v.0.1.14 changed runtime in rules to seconds in order to run on SLURM

maginator/workflow/alignment.Snakefile

@@ -24,7 +24,7 @@ rule align:
     resources:
         cores=1,
         memory=4,
-        runtime='10:00:00'
+        runtime='36000' #10h in s
     shell:
         """
         mkdir -p {output}
@@ -42,7 +42,7 @@ rule concat:
     resources:
         cores=10,
         memory=40,
-        runtime='10:00:00'
+        runtime='36000' #10h in s
     params:
         ali_dir=os.path.join(WD, 'phylo', 'alignments')
     script:

maginator/workflow/filter.Snakefile

@@ -22,7 +22,7 @@ mem = math.ceil(n_contigs/1000000)*30
 if mem > int(param_dict['max_mem']):
     mem = int(param_dict['max_mem'])
 ## time is 1 hour per million
-tim = str(math.ceil(n_contigs/1000000))*60*60 # runtime in seconds
+tim = str(math.ceil(n_contigs/1000000)*60*60) # runtime in seconds
 
 rule all:
     input:

maginator/workflow/filter_geneclusters.Snakefile

@@ -37,7 +37,7 @@ rule nonredundant_catalogue:
     resources:
         cores = 1,
         memory = 50,
-        runtime = '12:00:00'
+        runtime = '43200' #12h in s
     shell:
         "perl -ne 'if(/^>(\S+)/){{$c=$i{{$1}}}}$c?print:chomp;$i{{$_}}=1 if @ARGV' <(cut -f1 {input.clusters} | uniq) {input.genecat} | awk '{{print $1}}' > {output}"
 
@@ -52,7 +52,7 @@ rule bwa_index:
     resources:
         cores = 40,
         memory = 188, 
-        runtime = '1:00:00:00'
+        runtime = '86400' #1d in s
     shell:
         "bwa-mem2 index -p {output.index} {input.fasta}; samtools faidx {input.fasta}; touch {output.index}"
 
@@ -72,6 +72,6 @@ rule bwa_readmap:
     resources:
         cores = 40,
         memory = 188,
-        runtime = '1:00:00:00'
+        runtime = '86400' #1d in s
     shell:
         "bwa-mem2 mem -t {resources.cores} {input.index} {input.fastq1} {input.fastq2} | samtools view -T {input.fasta} -F 3584  -b --threads {resources.cores} | samtools sort --threads {resources.cores} > {output.bam}; samtools index {output.bam}"

maginator/workflow/gene_count_mat.Snakefile

@@ -27,7 +27,7 @@ rule count_genes:
     resources:
         cores = 1,
         memory = 20,
-        runtime = '2:00:00'
+        runtime = '7200' #2h in s
     shell:
         "samtools idxstats {input} | cut -f3 > {output.readcounts}"
 
@@ -44,7 +44,7 @@ rule gene_names:
     resources:
         cores = 1,
         memory = 20,
-        runtime = '1:00:00'
+        runtime = '3600' #1h in s
     shell:
         "samtools idxstats {input} | cut -f1 > {output}"
 
@@ -58,7 +58,7 @@ rule create_header:
     resources:
         cores = 1,
         memory = 188,
-        runtime = '1:00:00'
+        runtime = '3600' #1h in s
     run:
         header = "Gene"
         for f in input:
@@ -82,6 +82,6 @@ rule gene_count_matrix:
     resources:
         cores = 1,
         memory = 188,
-        runtime = '1:00:00'
+        runtime = '3600' #1h in s
     shell:
         "paste {input.gene_names} {input.readcounts} | cat {input.header} - > {output}; sed -i '$d' {output}"

maginator/workflow/gene_tax.Snakefile

@@ -31,7 +31,7 @@ rule gene_tax:
     resources:
         cores = 1,
         memory = 80,
-        runtime = '02:00:00'
+        runtime = '7200' #2h in s
     script:
         "scripts/gene_cluster2tax.py"
 
