Mercurial > repos > matthias > genform
changeset 0:f17273aa599f draft default tip
planemo upload for repository https://github.com/workflow4metabolomics/tools-metabolomics/blob/master/tools/genform/ commit 479866669d9dcf8f89140c68f701db1cd12b006e-dirty
| author | matthias |
|---|---|
| date | Thu, 12 Sep 2019 12:20:47 -0400 |
| parents | |
| children | |
| files | gen-test.sh genform.xml test-data/CreatineMs.out test-data/CreatineMs.txt test-data/CreatineMsMs-oclean.out test-data/CreatineMsMs-oms.out test-data/CreatineMsMs-omsms.out test-data/CreatineMsMs.out test-data/CreatineMsMs.txt |
| diffstat | 9 files changed, 512 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/gen-test.sh Thu Sep 12 12:20:47 2019 -0400 @@ -0,0 +1,3 @@ +genform ms=test-data/CreatineMs.txt out=test-data/CreatineMs.out exist out=test-data/CreatineMs.out acc=20 rej=30 + +genform ms=test-data/CreatineMs.txt msms=test-data/CreatineMsMs.txt exist oms=test-data/CreatineMsMs-oms.out omsms=test-data/CreatineMsMs-omsms.out oclean=test-data/CreatineMsMs-oclean.out out=test-data/CreatineMsMs.out acc=20 rej=30 analyze loss intens dbe cm pc sc
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/genform.xml Thu Sep 12 12:20:47 2019 -0400 @@ -0,0 +1,495 @@ +<tool id="genform" name="genform" version="@GENFORM_VERSION@" python_template_version="3.5"> + <description>Generation of molecular formulas by high-resolution MS and MS/MS data</description> + <macros> + <token name="@GENFORM_VERSION@">8</token> + </macros> + <requirements> + <requirement type="package" version="r@GENFORM_VERSION@">genform</requirement> + </requirements> + <command detect_errors="exit_code"><![CDATA[ +genform + ms='$ms' + #if $msms + msms='$msms' + #end if + #if $formula_cond.formula_select != 'advanced' + $formula_cond.formula_select + #else + $formula_cond.vsp + #if str($formula_cond.vsm2mv) != '' + vsm2mv=$formula_cond.vsm2mv + #end if + #if str($formula_cond.vsm2ap2) != '' + vsm2ap2=$formula_cond.vsm2ap2 + #end if + #if str($formula_cond.ivsm2mv) != '' + ivsm2mv=$formula_cond.ivsm2mv + #end if + #if str($formula_cond.ivsm2ap2) != '' + ivsm2ap2=$formula_cond.ivsm2ap2 + #end if + #end if + #if str($m) != '' + m=$m + #end if + ion=$ion + ppm=$ppm + $msmv + acc=$acc + rej=$rej + thms=$thms + thmsms=$thmsms + thcomb=$thcomb + $sort + #if $elemfilt_cond.elemfilt_select == 'elem' + el=#echo "".join(str($elemfilt_cond.el).split(',')) + #elif $elemfilt_cond.elemfilt_select == 'oc' + oc + #elif $elemfilt_cond.elemfilt_select == 'fuzzy' + ff=$elemfilt_cond.fuzzy + #end if + $het + $hcf + $wm + $wi_cond.wi + #if $wi_cond.wi == 'wi=log' and str($wi_cond.exp) != '' + exp=$wi_cond.exp + #end if + $oei + #if str($dbeexc) != '' + dbeexc=$dbeexc + #end if + #if $output.out_cond.out_select == 'analyze': + analyze + $output.out_cond.loss + $output.out_cond.intens + #end if + $output.dbe + $output.cm + $output.pc + $output.sc + out=out + #if $addoutput.oms + oms='$outoms' + #end if + #if $addoutput.omsms + omsms='$outomsms' + #end if + #if $addoutput.oclean + oclean='$outoclean' + #end if + + ## for some reason genform prints the file twice if sorting is selected + ## (once unsorted and once sorted). hence, if soring is enabled just + ## the lower half of the file is returned + #if $sort != '' + && + wc=\$(wc -l out | cut -d" " -f 1 ) + && + hwc=\$(echo "\$wc/2" | bc) + && + tail -n \$hwc > '$out' + #else + && cp out '$out' + #end if + ]]></command> + <inputs> + <param type="data" argument="ms" label="MS data" format="tabular" help="" /> + <param type="data" argument="msms" label="MS/MS data" optional="true" format="tabular" help="" /> + <conditional name="formula_cond"> + <param