Update raw_inputs system

generate_workflow.py

@@ -98,6 +98,12 @@ def generate_params(pipeline):
         params_info[option["name"]] = collections.OrderedDict()
         params_info[option["name"]]["type"] = option["type"]
 
+    if "input" in pipeline_config:
+        raw_inputs_yaml = read_yaml("./raw_inputs/"+pipeline_config["input"]+".yaml")
+        for option in raw_inputs_yaml["options"]:
+            params_info[option["name"]] = collections.OrderedDict()
+            params_info[option["name"]]["type"] = option["type"]
+
     for step in pipeline_config["steps"]:
         params["params"][step["name"]] = step["default"]
         for tool in step["tools"]:

generate_workflow_snakefile.py

@@ -55,6 +55,7 @@ def generate(name):
         raw_inputs_yaml = read_yaml("./raw_inputs/"+yaml["input"]+".yaml")
         result += "# raw_inputs function call\n"
         result += yaml["input"]+" = "+raw_inputs_yaml["function_call"]+"\n"
+        result += "config.update("+yaml["input"]+")\n"
         result += "SAMPLES = "+yaml["input"]+"['samples']\n"
     #else : # OLD (to replace for all workflows with input raw_reads)
     #    result += "# Generic input functions\n"

raw_inputs/raw_reads.py

@@ -41,10 +41,11 @@ def raw_reads(results_dir, sample_dir, SeOrPe):
             for sample in sorted(samples):
                 sampleTab.write("\n"+sample+"\t"+"\t".join(sorted(dicoSamples[sample])))
 
-        out = {'samples': sorted(samples), 'suffix': suffix, 'dico': dicoSamples}
+        out = {'samples': sorted(samples), 'sample_suffix': suffix, 'dico': dicoSamples}
 
         if SeOrPe == "SE":
             out ["read"] = os.path.join(sample_dir,"{sample}"+suffix)
+            out ["read2"] = ""
         else:
             out ["read"] = os.path.join(sample_dir,"{sample}"+PE_mark+"1"+suffix)
             out ["read2"] = os.path.join(sample_dir,"{sample}"+PE_mark+"2"+suffix)

workflows/Genome_Profile/Genome_Profile.snakefile

@@ -20,6 +20,7 @@ config = config["params"]
 
 # raw_inputs function call
 raw_reads = raw_reads(config['results_dir'], config['sample_dir'], config['SeOrPe'])
+config.update(raw_reads)
 SAMPLES = raw_reads['samples']
 
 # Tools inputs functions

workflows/Long_Read_Assembly/Long_Read_Assembly.snakefile

@@ -20,6 +20,7 @@ config = config["params"]
 
 # raw_inputs function call
 raw_long_reads = raw_long_reads(config['results_dir'], config['sample_dir'])
+config.update(raw_long_reads)
 SAMPLES = raw_long_reads['samples']
 
 # Tools inputs functions

workflows/Metabarcoding/Metabarcoding.snakefile

@@ -20,6 +20,7 @@ config = config["params"]
 
 # raw_inputs function call
 raw_reads = raw_reads(config['results_dir'], config['sample_dir'], config['SeOrPe'])
+config.update(raw_reads)
 SAMPLES = raw_reads['samples']
 
 # Tools inputs functions

workflows/MitoZ/MitoZ.snakefile

@@ -20,6 +20,7 @@ config = config["params"]
 
 # raw_inputs function call
 raw_reads = raw_reads(config['results_dir'], config['sample_dir'], config['SeOrPe'])
+config.update(raw_reads)
 SAMPLES = raw_reads['samples']
 
 # Tools inputs functions

workflows/Mito_Assembler_Megahit/Mito_Assembler_Megahit.snakefile

@@ -20,6 +20,7 @@ config = config["params"]
 
 # raw_inputs function call
 raw_reads = raw_reads(config['results_dir'], config['sample_dir'], config['SeOrPe'])
+config.update(raw_reads)
 SAMPLES = raw_reads['samples']
 
 # Tools inputs functions

workflows/RADseq_denovo/RADseq_denovo.snakefile

@@ -30,6 +30,7 @@ individus = get_individus()
 
 # raw_inputs function call
 raw_reads = raw_reads(config['results_dir'], config['sample_dir'], config['SeOrPe'])
+config.update(raw_reads)
 SAMPLES = raw_reads['samples']
 
