gene query to mygene run redundantly for each fold

[coleslaw481]

• cellmaps_imagedownloader version: 0.1.6a1
• Python version: 3.8
• Operating System: mac

Description

gene query to mygene is being run twice (once for each fold)

Downloading proteinatlas.xml.gz: 100%|███████████████████████████████████████████████████████████████| 851M/851M [03:24<00:00, 4.35MB/s]
Download: 100%|████████████████████████████████████████████████████████████████████████████▉| 94147/94148 [00:39<00:00, 2365.83images/s]
Get updated gene symbols:   0%|                                                                                | 0/5 [00:00<?, ?steps/s]querying 1-1000...done.
querying 1001-2000...done.
querying 2001-3000...done.
querying 3001-4000...done.
querying 4001-5000...done.
querying 5001-6000...done.
querying 6001-7000...done.
querying 7001-8000...done.
querying 8001-9000...done.
querying 9001-10000...done.
querying 10001-10814...done.
Finished.
2 input query terms found dup hits:
	[('ENSG00000274175', 3), ('ENSG00000268674', 3)]
8 input query terms found no hit:
	['ENSG00000285762', 'ENSG00000112096', 'ENSG00000285162', 'ENSG00000168078', 'ENSG00000189144', 'ENS
Pass "returnall=True" to return complete lists of duplicate or missing query terms.
Get updated gene symbols:  80%|█████████████████████████████████████████████████████████▌              | 4/5 [00:19<00:04,  4.90s/steps]
Get updated gene symbols:   0%|                                                                                | 0/5 [00:00<?, ?steps/s]querying 1-1000...done.
querying 1001-2000...done.
querying 2001-3000...done.
querying 3001-4000...done.
querying 4001-5000...done.
querying 5001-6000...done.
querying 6001-7000...done.
querying 7001-8000...done.
querying 8001-9000...done.
querying 9001-10000...done.
querying 10001-10814...done.

What I Did

Ran via pipeline, but can directly invoke to get this behavior

cellmaps_pipelinecmd.py -vvvv 6.15run \
  --samples TL_u2os_samples_unique_genes_10279.csv \
  --unique TL_u2os_unique_genes_10279.csv \
  --edgelist edgeList.tsv --baitlist baitList.tsv \
  --model_path model.pth --provenance provenance.json --fake