Mercurial > repos > galaxyp > diann
diff diann.xml @ 2:65134626eb2b draft
planemo upload for repository https://github.com/vdemichev/DiaNN commit 005bb8d9fa17c3f28b960d99b23947841e06d90a
| author | galaxyp |
|---|---|
| date | Mon, 31 Mar 2025 19:30:22 +0000 |
| parents | c9228a392c74 |
| children | a8f461b7d193 |
line wrap: on
line diff
--- a/diann.xml Mon Oct 02 14:15:30 2023 +0000 +++ b/diann.xml Mon Mar 31 19:30:22 2025 +0000 @@ -1,12 +1,15 @@ -<tool id="diann" name="DIA-NN" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@"> +<tool id="diann" name="DIA-NN" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="23.2"> <description>is a software for DIA/SWATH data processing</description> <macros> <token name="@TOOL_VERSION@">1.8.1</token> - <token name="@VERSION_SUFFIX@">1</token> + <token name="@VERSION_SUFFIX@">4</token> </macros> <requirements> - <container type="docker">biocontainers/diann:v@TOOL_VERSION@_cv1</container> + <container type="docker">biocontainers/diann:@TOOL_VERSION@_cv2</container> </requirements> + <stdio> + <regex source="stdout" match="invalid raw MS data format" level="fatal" description="One of the inputs could not be loaded"/> + </stdio> <command detect_errors="exit_code"><![CDATA[ mkdir ./input_data && mkdir ./tmp && @@ -17,10 +20,11 @@ ## if brukertdf.d.tar, extract to ./input_data and append "./input_data/" to infiles_str #if $infile.is_of_type("brukertdf.d.tar"): tar -xf '$infile' -C ./input_data && - #set $infiles_str += '--f ./input_data/' + str($infile.element_identifier[:-4]) + ' ' + #set $infiles_str += '--f ./input_data/' + str($infile.element_identifier[:-4]) #else - ln -s '$infile' './input_data/$infile.element_identifier' && - #set $infiles_str += '--f ./input_data/' + str($infile.element_identifier) + #set name = './input_data/' + $infile.element_identifier + '.' + $infile.ext + ln -s '$infile' '$name' && + #set $infiles_str += '--f ' + $name + ' ' #end if #end for @@ -29,13 +33,17 @@ #set $fasta_file_str += '--fasta ' + str($fasta_file) + ' ' #end for + #if $input.spectral_lib_options.lib + ln -s '$input.spectral_lib_options.lib' './input_data/report-lib.predicted.speclib' && + #end if + diann #if $input.f != 'None' '$infiles_str' #end if --dir ./ #if $input.spectral_lib_options.lib - --lib '$input.spectral_lib_options.lib' + --lib './input_data/report-lib.predicted.speclib' #else --lib #end if @@ -60,12 +68,12 @@ $input.spectral_lib_options.out_measured_rt $input.spectral_lib_options.predictor $input.spectral_lib_options.reannotate - #if $input.spectral_lib_options.ref - --ref '$input.spectral_lib_options.ref' - #end if + ##if $input.spectral_lib_options.ref + ##--ref '$input.spectral_lib_options.ref' + ###end if ## FASTA database options - #if $fasta_file_str != 'None' + #if $fasta_file_str != '--fasta None ' '$fasta_file_str' #end if #if $input.fasta_db_options.fasta_filter @@ -84,7 +92,7 @@ #if $algo_options.mass_acc_ms1 --mass-acc-ms1 '$algo_options.mass_acc_ms1' #end if - $algo_options.quick_mass_acc + ##$algo_options.quick_mass_acc $algo_options.reanalyse $algo_options.mbr_fix_settings $algo_options.relaxed_prot_inf @@ -135,9 +143,9 @@ ## Channel options ## ToDo: no_decoy_channel as condition? - #if $channel_options.channels - --channels '$channel_options.channels' - #end if + ##if $channel_options.channels + ##--channels '$channel_options.channels' + ###end if #if $channel_options.decoy_channel --decoy-channel '$channel_options.decoy_channel' #end if @@ -191,14 +199,14 @@ $other_options.full_unimod $other_options.gen_fr_restriction $other_options.global_mass_cal - $other_options.il_eq + ##$other_options.il_eq $other_options.individual_mass_acc $other_options.individual_reports $other_options.individual_windows $other_options.no_isotopes $other_options.regular_swath $other_options.scanning_swath - $other_options.semi + ##$other_options.semi $other_options.species_genes $other_options.tims_skip_errors @@ -234,22 +242,22 @@ <inputs> <!-- not used: cfg, convert, dir, ext, no_quant_files, out, out_lib, out_lib_copy, prefix, temp, threads, use-quant --> <section name="input" expanded="true" title="Input files"> - <param name="f" type="data" format="mzml,dia,wiff,thermo.raw,brukertdf.d.tar" multiple="true" optional="true" label="Input file" help="Specify a run to be analysed"/> + <param name="f" type="data" format="mzml,wiff,thermo.raw,brukertdf.d.tar" multiple="true" optional="true" label="Input file" help="Specify a run to be analysed"/> <!