Several fixes on MP workflow

Fix on inputting mods to generate_parameters_file

workflow/envs/metaproteomics.yaml

@@ -5,146 +5,16 @@ channels:
   - anaconda
   - defaults
 dependencies:
-  - _libgcc_mutex=0.1=conda_forge
-  - _openmp_mutex=4.5=2_gnu
-  - alsa-lib=1.2.8=h166bdaf_0
-  - blast=2.2.31=pl526he19e7b1_5
-  - bzip2=1.0.8=h7f98852_4
-  - c-ares=1.18.1=h7f98852_0
-  - ca-certificates=2022.12.7=ha878542_0
-  - cairo=1.16.0=ha61ee94_1014
-  - certifi=2022.12.7=pyhd8ed1ab_0
-  - charset-normalizer=2.1.1=pyhd8ed1ab_0
-  - colorama=0.4.6=pyhd8ed1ab_0
-  - curl=7.87.0=hdc1c0ab_0
-  - dotnet-runtime=3.1.18=h73ebe80_0
-  - entrez-direct=16.2=he881be0_1
-  - expat=2.5.0=h27087fc_0
-  - font-ttf-dejavu-sans-mono=2.37=hab24e00_0
-  - font-ttf-inconsolata=3.000=h77eed37_0
-  - font-ttf-source-code-pro=2.038=h77eed37_0
-  - font-ttf-ubuntu=0.83=hab24e00_0
-  - fontconfig=2.14.1=hc2a2eb6_0
-  - fonts-conda-ecosystem=1=0
-  - fonts-conda-forge=1=0
-  - freetype=2.12.1=hca18f0e_1
-  - gettext=0.21.1=h27087fc_0
-  - giflib=5.2.1=h36c2ea0_2
-  - graphite2=1.3.13=h58526e2_1001
-  - harfbuzz=6.0.0=h8e241bc_0
-  - icu=70.1=h27087fc_0
-  - idna=3.4=pyhd8ed1ab_0
-  - jpeg=9e=h166bdaf_2
-  - keyutils=1.6.1=h166bdaf_0
-  - krb5=1.20.1=h81ceb04_0
-  - lcms2=2.14=hfd0df8a_1
-  - ld_impl_linux-64=2.39=hcc3a1bd_1
-  - lerc=4.0.0=h27087fc_0
-  - libblas=3.9.0=16_linux64_openblas
-  - libcblas=3.9.0=16_linux64_openblas
-  - libcups=2.3.3=h36d4200_3
-  - libcurl=7.87.0=hdc1c0ab_0
-  - libdeflate=1.14=h166bdaf_0
-  - libedit=3.1.20191231=he28a2e2_2
-  - libev=4.33=h516909a_1
-  - libffi=3.4.2=h7f98852_5
-  - libgcc-ng=12.2.0=h65d4601_19
-  - libgfortran-ng=12.2.0=h69a702a_19
-  - libgfortran5=12.2.0=h337968e_19
-  - libglib=2.74.1=h606061b_1
-  - libgomp=12.2.0=h65d4601_19
-  - libiconv=1.17=h166bdaf_0
-  - libidn2=2.3.4=h166bdaf_0
-  - liblapack=3.9.0=16_linux64_openblas
-  - libnghttp2=1.47.0=hff17c54_1
-  - libnsl=2.0.0=h7f98852_0
-  - libopenblas=0.3.21=pthreads_h78a6416_3
-  - libpng=1.6.39=h753d276_0
-  - libsqlite=3.40.0=h753d276_0
-  - libssh2=1.10.0=hf14f497_3
-  - libstdcxx-ng=12.2.0=h46fd767_19
-  - libtiff=4.5.0=h82bc61c_0
-  - libunistring=0.9.10=h7f98852_0
-  - liburcu=0.13.2=h166bdaf_0
-  - libuuid=2.32.1=h7f98852_1000
-  - libwebp-base=1.2.4=h166bdaf_0
-  - libxcb=1.13=h7f98852_1004
-  - libzlib=1.2.13=h166bdaf_4
-  - lttng-ust=2.13.4=hfdfcbd3_0
-  - metamorpheus=0.0.317=h7f98852_2
-  - mono=6.12.0.90=h780b84a_0
-  - ncurses=6.3=h27087fc_1
-  - openjdk=17.0.3=h58dac75_5
-  - openssl=3.0.7=h0b41bf4_1
-  - pcre=8.45=h9c3ff4c_0
