added header extraction rules to Snakefile

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

@@ -25,9 +25,9 @@ zymo_prodigal:
 diamond_db:
   partition: "batch"
   quality: "normal"
-  runtime: "00-00:30:00"
+  runtime: "00-00:15:00"
 
 analysis_diamond:
   partition: "batch"
   quality: "normal"
-  runtime: "00-2:00:00"
\ No newline at end of file
+  runtime: "00-00:15:00"

workflow_zymo/Snakefile

@@ -62,7 +62,12 @@ rule all:
         expand(os.path.join(RESULTS_DIR,"annotation/diamond/zymo.dmnd")),
         expand(os.path.join(RESULTS_DIR, "analysis/diamond/{rtype_tool}.{ext}"), 
             rtype_tool=["%s_%s" % (rtype, tool) for rtype, tool in READ_ASSEMBLERS],
-            ext=["daa", "tsv"]) 
+            ext=["daa", "tsv"]),
+        expand(os.path.join(RESULTS_DIR, "analysis/headers/{combi}_headers.txt"),
+            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/headers/{rtype_tool}_zymo_headers.txt"), 
+            rtype_tool=["%s_%s" % (rtype, tool) for rtype, tool in READ_ASSEMBLERS]) 
 
 
 rule download_genomes:
@@ -160,3 +165,37 @@ rule analysis_diamond:
         "diamond blastp -q {input.faa} --db {input.db} --out {output.daa} -p {threads} --outfmt 100 && "
         "diamond view --daa ${{daa%.*}} --max-target-seqs 1 -p {threads} --outfmt {params.outfmt} --out {output.tsv} && "
         "date) &> {log}"
+
+rule get_headers:
+    input:
+        os.path.join(DATA_DIR, "analysis/cdhit/{rtype1}_{tool1}__{rtype2}_{tool2}.faa")
+    output:
+        os.path.join(RESULTS_DIR,"analysis/headers/{rtype1}_{tool1}__{rtype2}_{tool2}_headers.txt")
+    log:
+        out="logs/headers.{rtype1}.{tool1}.{rtype2}.{tool2}.out.log",
+        err="logs/headers.{rtype1}.{tool1}.{rtype2}.{tool2}.err.log"
+    wildcard_constraints:
+        rtype1="|".join(READ_TYPES),
+        rtype2="|".join(READ_TYPES),
+        tool1="|".join(ASSEMBLERS),
+        tool2="|".join(ASSEMBLERS)
+    shell:
+       "(date && "
+       "grep '>' {input} | sed 's/^.*\_\_//' | sed 's/\ .*//' > {output} && "
+       "date) 2> {log.err} > {log.out}"
+
+rule zymo_headers:
+    input:
+        os.path.join(RESULTS_DIR, "analysis/diamond/{rtype}_{tool}.tsv")
+    output:
+        os.path.join(RESULTS_DIR,"analysis/headers/{rtype}_{tool}_zymo_headers.txt")
+    log:
+        out="logs/zymo_headers.{rtype}.{tool}.out.log",
+        err="logs/zymo_headers.{rtype}.{tool}.err.log"
+    wildcard_constraints:
+        rtype="|".join(READ_TYPES),
+        tool="|".join(ASSEMBLERS)
+    shell:
+       "(date && "
+       "awk '{{print $1}}' {input} > {output} && "
+       "date) 2> {log.err} > {log.out}"
\ No newline at end of file

workflow_zymo/envs/diamond.yaml

@@ -3,37 +3,37 @@ channels:
   - bioconda
   - defaults
 dependencies:
-  - _libgcc_mutex=0.1=conda_forge
-  - _openmp_mutex=4.5=1_llvm
-  - boost=1.70.0=py38h9de70de_1
-  - boost-cpp=1.70.0=h7b93d67_3
-  - bzip2=1.0.8=h516909a_2
-  - ca-certificates=2020.6.20=hecda079_0
-  - certifi=2020.6.20=py38h32f6830_0
-  - diamond=0.9.25=hfb76ee0_0
-  - icu=67.1=he1b5a44_0
-  - ld_impl_linux-64=2.34=h53a641e_5
-  - libblas=3.8.0=16_openblas
-  - libcblas=3.8.0=16_openblas
-  - libffi=3.2.1=he1b5a44_1007
-  - libgcc-ng=9.2.0=h24d8f2e_2
-  - libgfortran-ng=7.5.0=hdf63c60_6
-  - liblapack=3.8.0=16_openblas
-  - libopenblas=0.3.9=h5ec1e0e_0
-  - libstdcxx-ng=9.2.0=hdf63c60_2
-  - llvm-openmp=10.0.0=hc9558a2_0
-  - lz4-c=1.9.2=he1b5a44_1
-  - ncurses=6.1=hf484d3e_1002
-  - numpy=1.18.5=py38h8854b6b_0
-  - openssl=1.1.1g=h516909a_0
-  - pip=20.1.1=py_1
-  - python=3.8.3=cpython_he5300dc_0
-  - python_abi=3.8=1_cp38
-  - readline=8.0=hf8c457e_0
-  - setuptools=47.3.1=py38h32f6830_0
-  - sqlite=3.30.1=hcee41ef_0
-  - tk=8.6.10=hed695b0_0
-  - wheel=0.34.2=py_1
-  - xz=5.2.5=h516909a_0
-  - zlib=1.2.11=h516909a_1006
-  - zstd=1.4.4=h6597ccf_3
+  - _libgcc_mutex=0.1
+  - _openmp_mutex=4.5
+  - boost=1.70.0
+  - boost-cpp=1.70.0
+  - bzip2=1.0.8
+  - ca-certificates=2020.6.20
+  - certifi=2020.6.20
+  - diamond=0.9.25
+  - icu=67.1
+  - ld_impl_linux-64=2.34
+  - libblas=3.8.0
+  - libcblas=3.8.0
+  - libffi=3.2.1
+  - libgcc-ng=9.2.0
+  - libgfortran-ng=7.5.0
+  - liblapack=3.8.0
+  - libopenblas=0.3.9
+  - libstdcxx-ng=9.2.0
+  - llvm-openmp=10.0.0
+  - lz4-c=1.9.2
+  - ncurses=6.1
+  - numpy=1.18.5
+  - openssl=1.1.1g
+  - pip=20.1.1
+  - python=3.8.3
+  - python_abi=3.8
+  - readline=8.0
+  - setuptools=47.3.1
+  - sqlite=3.30.1
+  - tk=8.6.10
+  - wheel=0.34.2
+  - xz=5.2.5
+  - zlib=1.2.11
+  - zstd=1.4.4