AI and Autism

Many mutations in DNA that contribute to disease are not in actual genes but instead lie in the 99% of the genome once considered "junk." Even though scientists have recently come to understand that these vast stretches of DNA do in fact play critical roles, deciphering these effects on a wide scale has been impossible until now.

It was previously thought that the only important parts of genetics was the parts that coded proteins and anything in between was just junk. But over time, scientists have realised that they are important too and can have critical responsibility in deciding how DNA works.

Researchers used to manually map DNA to diseases, this usually works well enough, but for more complex DNA, but in the case of most complex diseases such as autism, this is not enough and the massive junk DNA needs to be scanned

Researchers used to manually map DNA to diseases, this usually works well enough, but for more complex DNA, but in the case of most complex diseases such as autism, this is not enough and the massive junk DNA needs to be scanned

 Using artificial intelligence, a team from Princeton has compared a data set  (n=1,790) of this “junk DNA” with whether these people have autism. Through this study, the AI wasn’t able to figure out the exact cause of autism, they do reveal a sea of contributors and generally indicate the “junk DNA” isn’t junk.

 The “junk DNA” is very very big compared to DNA that codes proteins (about 100x bigger) meaning it is very hard for scientists to manually go through the DNA, due to this AI might just be the only tool that can do the job and see the correlation between the junk DNA and different diseases.