-  - pcre2=10.40=hc3806b6_0
-  - peptide-shaker=2.2.6=hec16e2b_1
+  - curl
+  - peptide-shaker=2
   - perl=5.26.2=h36c2ea0_1008
-  - perl-archive-tar=2.32=pl526_0
-  - perl-carp=1.38=pl526_3
-  - perl-common-sense=3.74=pl526_2
-  - perl-compress-raw-bzip2=2.087=pl526he1b5a44_0
-  - perl-compress-raw-zlib=2.087=pl526hc9558a2_0
-  - perl-exporter=5.72=pl526_1
-  - perl-exporter-tiny=1.002001=pl526_0
-  - perl-extutils-makemaker=7.36=pl526_1
-  - perl-io-compress=2.087=pl526he1b5a44_0
-  - perl-io-zlib=1.10=pl526_2
-  - perl-json=4.02=pl526_0
-  - perl-json-xs=2.34=pl526h6bb024c_3
-  - perl-list-moreutils=0.428=pl526_1
-  - perl-list-moreutils-xs=0.428=pl526_0
-  - perl-pathtools=3.75=pl526h14c3975_1
-  - perl-scalar-list-utils=1.52=pl526h516909a_0
-  - perl-types-serialiser=1.0=pl526_2
-  - perl-xsloader=0.24=pl526_0
-  - pip=22.3.1=pyhd8ed1ab_0
-  - pixman=0.40.0=h36c2ea0_0
-  - pthread-stubs=0.4=h36c2ea0_1001
-  - pycparser=2.21=pyhd8ed1ab_0
-  - pyopenssl=22.1.0=pyhd8ed1ab_0
-  - pysocks=1.7.1=pyha2e5f31_6
-  - python=3.11.0=ha86cf86_0_cpython
-  - python-dateutil=2.8.2=pyhd8ed1ab_0
-  - python_abi=3.11=3_cp311
-  - pytz=2022.7=pyhd8ed1ab_0
-  - readline=8.1.2=h0f457ee_0
-  - requests=2.28.1=pyhd8ed1ab_1
-  - searchgui=4.0.41=h779adbc_1
-  - seqkit=2.3.1=h9ee0642_0
-  - setuptools=65.6.3=pyhd8ed1ab_0
-  - six=1.16.0=pyh6c4a22f_0
-  - tk=8.6.12=h27826a3_0
-  - tqdm=4.64.1=pyhd8ed1ab_0
-  - tzdata=2022g=h191b570_0
-  - urllib3=1.26.13=pyhd8ed1ab_0
-  - wget=1.20.3=ha35d2d1_1
-  - wheel=0.38.4=pyhd8ed1ab_0
-  - xorg-fixesproto=5.0=h7f98852_1002
-  - xorg-inputproto=2.3.2=h7f98852_1002
-  - xorg-kbproto=1.0.7=h7f98852_1002
-  - xorg-libice=1.0.10=h7f98852_0
-  - xorg-libsm=1.2.3=hd9c2040_1000
-  - xorg-libx11=1.7.2=h7f98852_0
-  - xorg-libxau=1.0.9=h7f98852_0
-  - xorg-libxdmcp=1.1.3=h7f98852_0
-  - xorg-libxext=1.3.4=h7f98852_1
-  - xorg-libxfixes=5.0.3=h7f98852_1004
-  - xorg-libxi=1.7.10=h7f98852_0
-  - xorg-libxrender=0.9.10=h7f98852_1003
-  - xorg-libxtst=1.2.3=h7f98852_1002
-  - xorg-recordproto=1.14.2=h7f98852_1002
-  - xorg-renderproto=0.11.1=h7f98852_1002
-  - xorg-xextproto=7.3.0=h7f98852_1002
-  - xorg-xproto=7.0.31=h7f98852_1007
-  - xtandem=15.12.15.2=h072c6ed_6
-  - xz=5.2.6=h166bdaf_0
-  - zlib=1.2.13=h166bdaf_4
-  - zstd=1.5.2=h6239696_4
-  - pip:
-    - brotlipy==0.7.0
-    - cffi==1.15.1
-    - cryptography==38.0.4
-    - numpy==1.24.0
-    - pandas==1.5.2
+  - readline
+  - requests
+  - searchgui=4
+  - seqkit=2
+  - tqdm
+  - urllib3
+  - wget
+  - numpy
+  - pandas
 prefix: /opt/conda/envs/my_env