-- ToDo lib: The use of multiple lib commands (experimental) allows to load multiple libraries in .tsv format --> <section name="spectral_lib_options" title="Spectral library"> <param name="gen_spec_lib" type="boolean" truevalue="--gen-spec-lib" falsevalue="" checked="false" label="Generate a spectral library" help="Instructs DIA-NN to generate a spectral library"/> <param name="predictor" type="boolean" truevalue="--predictor" falsevalue="" checked="false" label="Perform deep learning-based prediction of spectra, retention times and ion mobility values" help="Instructs DIA-NN to perform deep learning-based prediction of spectra, retention times and ion mobility values"/> - <param name="lib" type="data" format="csv,tsv,xls,txt,binary,speclib,sptxt,msp" optional="true" label="Spectral library" help="Specify a spectral library"/> +<!-- Removed sptxt,msp as input format > experimental feature--> + <param name="lib" type="data" format="csv,tsv,xls,txt,binary" optional="true" label="Spectral library" help="Specify a spectral library"/> <param name="library_headers" type="text" optional="true" label="Library headers" help="Specifies column names in the spectral library to be used, in the order described in Spectral library formats [name 1],[name 2],.... Use '*' instead of the column name if DIA-NN already recognizes its name"/> <param name="no_lib_filter" type="boolean" truevalue="--no-lib-filter" falsevalue="" checked="false" label="Use the input library 'as is'" help="The input library will be used 'as is' without discarding fragments that might be harmful for the analysis; use with caution"/> <param name="learn_lib" type="data" format="tsv" optional="true" label="Training library" help="Specifies a 'training library' for the legacy predictor"/> <param name="out_measured_rt" type="boolean" truevalue="--out-measured-rt" falsevalue="" checked="false" label="Save raw empirical retention times in the spectral library" help="Instructs DIA-NN to save raw empirical retention times in the spectral library being generated, instead of saving RTs aligned to a particular scale"/> <param name="reannotate" type="boolean" truevalue="--reannotate" falsevalue="" checked="false" label="Reannotate the spectral library with protein information from the FASTA database" help="Reannotate the spectral library with protein information from the FASTA database, using the specified digest specificity"/> - <param name="ref" type="text" optional="true" label="Reference run" help="(Experimental) Specify a special (small) spectral library which will be used exclusively for calibration - this function can speed up calibration in library-free searches"/> +<!-- <param name="ref" type="text" optional="true" label="Reference run" help="(Experimental) Specify a special (small) spectral library which will be used exclusively for calibration - this function can speed up calibration in library-free searches"/>--> </section> <section name="fasta_db_options" title="FASTA database"> - <!-- ToDo fasta: use multiple fasta commands to specify multiple databases --> - <param name="fasta" type="data" format="fasta" multiple="true" label="Sequence database" help="Specify a sequence database in FASTA format"/> + <param name="fasta" type="data" format="fasta" optional="true" multiple="true" label="Sequence database" help="Specify a sequence database in FASTA format"/> <param name="fasta_filter" type="data" format="txt" optional="true" label="Fasta filter" help="Only consider peptides matching the stripped sequences specified in the text file provided, when processing a sequence database"/> <param name="fasta_search" type="boolean" truevalue="--fasta-search" falsevalue="" checked="false" label="Perform in silico digest of the sequence database" help="Instructs DIA-NN to perform an in silico digest of the sequence database"/> </section> @@ -259,7 +267,7 @@ <param name="mass_acc" type="float" min="0" optional="true" label="MS2 mass accuracy" help="Sets the MS2 mass accuracy to N ppm"/> <param name="mass_acc_cal" type="float" min="0" optional="true" label="Mass accuracy during calibration phase" help="Sets the mass accuracy used during the calibration phase of the search to N ppm"/> <param name="mass_acc_ms1" type="float" min="0" optional="true" label="MS1 mass accuracy" help="Sets the MS1 mass accuracy to N ppm"/> - <param name="quick_mass_acc" type="boolean" truevalue="--quick-mass-acc" falsevalue="" checked="false" label="(Experimental) Use a fast heuristical algorithm for MS2 mass accuracy" help="When choosing the MS2 mass accuracy setting automatically, DIA-NN will use a fast heuristical algorithm instead of IDs number optimisation"/> +<!