. Re:Markov? by Anonymous Coward · · Score: 0

      There are many examples of the Markov model being used to generate random text in syntax. Here is a sample from one that goofs around with interpreted Arabian language based insults:

      We no speak english so nice so some of these make no sense perfectly. We many sorries.

      May a crowd of nymphomaniac single mothers snuggle with genitals while rummaging through your freakin' huge dog.
      May 96 chalky half-single mothers, half-wedding singers remark "Oops, I crapped my pants" to Janet Reno after waxing your hotel minibar.
      May a hogshead of homeless grave diggers suck on Barbie Dolls after genetically cloning your crazy little yappy dog.
      May 3,000 mutant ligers paint a picture of Gumbi while tinkering with your fungus.
      May a buttload of moldy convenient store clerks fixate on Diabetic Desserts while having a bowel movement on your treehouse.
      May 2,000 ripe CRNet Owners insert nipples behind your lice-infested silly putty.
      May a buttload of African American Twinkie salesmen withdraw from nipples at a fund-raising event for your tasty intestines.
      May a plethora of crafty retards taser John Travolta within your imaginary car trunk.
      May one too many aerodynamic lawyers build up a tolerance to John Travolta after genetically cloning your filthy car trunk.
      May 911 funny elected officials dip their balls in Diabetic Desserts while standing on your hairy demonic cat.
      May 64 bi-sexual Fem-Bots withdraw from weenies while rummaging through your wart covered little yappy dog.
      May 411 strange Twinkie salesmen regurgitate yogurt by your shrunken golf cart.
      May a mob of strange ball-lickers watch "Bakin' Bacon with Macon" with bacon bits beside your spastic pet jelly-fish.
      May an overabundance of sticky elected officials consume mass quantities of sporks after shoving glass shards into a portion of your shower.
      May a herd of withered Twinkie salesmen have an intense craving for rabid dogs topped with single sauce after they steal jelly beans after setting fire to your dreaded decapitated head.
      May 42 skanky Elvis impersonators pay homage to the god of poopie poopie poop poopity poop poop poopie poop poop poop by sacrificing urinal cakes after pledging allegiance to your sand castle.
      May one million stinky half-wedding singers, half-porn stars crossbreed with strange Colon Blow Cereal after hearing a loud *pop* coming from your neighbor's sand castle.
      May a gross of funkedified Super Mario Brothers toss your salad with lepers while fending off your cat's skid-marked undies.
      May 96 creamy extra-terrestrials masturbate their a can of Lysol disinfectant spray after being forced to smell your liquified dinner guest.
      May a hogshead of soaking cannibals smell like a mixture of ass and Ronald McDonald by your holiest of holys.
      May you witness of my favorite Christins sell their souls to the devil for a box of monkey brains while having a bowel movement on your expensive prosthetic forehead.
      May 2 stinky aerobics instructors go down on government agents after being forced to smell your gnarly barnyard animals.
      May a crowd of unshaven elected officials place their buttocks on the office copying machine next to Saran Wrap within a portion of your Prime Number Shitting Bear.
      May a buttload of hairy telemarketers pay homage to the god of Big League Chew by sacrificing easter eggs around your homemade blue and red tights.
      May 3,000 naked Hare Krishnas pay homage to the god of a can of Lysol disinfectant spray by sacrificing icecube trays after genetically cloning your calcium enriched shower.

      Insulter v2.0 BETA 6 by Mike Newman
      Words by Ted Harapat, Mike Newman, and others

    8. Re:Markov? by Anonymous Coward · · Score: 0

      "May 42 skanky Elvis impersonators pay homage to the god of poopie poopie poop poopity poop poop poopie poop poop poop by sacrificing urinal cakes after pledging allegiance to your sand castle."

      If it's so bad then how did it sum up religion so nicely?

    9. Re:Markov? by Samantha+Wright · · Score: 1

      That... is the weirdest definition of Markov model I have ever heard, but I guess Wikipedia agrees with you.

      --
      Bio questions? Ask me to start a Q&A journal. Computer analogies available for most topics!
    10. Re:Markov? by Anonymous Coward · · Score: 0

      Why is there no comprehensive research done towards generation human readable text by automation?

      It's because "journalists" are cheaper than such researchers, for the time being.

  3. reverse engineer by Anonymous Coward · · Score: 0

    than we can reverse engineer their biological works and cut off teh internetz astroturferz and trollz using google?

  4. Google's? by slasho81 · · Score: 1

    The technique these researchers and Google Search use is known from the 1950s. Google didn't invent it. Just as Steve Jobs didn't invent the smartphone, Mark Zuckerberg didn't invent social networks, and Bill Gates didn't invent the PC.

    1. Re:Google's? by StripedCow · · Score: 1

      Doesn't matter. They have the patent. That's all that counts.

      So, expect any future cancer cures to either be blocked from the market, or served with craploads of ads.

      --
      If Pandora's box is destined to be opened, *I* want to be the one to open it.
  5. Ballmer Was Right about it? by Anonymous Coward · · Score: 0

    According to Steve Linux and Google are a cancer!

  6. Tumor cell post by Anonymous Coward · · Score: 0

    (Score:-1, Carcinogenic)

    So will moderators have the power to delete cancer cells, then?