workflow/rules/general_report.smk

@@ -2,17 +2,18 @@ rule protein_report:
     input:
         expand("{output}/Annotation/{sample}/UPIMAPI_results.tsv", output=OUTPUT, sample=set(EXPS['Sample'])),
         expand("{output}/Annotation/{sample}/reCOGnizer_results.xlsx", output=OUTPUT, sample=set(EXPS["Sample"])),
-        expand("{output}/Quantification/{sample}_mg.readcounts", output=OUTPUT, sample=set(mg_exps['Sample'])),
-        expand("{output}/Quantification/{sample}_mg_norm.tsv", output=OUTPUT, sample=set(mg_exps['Sample'])),
-        expand("{output}/Quantification/{sample}_mt.readcounts", output=OUTPUT, sample=set(mt_exps['Sample'])),
-        expand("{output}/Quantification/{sample}_mt_norm.tsv", output=OUTPUT, sample=set(mg_exps['Sample'])),
+        expand("{output}/Quantification/{sample}_mg.readcounts", output=OUTPUT, sample=set(mg_exps['Sample'])) if len(mg_exps) > 0 else [],
+        expand("{output}/Quantification/{sample}_mg_norm.tsv", output=OUTPUT, sample=set(mg_exps['Sample'])) if len(mg_exps) > 0 else [],
+        expand("{output}/Quantification/{sample}_mt.readcounts", output=OUTPUT, sample=set(mt_exps['Sample'])) if len(mt_exps) > 0 else [],
+        expand("{output}/Quantification/{sample}_mt_norm.tsv", output=OUTPUT, sample=set(mg_exps['Sample'])) if len(mt_exps) > 0 else [],
         expand("{output}/Metaproteomics/{sample}_mp.spectracounts", output=OUTPUT, sample=set(mp_exps['Sample']))
     output:
         expand("{output}/MOSCA_{sample}_General_Report.tsv", output=OUTPUT, sample=set(mg_exps['Sample'])),
         f"{OUTPUT}/MOSCA_General_Report.xlsx",
         f"{OUTPUT}/Quantification/dea_input.tsv",
-        f"{OUTPUT}/Quantification/mg_entry_quant.tsv",
-        f"{OUTPUT}/Quantification/mt_entry_quant.tsv" if len(mt_exps) > 0 else f"{OUTPUT}/Metaproteomics/mp_entry_quant.tsv"
+        f"{OUTPUT}/Quantification/mg_entry_quant.tsv" if len(mg_exps) > 0 else [],
+        f"{OUTPUT}/Quantification/mt_entry_quant.tsv" if len(mt_exps) > 0 else [],
+        f"{OUTPUT}/Metaproteomics/mp_entry_quant.tsv" if len(mp_exps) > 0 else []
     threads:
         1
     params:

workflow/rules/metaproteomics.smk

@@ -1,9 +1,9 @@
 rule metaproteomics:
     input:
         [directory(folder) for folder in mp_exps[mp_exps['Sample'] == (lambda wildcards: wildcards.sample)]['Files']],
-        "{output}/Annotation/{sample}/UPIMAPI_results.tsv"
+        "{out_dir}/Annotation/{sample}/UPIMAPI_results.tsv"
     output:
-        "{output}/Metaproteomics/{sample}_mp_spectracounts.tsv"
+        "{out_dir}/Metaproteomics/{sample}_mp.spectracounts"
     threads:
         config["threads"]
     params:

