cleanup

cluster.json

@@ -1,12 +1,11 @@
 {
     "__default__" :
     {
-        "name" : "{rule}.{wildcards}",
         "time" : "00:10:00",
         "partition" : "main",
         "cpus-per-task" : 1,
         "mem" : 2000,
-        "output" : "logs/{rule}_{wildcards}_slurm_%j.log"
+        "output" : "logs/slurm/slurm_%j.log"
     },
     "fastp" :
     {

config.yml

@@ -1,9 +1,6 @@
 
 # Global parameters -------------------
 
-# Run virome characterisation (default) or virus discovery workflow (set virome to False)
-virome: True
-
 # Option to save time by not running blastx
 run_blastx: False
 
@@ -23,22 +20,13 @@ virus_nr: "/gpfs/software/VirusSeeker/databases/VirusDBNR_20160802/VirusDBNR_201
 
 # Path to taxonomy database
 vhunter: "/gpfs/software/VirusSeeker/databases/taxdump_300817/vhunter.db"
-names: "/gpfs/software/VirusSeeker/databases/taxdump_300817/names.dmp"
-nodes: "/gpfs/software/VirusSeeker/databases/taxdump_300817/nodes.dmp"
-division: "/gpfs/software/VirusSeeker/databases/taxdump_300817/division.dmp"
-gi_taxid_nucl: "/gpfs/software/VirusSeeker/databases/taxdump_300817/gi_taxid_nucl.dmp"
-gi_taxid_prot: "/gpfs/software/VirusSeeker/databases/taxdump_300817/gi_taxid_prot.dmp"
 
 # Paths to nt and nr blast database to be used for environment variable
 nt: "/gpfs/software/VirusSeeker/databases/nt/nt"
 nr: "/gpfs/software/VirusSeeker/databases/nr/nr"
 
 # Rule parameters ---------------------
 
-# Fastp
-fastp:
-    threads: 4
-
 # fastq-join
 fastq-join:
     maximum_difference: 5

rules/common.smk

@@ -1,19 +1,18 @@
 
 # Load required libraries
-import os.path
+import os
 import json
-from os import listdir
 import glob
 import pandas as pd
+shell.executable("bash")
 
 # Load configuration file with sample and path info
 configfile: "config.yml"
 samples = pd.read_table(config["samples"], sep = "\s+", index_col = "sample", dtype = str)
 sample_ids = samples.index.values.tolist()
 n_files = config["split_fasta"]["n_files"]
 
-# Create logs dir
-import os
-if not os.path.exists("logs"):
-    os.makedirs("logs")
+# Create slurm logs dir
+if not os.path.exists("logs/slurm"):
+    os.makedirs("logs/slurm")
 

rules/refgenomefilter.smk

@@ -47,7 +47,7 @@ rule megablast_refgenome:
       db = config["ref_genome"],
       query = rules.refgenome_unmapped_masked.output
     output:
-      out = "refgenomefilter2/{sample}_megablast_{n}.tsv"
+      out = "refgenomefilter/{sample}_megablast_{n}.tsv"
     params:
       task = "megablast",
       perc_identity = config["megablast_ref_genome"]["perc_identity"],
@@ -68,8 +68,8 @@ rule parse_megablast:
       blast_result = rules.megablast_refgenome.output.out,
       query = rules.refgenome_unmapped_masked.output
     output:
-      mapped = "refgenomefilter2/{sample}_refgenome_filtered_{n}_known-host.tsv",
-      unmapped = "refgenomefilter2/{sample}_refgenome_filtered_{n}_unmapped.fa"
+      mapped = "refgenomefilter/{sample}_refgenome_filtered_{n}_known-host.tsv",
+      unmapped = "refgenomefilter/{sample}_refgenome_filtered_{n}_unmapped.fa"
     params:
       e_cutoff = 1e-10,
       outfmt = rules.megablast_refgenome.params.outfmt