type="select" name="formula_select" label="structural formula existence check" help="allow only molecular formulas for that at least one structural formula exists or specify advanced restictions, note that the default of genform is 'no existence check'"> + <option value="">no existence check</option> + <option value="exist" selected="true">only molecular formulas for that at least one structural formula exists (exist)</option> + <option value="exist=mv">enable multiple valencies for P and S (exist=mv)</option> + <option value="advanced">advanced</option> + </param> + <when value=""/> + <when value="exist"/> + <when value="exist=mv"/> + <when value="advanced"> + <param type="select" argument="vsp" label="valency sum parity" help="even for graphical formulas" > + <option value="">use default</option> + <option value="vsp=even">even</option> + <option value="vsp=odd">odd</option> + </param> + <param type="integer" argument="vsm2mv" label="lower bound for valency sum - 2 * maximum valency for graphical formulas" min="0" value="" help="" /> + <param type="integer" argument="vsm2ap2" label="lower bound for valency sum - 2 * number of atoms + 2 for graphical connected formulas" min="0" value="" help="" /> + <param type="integer" argument="ivsm2mv" label="lower bound for valency sum - 2 * maximum valency for fragment ions" min="0" value="" help="" /> + <param type="integer" argument="ivsm2ap2" label="lower bound for valency sum - 2 * number of atoms + 2 for fragment ions" min="0" value="" help="" /> + </when> + </conditional> + <param type="float" argument="m" label="experimental molecular mass" min="0" optional="true" help="(default: mass of MS basepeak)" /> + <param type="select" argument="ion" label="type of ion measured" help="" > + <option value="M+H">[M+H]+</option> + <option value="M-H">[M-H]-</option> + <option value="M+e">M+</option> + <option value="M-e">M-</option> + <option value="M+Na">[M+Na]+</option> + </param> + <param type="integer" argument="ppm" label="accuracy of measurement of MS1" min="0" value="5" help="in parts per million" /> + <param type="select" argument="msmv" label="MS match value" help="select output type of the MS match value" > + <option value="msmv=ndp">normalized dot product</option> + <option value="msmv=nsse">normalized sum of squared</option> + <option value="msmv=nsae" selected="true">absolute errors</option> + </param> + <param type="integer" argument="acc" label="allowed deviation for full acceptance" min="0" value="2" help="of MS/MS peak in ppm" /> + <param type="integer" argument="rej" label="allowed deviation for total rejection" min="0" value="4" help="of MS/MS peak in ppm" /> + <param type="float" argument="thms" label="threshold for the MS match value" min="0" max="1" value="0" help="" /> + <param type="float" argument="thmsms" label="threshold for the MS/MS match value" min="0" max="1" value="0" help="" /> + <param type="float" argument="thcomb" label="threshold for the combined match value" min="0" max="1" value="0" help="" /> + <param type="select" argument="sort" label="sort generated formulas by" help="" > + <option value="">do not sort</option> + <option value="sort=ppm">mass deviation in ppm</option> + <option value="sort=msmv">MS match value</option> + <option value="sort=msmsmv">MS/MS match value</option> + <option value="sort=combmv">combined match value</option> + </param> + <conditional name="elemfilt_cond"> + <param type="select" name="elemfilt_select" label="chemical element filtering"> + <option value="nofilter">no filter</option> + <option value="elem">by used elements</option> + <option value="oc">only organic compounds (oc)</option> + <option