workflow/rules/quantification.smk

@@ -6,10 +6,10 @@ rule quantification:
         expand("{output}/Annotation/{sample}/fgs.ffn", output=OUTPUT, sample=set(EXPS["Sample"]))
     output:
         expand("{output}/Quantification/{name}.readcounts", output=OUTPUT, name=set(not_mp_exps['Name'])),
-        expand("{output}/Quantification/{sample}_mg.readcounts", output=OUTPUT, sample=set(mg_exps['Sample'])),
-        expand("{output}/Quantification/{sample}_mg_norm.tsv", output=OUTPUT, sample=set(mg_exps['Sample'])),
-        expand("{output}/Quantification/{sample}_mt.readcounts", output=OUTPUT, sample=set(mt_exps['Sample'])),
-        expand("{output}/Quantification/{sample}_mt_norm.tsv", output=OUTPUT, sample=set(mg_exps['Sample']))
+        expand("{output}/Quantification/{sample}_mg.readcounts", output=OUTPUT, sample=set(mg_exps['Sample'])) if len(mg_exps) > 0 else [],
+        expand("{output}/Quantification/{sample}_mg_norm.tsv", output=OUTPUT, sample=set(mg_exps['Sample'])) if len(mg_exps) > 0 else [],
+        expand("{output}/Quantification/{sample}_mt.readcounts", output=OUTPUT, sample=set(mt_exps['Sample'])) if len(mt_exps) > 0 else [],
+        expand("{output}/Quantification/{sample}_mt_norm.tsv", output=OUTPUT, sample=set(mg_exps['Sample'])) if len(mt_exps) > 0 else []
     threads:
         config["threads"]
     params:

workflow/scripts/metaproteomics.py

@@ -160,23 +160,23 @@ def create_decoy_database(self, database):
 
     def generate_parameters_file(
             self, output, protein_fdr=1, frag_tol=0.5, prec_tol=10, enzyme='Trypsin', mc=2,
-            fixed_mods=('Carbamidomethylation of C'),
-            variable_mods=('Oxidation of M', 'Acetylation of protein N-term')):
+            fixed_mods='Carbamidomethylation of C', variable_mods='Oxidation of M,Acetylation of protein N-term'):
         """
         param: output: name of parameters file
         param: protein_fdr: float - FDR at the protein level in percent
         param: frag_tol: float - fragment ion mass tolerance in ppm
         param: prec_tol: float - precursor ion mass tolerance in ppm
         param: enzyme: str - enzyme used for digestion
         param: mc: int - maximum number of missed cleavages
-        param: fixed_mods: tuple - fixed modifications
-        param: variable_mods: tuple - variable modifications
+        param: fixed_mods: str - fixed modifications comma-separated
+        param: variable_mods: str - variable modifications comma-separated
         returns: a parameters file will be produced for SearchCLI and/or PeptideShakerCLI
         """
+        fixed_mods, variable_mods = fixed_mods.split(','), variable_mods.split(',')
         run_pipe_command(
-            f'''searchgui eu.isas.searchgui.cmd.IdentificationParametersCLI -out {output} -prec_tol {prec_tol} '
-            f'-frag_tol {frag_tol} -enzyme {enzyme} -fixed_mods "{', '.join(fixed_mods)}" -variable_mods '
-            f'"{', '.join(variable_mods)}" -mc {mc} -protein_fdr {protein_fdr}''')
+            f'''searchgui eu.isas.searchgui.cmd.IdentificationParametersCLI -out {output} -prec_tol {prec_tol} ''' +
+            f'''-frag_tol {frag_tol} -enzyme {enzyme} -fixed_mods "{', '.join(fixed_mods)}" ''' +
+            f'''-variable_mods "{', '.join(variable_mods)}" -mc {mc} -protein_fdr {protein_fdr}''')
 
     def split_database(self, database, n_proteins=5000000):
         """