-- <param name="quick_mass_acc" type="boolean" truevalue="--quick-mass-acc" falsevalue="" checked="false" label="(Experimental) Use a fast heuristical algorithm for MS2 mass accuracy" help="When choosing the MS2 mass accuracy setting automatically, DIA-NN will use a fast heuristical algorithm instead of IDs number optimisation"/>--> <!-- ToDo mbr_fix_settings: what does 'Unrelated runs' mean? --> <param name="reanalyse" type="boolean" truevalue="--reanalyse" falsevalue="" checked="false" label="Enable MBR" help="Enables MBR"/> <param name="mbr_fix_settings" type="boolean" truevalue="--mbr-fix-settings" falsevalue="" checked="false" label="Use the same settings for all runs during the second MBR pass" help="When using the 'Unrelated runs' option in combination with MBR, the same settings will be used to process all runs during the second MBR pass"/> @@ -286,7 +294,7 @@ <param name="cross_run_norm" type="select" label="Cross-run normalisation" help="Normalisation strategy. --global-norm/Global: Instructs DIA-NN to use simple global normalisation instead of RT-dependent normalisation. RT-dependent: Instructs DIA-NN to use RT-dependent normalisation. --sig-norm/RT and signal-dep. (experimental): Instructs DIA-NN to use RT and signal dependent normalisation (experimental). --no-norm/Off: disables cross-run normalisation. Normalised quantities reported along with the raw quantities. Default: RT-dependent"> <option value="--global-norm">Global</option> <option value="" selected="True">RT-dependent</option> - <option value="--sig-norm">RT and signal-dep. (experimental)</option> +<!-- <option value="--sig-norm">RT and signal-dep. (experimental)</option>--> <option value="--no-norm">Off</option> </param> <param name="lib_gen_strategy" type="select" label="Library generationm strategy" help="Enables an intelligent algorithm which determines how to extract spectra, when creating a spectral library from DIA data. This is highly recommended and should almost always be enabled"> @@ -360,7 +368,7 @@ <param name="target_fr" type="integer" min="0" optional="true" label="Number of fragment ions for spectral library" help="Fragment ions beyond this number will only be included in the spectral library being created (from DIA data) if they have high-quality chromatograms. Default value is 6"/> </section> <section name="channel_options" title="Channel"> - <param name="channels" type="text" optional="true" label="(Experimental) List multiplexing channels" help="Lists multiplexing channels, wherein each channel declaration has the form [channel] = [label group],[channel name],[sites],[mass1:mass2:...], wherein [sites] has the same syntax as for --var-mod and if N sites are listed, N masses are listed at the end of the channel declaration. Examples: '--channels SILAC,L,KR,0:0; SILAC,H,KR,8.014199:10.008269' - declares standard light/heavy SILAC labels, '--channels mTRAQ,0,nK,0:0; mTRAQ,4,nK,4.0070994:4.0070994;mTRAQ,8,nK,8.0141988132:8.0141988132' - declares mTRAQ. The spectral library will be automatically split into multiple channels, for precursors bearing the [label group] modification. To add the latter to a label-free spectral library, can use --lib-fixed-mod, e.g. --fixed-mod SILAC,0.0,KR,label --lib-fixed-mod SILAC. The --channels command must be used in conjunction with --peak-translation."/> +<!