Subsample reads, so that crossmathc doesn't choke

src/rules/fastqProcessors/Seqtk.rules

+"""
+@version: 0.1
+
+Use seqtk toolkit
+
+Required programs:
+* seqtk (bioconda)
+
+"""
+
+import os, subprocess
+import configparser
+
+__author__ = "Jan van Haarst"
+__email__ = "jan.vanhaarst@wur.nl"
+
+
+rule seqtk_sample:
+    input: "{name}.fasta"
+    params:        
+        number = CONFIG["seqtk"]["options"]["number"],
+        seed = CONFIG["seqtk"]["options"]["seed"]
+    output: "{name}.sampled.fasta"
+    shell:
+        """
+        seqtk sample -s{params.seed} {input} {params.number} > {output}
+        """     

src/workflows/repeats/reas/Snakefile

@@ -50,6 +50,9 @@ workdir:  CONFIG["base"]["working_dir"]
 # Include necessary rules
 include: ruleDir + "/repeats/reas.rules"
 include: ruleDir + "/fastqProcessors/Sra.rules"
+include: ruleDir + "/fastqProcessors/Seqtk.rules"
+
+os.mkdir(strip_path_level(CONFIG['executables']['reas'],1))
 
 rule all:
     input:

src/workflows/repeats/reas/config.json

@@ -48,6 +48,12 @@
             "seg_file" : "seg.fa"
             }
 	},
+	"seqtk":{
+		"options":{
+			"number" : "1000000",
+			"seed"	 : "314159"
+		}
+	},
 	"sra": 
 	{
 		"sra_download" :{
@@ -57,5 +63,5 @@
 			"options" : "--split-files --fasta"
 		}
 	},
-	"reads" : "{download_dir}sra/ERR171441_1.fasta"
+	"reads" : "{download_dir}sra/ERR171441_1.sampled.fasta"
 }