Doing Science With Virtual Biologists

An anonymous reader sends word of new research into automating computational experiments. A team of scientists developed a piece of software, dubbed Eureqa, to help solve complex, computationally-intense biological problems. A new paper in the journal Physical Biology details their success (abstract). "The researchers chose this specific system, called glycolytic oscillations, to perform a virtual test of the software because it is one of the most extensively studied biological control systems. Jenkins and Vallabhajosyula used one of the process' detailed mathematical models to generate a data set corresponding to the measurements a scientist would make under various conditions. To increase the realism of the test, the researchers salted the data with a 10 percent random error. When they fed the data into Eureqa, it derived a series of equations that were nearly identical to the known equations. 'What’s really amazing is that it produced these equations a priori,' said Vallabhajosyula. 'The only thing the software knew in advance was addition, subtraction, multiplication and division.'"

Comments

Pretty impressive

[werepants]

Now the scientist's jobs will be done by machines as well.

In reality, I'm sure that there is only a very small subset of problems that this system will work for, but, there is no reason that we shouldn't put it to work on those posthaste. It will be interesting to see what it can do with an unsolved problem.

Re:Pretty impressive

[Daniel Dvorkin]

It's neat stuff, but I'm skeptical that it will replace human biologists any time soon. As is often the case, the pop-sci writeup is a lot more dramatic than the article itself. Reading the latter, I'd say that what they've done is a clever bit of data mining combined with mathematical modeling -- they use an evolutionary algorithm to find the best set of differential equations, out of an enormous number of possible models, which describe the behavior of the data.

This is easier, and probably produces better results, than the traditional method of coming up with sets of diff. eqs. to describe the behavior of complex systems, but it's not a replacement for human judgement in coming up with the model space in the first place. (I'll also note that they performed almost the entire "experiment" on simulated data, which is always a valuable first step in the development of any modeling method, but it's not enough to show that the method "works" -- real data is always messier than the best simulations, and biological data is particularly so.) That being said, it's a very nice technique, and I'll be interested to see if the same approach can be applied to building the kinds of statistical models I work with, Bayesian networks and such.

Re:Pretty impressive

[Anonymous Coward]

Nobody's job has been removed--it has just been made easier. At best, they have just demonstrated some kind good automatic fitting for rational functions of at least a few variables. I'm betting this is more like the rediscovery of integration we saw before.

Re:Pretty impressive

[HiThere]

FWIW, mathematical modeling isn't science. It's quite important, but it isn't science until it's tested against a physical environment to determine whether the predictions are correct.

This is a bit nit-picky, but too many people seem to be forgetting it, and the distinction is extremely important.

Re:Pretty impressive

[Anonymous Coward]

It is science. A mathematical model can help you find the answer faster (i.e. if you know A has a better chance of working than B you test A first instead of trying randomly). That said, this AI is nothing special - it may help them and all that, but is not something new.

Re:Pretty impressive

[gardyloo]

Check into how this software works. It chooses a sparse set of data points, creates its "model", and then brings in more points to test against. I've used it (though not super seriously) and heard a talk by one of its creators. It's based upon a heuristic of finding the _most_surprising_, _worst_ matches to its guesses and then refining the model. In the sense that it is explicitly used to predict how well it fits to further actual, experimentally-obtained data points, your criterion of it being "tested against a physical environment to determine whether the predictions are correct" is exactly what it does.

Re:Pretty impressive

[epine]

The only paragraph I found at all useful:

Generally, the way that scientists design experiments is to vary one factor at a time while keeping the other factors constant, but, in many cases, the most effective way to test a biological system may be to tweak a large number of different factors at the same time and see what happens. ABE will let us do that.

The rest is all mystery meat about the actual method.

This is certainly the way of the future. IBM has pumping that notion right now, as well. I'm not inclined to think this is a huge step if they've only found signal under Gaussian noise.

Re:Pretty impressive

[Anonymous Coward]

FWIW, mathematical modeling isn't science. It's quite important, but it isn't science until it's tested against a physical environment to determine whether the predictions are correct.

This is a bit nit-picky, but too many people seem to be forgetting it, and the distinction is extremely important.

And no doubt you also don't think Computer Science is science, right?

Re:Pretty impressive

[HiThere]

PARTS of computer science are science. Parts are math. Where I went to school the science parts were emphasized in the EE department, and the math parts in the math part. I suspect that by now "Computer Science" has become it's own department, but the name is not the thing.

Re:Pretty impressive

[HiThere]

Yes, that's a mathematical model of science. But it doesn't become science until it makes a prediction that is then tested against the physical world. And it's the complete process that's science, not any one piece of it.

Thus, String Theory is mathematics that is endeavoring to become science. Some parts of String Theory have become science. Failed science, as the predictions were not validated, but still science. Other parts of it can't yet be tested.

Science requires BOTH the prediction of a previously unpredicted phenomenon AND the test in the external world to find that phenomenon. It's science whether it is validated or refuted. It's not science until it is tested.

This has run into problems because of many theories predicting things which are "testable in theory, but not currently", which has caused people to fuzz their definitions to not require that theories be tested. But to fuzz that boundary removes the distinction between science and religion. With all the problems that that brings. If you can't test it, it's not science. If you can, but don't test it, it's not science.

Mathematical models are quite important, but they are not science, but only a tool that can be used to produce science. And they aren't sufficient in and of themselves.

Geez, this stuff has been around ....