@@ -47,7 +47,7 @@ rule synteny_graph:
     resources:
         cores = 1,
         memory = 40,
-        runtime = '10:00:00'
+        runtime = '36000' #10h in s
     script:
         "scripts/synteny.py"
 
@@ -67,7 +67,7 @@ rule synteny_mcl:
     resources:
         cores = 40,
         memory = 180,
-        runtime = '24:00:00'
+        runtime = '86400' #1d in s
     shell:
         """
         join -1 2 -2 1 <(join -j1 <(sed 's/.*(//;s/)//;s/,//;s/\.0$//' {input.graph} | sort -k1,1) <(sort -k1,1 {input.index}) | sort -k2,2) <(sort -k1,1 {input.index}) \

maginator/workflow/gtdbtk.Snakefile

@@ -19,7 +19,7 @@ CLUSTERS = {x for x in CLUSTERS if x.isdigit()}
 out = subprocess.Popen(['wc', '-l', READS], stdout=subprocess.PIPE, stderr=subprocess.STDOUT).communicate()[0]
 n_samples = int(out.partition(b' ')[0])
 ## time is 1 hour per 30 samples
-tim = str(math.ceil(n_samples/30))+':00:00'
+tim = str(math.ceil(n_samples/30)*60*60) # time in seconds
 
 wildcard_constraints:
     cluster="\d+"

maginator/workflow/outgroup.Snakefile

@@ -32,7 +32,7 @@ rule markers:
     resources:
         cores=1,
         memory=10,
-        runtime='10:00:00'
+        runtime='36000' #10h in s
     script:
         "scripts/marker_genes.py"
 
@@ -47,7 +47,7 @@ rule fasta1:
     resources:
         cores=1,
         memory=10,
-        runtime='10:00:00'
+        runtime='36000' #10h in s
     shell:
         "perl -ne 'if(/^>(\S+)/){{$c=$i{{$1}}}}$c?print:chomp;$i{{$_}}=1 if @ARGV' <(cut -f4 {input.tab} | sort | uniq) {input.fasta} > {output}"
 
@@ -62,7 +62,7 @@ rule fasta2:
     resources:
         cores=1,
         memory=10,
-        runtime='10:00:00'
+        runtime='36000' #10h in s
     shell:
         "perl -ne 'if(/^>(\S+)/){{$c=$i{{$1}}}}$c?print:chomp;$i{{$_}}=1 if @ARGV' <(cut -f5 {input.tab} | sort | uniq) {input.fasta} > {output}"
 
@@ -77,7 +77,7 @@ rule fasta3:
     resources:
         cores=1,
         memory=10,
-        runtime='10:00:00'
+        runtime='36000' #10h in s
     shell:
         "perl -ne 'if(/^>(\S+)/){{$c=$i{{$1}}}}$c?print:chomp;$i{{$_}}=1 if @ARGV' <(cut -f1 {input.tab}) {input.fasta} > {output}"
 
@@ -93,7 +93,7 @@ rule bed:
     resources:
         cores=1,
         memory=10,
-        runtime='10:00:00'
+        runtime='36000' #10h in s
     shell:
         """
         awk '{{print $1"\t0\t1000000"}}' {input.sig} > {output.beds}
@@ -114,7 +114,7 @@ rule uniq:
     resources:
         cores=1,
         memory=10,
-        runtime='10:00:00'
+        runtime='36000' #10h in s
     shell:
         """
         cat {input.beds} {input.bedm} | sort | uniq > {output.bed}
@@ -131,9 +131,8 @@ rule index:
     resources:
         cores=1,
         memory=10,
-        runtime='10:00:00'
+        runtime='36000' #10h in s
     shell:
         """
         samtools faidx {input}
         """
-

maginator/workflow/parse_gtdbtk.Snakefile

@@ -35,7 +35,7 @@ rule parse_gtdbtk:
     resources:
         cores=1,
         memory=32,
-        runtime='10:00:00'
+        runtime='36000' #10h in s
     script:
         "scripts/parse_gtdbtk.py"
 