-- <param name="channels" type="text" optional="true" label="(Experimental) List multiplexing channels" help="Lists multiplexing channels, wherein each channel declaration has the form [channel] = [label group],[channel name],[sites],[mass1:mass2:...], wherein [sites] has the same syntax as for --var-mod and if N sites are listed, N masses are listed at the end of the channel declaration. Examples: '--channels SILAC,L,KR,0:0; SILAC,H,KR,8.014199:10.008269' - declares standard light/heavy SILAC labels, '--channels mTRAQ,0,nK,0:0; mTRAQ,4,nK,4.0070994:4.0070994;mTRAQ,8,nK,8.0141988132:8.0141988132' - declares mTRAQ. The spectral library will be automatically split into multiple channels, for precursors bearing the [label group] modification. To add the latter to a label-free spectral library, can use --lib-fixed-mod, e.g. --fixed-mod SILAC,0.0,KR,label --lib-fixed-mod SILAC. The --channels command must be used in conjunction with --peak-translation."/>--> <param name="decoy_channel" type="text" optional="true" label="Decoy channel" help="Specifies the decoy channel masses (same syntax as for --channels)"/> <param name="no_decoy_channel" type="boolean" truevalue="--no-decoy-channel" falsevalue="" checked="false" label="Disable the use of a decoy channel" help="Disables the use of a decoy channel for channel q-value calculation"/> </section> @@ -381,7 +389,7 @@ <param name="full_unimod" type="boolean" truevalue="--full-unimod" falsevalue="" checked="false" label="Full UniMod modification database" help="Loads the complete UniMod modification database and disables the automatic conversion of modification names to the UniMod format"/> <param name="gen_fr_restriction" type="boolean" truevalue="--gen-fr-restriction" falsevalue="" checked="false" label="Generate fragment exclusion information" help="Annotates the library with fragment exclusion information, based on the runs being analysed (fragments least affected by interferences are selected for quantification, why the rest are excluded)"/> <param name="global_mass_cal" type="boolean" truevalue="--global-mass-cal" falsevalue="" checked="false" label="Disable RT-dependent mass calibration" help="Disables RT-dependent mass calibration"/> - <param name="il_eq" type="boolean" truevalue="--il-eq" falsevalue="" checked="false" label="(Experimental) Isoleucine and leucine equivalent" help="When using the 'Reannotate' function, peptides will be matched to proteins while considering isoleucine and leucine equivalent"/> +<!-- <param name="il_eq" type="boolean" truevalue="--il-eq" falsevalue="" checked="false" label="(Experimental) Isoleucine and leucine equivalent" help="When using the 'Reannotate' function, peptides will be matched to proteins while considering isoleucine and leucine equivalent"/>--> <!-- ToDo individual_mass_acc: what does automatic mean? --> <param name="individual_mass_acc" type="boolean" truevalue="--individual-mass-acc" falsevalue="" checked="false" label="Independent mass accuracies" help="Mass accuracies, if set to automatic, will be determined independently for different runs"/> <param name="individual_reports" type="boolean" truevalue="--individual-reports" falsevalue="" checked="false" label="Individual output reports" help="A separate output report will be created for each run"/> @@ -390,7 +398,7 @@ <param name="no_isotopes" type="boolean" truevalue="--no-isotopes" falsevalue="" checked="false" label="Do not extract chromatograms for heavy isotopologues" help="Do not extract chromatograms for heavy isotopologues"/> <param name="regular_swath" type="boolean" truevalue="--regular-swath" falsevalue="" checked="false" label="Analyse all runs as regular runs" help="All runs will be analysed as if they were not Scanning SWATH runs"/> <param name="scanning_swath" type="boolean" truevalue="--scanning-swath" falsevalue="" checked="false" label="Analyse all runs as Scanning SWATH runs" help="All runs will be analysed as if they were Scanning SWATH runs"/> - <param name="semi" type="boolean" truevalue="--semi" falsevalue="" checked="false" label="(Experimental) Match a peptide to a protein with one specific and one non-specific cut" help="When using the 'Reannotate' function, a peptide will be matched to a protein also if it could be obtained with one specific and one non-specific cut (at either of the termini)"/> +<!-- <param name="semi" type="boolean" truevalue="--semi" falsevalue="" checked="false" label="(Experimental) Match a peptide to a protein with one specific and one non-specific cut" help="When using the 'Reannotate' function, a peptide will be matched to a protein also if it could be obtained with one specific and one non-specific cut (at either of the termini)"/>--> <param name="species_genes" type="boolean" truevalue="--species-genes" falsevalue="" checked="false" label="Add the organism identifier to the gene names" help="Instructs DIA-NN to add the organism identifier to the gene names - useful for distinguishing genes from different species, when analysing mixed samples. Works with UniProt sequence databases."