add check for reference files

workflow/modules/1-define.smk

@@ -1,9 +1,10 @@
 import pandas as pd
 from pathlib import Path
 import os
+import sys
 from snakemake.utils import validate
 
-# load and validate config 
+# Load and validate config 
 configfile: "inputs/config/config.yaml"
 config_schema = "../schema/config.schema.yaml"
 validate(config, config_schema)
@@ -13,13 +14,12 @@ common_config = config["common"]
 pipeline_config = config["pipeline"]
 deseq_config = config["DESeq2"]
 
-# Set up input directories
+# Set up input directories and files
 main_dir = common_config["projectdir"]
 if main_dir is None:
     main_dir = os.getcwd()
 main_dir = Path(main_dir)
 
-
 genome_dir = Path(pipeline_config["genomedir"])
 num_threads = pipeline_config["threads"]
 
@@ -40,6 +40,33 @@ sample_id_col = pipeline_config["sample_id"]
 SAMPLES = pd.read_table(metadata_file)[sample_id_col].tolist()
 print("samples: " + str(SAMPLES))
 
+
+# Check existence of reference files, break if not there
+genome_filename = pipeline_config["genome_filename"]
+annotation_filename = pipeline_config["annotation_filename"]
+
+genome_filepath = genome_dir / genome_filename
+annotation_filepath = genome_dir / annotation_filename
+
+check_ref_fasta = os.path.exists(genome_filepath)
+
+if check_ref_fasta == False:
+    sys.exit(f"Error! You are missing the expected reference genome file: {genome_filepath}")
+
+check_ref_genome = os.path.exists(annotation_filepath)
+
+if check_ref_genome == False:
+    sys.exit(f"Error! You are missing the expected reference annotation file: {annotation_filepath}")
+
+if common_config["platform"] =="TempO-Seq":
+    biospyder_filepath = common_config["biospyder_dbs"] + common_config["biospyder_manifest_file"]
+
+    check_manifest = os.path.exists(biospyder_filepath)
+
+    if check_manifest == False:
+        sys.exit(f"Error! You are missing the expected biospyder manifest file: {biospyder_filepath}")
+
+
 # Set up output directories
 
 output_dir = main_dir / "output"