 ## get reads (trimmed or raw)

workflows/RADseq_ref/RADseq_ref.snakefile

@@ -30,6 +30,7 @@ individus = get_individus()
 
 # raw_inputs function call
 raw_reads = raw_reads(config['results_dir'], config['sample_dir'], config['SeOrPe'])
+config.update(raw_reads)
 SAMPLES = raw_reads['samples']
 
 ## get reads (trimmed or raw)

workflows/RNAseq/RNAseq.snakefile

@@ -16,6 +16,7 @@ config = config["params"]
 
 # raw_inputs function call
 raw_reads = raw_reads(config['results_dir'], config['sample_dir'], config['SeOrPe'])
+config.update(raw_reads)
 SAMPLES = raw_reads['samples']
 
 ## get reads (trimmed or raw)

workflows/RNAseq_denovo/RNAseq_denovo.snakefile

@@ -7,7 +7,6 @@ import csv
 # Wildcards #
 #############
 
-SAMPLES = config["samples"]
 STEPS = config["steps"]
 PREPARE_REPORT_OUTPUTS = config["prepare_report_outputs"]
 PREPARE_REPORT_SCRIPTS = config["prepare_report_scripts"]
@@ -19,28 +18,15 @@ config = config["params"]
 # Inputs #
 ##########
 
-# Generic input functions
-## get raw_reads
-def raw_reads():
-    inputs = dict()
-    if (config["SeOrPe"] == "PE"):
-        inputs["read"] = config['sample_dir']+'/{sample}_R1'+config["sample_suffix"]
-        inputs["read2"] = config['sample_dir']+'/{sample}_R2'+config["sample_suffix"]
-    elif (config["SeOrPe"] == "SE"):
-        inputs["read"] = config['sample_dir']+'/{sample}'+config["sample_suffix"]
-    else:
-        sys.exit("SeOrPe should be SE or PE")
-    return inputs
-
-## get reads (trimmed or raw)
-def reads():
-    return raw_reads()
-
+# raw_inputs function call
+raw_reads = raw_reads(config['results_dir'], config['sample_dir'], config['SeOrPe'])
+config.update(raw_reads)
+SAMPLES = raw_reads['samples']
 
 # Tools inputs functions
 
 def trimmomatic_inputs():
-    return raw_reads()
+    return raw_reads
 
 def fastqc_inputs():
     inputs = dict()

workflows/RNAseq_denovo/RNAseq_denovo.yaml

@@ -4,6 +4,7 @@
   description: ,
   version: "0.0.1",
   author: "MBB",
+  input: raw_reads,
   steps:
     [
         { title: Trimming, name: trimming, tools: [trimmomatic, "null"], default: "null" },
@@ -22,25 +23,5 @@
         label: "Results directory: ",
         volumes:  [Results: "/Results"]
       },
-      {
-        name: "sample_dir",
-        type: "input_dir",
-        value: "/Data",
-        label: "Data directory: ",
-        volumes:  [Data: "/Data", Results: "/Results"]
-      },
-      #{
-      #  name: "sample_suffix",
-      #  type: "text",
-      #  value: ".fastq.gz",
-      #  label: "Samples suffix: ",
-      #},
-      {
-        name: "SeOrPe",
-        type: "radio",
-        value: "PE",
-        choices: [Single end: SE, Paired end: PE],
-        label: "Single end reads (SE) or Paired end reads (PE): ",
-      },
     ],
 }
\ No newline at end of file

workflows/Variant_calling/Variant_calling.snakefile

@@ -20,6 +20,7 @@ config = config["params"]
 
 # raw_inputs function call
 raw_reads = raw_reads(config['results_dir'], config['sample_dir'], config['SeOrPe'])
+config.update(raw_reads)
 SAMPLES = raw_reads['samples']
 
 # Tools inputs functions

workflows/Virus_Assembler_Megahit/Virus_Assembler_Megahit.snakefile

@@ -20,6 +20,7 @@ config = config["params"]
 
 # raw_inputs function call
 raw_reads = raw_reads(config['results_dir'], config['sample_dir'], config['SeOrPe'])
+config.update(raw_reads)
 SAMPLES = raw_reads['samples']
 
 # Tools inputs functions