Re:110M-year-old dinosaur discovered with skin and soft tissue
by 0xdeadbeefbabe on Friday May 12, 2017 @05:54PM
(#14328243)
Can we use CRISPR to create something from ~500 year old bones? Okay, I already know the answer.
Re:110M-year-old dinosaur discovered with skin and soft tissue
by perseusprime11 on Friday May 12, 2017 @04:42PM
(#14327743)
Is it possible to use deep learning to fill out the missing parts? I am guessing that DNA is like code with a set of instructions encoded.
Re:110M-year-old dinosaur discovered with skin and soft tissue
by objclxt on Friday May 12, 2017 @05:01PM
(#14327898)
> Is it possible to use deep learning to fill out the missing parts?
The half life is 521 years - there is nothing left to fill in. If you read the linked article you'll see even under perfect conditions all DNA is destroyed after about 6 million years. This fossil is 110 million years old.
Re:110M-year-old dinosaur discovered with skin and soft tissue
by wil421 on Friday May 12, 2017 @04:44PM
(#14327765)
You could always fill in the gaps with amphibian DNA.
Re:110M-year-old dinosaur discovered with skin and soft tissue
by giarc on Friday May 12, 2017 @05:05PM
(#14327928)
I imagine that is a Jurassic Park reference and not an actual suggestion. However, if it is, you would just then end up with a frog.
Re:110M-year-old dinosaur discovered with skin and soft tissue
by wil421 on Friday May 12, 2017 @07:49PM
(#14328822)
You're right we should just build humanoid robots for the guests instead.
Re:110M-year-old dinosaur discovered with skin and soft tissue
by asadlionpk on Saturday May 13, 2017 @07:15AM
(#14330383)
building either of those leads to violent ends.
Re:110M-year-old dinosaur discovered with skin and soft tissue
by biot on Friday May 12, 2017 @05:05PM
(#14327927)
If you use deep learning, the missing parts will be filled with something based on whatever you trained the model on. In other words, the training data won't be dinosaur DNA as we don't have that. At best, during training you can classify some DNA as "more dinosaur" and other DNA as "less dinosaur" and you hope the result will be some extrapolation towards "most dinosaur". Despite the practical limitations, it's certainly an interesting thought.
Re:110M-year-old dinosaur discovered with skin and soft tissue
by perseusprime11 on Saturday May 13, 2017 @02:46PM
(#14332350)
What if the training set is evolution data? To me CRISPR + Deep Learning seems like a powerful combination. Looking to see some amazing advances in this area.
1. http://www.the-scientist.com/?articles.view/articleNo/32799/...