Merge pull request #1072 from maxplanck-ie/createIndices_orgyamls

Create indices orgyamls

.github/workflows/linux.yml

@@ -100,7 +100,8 @@ jobs:
           'CONDA_PREPROCESSING_ENV',
           'CONDA_NONCODING_RNASEQ_ENV',
           'CONDA_SAMBAMBA_ENV',
-          'CONDA_pysam_ENV'
+          'CONDA_pysam_ENV',
+          'CONDA_FQLINT_ENV'
         ]
     runs-on: ubuntu-latest
     steps:

.github/workflows/osx.yml

@@ -31,7 +31,8 @@ jobs:
           'CONDA_PREPROCESSING_ENV',
           'CONDA_NONCODING_RNASEQ_ENV',
           'CONDA_SAMBAMBA_ENV',
-          'CONDA_pysam_ENV'
+          'CONDA_pysam_ENV',
+          'CONDA_FQLINT_ENV'
         ]
     runs-on: macos-latest
     steps:

docs/content/News.rst

@@ -6,6 +6,7 @@ ________________
 
  * installation test for python 3.13
  * bulk mode in makePairs wf
+ * Removal of --user flag in createIndices. Organism yamls are by default written to both installation folder and output folder.
 
 snakePipes 3.0.0
 ________________

snakePipes/common_functions.py

@@ -42,7 +42,9 @@ def set_env_yamls():
             'CONDA_NONCODING_RNASEQ_ENV': 'envs/noncoding.yaml',
             'CONDA_SAMBAMBA_ENV': 'envs/sambamba.yaml',
             'CONDA_pysam_ENV': 'envs/pysam.yaml',
-            'CONDA_SEACR_ENV': 'envs/chip_seacr.yaml'}
+            'CONDA_SEACR_ENV': 'envs/chip_seacr.yaml',
+            'CONDA_FQLINT_ENV': 'envs/fqlint.yaml'
+            }
 
 
 def merge_dicts(x, y):

snakePipes/shared/rules/FASTQ.snakefile

@@ -5,7 +5,7 @@ if pairedEnd or pipeline=="scrnaseq":
             r2 = indir+"/{sample}"+reads[1]+ext
         output:
             temp("originalFASTQ/{sample}.valid")
-        conda: CONDA_SHARED_ENV
+        conda: CONDA_FQLINT_ENV
         shell:"""
             fq lint {input.r1} {input.r2}
             touch {output}
@@ -16,7 +16,7 @@ else:
             r1 = indir+"/{sample}"+reads[0]+ext
         output:
             temp("originalFASTQ/{sample}.valid")
-        conda: CONDA_SHARED_ENV
+        conda: CONDA_FQLINT_ENV
         shell:"""
             fq lint {input.r1}
             touch {output}

snakePipes/shared/rules/envs/fqlint.yaml

@@ -0,0 +1,4 @@
+channels:
+ - bioconda
+dependencies:
+ - fq = 0.12.0

snakePipes/shared/rules/envs/shared.yaml

@@ -15,6 +15,5 @@ dependencies:
  - multiqc = 1.23
  - fastp = 0.23.4
  - umi_tools = 1.1.4
- - fq = 0.11.0
  - pybigwig = 0.3.22
 

snakePipes/workflows/createIndices/Snakefile

@@ -171,12 +171,15 @@ onsuccess:
     f = open(os.path.join(outdir, "genome_fasta", "effectiveSize"))
     organismDictionary['genome_size'] = int(float(f.read().strip()))
     f.close()
-    if not userYAML:
-        yamlPath = os.path.join(maindir, organismsDir, "{}.yaml".format(genome))
-    else:
-        yamlPath = os.path.join(outdir, "{}.yaml".format(genome))
-    print("Storing the organism YAML file in {}".format(yamlPath))
-    cf.write_configfile(yamlPath, organismDictionary)
+    orgDir_yamlPath = os.path.join(maindir, organismsDir, f"{genome}.yaml")
+    outDir_yamlPath = os.path.join(outdir, f"{genome}.yaml")
+    try:
+        cf.write_configfile(orgDir_yamlPath, organismDictionary)
+        print(f"{genome} yaml written to {orgDir_yamlPath}")
+    except (PermissionError, FileNotFoundError) as e:
+        print(f"Error writing in the organism dir {e}")
+    cf.write_configfile(outDir_yamlPath, organismDictionary)
+    print(f"{genome} yaml written to {outDir_yamlPath}")
     if "verbose" in config and config["verbose"]:
         print("\n--- index creation workflow finished successfully! --------------------------------\n")
 

snakePipes/workflows/createIndices/createIndices.py

@@ -77,10 +77,6 @@ def parse_args(defaults={"configFile": None, "clusterConfigFile": None,
     optional.add_argument("--rmskURL",
                           help="URL or local path to where the repeat masker output file is located. This is only required if you plan to run the ncRNAseq workflow.")
 
-    optional.add_argument("--userYAML",
-                          action="store_true",
-                          help="By default, this workflow creates an organism YAML file where snakePipes will look for it by default. If this isn't desired (e.g., you don't want the organism to be selectable by default or you don't have write permissions to the snakePipes installation) you can specify this option and the YAML file will instead be created in the location specified by the `-o` option.")
-
     optional.add_argument("--salmonIndexOptions",
                           help="Options to pass to salmon for index creation.",
                           default=defaults["salmonIndexOptions"])