update test module

config.yaml

 pathofact:
-  sample: ["test_sample"] # requires user input
-  project: PathoFact_update_trial_new # requires user input
-  datadir: ../test_dataset # requires user input
+  sample: ["SRR2582233","SRR2582234","SRR2582237","SRR2582238","SRR2582241","SRR2582243","SRR2582246","SRR2582247","SRR2582248","SRR2582251","SRR2582252","SRR2582253","SRR2582255","SRR2582257","SRR2582258"] # requires user input
+  project: PathoFact_v2 # requires user input
+  datadir: /work/projects/ecosystem_biology/local_tools/PathoFact_update/Datasets/CDI # requires user input
   workflow: "complete" 
-  size_fasta: 1000
+  size_fasta: 10000
   scripts: "scripts"
   signalp: "/work/projects/ecosystem_biology/local_tools/SignalP/signalp-5.0b/bin" # requires user input
   deepvirfinder: "submodules/DeepVirFinder/dvf.py"

rules/Universal/Annotation.smk

-#Prepare fasta
-
-import glob
-import os
-
-configfile: "config.yaml"
-
-rule all:
-	input: expand("{datadir}/{project}/Prodigal/{sample}.contig", datadir=config["pathofact"]["datadir"], project=config["pathofact"]["project"], sample=config["pathofact"]["sample"])
-
-#     Generate ORFs and GFF
-
-# Generate unique ID number for each sequence
-rule Prodigal:
-    input:
-        "{datadir}/{sample}.fna"
-    output:
-        ORF="{datadir}/{project}/Prodigal/{sample}.faa",
-        GFF="{datadir}/{project}/Prodigal/{sample}.gff"
-    message:
-        "Generates ORFs and gff"
-    params:
-        outdir="{datadir}"
-    conda: 
-        "../../envs/Prodigal.yaml"
-    shell:
-        """
-       prodigal -i {input} -o {output.GFF} -a {output.ORF} -f gff -p meta 
-	"""
-
-rule mapping_file:
-    input:
-        ORF="{datadir}/{project}/Prodigal/{sample}.faa",
-        GFF="{datadir}/{project}/Prodigal/{sample}.gff"
-    output:
-        "{datadir}/{project}/Prodigal/{sample}.contig"
-    message: 
-        "Generate mapping file"
-    params:
-        outdir="{datadir}"
-    shell: 
-        """
-	sed -i 's/[^>]*ID=//;s/;.*//' {input.ORF}
-	sed -i '/^#/d' {input.GFF}
-	cut -f 1,9 {input.GFF} |cut -d';' -f1| sed 's/ID=//' > {output}
-        """
-
-
-
-

rules/Universal/Preprocessing.smk

@@ -91,8 +91,8 @@ checkpoint splitting:
         "{datadir}/{project}/renamed/{sample}_ID.faa"
     output:
         splits=directory("{datadir}/{project}/splitted/{sample}/")
-#    log:
-#        "{datadir}/{project}/splitted/{sample}.log"
+    log:
+        "{datadir}/{project}/splitted/{sample}.log"
     params:
         outdir="{datadir}",
         runtime=config["pathofact"]["runtime"]["short"],

test/README.md

@@ -4,22 +4,11 @@ This is a data set to test the `PathoFact` pipeline.
 
 See `README.md` in parent directory for `PathoFact` set-up instructions.
 
-## Input files
-
-How input files were created:
-
-```bash
-# *.fna, *.faa and *.gff
-rsync -avP /work/projects/ecosystem_biology/local_tools/IMP3/test/testRAW/run150320/Analysis/annotation/prokka.gff test_sample.gff
-rsync -avP /work/projects/ecosystem_biology/local_tools/IMP3/test/testRAW/run150320/Analysis/annotation/prokka.fna test_sample.fna
-rsync -avP /work/projects/ecosystem_biology/local_tools/IMP3/test/testRAW/run150320/Analysis/annotation/prokka.faa test_sample.faa
-
-# set-up: modify files, create other required files
-./set-up.sh
-```
 
 ## Test run
 
+Include the required path to the SingalP v5.0 installation to the config file
+
 ```
 # activate env
 conda activate PathoFact

test/Snakefile

@@ -33,9 +33,9 @@ PF = pathofact(
         [
             "{datadir}/{project}/AMR_MGE_prediction_{sample}_report.tsv",
             "{datadir}/{project}/Toxin_gene_library_{sample}_report.tsv",
-            "{datadir}/{project}/Toxin_prediction_{sample}_report.csv",
-            "{datadir}/{project}/Virulence_prediction_{sample}_report.csv",
-            "{datadir}/{project}/PathoFact_{sample}_predictions.csv"
+            "{datadir}/{project}/Toxin_prediction_{sample}_report.tsv",
+            "{datadir}/{project}/Virulence_prediction_{sample}_report.tsv",
+            "{datadir}/{project}/PathoFact_{sample}_predictions.tsv"
         ],
         datadir=config["pathofact"]["datadir"],
         project=config["pathofact"]["project"],
@@ -48,9 +48,9 @@ CHECKS = expand(
         [
             "{datadir}/{project}/AMR_MGE_prediction_{sample}_report.tsv.checked",
             "{datadir}/{project}/Toxin_gene_library_{sample}_report.tsv.checked",
-            "{datadir}/{project}/Toxin_prediction_{sample}_report.csv.checked",
-            "{datadir}/{project}/Virulence_prediction_{sample}_report.csv.checked",
-            "{datadir}/{project}/PathoFact_{sample}_predictions.csv.checked"
+            "{datadir}/{project}/Toxin_prediction_{sample}_report.tsv.checked",
+            "{datadir}/{project}/Virulence_prediction_{sample}_report.tsv.checked",
+            "{datadir}/{project}/PathoFact_{sample}_predictions.tsv.checked"
         ],
         datadir=config["pathofact"]["datadir"],
         project=config["pathofact"]["project"],

test/set-up.sh

-#!/bin/bash -l
-
-# modify *.faa: rm record descriptions
-sed -i '/^>/ s/ .*//' test_sample.faa
-
-# *.gff to *.contig: contig ID, feature ID
-sed -n '/^##gff/,/^##FASTA/p' test_sample.gff | grep -v '^#' | cut -f1,9 | cut -d';' -f1 | sed 's/ID=//' > test_sample.contig

test/test_config.yaml

@@ -5,8 +5,7 @@ pathofact:
   workflow: "complete"
   size_fasta: 10000
   scripts: "scripts"
-  signalp: "/mnt/irisgpfs/projects/ecosystem_biology/local_tools/SignalP/signalp-4.1/signalp"
-  deeparg: "submodules/deeparg-ss/deepARG.py"
+  signalp: "/work/projects/ecosystem_biology/local_tools/SignalP/signalp-5.0b/bin" # User input
   deepvirfinder: "submodules/DeepVirFinder/dvf.py"
   tox_hmm: "databases/toxins/combined_Toxin.hmm"
   tox_lib: "databases/library_HMM_Toxins.csv"
@@ -24,4 +23,4 @@ pathofact:
     big_mem_per_core_gb: "30G"
 test:
   datadir: "test"
-  project: "output_expected"
\ No newline at end of file
+  project: "output_expected"