Extracting features for mutated gene sequences

Question

[muvinika]

Hi,

I need to extract features from gene sequences for disease identification through machine learning techniques. Kindly help.

[muvinika]

As am using large number of sequences am in need to extract features to predict disease from gene sequences based on machine learning techniques.

[Sam]

What kind of feature? What kind of data? Please provide more information

[muvinika]

For missense/nonsense mutation data

[muvinika]

My aim to identify disease from missense mutations based on machine learning algorithms.

[Sam]

So you are saying, you have a bunch of missense mutations and try to use machine learning algorithms to see if they are related to a particular disease?

[muvinika]

Yes sir you are right

[Sam]

If you have the case and control, then why don't you just use the statistic test to test the association?

[Sam]

So you are saying that you are having snps on multiple different sequences and are trying to see if certain nucleotide sequences can help you to predict the disease status?