Mercurial > repos > pieterlukasse > prims_proteomics
changeset 19:d31c6978d9d0
fixes for NapQ
| author | pieter.lukasse@wur.nl |
|---|---|
| date | Mon, 26 Jan 2015 06:24:15 +0100 |
| parents | ad911e9aaf33 |
| children | 125a6afa800c |
| files | Csv2Apml.jar MsFilt.jar NapQ.jar PRIMS.jar ProgenesisConv.jar Quantifere.jar Quantiline.jar SedMat_cli.jar napq.xml quantifere.xml static/images/napq_overview.png |
| diffstat | 11 files changed, 60 insertions(+), 6 deletions(-) [+] |
line wrap: on
line diff
--- a/napq.xml Fri Aug 01 17:22:37 2014 +0200 +++ b/napq.xml Mon Jan 26 06:24:15 2015 +0100 @@ -27,8 +27,25 @@ <param name="namingConventionCodesForSamples" type="text" size="100" value="" label="Part of run/file name that identifies the sample" help="Add the CSV list of codes that occur in the file names - and that stand for a sample code. E.g. '_S1,_S2,_S3,etc.' "/> <!-- could do regular expressions as well but this would be hard for biologists, e.g. _F\d\b --> - + and that stand for a sample code. E.g. '_S1,_S2,_S3,etc.' "> <!-- could do regular expressions as well but this would be hard for biologists, e.g. _F\d\b --> + <sanitizer> + <!-- adding more characters to the set of "valid" ones: --> + <valid> + <add preset="string.printable"/> + <add value="#"/> + <add value="@"/> + <add value="$"/> + <add value="%"/> + <add value="&"/> + <add value="*"/> + <add value="["/> + <add value="]"/> + <add value="|"/> + <add value="{"/> + <add value="}"/> + </valid> + </sanitizer> + </param> <conditional name="is2D_LC_MS"> <param name="fractions" type="boolean" truevalue="Yes" falsevalue="No" checked="false" @@ -39,7 +56,26 @@ label="Part of run/file name that identifies the 2D LC-MS fraction" help="Add the CSV list of codes that occur in the file names and that stand for a fraction code. E.g. '_F1,_F2,_F3,etc.' Use this to avoid - that each (fraction) file is seen as a separate run."/> <!-- could do regular expressions as well but this would be hard for biologists, e.g. _F\d\b --> + that each (fraction) file is seen as a separate run."> <!-- could do regular expressions as well but this would be hard for biologists, e.g. _F\d\b --> + <sanitizer> + <!-- adding more characters to the set of "valid" ones: --> + <valid> + <add preset="string.printable"/> + <add value="#"/> + <add value="@"/> + <add value="$"/> + <add value="%"/> + <add value="&"/> + <add value="*"/> + <add value="["/> + <add value="]"/> + <add value="|"/> + <add value="{"/> + <add value="}"/> + </valid> + </sanitizer> + </param> + </when> <when value="No"> </when>
--- a/quantifere.xml Fri Aug 01 17:22:37 2014 +0200 +++ b/quantifere.xml Mon Jan 26 06:24:15 2015 +0100 @@ -56,6 +56,8 @@ way different peptide identifications from the same sample but measured in different fractions can be merged together. Otherwise each (fraction) file is seen as a separate sample."/> <!-- could do regular expressions as well but this would be hard for biologists, e.g. _F\d\b --> + <!-- on help above: the given codes are removed from source name...separate features are clustered, not peptides, peptides + are quantified based on summing features (raw), or summing patterns : TODO document the quantification columns present in the output CSV --> </when> <when value="No"> </when> @@ -89,15 +91,17 @@ sample intensity values correlation. Set here the minimum correlation expected between grouped members. This is used to guide the clustering algorithm."/> <!-- simple extra heuristics to remove some "noise" protein hits --> - <param name="minProtCoverage" type="float" size="10" value="5.0" label="Minimum protein coverage (%)" help="This will remove proteins that have a too small - portion of their sequence covered by peptide matches."/> + <param name="minProtCoverage" type="float" size="10" value="0.0" label="Minimum protein coverage (%)" help="Set this to e.g. 5.0 if you have protein coverage + information in your data. This will remove proteins that have a too small portion of their sequence covered by peptide matches."/> + <!-- TODO : ADD warning to report if this is left 0 and no coverage is found ...or maybe validate the other way around--> <param name="minAboveAverageHits" type="integer" size="10" value="1" label="Minimum number of different peptide matches with a score above average" help="This will remove proteins that do not have enough reasonable peptides hits."/> <param name="minNrIdsForInferencePeptide" type="integer" size="10" value="1" label="Minimum number of peptide identifications for inference peptides" help="Minimum number of peptide identifications a peptide needs to be used as inference peptide for secondary proteins."/> - + <!-- currently, when one feature clusters with foreign peptide, then it is not inference peptide anymore...quite strict, could be less strict + by letting user indicate for example: 90% of features should be inference features...then it is an inference pep. See QuantifereTool.inferSecondaryProteins() --> <param name="functionalAnnotationCSV" type="data" format="csv,txt,tsv" optional="true" label="(Functional)annotation mapping file (csv or tsv format)" @@ -207,6 +211,20 @@ .. _Cytoscape chartplugin: http://apps.cytoscape.org/apps/chartplugin +**References** + +If you use this Galaxy tool in work leading to a scientific publication please +cite the following papers: + +Pieter N. J. Lukasse and Antoine H. P. America (2014). +Protein Inference Using Peptide Quantification Patterns. +http://dx.doi.org/10.1021/pr401072g + </help> + <citations> + <citation type="doi">10.1021/pr401072g</citation> <!-- example + see also https://wiki.galaxyproject.org/Admin/Tools/ToolConfigSyntax#A.3Ccitations.3E_tag_set + --> + </citations> </tool>