added rules and config parameters for SibeliaZ

config/Zymo/config.yaml

@@ -273,6 +273,11 @@ kaiju:
 mash:
     threads: 10
 
+# Genome comparison: https://github.com/medvedevgroup/SibeliaZ
+sibeliaz:
+    threads: 24
+    kmer: 25
+    mem: 2
 ##############################
 # Binning
 

config/Zymo/sbatch.zymo.sh

@@ -42,6 +42,6 @@ snakemake -s ${ONTP_SMK} -rp --jobs 10 --local-cores 1 \
  --cluster-config ${ONTP_SLURM} --cluster "${ONTP_CLUSTER}" --unlock 
  
 # run the pipeline
-snakemake -s ${ONTP_SMK} -rp --jobs 10 --local-cores 1 \
+snakemake -s ${ONTP_SMK} -rpn --jobs 10 --local-cores 1 \
  --configfile ${ONTP_CONFIG} --use-conda --conda-prefix ${CONDA_PREFIX}/pipeline \
  --cluster-config ${ONTP_SLURM} --cluster "${ONTP_CLUSTER}"

config/Zymo/slurm.zymo.yaml

@@ -40,3 +40,8 @@ zymo_headers:
 
 comparison:
   runtime: "00-00:15:00"
+
+sibeliaz:
+  partition: "batch"
+  quality: "normal"
+  runtime: "00-04:00:00" 

workflow_zymo/Snakefile

@@ -73,8 +73,11 @@ rule all:
             combi=["%s_%s__%s_%s" % (p[0][0], p[0][1], p[1][0], p[1][1]) for p in READ_ASSEMBLER_PAIRS] +
             ["%s_%s__%s_%s" % (p[1][0], p[1][1], p[0][0], p[0][1]) for p in READ_ASSEMBLER_PAIRS]),
         expand(os.path.join(RESULTS_DIR, "analysis/comparison/{rtype_tool}_comparison.txt"), 
-            rtype_tool=["%s_%s" % (rtype, tool) for rtype, tool in READ_ASSEMBLERS])
-
+            rtype_tool=["%s_%s" % (rtype, tool) for rtype, tool in READ_ASSEMBLERS]),
+         expand(os.path.join(RESULTS_DIR, "analysis/sibeliaz/{combi}_output/blocks_coords.gff"),
+            combi=["%s_%s__%s_%s" % (p[0][0], p[0][1], p[1][0], p[1][1]) for p in READ_ASSEMBLER_PAIRS] +
+            ["%s_%s__%s_%s" % (p[1][0], p[1][1], p[0][0], p[0][1]) for p in READ_ASSEMBLER_PAIRS])
+            
 
 rule download_genomes:
     output:
@@ -248,3 +251,30 @@ rule comparison:
         
         # save
         df.to_csv(output[0], sep='\t', header=0)
+
+
+#####################
+# Genome comparison #
+#####################
+rule sibeliaz:
+    input:
+        asm1=os.path.join(DATA_DIR, "assembly/{rtype1}/{tool1}/ASSEMBLY.POLISHED.fasta"),
+        asm2=os.path.join(DATA_DIR, "assembly/{rtype2}/{tool2}/ASSEMBLY.POLISHED.fasta")
+    output:
+        os.path.join(RESULTS_DIR, "analysis/sibeliaz/{rtype1}_{tool1}__{rtype2}_{tool2}_output/blocks_coords.gff")
+    log:
+        out="logs/sibeliaz.{rtype1}.{tool1}.{rtype2}.{tool2}.out.log",
+        err="logs/sibeliaz.{rtype1}.{tool1}.{rtype2}.{tool2}.err.log"
+    wildcard_constraints:
+        rtype1="|".join(READ_TYPES),
+        rtype2="|".join(READ_TYPES),
+        tool1="|".join(ASSEMBLERS),
+        tool2="|".join(ASSEMBLERS)
+    conda:
+        os.path.join(ENV_DIR, "sibeliaz.yaml")
+    message:
+        "Genome comparision: Sibeliaz: {input.asm1} {input.asm2}"        
+    shell:
+       "(date && "
+       "sibeliaz -t config[sibeliaz][threads] -k config[sibeliaz][kmer] -f config[threads][mem] -o $(dirname {output}) {input.asm1} {input.asm2} && "
+       "date) 2> {log.err} > {log.out}"        
\ No newline at end of file