[sgt_doom]

...for quite awhile, and few comprehend that it is, in actuality, the very first REAL A.I. in existence (unless there's some secret stuff out there???). It is truly brilliant, and predictably derives from genetic programming algorithms.

And of course the AI program was recalcitrant about revealing how it does it's thing, haven't all of us from time to time exhibited the exact same behavior?

Now, if only they could couple this with Google's API, and SkyGrabber, I'd bet we'd end up with some really fantastic AI stuff going on!!!!!!!!!!!!!! Lisp, anyone?

Re:Geez, this stuff has been around ....

[Anonymous Coward]

"AI program was recalcitrant about revealing how it does it's thing"

How do you put apotrophes where they don't belong?

I ran the events of the last 2 weeks through it...

[sgt_doom]

And this is why my own version of Eureqa spewed forth:

This has been a very confusing few weeks, so allow me to summarize.

The Attorney General for Chiquita and ExxonMobil, Eric Holder, in a public announcement stated that he'd found the Smoking S**t, the connection between the Underwear Bomber's Calvin Klein's and the Iranian Quds Force.

Meanwhile, Swami Rami of India's Ta Ta Agency said that all religion is B.S. and demanded that President Obama ship 500,000 more jobs to India.

President Obama responded, "Jobs, jobs, jobs!"

His able VP, Joey bin Biden, declared that Julian Assange was the international terrorist behind everything, and that the administration was dispatching Frank Wisner, Jr., to ascertain the demands of the "Occupy Wall Street" movement.

Rue Paul lodged an official protest: "Does Calvin Klein still make undies?"

In breaking news from the crack American Propaganda Network, Fox-CNN-ABC-CBS-NPR-AP, it was reported that Britney Spears admonished the American people to robotically follow their Fearless Leader, George W. Bush.

When former President Bush was reached for comment, he promptly pooped his pants.

After meeting with the Occupy Wall Street group, the Obama Administration's roving rover, Frank Wisner, Jr., announced his agreement with the Occupy Wall Street movement: that Wall Street should be immediately nuked, and Fifth Avenue should be crop dusted with LSD, just like his daddy did to that French town back in 1951. (Franky also announced his divorce from French President Sarkozy's stepmother, and that he would be shacking out with a pretty 18-year-old Wall Street protester he had conferred with.)

In breaking with the administration, Hillary Clinton declared China to be her private banker, and said they could manipulate their currency anyway they damn well pleased!

In a bold move, Lloyd Blankfein, Jamie Dimon, Robert Rubin, Alan Greenspan, and Stephen Schwarzman renounced their American citizenship and defected to Dubai.

The Obama Administration formerly declared they were officially distancing themselves from Frank Wisner, Jr., Eric Holder, Joey bin Biden, Hillary Clinton, Julian Assange and Sponge Bob.

Meanwhile, Warren Buffett's company still hasn't paid the billions owed in back taxes!

(I have it hooked up to local and international newsfeeds, BTW....)

I'm doing science

[Anonymous Coward]

and I'm still alive.

A priori or ab initio?

[MurukeshM]

I'm confused. Did the program derive the equations a priori or ab initio? If a priori, wow!

Re:A priori or ab initio?

[Anonymous Coward]

Isn't sua sponte more appropriate? ("of its own accord")

'Virtual Biologists' huh

[Anonymous Coward]

So if I use Matlab to do statistical analysis (econometrics) on my econ dataset, then my computer is a 'virtual economist', huh.

Re:I ran the events of the last 2 weeks through it

[Dexter Herbivore]

I am intrigued by your thoughts and would like to subscribe to your newsletter (or your A.I.s drug supplier).

And for the less informed among us...

[TubeSteak]

When they fed the data into Eureqa, it derived a series of equations that were nearly identical to the known equations.

How useful is "nearly identical"?

Re:And for the less informed among us...

[M0j0_j0j0]

enough to make a headline.

Re:And for the less informed among us...

[Anonymous Coward]

I award you one full Internets, sir.

Re:And for the less informed among us...

[Hentes]

It might be just some constants being a little off.

Random error

[vossman77]

The problem with research is that there is no such thing a pure random error. Time and time again, we develop methods that work awesome with random error. In reality, the error in the data is not purely random, but a combination of systematic and random error (that is not Gaussian), so it takes a trained eye to work through this. I would much preferred that they used real data rather than only fabricated data, then you can say that you have something.

okay..

[Anonymous Coward]

If I told you I can fit equations with data you wouldn't think it was magical .. (after all thats exactly what any series expansions are guaranteed to do) why do biological modelers its somehow more magical to do when we are in ODE land?

-avi

you call that impressive?

[Anonymous Coward]

wake me when you can play doctor with a hot virtual nurse.

Doing Intelligent Design With Virtual Creationists

[Mr Foobar]

Now that would be impressive!

Giant Miscue

[Anonymous Coward]

Why is it that real "flesh and mud" bio studies are 'boring' but this advanced gaming is 'hot' in Western Society?
I claim its because our brains are wired to tune out details of nature to focus on fight and flight type things.. All the lip-service to "native peoples wisdom" seems dumb - at first, until its measured against "people that pay attention to ordinary daily things in nature" vs "people that build insulated indoor lives" en masse.. and go on to make highly abstracted models of biology.. or try to rule the world with genetic engineering.. I claim The West has major flawed evolutionary patterns around nature.. and we are very rapidly paying the price

Re:I ran the events of the last 2 weeks through it

[Anonymous Coward]

Me three. This makes the most sense I've heard in months, and I need to borrow your lighter.