SoylentNews is people
SoylentNews
In May last year, a supercomputer in San Jose, California, read 100,000 research papers in 2 hours. It found completely new biology hidden in the data. Called KnIT, the computer is one of a handful of systems pushing back the frontiers of knowledge without human help.
KnIT didn't read the papers like a scientist – that would have taken a lifetime. Instead, it scanned for information on a protein called p53, and a class of enzymes that can interact with it, called kinases. Also known as "the guardian of the genome", p53 suppresses tumors in humans. KnIT trawled the literature searching for links that imply undiscovered p53 kinases, which could provide routes to new cancer drugs.
Having analyzed papers up until 2003, KnIT identified seven of the nine kinases discovered over the subsequent 10 years. More importantly, it also found what appeared to be two p53 kinases unknown to science. Initial lab tests confirmed the findings, although the team wants to repeat the experiment to be sure.
(Score: 4, Informative) by tynin on Sunday August 31 2014, @04:28AM
It is true, but the new level of awesomeness in this is at least two part....
1. Thanks to machine learning, we can re-eval everything we have gathered significant data on. Where we feel we understand a myriad of properties (which might be greater than a single mind can ingest), we can uncover what should have been obvious (or not) but got lost in the mix, or...
2. the right person who thinks to ask the right questions (writes the right algorithm) might just come away with a new understanding that could propel us all forward, to being able to keep this (biological/metaphysical) game in play.
While we aren't there today... perhaps soon. As they say, We are standing on the shoulders of giants.
(Score: 3, Interesting) by Anonymous Coward on Sunday August 31 2014, @05:29AM
> While we aren't there today... perhaps soon. As they say, We are standing on the shoulders of giants.
If they are able to make this technique work for anything even remotely close to a generalizable form then it will turn those millions of essentially unread scientific papers that the publish-or-perish system creates into a fertile resource. It may also make cases of negative results more valuable - all those experiments from drug companies that failed to pan out and normally get binned instead of published might reveal something else. But I think your analogy is reversed - it will be more like giants standing on the shoulders of millions of ants.