Added AMRFinderPlus

config/config.yaml

@@ -14,7 +14,7 @@ input_manager:
 # and script required for the various analysis
 
 analysis_settings:
-    
+
     kmeraligner:
         yaml : ../envs/kmeraligner.yaml
 
@@ -58,7 +58,10 @@ analysis_settings:
         yaml : ../envs/CHtyper.yaml
         script: workflow/scripts/  # Path to CHTyper script directory
 
-
+
+    amrfinder:
+        yaml : ../envs/amrfinder.yaml
+
     # Illumina lineage determination (commented out for now):
     # reference_fasta_file: /home/simonescrima/Desktop/ssi_analysis_utility/resources/lineage_determination/MGAS5005.fasta  # Fasta file for reference genome
     # lineage_variant_file: /home/simonescrima/Desktop/ssi_analysis_utility/resources/lineage_determination/Spyogenes_LOCs.tsv  # File with lineage variants

workflow/Snakefile

@@ -159,6 +159,14 @@ rule all:
             ],
             out=OUT_FOLDER
         ),
+        expand(
+            "{out}/{sample}/amrfinder", 
+            sample=[
+                s for s in SAMPLES 
+                if species_configs[sample_to_organism[s]]["analyses_to_run"]["amrfinder"]["status"] is True
+            ],
+            out=OUT_FOLDER
+        ),
 
 
 

workflow/configs_species/E.coli.yaml

@@ -6,21 +6,21 @@
 analyses_to_run: 
 
     kmeraligner:
-        status : True
+        status : False
         Title : Kmer Aligner on two pair reads
         ID: 90
         additional_option : -matrix 
         database : resources/plasmidfinder_db/enterobacteriales
 
     emm_typing: 
-        status : True
+        status : False
         Title: Typing of M protein gene using blast against CDC curated alleles
         cov_threshold: 90
         emm_allele_file: resources/emm_typing/emm_alleles.fasta  # Fasta file with emm alleles
         emm_cluster_file: resources/emm_typing/emm_enn_mrp_subgroups.txt  # File with emm allele clusters
 
     assembly_lineage_determination: 
-        status : True
+        status : False
         Title: Lineage determination based on presence of specified SNPs when mapping genome assembly against reference genome
         percent_snp_threshold: 50
         nucmerargs : "\"\""
@@ -29,15 +29,15 @@ analyses_to_run:
         lineage_variant_file: resources/lineage_determination/Spyogenes_LOCs.tsv
 
     resistance_gene_detection: 
-        status : True
+        status : False
         Title: Presence of resistance gens tetM, ermA and ermB
         query_fasta_resistance_gene_detection: resources/AMR/AMR_genes.fasta  # Fasta file with AMR genes
         query_fasta_virulence_gene_detection: resources/virulence_factors/VFDB_genes.fasta  # Fasta file with virulence genes
         pident_threshold: 80
         cov_threshold: 80
 
     virulence_gene_detection: 
-        status : True
+        status : False
         Title: Presence of Streptococcal virulence genes from the Virulence Factor Database
 
     plasmidfinder: 
@@ -58,24 +58,24 @@ analyses_to_run:
         database: resources/virulencefinder_db  # VirulenceFinder database
 
     LRE-finder: 
-        status : True
+        status : False
         Title : LRE-Finder
         min_consensus_ID : 80
         additional_option : -1t1 -cge -matrix
         database: resources/lre-finder_db/elm  # Database for LRE-finder
 
     serotypefinder :
-        status : True
+        status : False
         Title : Serotypefinder
         database: resources/serotypefinder_db/  # SerotypeFinder database
 
     kleborate : 
-        status : True
+        status : False
         Title : Kleborate
         preset : kpsc
 
     CHtyper : 
-        status : True
+        status : False
         Title: Chtyper
         threshold : 0.90
         coverage : 0.60
@@ -88,7 +88,14 @@ analyses_to_run:
     #     database: resources/kmerfinder_db/kmerfinder_db_old/bacteria.ATG  # KmerFinder database for bacterial genomes
 
     cgMLSTFinder : 
-        status : True
+        status : False
         Title : cgMLST
         scheme : ecoli # choose between  salmonella,campylobacter,yersinia,clostridium,ecoli
         database: resources/cgmlstfinder_db/  # cgMLSTFinder database
+
+
+    amrfinder:
+        status : True
+        Title : NCBI resistance gene finder
+        database: resources/amrfinderplus/latest
+        organism: --organism Escherichia # Leave blank or insert --organism alongside one of the supported organisms, listed here: https://github.com/evolarjun/amr/wiki/Curated-organisms

workflow/envs/amrfinder.yaml

@@ -0,0 +1,6 @@
+name: AMRFinder
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - ncbi-amrfinderplus

workflow/rules/finders.smk

@@ -201,3 +201,24 @@ rule cgMLSTFinder:
         # Run cgMLSTFinder with the specified inputs, outputs, and scheme.
         python {params.app_path}/cgMLST.py  -i {input.R1},{input.R2} -o {output} -db {params.db_path}  -s {params.scheme}
         """
+
+# Rule: AMRFinder
+# Runs AMRFinder to identify acquired resistance genes in the sample.
+rule AMRFinder:
+    input:
+        assembly = lambda wildcards: sample_to_assembly_file[wildcards.sample],
+    params:
+        # Paths to the databases
+        res_db_path = lambda wildcards: species_configs[sample_to_organism[wildcards.sample]]["analyses_to_run"]["amrfinder"]["database"],
+        # Point mutation
+        organism = lambda wildcards: species_configs[sample_to_organism[wildcards.sample]]["analyses_to_run"]["amrfinder"]["organism"]
+    output:
+        # "{out}/{sample}/amrfinder/{sample}.tsv"
+        directory("{out}/{sample}/amrfinder")
+    conda:
+        config["analysis_settings"]["amrfinder"]["yaml"]
+    shell:
+        """
+        mkdir -p {output}
+        amrfinder --nucleotide {input.assembly} --database {params.res_db_path} {params.organism} --output {output}/{wildcards.sample}.tsv
+        """