refactor: merge prepare, map & quantify workflows

Closes #25 (closed)

• trigger workflows prepare.smk, map.smk and quantify.smk from a single Snakefile
• the separation over three files is conserved; each file is imported in the Snakefile
• use a single config.yaml file to trigger the entire run (preparation, mapping & quantification)

test/config.yaml

@@ -3,12 +3,23 @@
 
 # Directories
 # Usually there is no need to change these
+map_input_dir: "test_files" # For the mapping worflow
+quantify_input_dir: "results" # For the quantify worflow
 output_dir: "results"
 scripts_dir: "../scripts"
 local_log: "logs/local"
 cluster_log: "logs/cluster"
 
-# Isomirs annotation file
+# Inputs information
+sample: ["test_lib"]
+
+#######################################################################################################
+####
+#### PREPARE PARAMETERS
+####
+#######################################################################################################
+
+# Isomirs annotation 
 # Number of base pairs to add/substract from 5' (start) and 3' (end) coordinates.
 bp_5p: [-1, 0, +1]
 bp_3p: [-1, 0, +1]
@@ -30,4 +41,58 @@ homo_sapiens/chrY:
   # Chromosome name mapping parameters:
   column: 1
   delimiter: "TAB"
-...
+
+#######################################################################################################
+####
+#### MAP PARAMETERS
+####
+#######################################################################################################
+
+# Resources: genome, transcriptome, genes, miRs
+# All of these are produced by the "prepare" workflow
+
+genome: "results/homo_sapiens/chrY/genome.processed.fa"
+gtf: "results/homo_sapiens/chrY/gene_annotations.filtered.gtf"
+transcriptome: "results/homo_sapiens/chrY/transcriptome_idtrim.fa"
+transcriptome_index_segemehl: "results/homo_sapiens/chrY/transcriptome_index_segemehl.idx"
+genome_index_segemehl: "results/homo_sapiens/chrY/genome_index_segemehl.idx"
+exons: "results/homo_sapiens/chrY/exons.bed"
+header_of_collapsed_fasta: "results/homo_sapiens/chrY/headerOfCollapsedFasta.sam"
+
+# Tool parameters: quality filter
+q_value: 10
+p_value: 50
+
+# Tool parameters: adapter removal
+error_rate: 0.1
+minimum_length: 15
+overlap: 3
+max_n: 0
+
+# Tool parameters: mapping
+max_length_reads: 30
+nh: 100
+
+
+#### PARAMETERS SPECIFIC TO INPUTS ####
+
+test_lib:
+  adapter: "AACTGTAGGCACCATCAAT"
+  format: "fa"
+
+#######################################################################################################
+####
+#### QUANTIFY PARAMETERS
+####
+#######################################################################################################
+
+
+# Types of miRNAs to quantify
+#mir_list: ["miRNA", "miRNA_primary_transcript", "isomirs"]
+mir_list: ["miRNA", "miRNA_primary_transcript"]
+
+# Resources: miR annotations, chromosome name mappings
+# All of these are produced by the "prepare" workflow
+mirnas_anno: "results/homo_sapiens/chrY/mirna_filtered.bed"
+isomirs_anno: "results/homo_sapiens/chrY/isomirs_annotation.bed"
+...
\ No newline at end of file