  7. All fucking journos must fucking die by Rogerborg · · Score: 4, Insightful
    • Researchers: "[NetRank operates] in a manner similar to Google's PageRank"
    • Retard masquerading as a professional journalist: "Researchers modified PageRank to develop NetRank"

    Die. Just die in a fire. Die, die, die.

    --
    If you were blocking sigs, you wouldn't have to read this.
    1. Re:All fucking journos must fucking die by durathor · · Score: 2

      Seriously, did you RTFA where the researcher himself described the algorithm as being based on PageRank

      “We first experimented with our own ideas on network algorithms until we realized that what we needed existed already with the PageRank algorithm, so why reinvent the wheel?” Winter recalled.
      “Our PageRank-based algorithm singles out proteins in the cancer cells that seem to either promote or suppress disease progression,” Winter said.

      How about the abstract of the research paper in question, which specifically mentions Google Page Rank
      http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1002511

      Are you sure it's the journalist who's the retard here?

    2. Re:All fucking journos must fucking die by Anonymous Coward · · Score: 0

      Well, the question is, is modified an accurate word for utilization an algorithm from abstract rather then any actual code. If anything, i'd be more inclined to use the word, *implemented* a modified version of the page range algorithm.

    3. Re:All fucking journos must fucking die by Kurrel · · Score: 1

      PageRank is designed around the 'random surfer' model (15% chance to jump to a random webpage) and returns the probability that a surfer will arrive back at the same page after a large number of links. A node that only has two edges can easily have the highest PageRank.

      If all they want is to find highly-connected nodes, then the Oracle of Bacon-style average length solution would work just as well.

    4. Re:All fucking journos must fucking die by Anonymous Coward · · Score: 0

      Well, the question is, is utilization an accurate word for USING something or putting it to USE? If anything, I'd be more inclined to use the word, *USAGE* a real word that wasn't invented by business majors.

    5. Re:All fucking journos must fucking die by Daniel+Dvorkin · · Score: 1

      Researchers: "[NetRank operates] in a manner similar to Google's PageRank"
      Retard masquerading as a professional journalist: "Researchers modified PageRank to develop NetRank"

      Die. Just die in a fire. Die, die, die.

      Researchers' paper: "NetRank is based on Google's PageRank algorithm."

      Read. Just read the article. Read, read, read.

      --
      The correlation between ignorance of statistics and using "correlation is not causation" as an argument is close to 1.
  8. Re:So the cure for cancer . . . is porn . . . ? by Anonymous Coward · · Score: 0

    That's because Google now tailors its results for each user - surf less porn and Google won't be so keen to help you find it!

  9. Interesting idea, flawed paper by Anonymous Coward · · Score: 4, Interesting

    The idea is interesting but the paper seems flawed. They integrate data and then look at how genes are positioned in the network with page-rank. The problem is that genes positioning in the network is highly dependent on how studied they are. Therefore, very well studied will get a high "NetRank." Genes known to be predictive of cancer progression are very well studied (lots of fudning in that area). This means the algorithm is basically finding and returning a list of what we already know, and it turns out that what we know is reasonably predictive when you combine 400+ markers.

    I'm surprised this made it by peer review without additional experiments to assess the role that this bias plays.

  10. Thigh bone's connected to the ... by coinreturn · · Score: 2

    The thigh bone's connected to the leg bone; the leg bone's connected to the ankle bone...

  11. PageRank is no search algorithm by allo · · Score: 1

    look at the name, it says it all .. its a ranking algorithm.

  12. Re:So the cure for cancer . . . is porn . . . ? by Samantha+Wright · · Score: 2

    Are you sure it was cottage cheese and alligator clamps? Not sour cream or banana clips or something? I ... can't reproduce your search results.

    --
    Bio questions? Ask me to start a Q&A journal. Computer analogies available for most topics!
  13. Re:So the cure for cancer . . . is porn . . . ? by Anonymous Coward · · Score: 0

    Porn fixes everything.

    I still don't understand that weird kink involving WebSphere WSRP (what I goggled for), a vat of cottage cheese and alligator clamps.

    Stop using the German Researcher customized version of Google's algorithm. You might want to avoid the Brazilian Researcher customized version as well.

  14. Thank you by Anonymous Coward · · Score: 0

    thank youu webmaster...

    www.kamsis.com

  15. Okay google I get by Dyinobal · · Score: 1

    Look Google we get it you still take your whole 'don't be evil' thing serious but I think you might be brown nosing a bit now.

  16. This is why Medical Science is garbage by Anonymous Coward · · Score: 0

    Has anyone else noticed that you can say anything, append it with, "...which may help reveal new therapies for X", and basically get published or funded?

    For example:

    I want to perform a study of posting on Slashdot while eating pizza and ruining the lives of suckers with potential who have signed up for graduate school. We believe that there is a relationship between peperoni and cancer. By identifying the relationships between pizza eaten and the amount of cancer a patient dreams about, we may discover new tumor treatments.

    BULL SHIT.

    Medical "Science" is thte worst example of research in academia.

  17. Colour me surprised if... by Errol+backfiring · · Score: 2

    Colour me surprised if cancer cells use Google to fight back.

    --
    Nae king! Nae laird! Nae yurrupiean pressedent! We willna be fooled again!
  18. Spare CPU cycles for cancer? by MotherErich · · Score: 1

    That should make this guy happy.

    --
    You have to be smarter than the machine you're working with.