diff --git a/2019_GDB/config/CONFIG.yaml b/2019_GDB/config/CONFIG.yaml index bb91d499ca7c05359f0144ca6b02e0be38e133dd..aab8911bf4efe9daef1f357fbf111082335ffbd0 100755 --- a/2019_GDB/config/CONFIG.yaml +++ b/2019_GDB/config/CONFIG.yaml @@ -1,5 +1,5 @@ # steps: "assembly_annotation mapping metaT mmseq binning taxonomy analysis" -steps: "binning taxonomy" +steps: "binning taxonomy analysis" data_dir: "data" results_dir: "results" db_dir: "dbs" @@ -91,7 +91,8 @@ rebaler: threads: 28 diamond: threads: 28 - db: "/mnt/isilon/projects/ecosystem_biology/NOMIS/DIAMOND/new_nr.dmnd" + #db: "/mnt/isilon/projects/ecosystem_biology/NOMIS/DIAMOND/new_nr.dmnd" + db: "/work/projects/ecosystem_biology/local_tools/databases/nr_uniprot_trembl.dmnd" metaspades: threads: 28 mmseq2: @@ -151,3 +152,11 @@ mmseqs: createdb: "/home/users/sbusi/apps/mmseqs/bin/mmseqs createdb" rbh: "/home/users/sbusi/apps/mmseqs/bin/mmseqs rbh" convertalis: "/home/users/sbusi/apps/mmseqs/bin/mmseqs convertalis" + +# Paths to CASC and minced for CRISPR +CASC: + PATH: "$PATH:/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/bin" + PERL5LIB: "/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/lib/site_perl" + +minced: + PATH: "$PATH:/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/minced/" diff --git a/2019_GDB/rules/ANALYSIS_RULES b/2019_GDB/rules/ANALYSIS_RULES index 8ad82ef0ec23162c56e5029ee6332d2803b556ed..da245790fdb6bfb0150950c8d993bd6ef8704eef 100755 --- a/2019_GDB/rules/ANALYSIS_RULES +++ b/2019_GDB/rules/ANALYSIS_RULES @@ -165,11 +165,12 @@ rule casc: shell: """ (date &&\ - export PATH=$PATH:/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/bin &&\ - export PERL5LIB=/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/lib/site_perl + export PATH={config[CASC][PATH]} &&\ + export PERL5LIB={config[CASC][PERL5LIB]} &&\ casc -i {input} -o $(dirname {output.cas1}) -n 12 --conservative &&\ echo $(basename -s ".results.txt" {output.cas1}) >> {output.cas2} &&\ - awk '$8 == "true" {{sum += $2}} END {{print sum}}' {output.cas1} >> {output.cas2} &&\ +# awk '$8 == "true" {{sum += $2}} END {{print sum}}' {output.cas1} >> {output.cas2} &&\ + cat {output.cas1}) | awk '$8 == "true" {{sum += $2}} END {{print sum}}' >> {output.cas2} &&\ date) &> >(tee {log}) """ @@ -184,7 +185,7 @@ rule minced: shell: """ (date &&\ - export PATH=$PATH:/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/minced/ &&\ + export PATH={config[minced][PATH]} &&\ minced {input} {output.mn1} {output.mn2} &&\ echo $(basename -s ".txt" {output.mn1}) >> minced_CRISPR_output.txt &&\ grep -c 'CRISPR' {output.mn1} >> minced_CRISPR_output.txt &&\ diff --git a/config/CONFIG.yaml b/config/CONFIG.yaml index bb91d499ca7c05359f0144ca6b02e0be38e133dd..aab8911bf4efe9daef1f357fbf111082335ffbd0 100755 --- a/config/CONFIG.yaml +++ b/config/CONFIG.yaml @@ -1,5 +1,5 @@ # steps: "assembly_annotation mapping metaT mmseq binning taxonomy analysis" -steps: "binning taxonomy" +steps: "binning taxonomy analysis" data_dir: "data" results_dir: "results" db_dir: "dbs" @@ -91,7 +91,8 @@ rebaler: threads: 28 diamond: threads: 28 - db: "/mnt/isilon/projects/ecosystem_biology/NOMIS/DIAMOND/new_nr.dmnd" + #db: "/mnt/isilon/projects/ecosystem_biology/NOMIS/DIAMOND/new_nr.dmnd" + db: "/work/projects/ecosystem_biology/local_tools/databases/nr_uniprot_trembl.dmnd" metaspades: threads: 28 mmseq2: @@ -151,3 +152,11 @@ mmseqs: createdb: "/home/users/sbusi/apps/mmseqs/bin/mmseqs createdb" rbh: "/home/users/sbusi/apps/mmseqs/bin/mmseqs rbh" convertalis: "/home/users/sbusi/apps/mmseqs/bin/mmseqs convertalis" + +# Paths to CASC and minced for CRISPR +CASC: + PATH: "$PATH:/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/bin" + PERL5LIB: "/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/lib/site_perl" + +minced: + PATH: "$PATH:/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/minced/" diff --git a/rules/ANALYSIS_RULES b/rules/ANALYSIS_RULES index 8ad82ef0ec23162c56e5029ee6332d2803b556ed..da245790fdb6bfb0150950c8d993bd6ef8704eef 100755 --- a/rules/ANALYSIS_RULES +++ b/rules/ANALYSIS_RULES @@ -165,11 +165,12 @@ rule casc: shell: """ (date &&\ - export PATH=$PATH:/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/bin &&\ - export PERL5LIB=/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/lib/site_perl + export PATH={config[CASC][PATH]} &&\ + export PERL5LIB={config[CASC][PERL5LIB]} &&\ casc -i {input} -o $(dirname {output.cas1}) -n 12 --conservative &&\ echo $(basename -s ".results.txt" {output.cas1}) >> {output.cas2} &&\ - awk '$8 == "true" {{sum += $2}} END {{print sum}}' {output.cas1} >> {output.cas2} &&\ +# awk '$8 == "true" {{sum += $2}} END {{print sum}}' {output.cas1} >> {output.cas2} &&\ + cat {output.cas1}) | awk '$8 == "true" {{sum += $2}} END {{print sum}}' >> {output.cas2} &&\ date) &> >(tee {log}) """ @@ -184,7 +185,7 @@ rule minced: shell: """ (date &&\ - export PATH=$PATH:/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/minced/ &&\ + export PATH={config[minced][PATH]} &&\ minced {input} {output.mn1} {output.mn2} &&\ echo $(basename -s ".txt" {output.mn1}) >> minced_CRISPR_output.txt &&\ grep -c 'CRISPR' {output.mn1} >> minced_CRISPR_output.txt &&\