SNAP bootstrap training

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

SNAP bootstrap training

Timo Metz
Hello,

I am using MAKER for a non-model organism, and I am currently trying to do the bootstrap training for SNAP as outlined in the tutorial and the paper for MAKER.

For the training I am using a set of ~300 sequences which are conserved (no golden standard genes available) and have very high quality and stop training after third round of bootstrap training.

However, it seems as training does not work properly, because when checking the AEDs for each round of bootstrap training, they actually get worse each round. Also the performance of snap after training is practically similar as before training and significantly worse than using a training file for a model organism.

Are there any suggestions what could be wrong? Is there anything special to check or look at what is not mentioned in the tutorial?

thanks in advance

kind regards
Timo Metz

_______________________________________________
maker-devel mailing list
[hidden email]
http://box290.bluehost.com/mailman/listinfo/maker-devel_yandell-lab.org
Reply | Threaded
Open this post in threaded view
|

Re: SNAP bootstrap training

Daniel Ence-2
Hi, what evidence are you using to get AEDs for the results of your bootstrap training? I don’t find it surprising that the AEDs get worse in subsequent rounds of bootstrap training since overtraining is a real possibility when training ab initio predictors. 300 genes also might not be enough genes, since I think the tutorials and protocols here and here use 1000 genes for training SNAP. 

I do find it surprising that training file from a different organism gives models that match evidence from your organism of interest. Is that correct? 

~Daniel


On Apr 6, 2018, at 9:23 AM, Timo Metz <[hidden email]> wrote:

Hello,

I am using MAKER for a non-model organism, and I am currently trying to do the bootstrap training for SNAP as outlined in the tutorial and the paper for MAKER.

For the training I am using a set of ~300 sequences which are conserved (no golden standard genes available) and have very high quality and stop training after third round of bootstrap training.

However, it seems as training does not work properly, because when checking the AEDs for each round of bootstrap training, they actually get worse each round. Also the performance of snap after training is practically similar as before training and significantly worse than using a training file for a model organism.

Are there any suggestions what could be wrong? Is there anything special to check or look at what is not mentioned in the tutorial?

thanks in advance

kind regards
Timo Metz
_______________________________________________
maker-devel mailing list
[hidden email]
http://box290.bluehost.com/mailman/listinfo/maker-devel_yandell-lab.org


_______________________________________________
maker-devel mailing list
[hidden email]
http://box290.bluehost.com/mailman/listinfo/maker-devel_yandell-lab.org

smime.p7s (1K) Download Attachment