Considering the MouseAge Project

Here, an update on the MouseAGE project from the popular science press. This initiative aims to produce a viable biomarker of aging based on visual inspection of mouse faces. Since age-related mortality in humans correlates fairly well with apparent age of the face, and since machine learning techniques can be used to assess aging from photographs in an automated fashion, it seems reasonable to think that it might be possible to achieve a similar analysis in mice. If successful, it might by used to speed up the assessment of potential rejuvenation therapies, a faster alternative to running life span studies. Given the low cost of development, it is worth a try as an alternative approach to the epigenetic clock and other biomarkers of aging under development. The project was crowdfunded in 2017 and data collection began last year.

Vadim Gladyshev is asking lab scientists to whip out their smartphones and take photos. Not selfies, exactly, but snapshots of their lab mice. It's a fiddly task, Gladyshev admits: mice move fast, and need to be kept still for the camera. He suggests grabbing them with one hand or taking them by the tail while they use their front paws to hold a rod. The impromptu photo shoots are all part of a crowdsourced effort to develop an algorithm that can help predict the biological age of a mouse from its mug shot - information that could help researchers studying aging understand the connection between a person's biology and how old he or she looks.

Scientists now know, for example, that people who look younger than their years tend to live longer than people whose appearance more closely matches the time they've been alive. People are surprisingly good at predicting biological age when it comes to fellow Homo sapiens. But pinpointing the biological age of mice is far more challenging. Instead, assessing the effect of anti-aging drugs in lab mice often involves taking blood samples and running expensive tests. Biomarkers such as DNA methylation signatures and analyses of metabolites and biochemical measurements consume resources and run up costs. Alternatively, researchers may need to sacrifice mice in order to examine the internal effects of a compound.

The idea for a cheap and less wasteful alternative came to Gladyshev and Alex Zhavoronkov, founder of Insilico Medicine, a company specializing in artificial intelligence (AI) for aging research and drug discovery, a couple of years ago. The pair got to chatting and came up with the idea of using a mouse's appearance as a marker of biological age - just as developers have attempted to do for humans. Mouse photo shoots have already been staged in labs across the US and Europe, and around 500 lab mice are in the catalog. The team plans to release the algorithm publicly a few months from now and allow researchers to use it for free. But the project is still in the image-collection stage, as the more reference images it has, the better the algorithm will perform. The team aims to collect images of 1,000 mice by March, but Gladyshev is planning to continue collecting until the project has sourced at least 10,000. "Future programs would tell whether one group of mice is biologically younger than another, allowing us to more easily test interventions. Instead of waiting for mice to die, they can be quickly assessed for their potential to live longer."



We also have an update from the MouseAge team on LEAF today which may be of interest to readers.

Posted by: Steve Hill at February 7th, 2019 6:06 AM

It might turn out that determining the age from the appearance of much easier in mice than in humans. After all, we have an industry worth a few billion dollars which servers the appearance. For example, the most obvious indicator is the grey hair. Now it is so easy to dye it...

Posted by: Cuberat at February 7th, 2019 8:01 AM

Really useless project -- because anyway you have to check biomarkers from samles of the mice. Vadim Gladyshev is very fit for NIH or Calico ;-)

Posted by: Ariel at February 7th, 2019 1:03 PM

Okay. How do mice recognize each other. Smell? (I don't know for sure. I'm asking.) How do humans recognize each other? Usually facial features for sure. My hunch is humans have unique, complex pathways leading to greater variability in facial features than mice. And we need to understand it to treat aging.

Posted by: NY2LA at February 7th, 2019 6:39 PM

The project has great potential and a number of researchers are certainly happy with the application so far, the app is currently being refined and should hopefully become increasingly useful in the future. The project update I mentioned earlier is now published:

Hopefully, those of you who understand rodent research and have an open mind to new approaches will find it interesting.

Posted by: Steve Hill at February 7th, 2019 7:27 PM

Post a comment; thoughtful, considered opinions are valued. New comments can be edited for a few minutes following submission. Comments incorporating ad hominem attacks, advertising, and other forms of inappropriate behavior are likely to be deleted.

Note that there is a comment feed for those who like to keep up with conversations.