Doesn't work for the the sequences in variable lengths

[ruizhideng]

Hi!

Thanks for the amazing work!

I am testing the original notebook from https://github.com/kundajelab/tfmodisco/blob/master/examples/simulated_TAL_GATA_deeplearning/TF_MoDISco_TAL_GATA.ipynb, it seems the original GitHub is deprecated.

In the original notebook, you mentioned the TF-modisco pipeline also works for the sequences in different lengths. However, when I was testing the notebook with input data with shape of [100, length, 4], the length ranges from 500-1000 bp, it raised the ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (100,) + inhomogeneous part.
Then if I crop the sequences and contribution scores to the same length, it works again. I am wondering is there any version available for the sequences with different length?
https://github.com/kundajelab/tfmodisco/blob/master/examples/simulated_TAL_GATA_deeplearning/TF_MoDISco_TAL_GATA.ipynb

Thank you again!

Best wishes,
Ruizhi

[jmschrei]

Hi Ruizhi

I didn't write that notebook or the original repository. This repo is a rewrite of that code that simplifies things significanty. One of the simplifications is that this only works on sequences of fixed length. Sorry about that.

[ruizhideng]

Hi Jacob, thank you for the prompt reply!