morganx

I'm having this issue too. I found this link (https://stackoverflow.com/questions/56127592/attributeerror-module-tensorflow-has-no-attribute-configproto) suggesting this fix import tensorflow.compat.v1 as tf tf.disable_v2_behavior() So I tried substituting that in the deepbinner.py and classify.py headers, but...

Edit: I could not get this to work on my Mac, but I got it to work on linux in a conda environment with python 3.6, tensorflow==1.15.0, and keras==2.1.5.

The ipython notebook format for STAMPS2013 was very easy to use. I think it is a good format for tutorials. Thank you.

FYI: I wondered if updating R would help, but it didn't. sessionInfo() R version 4.0.3 (2020-10-10) Platform: x86_64-apple-darwin17.0 (64-bit) Running under: macOS Catalina 10.15.4 Matrix products: default BLAS: /System/Library/Frameworks/Accelerate.framework/Versions/A/Frameworks/vecLib.framework/Versions/A/libBLAS.dylib LAPACK:...

Update: This works. install_github("waldronlab/lefser") Installing from bioconductor still doesn't work because it thinks it's incompatible with my version of R.

It looks to be hard-coded into the lefserPlot function but you can change the labels to whatever you want with scale_fill_discrete(). It does require knowing which group should be zero...