diff --git a/assets/PXD026600.sdrf.tsv b/assets/PXD026600.sdrf.tsv index ebe0a137..f2d97378 100644 --- a/assets/PXD026600.sdrf.tsv +++ b/assets/PXD026600.sdrf.tsv @@ -1,4 +1,3 @@ Source Name Characteristics[organism] Characteristics[organism part] Characteristics[age] Characteristics[strain] Characteristics[developmental stage] Characteristics[cell line] Characteristics[cell type] Characteristics[sex] Characteristics[disease] characteristics[mass] characteristics[spiked compound] Characteristics[biological replicate] Material Type assay name technology type comment[data file] comment[file uri] comment[technical replicate] comment[fraction identifier] comment[proteomics data acquisition method] comment[label] comment[instrument] comment[modification parameters] comment[modification parameters] comment[cleavage agent details] comment[dissociation method] comment[collision energy] comment[precursor mass tolerance] comment[fragment mass tolerance] factor value[spiked compound] Sample 1 Escherichia coli K-12 whole plant not available K12 not available not applicable not available not available not available 1 ug CT=Mixture;CN=UPS1;QY=0.1 fmol 1 whole organism run 1 proteomic profiling by mass spectrometry RD139_Narrow_UPS1_0_1fmol_inj1.raw ftp://massive.ucsd.edu/MSV000087597/raw/RD139_Raw_files_DIA_Narrow/RD139_Narrow_UPS1_0_1fmol_inj1.raw 1 1 NT=Data-Independent Acquisition;AC=NCIT:C161786 AC=MS:1002038;NT=label free sample NT=Orbitrap Fusion;AC=MS:1002416 NT=Oxidation;MT=Variable;TA=M;AC=Unimod:35 NT=Carbamidomethyl;TA=C;MT=fixed;AC=UNIMOD:4 AC=MS:1001313;NT=Trypsin NT=HCD;AC=PRIDE:0000590 35% CE 10 ppm 20 mmu CT=Mixture;CN=UPS1;QY=0.1 fmol Sample 1 Escherichia coli K-12 whole plant not available K12 not available not applicable not available not available not available 1 ug CT=Mixture;CN=UPS1;QY=0.1 fmol 1 whole organism run 2 proteomic profiling by mass spectrometry RD139_Narrow_UPS1_0_1fmol_inj2.raw ftp://massive.ucsd.edu/MSV000087597/raw/RD139_Raw_files_DIA_Narrow/RD139_Narrow_UPS1_0_1fmol_inj2.raw 2 1 NT=Data-Independent Acquisition;AC=NCIT:C161786 AC=MS:1002038;NT=label free sample NT=Orbitrap Fusion;AC=MS:1002416 NT=Oxidation;MT=Variable;TA=M;AC=Unimod:35 NT=Carbamidomethyl;TA=C;MT=fixed;AC=UNIMOD:4 AC=MS:1001313;NT=Trypsin NT=HCD;AC=PRIDE:0000590 35% CE 10 ppm 20 mmu CT=Mixture;CN=UPS1;QY=0.1 fmol -Sample 1 Escherichia coli K-12 whole plant not available K12 not available not applicable not available not available not available 1 ug CT=Mixture;CN=UPS1;QY=0.1 fmol 1 whole organism run 3 proteomic profiling by mass spectrometry RD139_Narrow_UPS1_0_1fmol_inj3.raw ftp://massive.ucsd.edu/MSV000087597/raw/RD139_Raw_files_DIA_Narrow/RD139_Narrow_UPS1_0_1fmol_inj3.raw 3 1 NT=Data-Independent Acquisition;AC=NCIT:C161786 AC=MS:1002038;NT=label free sample NT=Orbitrap Fusion;AC=MS:1002416 NT=Oxidation;MT=Variable;TA=M;AC=Unimod:35 NT=Carbamidomethyl;TA=C;MT=fixed;AC=UNIMOD:4 AC=MS:1001313;NT=Trypsin NT=HCD;AC=PRIDE:0000590 35% CE 10 ppm 20 mmu CT=Mixture;CN=UPS1;QY=0.1 fmol diff --git a/bin/prepare_diann_parameters.py b/bin/prepare_diann_parameters.py index 68467583..ced12ae4 100755 --- a/bin/prepare_diann_parameters.py +++ b/bin/prepare_diann_parameters.py @@ -44,31 +44,33 @@ def convert_mod(unimod_csv, fix_mod, var_mod): var_ptm = [] fix_ptm = [] unimod = pd.read_csv(unimod_csv, header=0, sep=",") - for mod in fix_mod.split(","): - diann_mod = unimod[unimod['name'] == mod.split(" ")[0]]["params"].values[0] - site = re.findall(pattern, " ".join(mod.split(" ")[1:]))[0] - if site == "Protein N-term": - site = "*n" - elif site == "N-term": - site = "n" - - if "TMT" in diann_mod or "Label" in diann_mod or "iTRAQ" in diann_mod or "mTRAQ" in diann_mod: - fix_ptm.append(diann_mod + "," + site + "," + "label") - else: - fix_ptm.append(diann_mod + "," + site) - - for mod in var_mod.split(","): - diann_mod = unimod[unimod['name'] == mod.split(" ")[0]]["params"].values[0] - site = re.findall(pattern, " ".join(mod.split(" ")[1:]))[0] - if site == "Protein N-term": - site = "*n" - elif site == "N-term": - site = "n" - - if "TMT" in diann_mod or "Label" in diann_mod or "iTRAQ" in diann_mod or "mTRAQ" in diann_mod: - var_ptm.append(diann_mod + "," + site + "," + "label") - else: - var_ptm.append(diann_mod + "," + site) + if fix_mod != "": + for mod in fix_mod.split(","): + diann_mod = unimod[unimod['name'] == mod.split(" ")[0]]["params"].values[0] + site = re.findall(pattern, " ".join(mod.split(" ")[1:]))[0] + if site == "Protein N-term": + site = "*n" + elif site == "N-term": + site = "n" + + if "TMT" in diann_mod or "Label" in diann_mod or "iTRAQ" in diann_mod or "mTRAQ" in diann_mod: + fix_ptm.append(diann_mod + "," + site + "," + "label") + else: + fix_ptm.append(diann_mod + "," + site) + + if var_mod != "": + for mod in var_mod.split(","): + diann_mod = unimod[unimod['name'] == mod.split(" ")[0]]["params"].values[0] + site = re.findall(pattern, " ".join(mod.split(" ")[1:]))[0] + if site == "Protein N-term": + site = "*n" + elif site == "N-term": + site = "n" + + if "TMT" in diann_mod or "Label" in diann_mod or "iTRAQ" in diann_mod or "mTRAQ" in diann_mod: + var_ptm.append(diann_mod + "," + site + "," + "label") + else: + var_ptm.append(diann_mod + "," + site) return fix_ptm, var_ptm diff --git a/modules/local/thermorawfileparser/main.nf b/modules/local/thermorawfileparser/main.nf index 6432086e..eb6faceb 100644 --- a/modules/local/thermorawfileparser/main.nf +++ b/modules/local/thermorawfileparser/main.nf @@ -8,6 +8,8 @@ process THERMORAWFILEPARSER { 'https://depot.galaxyproject.org/singularity/thermorawfileparser:1.3.4--ha8f3691_0' : 'quay.io/biocontainers/thermorawfileparser:1.3.4--ha8f3691_0' }" + stageInMode {task.attempt == 1 ? 'link' : (task.attempt == 2 ? 'symlink' : 'copy')} + input: tuple val(meta), path(rawfile)