/> <param name="tims_skip_errors" type="boolean" truevalue="--tims-skip-errors" falsevalue="" checked="false" label="Ignore errors when loading dia-PASEF data" help="DIA-NN will ignore errors when loading dia-PASEF data"/> </section> @@ -426,7 +434,7 @@ <!-- test for default run --> <test expect_num_outputs="4"> <section name="input"> - <param name="f" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="f" value="small-peakpicking-cwt-allMS" /> <section name="spectral_lib_options"> <param name="gen_spec_lib" value="True"/> <param name="predictor" value="True"/> @@ -452,7 +460,25 @@ <!-- test for multiple fastas --> <test expect_num_outputs="1"> <section name="input"> - <param name="f" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="f" value="small-peakpicking-cwt-allMS" /> + <section name="fasta_db_options"> + <param name="fasta" value="bsa.fasta,bsa2.fasta"/> + <param name="fasta_search" value="True"/> + </section> + </section> + <output name="output_report" file="report.tsv"> + <assert_contents> + <has_text text="PG.Normalised"/> + </assert_contents> + </output> + </test> + <!-- test for spec library --> + <test expect_num_outputs="1"> + <section name="input"> + <param name="f" value="small-peakpicking-cwt-allMS" /> + <section name="spectral_lib_options"> + <param name="lib" value="report-lib.predicted.speclib"/> + </section> <section name="fasta_db_options"> <param name="fasta" value="bsa.fasta,bsa2.fasta"/> <param name="fasta_search" value="True"/> @@ -465,29 +491,29 @@ </output> </test> <!-- test for Bruker data --> -<!-- <test expect_num_outputs="2">--> -<!-- <section name="input">--> -<!-- <param name="f" value="ThyroglobMRM000003.d.tar" />--> -<!-- <section name="spectral_lib_options">--> -<!-- <param name="gen_spec_lib" value="True"/>--> -<!-- <param name="predictor" value="True"/>--> -<!-- </section>--> -<!-- <section name="fasta_db_options">--> -<!-- <param name="fasta" value="bsa.fasta"/>--> -<!-- <param name="fasta_search" value="True"/>--> -<!-- </section>--> -<!-- </section>--> -<!-- <output name="output_report" file="bruker-report.tsv">--> -<!-- <assert_contents>--> -<!-- <has_text text="PG.Normalised"/>--> -<!-- </assert_contents>--> -<!-- </output>--> -<!-- <output name="output_report_lib" file="bruker-report-lib.tsv">--> -<!-- <assert_contents>--> -<!-- <has_text text="PrecursorMz"/>--> -<!-- </assert_contents>--> -<!-- </output>--> -<!-- </test>--> + <!-- <test expect_num_outputs="2"> + <section name="input"> + <param name="f" value="ThyroglobMRM000003.d.tar" /> + <section name="spectral_lib_options"> + <param name="gen_spec_lib" value="True"/> + <param name="predictor" value="True"/> + </section> + <section name="fasta_db_options"> + <param name="fasta" value="bsa.fasta"/> + <param name="fasta_search" value="True"/> + </section> + </section> + <output name="output_report" file="bruker-report.tsv"> + <assert_contents> + <has_text text="PG.Normalised"/> + </assert_contents> + </output> + <output name="output_report_lib" file="bruker-report-lib.tsv"> + <assert_contents> + <has_text text="PrecursorMz"/> + </assert_contents> + </output> + </test> --> </tests> <help> <![CDATA[ @@ -517,7 +543,7 @@ *Spectral library formats* - DIA-NN supports comma-separated (.csv) or tab-separated (.tsv, .xls or .txt), .speclib (compact format used by DIA-NN), .sptxt (SpectraST, experimental) and .msp (NIST, experimental) library files. Important: the library must not contain non-fragmented precursor ions as 'fragments': each fragment ion must actually be produced by the peptide backbone fragmentation. + DIA-NN supports comma-separated (.csv) or tab-separated (.tsv, .xls or .txt), .speclib (compact format used by DIA-NN), .sptxt (SpectraST, experimental [not in Galaxy]) and .msp (NIST, experimental [not in Galaxy]) library files. Important: the library must not contain non-fragmented precursor ions as 'fragments': each fragment ion must actually be produced by the peptide backbone fragmentation. *Library-free search*