Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

DeepVariant: Highly Accurate Genomes with Deep Neural Networks

research.googleblog.com

Post reply on HN
Print view View original

11–14 of 14 posts

Re: DeepVariant: Highly Accurate Genomes with Deep Neural Networks

#11

Post by danblick »

j7ake wrote: post #4

very nice but do you think neural networks will also be able to interpret the function of these genotype ?

I'm skeptical. Machine learning algorithms are only as good as the training data you can provide them. There are lots of tools in genetic analysis you can use to try to understand function of some sequence (e.g. looking at conservation or homology). I don't see where deep learning would provide new value on top of hand-built statistical models that are already in use. (Geneticists have known about machine learning for a long time...)

Obligatory reference: https://xkcd.com/1831

Re: DeepVariant: Highly Accurate Genomes with Deep Neural Networks

#12

Post by nl »

danblick wrote: post #10
nl wrote: post #5

Earlier quoted context omitted.

Yes. LIME works really well for this type of problem.

What is LIME?

LIME: Local Interpretable Model-Agnostic Explanations; https://www.oreilly.com/learning/introduction-to-local-inter...

"“Why Should I Trust You?” Explaining the Predictions of Any Classifier": https://arxiv.org/pdf/1602.04938.pdf

https://homes.cs.washington.edu/~marcotcr/blog/lime/

https://github.com/marcotcr/lime

Anytime anyone makes snide HN comments like "oh you can't understand why neural networks make predictions" the correct response should always be "why doesn't LIME work in your specific case".

LIME is being used within the EU to explain credit decisions and fraud detection flagging on neural network based models, which is quite a high bar to regulatory oversight to pass.

Re: DeepVariant: Highly Accurate Genomes with Deep Neural Networks

#13

Post by danblick »

nl wrote: post #12
danblick wrote: post #10

Earlier quoted context omitted.

What is LIME?

LIME: Local Interpretable Model-Agnostic Explanations; https://www.oreilly.com/learning/introduction-to-local-inter... "“Why Should I Trust You?” Explaining the Predictions of Any Classifier": https://arxiv.org/pdf/1602.04938.pdf https://homes.cs.washington.edu/~marcotcr/blog/lime/ https://github.com/marcotcr/lime Anytime anyone makes snide HN comments like "oh you can't understand why neural networks make prediction…

Hadn't heard of that before, thanks!

In this case, I understood the question to be "will deep learning do a good job predicting the function of/phenotype emerging from individual SNPs" and I don't think model interpretation would help (for starters, the model is trained to predict linkage and doesn't deal with data related to phenotypes).

Re: DeepVariant: Highly Accurate Genomes with Deep Neural Networks

#14

Post by nl »

danblick wrote: post #13
nl wrote: post #12

Earlier quoted context omitted.

LIME: Local Interpretable Model-Agnostic Explanations; https://www.oreilly.com/learning/introduction-to-local-inter... "“Why Should I Trust You?” Explaining the Predictions of Any Classifier": https://arxiv.org/pdf/1602.04938.pdf https://homes.cs.washington.edu/~marcotcr/blog/lime/ https://github.com/marcotcr/lime Anytime anyone makes snide HN comments like "oh you can't understand why neural networks make prediction…

Hadn't heard of that before, thanks! In this case, I understood the question to be "will deep learning do a good job predicting the function of/phenotype emerging from individual SNPs" and I don't think model interpretation would help (for starters, the model is trained to predict linkage and doesn't deal with data related to phenotypes).

I believe that comment was edited.

Of course the NN won't interprete the results, it will just provide better results.

Post reply on HN