value="fuzzy">by fuzzy formula</option> + </param> + <when value="nofilter"/> + <when value="elem"> + <param type="select" multiple="true" argument="el" label="used chemical elements" help="" > + <option selected="true" value="C">C</option> + <option selected="true" value="N">N</option> + <option selected="true" value="O">O</option> + <option selected="true" value="P">P</option> + <option selected="true" value="S">S</option> + <option selected="true" value="H">H</option> + <option selected="true" value="Cl">Cl</option> + <option selected="true" value="Br">Br</option> + <option selected="true" value="F">F</option> + <option selected="true" value="I">I</option> + <option selected="true" value="Si">Si</option> + </param> + </when> + <when value="oc"/> + <when value="fuzzy"> + <param type="text" argument="ff" checked="false" label="uses fuzzy formula for limits of element multiplicities" help="" /> + </when> + </conditional> + <param type="boolean" argument="het" checked="false" truevalue="het" falsevalue="" label="formulas must have at least one hetero atom" help="" /> + <param type="boolean" argument="hcf" checked="false" truevalue="hcf" falsevalue="" label="apply Heuerding-Clerc filter" help="" /> + <param type="select" argument="wm" label="m/z weighting for MS/MS match value" help="" > + <option value="">no weighting</option> + <option value="wm=lin">linear</option> + <option value="wm=sqrt">square root</option> + <option value="wm=log">logarithmic</option> + </param> + <conditional name="wi_cond"> + <param type="select" argument="wi" label="intensity weighting for MS/MS match value" help="" > + <option value="">no weighting</option> + <option value="wi=lin">linear</option> + <option value="wi=sqrt">square root</option> + <option value="wi=log">logarithmic</option> + </param> + <when value=""/> + <when value="wi=lin"/> + <when value="wi=sqrt"/> + <when value="wi=log"> + <param type="float" argument="exp" optional="true" label="exponent" value="" help="" /> + </when> + </conditional> + <param type="boolean" argument="oei" checked="false" truevalue="oei" falsevalue="" label="allow odd electron ions for explaining MS/MS peaks" help="" /> + <param type="integer" argument="dbeexc" optional="true" label="excess of double bond equivalent for ions" help="" /> + <section name="output" title="output options for main output" expanded="true"> + <conditional name="out_cond"> + <param type="select" name="out_select" label="write explanations for MS/MS peaks to output" help="" > + <option value="">no</option> + <option value="analyze">yes</option> + </param> + <when value=""/> + <when value="analyze"> + <param type="boolean" argument="loss" checked="false" truevalue="loss" falsevalue="" label="for analyzing MS/MS peaks write losses instead of fragments" help="" /> + <param type="boolean" argument="intens" checked="false" truevalue="intens" falsevalue="" label="write intensities of MS/MS peaks to output" help="" /> + </when> + </conditional> + <param type="boolean" argument="dbe" checked="false" truevalue="dbe" falsevalue="" label="write double bond equivalents to output" help="" /> + <param type="boolean" argument="cm" checked="false" truevalue="cm" falsevalue="" label="write calculated ion masses to output" help="" /> + <param type="boolean" argument="pc" checked="false" truevalue="pc" falsevalue="" label="output match values in percent" help="" /> + <param type="boolean" argument="sc" checked="false" truevalue="sc" falsevalue="" label="strip calculated isotope distributions" help="" /> + </section> + <section name="addoutput" title="additional output data sets" expanded="true"> + <param