@@ -55,7 +55,7 @@ rule repres_genes:
     resources:
         cores = 14,
         memory = 50,
-        runtime = '2:00:00:00' 
+        runtime = '172800' #2d in s 
     params:
         tmp_dir = os.path.join(WD, 'tmp'),
         out_prefix = os.path.join(WD, 'genes', 'all_genes'),
@@ -77,7 +77,7 @@ rule join:
     resources:
         cores = 1,
         memory = 20,
-        runtime = '24:00:00'
+        runtime = '86400' #1d in s
     shell:
         "join -1 1 -2 2 <(sort -k1,1 {input.gtdb}) <(sort -k2,2 {input.cluster}) > {output}"
 
@@ -90,6 +90,6 @@ rule collect:
     resources:
         cores = 1,
         memory = 20,
-        runtime = '24:00:00'
+        runtime = '86400' #1d in s
     shell:
         "for i in {input}/*/*summary.tsv; do tail -n+2 $i; done | cut -f1,2 > {output}"

maginator/workflow/phylo.Snakefile

@@ -25,7 +25,7 @@ if param_dict['phylo'] == 'fasttree':
         resources:
             cores=1,
             memory=32,
-            runtime='12:00:00'
+            runtime='43200' #12h in s
         shell:
             """
             fasttree -nt {input} > {output}
@@ -46,7 +46,7 @@ if param_dict['phylo'] == 'iqtree':
         resources:
             cores=40,
             memory=180,
-            runtime='02:00:00:00'
+            runtime='172800' #2d in s
         shell:
             """
             iqtree -T {resources.cores} -s {input.fna} -p {input.part} -o Outgroup --prefix {params.prefix} || true && if [ -f {params.prefix}.treefile ]; then mv {params.prefix}.treefile {output}; else touch {output}; fi

maginator/workflow/pileup.Snakefile

@@ -25,7 +25,7 @@ rule subset:
     resources:
         cores = 1,
         memory = 20,
-        runtime = '12:00:00'
+        runtime = '43200' #12h in s
     shell:
         "samtools view -b -L {input.bed} {input.bam} | samtools sort -o {output}"
 
@@ -40,7 +40,7 @@ rule pileup:
     resources:
         cores = 1,
         memory = 20,
-        runtime = '24:00:00'
+        runtime = '86400' #1d in s
     shell:
         "samtools mpileup -A -x -f {input.fna} {input.bam} -o {output}"
 

maginator/workflow/pileup_parse.Snakefile

@@ -38,7 +38,7 @@ rule parse:
     resources:
         cores = 40,
         memory = 180,
-        runtime = '02:00:00:00'
+        runtime = '172800' #2d in s
     script:
         "scripts/mpileup.py"
 

maginator/workflow/prescreening_genes.Snakefile

@@ -35,7 +35,7 @@ rule geneID_collectionID:
     resources:
         cores = 1,
         memory = 188,
-        runtime = '12:00:00'
+        runtime = '43200' #12h in s
     script: 
         "scripts/species_collections.py"
 
@@ -51,7 +51,7 @@ rule sort_genes_across_MGS:
     resources:
         cores = 1, 
         memory = 188,
-        runtime = '12:00:00'
+        runtime = '43200' #12h in s
     script:
         "scripts/sort_gene_mat.py"
 
@@ -71,7 +71,7 @@ rule format_conversion:
     resources:
         cores = 1,
         memory = 188,
-        runtime = '24:00:00'
+        runtime = '86400' #1d in s
     script:
         "scripts/matrix2SG_formatconversion.R"
 
@@ -88,6 +88,6 @@ rule prescreening_genes:
     resources:
         cores = 1,
         memory = 188,
-        runtime = '24:00:00'
+        runtime = '86400' #1d in s
     script: 
         "scripts/prescreening_genes.R"