sorted sample files to avoid random output

bin/Quantification_clusters.py

@@ -145,7 +145,7 @@ print(str(datetime.now()))
 # For each count file (output of featureCounts), reading of lines one by one,
 # recovery of name of gene and count number and incrementing of corresponding
 # value in d_count_by_g_clstr.
-for (count_idx,counts_path) in enumerate(files_of_counts):
+for (count_idx,counts_path) in enumerate(sorted(files_of_counts)):
     with open(counts_path) as fh:
         for f_gene_counts in fh:
             if f_gene_counts.startswith('#') \

bin/merge_abundance_and_functional_annotations.py

@@ -80,7 +80,7 @@ with open(args.list_of_file_diamond) as fdiamond_list:
 concat_eggnog_mapper_files = pd.DataFrame()
 
 # Concatenate annotation files.
-for (annotations_idx,annotations_path) in enumerate(files_of_annotations):
+for (annotations_idx,annotations_path) in enumerate(sorted(files_of_annotations)):
     eggnog_mapper_file = pd.read_csv(annotations_path, delimiter='\t', decimal='.',skiprows=4)
     concat_eggnog_mapper_files = pd.concat([concat_eggnog_mapper_files, eggnog_mapper_file])
 
@@ -88,7 +88,7 @@ for (annotations_idx,annotations_path) in enumerate(files_of_annotations):
 concat_diamond_files = pd.DataFrame()
 
 # Concatenate diamond files.
-for (diamond_idx,diamond_path) in enumerate(diamond_files):
+for (diamond_idx,diamond_path) in enumerate(sorted(diamond_files)):
     diamond_columns = ["qseqid","sseqid","pident","length","mismatch","gapopen","qstart","qend","sstart","send","evalue","bitscore","qlen","slen","stitle"]
     diamond_file = pd.read_csv(diamond_path, delimiter='\t', decimal='.', header=None, names=diamond_columns)
     diamond_file.loc[:,"sseqid"] = 'https://www.ncbi.nlm.nih.gov/protein/' + diamond_file.loc[:,"sseqid"]