type="boolean" argument="oms" checked="false" truevalue="oms" falsevalue="" label="write scaled MS peaks output" help="" /> + <param type="boolean" argument="omsms" checked="false" truevalue="omsms" falsevalue="" label="write scaled MS/MS peaks output" help="" /> + <param type="boolean" argument="oclean" checked="false" truevalue="oclean" falsevalue="" label="write MS/MS with only explained peaks" help="" /> + <param type="boolean" argument="oclean" checked="false" truevalue="oms" falsevalue="" label="write MS/MS with only explained peaks" help="" /> + </section> + </inputs> + <outputs> + <data name="out" format="tabular" /> + <data name="outoms" format="tabular" label="${tool.name} on ${on_string}: MS"> + <filter>addoutput['oms']</filter> + </data> + <data name="outomsms" format="tabular" label="${tool.name} on ${on_string}: MS/MS" > + <filter>addoutput['omsms']</filter> + </data> + <data name="outoclean" format="tabular" label="${tool.name} on ${on_string}: clean"> + <filter>addoutput['oclean']</filter> + </data> + </outputs> + <tests> + <!-- test with MS input and mostly default values --> + <test expect_num_outputs="1"> + <param name="ms" ftype="tabular" value="CreatineMs.txt" /> + <param name="acc" value="20" /> + <param name="rej" value="40" /> + <output name="out" ftype="tabular" file="CreatineMs.out"/> + <assert_command> + <has_text text=" ms=" /> + <not_has_text text=" msms=" /> + <has_text text=" exist " /> + <not_has_text text=" m=" /> + <has_text text=" ion=M+H " /> + <has_text text=" ppm=5 " /> + <has_text text=" msmv=nsae " /> + <has_text text=" acc=20 " /> + <has_text text=" rej=40 " /> + <has_text text=" thmsms=0.0 " /> + <has_text text=" thmsms=0.0 " /> + <has_text text=" thcomb=0.0 " /> + <not_has_text text=" sort" /> + <not_has_text text=" el=" /> + <not_has_text text=" oc " /> + <not_has_text text=" ff=" /> + <not_has_text text=" het " /> + <not_has_text text=" vsp=" /> + <not_has_text text=" vsp2mv=" /> + <not_has_text text=" vsm2ap2=" /> + <not_has_text text=" hcf " /> + <not_has_text text=" wm=" /> + <not_has_text text=" wi=" /> + <not_has_text text=" exp=" /> + <not_has_text text=" oei " /> + <not_has_text text=" dbeexc=" /> + <not_has_text text=" ivsm2mv=" /> + <not_has_text text=" ivsm2ap2=" /> + <not_has_text text=" oms=" /> + <not_has_text text=" omsms=" /> + <not_has_text text=" oclean=" /> + <not_has_text text=" analyze " /> + <not_has_text text=" loss " /> + <not_has_text text=" intens " /> + <not_has_text text=" dbe " /> + <not_has_text text=" cm " /> + <not_has_text text=" pc " /> + <not_has_text text=" sc " /> + </assert_command> + </test> + <!-- test with MS/MS input and non default output options --> + <test expect_num_outputs="4"> + <param name="ms" ftype="tabular" value="CreatineMs.txt" /> + <param name="msms" ftype="tabular" value="CreatineMsMs.txt" /> + <param name="acc" value="20" /> + <param name="rej" value="40" /> + <section name="output"> + <conditional name="out_cond"> + <param name="out_select" value="analyze"/> + <param name="loss" value="loss" /> + <param name="intens" value="intens" /> + </conditional> + <param name="dbe" value="dbe" /> + <param name="cm" value="cm" /> + <param name="pc" value="pc" /> + <param name="sc" value="sc" /> + </section> + <section name="addoutput"> + <param name="oms" value="oms" /> + <param name="omsms" value="omsms" /> + <param name="oclean" value="oclean" /> + <param name="oclean" value="oms"/> + </section> + <output name="out" ftype="tabular" file="CreatineMsMs.out"/> + <output name="outoms" ftype="tabular" file="CreatineMsMs-oms.out"/> + <output name="outomsms" ftype="tabular" file="CreatineMsMs-omsms.out"/> + <output