Run terminates with error while on conda

[Anto007]

I get this error during the middle of running macrel on conda:

Traceback (most recent call last):
File "/user/conda_macrel_env/bin/macrel", line 11, in
sys.exit(main())
File "/user/conda_macrel_env/lib/python3.7/site-packages/macrel/main.py", line 282, in main
do_predict(args, tdir)
File "/user/conda_macrel_env/lib/python3.7/site-packages/macrel/main.py", line 241, in do_predict
fs)
File "/user/conda_macrel_env/lib/python3.7/site-packages/macrel/AMP_predict.py", line 7, in predict
model1 = pickle.load(gzip.open(model1, 'rb'))
ModuleNotFoundError: No module named 'sklearn'

The commandline that I used after activating the conda macrel environment is this:
macrel contigs --fasta test_bacterium_genome.fasta --output test_contigs

I would appreciate your feedback here.

[celiosantosjr]

Hi Anto007,

Could you clarify some details? Is your installation from source or directly from conda container?

Best,
Celio

[luispedro]

We will fix the underlying issue (that the conda package does not declare scikit-learn as a dependency), but, in the meanwhile, please try running conda install scikit-learn

[luispedro]

Closing here now that the new conda version is available

@Anto007 thank you for the report, it was helpful. Please report any further issues

[Anto007]

Thank you very much! It works fine now. I would like to make a few suggestions (if I may):

1. Can you mention in the README and manual what are the expected output files and a brief description of what kind of information they contain? This will be helpful for new users. Also, some elaboration on the type of information being represented in the macrel.out.prediction output file will be welcome. For example, from your experience, AMP_probability or Hemolytic_probability scores above what value should be taken with more confidence by the users?

2. Perhaps it can be considered a bit odd that the 'macrel.out.prediction' output file is gzipped? Have you ever ended with really bulky 'macrel.out.prediction' files? It's even more odd when considering the fact that the more bulkier *.faa files in the output directory are not gzipped?

Thanks again for your prompt support!

[Anto007]

One more thing: '--outtag' in the manual should be replaced with '--tag'

[luispedro]

Thanks, these are all good suggestions.

[luispedro]

The gzipping of some files and not others is a bit of laziness on our part: because pandas (the library we use) does implicit gzip when you save the TSV file, we did it, but for the fasta files, it would have been an extra step.