fixes #40 by adding a slight modification of the demo script

README.md

@@ -18,13 +18,13 @@ cd demo
 
 # build k-mer sketches for the query sample and ref genomes
 sourmash sketch dna -f -p k=31,scaled=1000,abund -o sample.sig.zip query_data/query_data.fq
-sourmash sketch fromfile ref_paths.csv -p dna,k=31,scaled=1000,abund -o ref.sig.zip 
+sourmash sketch fromfile ref_paths.csv -p dna,k=31,scaled=1000,abund -o ref.sig.zip --force-output-already-exists
 
 # preprocess the reference genomes (training step)
-python ../make_training_data_from_sketches.py --ref_file ref.sig.zip --ksize 31 --num_threads ${NUM_THREADS} --ani_thresh 0.95 --prefix 'demo_ani_thresh_0.95' --outdir ./
+python ../make_training_data_from_sketches.py --ref_file ref.sig.zip --ksize 31 --num_threads ${NUM_THREADS} --ani_thresh 0.95 --prefix 'demo_ani_thresh_0.95' --outdir ./ --force
 
 # run YACHT algorithm to check the presence of reference genomes in the query sample (inference step)
-python ../run_YACHT.py --json demo_ani_thresh_0.95_config.json --sample_file sample.sig.zip --significance 0.99 --num_threads ${NUM_THREADS} --min_coverage_list 1 0.6 0.2 0.1 --outdir ./
+python ../run_YACHT.py --json demo_ani_thresh_0.95_config.json --sample_file sample.sig.zip --significance 0.99 --num_threads ${NUM_THREADS} --min_coverage_list 1 0.6 0.2 0.1 --out_filename result.xlsx
 
 # convert result to CAMI profile format (Optional)
 python ../srcs/standardize_yacht_output.py --yacht_output result.xlsx --sheet_name min_coverage0.2 --genome_to_taxid toy_genome_to_taxid.tsv --mode cami --sample_name 'MySample' --outfile_prefix cami_result --outdir ./

run_YACHT.py

@@ -60,7 +60,7 @@
     if os.access(os.path.abspath(os.path.dirname(out_filename)), os.W_OK):
         pass
     else:
-        raise FileNotFoundError(f"Cannot write to the location: {out_filename}.")
+        raise FileNotFoundError(f"Cannot write to the location: {os.path.abspath(os.path.dirname(out_filename))}.")
 
     # check if min_coverage is between 0 and 1
     for x in min_coverage_list:

tests/test_workflow.py

@@ -133,7 +133,16 @@ def test_incorrect_workflow1():
     assert res.returncode == 1
 
 
-def test_incorrect_workflow2():
-    script_dir = os.path.dirname(os.path.dirname(os.path.realpath(__file__)))
-    demo_dir = os.path.join(script_dir, "demo")
+def test_demo_workflow():
+    cmd = "cd demo; sourmash sketch dna -f -p k=31,scaled=1000,abund -o sample.sig.zip query_data/query_data.fq"
+    res = subprocess.run(cmd, shell=True, check=True)
+    cmd = "cd demo; sourmash sketch fromfile ref_paths.csv -p dna,k=31,scaled=1000,abund -o ref.sig.zip --force-output-already-exists"
+    res = subprocess.run(cmd, shell=True, check=True)
+    cmd = "cd demo; python ../make_training_data_from_sketches.py --force --ref_file ref.sig.zip --ksize 31 --num_threads 1 --ani_thresh 0.95 --prefix 'demo_ani_thresh_0.95' --outdir ./"
+    res = subprocess.run(cmd, shell=True, check=True)
+    cmd = "cd demo; python ../run_YACHT.py --json demo_ani_thresh_0.95_config.json --sample_file sample.sig.zip --significance 0.99 --num_threads 1 --min_coverage_list 1 0.6 0.2 0.1 --out_filename result.xlsx"
+    res = subprocess.run(cmd, shell=True, check=True)
+    cmd = "cd demo; python ../srcs/standardize_yacht_output.py --yacht_output result.xlsx --sheet_name min_coverage0.2 --genome_to_taxid toy_genome_to_taxid.tsv --mode cami --sample_name 'MySample' --outfile_prefix cami_result --outdir ./"
+    res = subprocess.run(cmd, shell=True, check=True)
+