name="outoclean" ftype="tabular" file="CreatineMsMs-oclean.out"/> + <assert_command> + <has_text text=" ms=" /> + <has_text text=" msms=" /> + <has_text text=" exist" /> + <not_has_text text=" m=" /> + <has_text text=" ion=M+H " /> + <has_text text=" ppm=5 " /> + <has_text text=" msmv=nsae " /> + <has_text text=" acc=20 " /> + <has_text text=" rej=40 " /> + <has_text text=" thmsms=0.0 " /> + <has_text text=" thmsms=0.0 " /> + <has_text text=" thcomb=0.0 " /> + <not_has_text text=" sort" /> + <not_has_text text=" el=" /> + <not_has_text text=" oc " /> + <not_has_text text=" ff=" /> + <not_has_text text=" het " /> + <not_has_text text=" vsp=" /> + <not_has_text text=" vsp2mv=" /> + <not_has_text text=" vsm2ap2=" /> + <not_has_text text=" hcf " /> + <not_has_text text=" wm=" /> + <not_has_text text=" wi=" /> + <not_has_text text=" exp=" /> + <not_has_text text=" oei " /> + <not_has_text text=" dbeexc=" /> + <not_has_text text=" ivsm2mv=" /> + <not_has_text text=" ivsm2ap2=" /> + <has_text text=" oms=" /> + <has_text text=" omsms=" /> + <has_text text=" oclean=" /> + <has_text text=" analyze " /> + <has_text text=" loss " /> + <has_text text=" intens " /> + <has_text text=" dbe " /> + <has_text text=" cm " /> + <has_text text=" pc " /> + <has_text text=" sc " /> + </assert_command> + </test> + <!-- test with MS/MS input and other non-default values + (creates empty output .. but test is still usefull) --> + <test expect_num_outputs="1"> + <param name="ms" ftype="tabular" value="CreatineMs.txt" /> + <param name="msms" ftype="tabular" value="CreatineMsMs.txt" /> + <conditional name="formula_cond"> + <param name="formula_select" value=""/> + </conditional> + <param name="m" value="111.0201" /> + <param name="ion" value="M-H" /> + <param name="ppm" value="4" /> + <param name="msmv" value="msmv=ndp"/> + <param name="acc" value="21" /> + <param name="rej" value="39" /> + <param name="thms" value="0.3" /> + <param name="thmsms" value="0.2" /> + <param name="thcomb" value="0.1" /> + <param name="sort" value="sort=combmv" /> + <conditional name="elemfilt_cond"> + <param name="elemfilt_select" value="elem"/> + <param name="el" value="C,N,O,P,S,H,Cl,Br,F,I" /> + </conditional> + <param name="het" value="het" /> + <param name="hcf" value="hcf" /> + <param name="wm" value="wm=sqrt"/> + <conditional name="wi_cond"> + <param name="wi" value="wi=log"/> + <param name="exp" value="2.31"/> + </conditional> + <param name="oei" value="oei" /> + <param name="dbeexc" value="1" /> + <output name="out" ftype="tabular" file="CreatineMsMs.out" lines_diff="3"/> + <assert_command> + <has_text text=" ms=" /> + <has_text text=" msms=" /> + <not_has_text text=" exist" /> + <has_text text=" m=111.0201" /> + <has_text text=" ion=M-H" /> + <has_text text=" ppm=4" /> + <has_text text=" msmv=ndp" /> + <has_text text=" acc=21" /> + <has_text text=" rej=39" /> + <has_text text=" thms=0.3" /> + <has_text text=" thmsms=0.2" /> + <has_text text=" thcomb=0.1" /> + <has_text text=" sort=combmv" /> + <has_text text=" el=CNOPSHClBrFI" /> + <not_has_text text=" oc " /> + <not_has_text text=" ff=" /> + <has_text text=" het " /> + <not_has_text text=" vsp=" /> + <not_has_text text=" vsp2mv=" /> + <not_has_text text=" vsm2ap2=" /> + <has_text text=" hcf " /> + <has_text text=" wm=sqrt " /> + <has_text text=" wi=log " /> + <has_text text=" exp=2.31 " /> + <has_text text=" oei " /> + <has_text text=" dbeexc=1" /> + <not_has_text text=" ivsm2mv=" /> + <not_has_text text=" ivsm2ap2=" /> + <not_has_text text=" oms=" /> + <not_has_text text=" omsms=" /> + <not_has_text text=" oclean=" /> + <not_has_text text=" analyze " /> + <not_has_text text=" loss " /> + <not_has_text