I am trying to replicate the results for the creator of this repo: https://github.com/aldro61/kover2_paper for genotype to phenotype machine learning interpretable (decision tree) prediction.
Specifically in the data section when I try to create the dataset as explained here: https://github.com/aldro61/kover2_paper/tree/master/data
I make a directory called genomes_dir in the data directory. Then I do:
python download_genomes.py 'mycobacterium tuberculosis/kanamycin/metadata.tsv' genomes_dir
at the end of the download it tells me that it saved file genome_paths.tsv
the data directory, not genomes_dir. So I run command:
kover dataset create from-tsv --genomic-data genome_paths.tsv ---phenotype-description "Kanamycin resistance" --phenotype-metadata 'mycobacterium tuberculosis/kanamycin/metadata.tsv --output data_example.kover --progress
and it just hangs with a prompt:
(kover) nobu@gold3forever:~/Desktop/BioInformatics/ResearchAssistant/kover2_paper/data$ kover dataset create from-tsv --genomic-data genome_paths.tsv ---phenotype-description "Kanamycin resistance" --phenotype-metadata 'mycobacterium tuberculosis/kanamycin/metadata.tsv --output data_example.kover --progress
> ^C
it does nothing after hours and hours so I control-C'd to end the process.
Does anyone have any idea what is happening?
I also had to install this to get the datasets from PATRIC: https://github.com/aldro61/patric_tools