text=" intens " /> + <not_has_text text=" dbe " /> + <not_has_text text=" cm " /> + <not_has_text text=" pc " /> + <not_has_text text=" sc " /> + </assert_command> + </test> + </tests> + <help><![CDATA[ + +**Overview** + +The computer program genform generates candidate molecular formulas from high-resolution +MS data. It calculates match values (MV) that show how well candidate molecular formulas fit the MS +isotope peak distributions (MS MV) and the high-resolution MS/MS fragment peak masses (MSMS +MV). Finally it computes a combined match value from these two scores. This software can be +regarded as a further development of the ElCoCo and MolForm modules of MOLGEN-MS with a clear +specialization towards MS/MS. + +**Input** + +MS and MS/MS centroided spectra are given as tab separated files with two columns: + +1. m/z +2. intensity + +**Output** + +Main output containing a list of all possible molecular formulas, further options can be chosen: + +1. if the explained peaks shall also be written to the output +2. if the explanation shall be given as molecular formulas for the fragment or as neutral losses +3. double bond equivalents for each molecular formula +4. calculated ion masses +5. output match values in percent + +Output structure: + +molecular fomula / (double bond equivalent) / (calculated mass) / ppm / MS MV / MSMS MV / combined MV + +ppm: The value ppm denotes the relative deviation of +the calculated mass of the molecular ion from the mass of the basepeak (basemass) in the MS in +parts per million (ppm). + +MS MV: It is calculated from measured and +theoretical isotope peak intensities. The MV ranges from 0 to 1. The better theoretical and measured +isotope distributions fit, the higher is the MV. There are three different algorithms implemented for +calculating the MS MV, which are nomalized dot product, nomalized sum of squared errors and the normalized sum of absolute errors. + +MSMS MV: It shows how well the masses of the MS/MS fit possible fragments of the candidate molecular formula. Again, the MS/MS MV is a value +between 0 and 1, whereby higher values reflect a better fit. + +combined MV: combined match value + +Example output: + +======== === =========== ====== ======== ========= ======== +C4H9N3O2 2 132.07675 -0.8 96.674 100.000 96.674 +======== === =========== ====== ======== ========= ======== + +**Advanced options** + +... + + ]]></help> + + <citations> + <citation type="doi">10.3390/metabo3020440</citation> + <citation type="bibtex">@article{meringer2011ms, + title={MS/MS data improves automated determination of molecular formulas by mass spectrometry}, + author={Meringer, Markus and Reinker, Stefan and Zhang, Juan and Muller, Alban}, + journal={MATCH Commun. Math. Comput. Chem}, + volume={65}, + number={2}, + pages={259--290}, + year={2011} + }</citation> + </citations> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/CreatineMs.out Thu Sep 12 12:20:47 2019 -0400 @@ -0,0 +1,1 @@ +C4H9N3O2 -0.8 0.96674
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/CreatineMs.txt Thu Sep 12 12:20:47 2019 -0400 @@ -0,0 +1,2 @@ +132.07686 147049184 +133.08012 4004960.8
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/CreatineMsMs-oclean.out Thu Sep 12 12:20:47 2019 -0400 @@ -0,0 +1,2 @@ + 111.02010 0.04273602 + 132.07730 1.00000000
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/CreatineMsMs-oms.out Thu Sep 12 12:20:47 2019 -0400 @@ -0,0 +1,2 @@ + 132.07686 0.97348659 + 133.08012 0.02651341
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/CreatineMsMs-omsms.out Thu Sep 12 12:20:47 2019 -0400 @@ -0,0 +1,2 @@ + 111.02010 1.00000000 + 132.07730 1.00000000