| Previous changeset 14:c9944a2600f1 (2024-03-18) Next changeset 16:b0fe3e482cb7 (2024-10-28) |
|
Commit message:
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/salmon commit d5c7ca22af1d4f0eaa7a607886554bebb95e8c50 |
|
added:
macros.xml.orig |
| b |
| diff -r c9944a2600f1 -r b8f3b923d066 macros.xml.orig --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml.orig Mon Oct 28 17:36:04 2024 +0000 |
| [ |
| b'@@ -0,0 +1,611 @@\n+<macros>\n+ <token name="@VERSION@">1.4.0</token>\n+ <token name="@GALAXY_VERSION@">galaxy0</token>\n+ <token name="@IDX_VERSION@">q7</token>\n+ <xml name="requirements">\n+ <requirements>\n+ <requirement type="package" version="@VERSION@">salmon</requirement>\n+ <requirement type="package" version="1.3">seqtk</requirement>\n+ <requirement type="package" version="1.10">samtools</requirement>\n+ <requirement type="package" version="0.2.0">vpolo</requirement>\n+ <requirement type="package" version="1.0.3">pandas</requirement>\n+ <requirement type="package" version="1.4.1">scipy</requirement>\n+ </requirements>\n+ </xml>\n+\n+ <xml name="geometry">\n+ <section name="read_geometry">\n+ <param name="geometry" type="select" label="The read one wich your sequence is located" help="">\n+ <option value="1" selected="True">forward read (1)</option>\n+ <option value="2">reverse read (2)</option>\n+ </param>\n+ <repeat name="range" title="Specify the position of your sequence" min="1" max="2">\n+ <param name="start" type="integer" value="1" label="The index of the start base" help="The counting is 1-based." />\n+ <param name="end" type="integer" value="" optional="true" label="The index of the end base" help="The counting is 1-based. Leaf blank for \'until end\'." />\n+ </repeat>\n+ </section>\n+ <!--\n+ -\\-read-geometry 2[1-end] -\\-bc-geometry 1[1-16] -\\-umi-geometry 1[17-26]\n+ This specifies that the "sequence" read (the biological sequence to be aligned) comes from read 2,\n+ and it spans from the first index 1 (this syntax used 1-based indexing) until the end of the read.\n+ Likewise, the barcode derives from read 1 and occupies positions 1-16, and the UMI comes from read 1\n+ and occupies positions 17-26. The syntax can specify multiple ranges, and they will simply be concatenated\n+ together to produce the string. For example, one could specify -\\-bc-geometry 1[1-8,16-23] to designate that\n+ the barcode should be taken from the substring in positions 1-8 of read 1 followed by the substring in positions 16-23 of read 1.\n+ -->\n+ </xml>\n+\n+ <token name="@geometry@"><![CDATA[\n+ #set $range = ""\n+ #for $pos $read_geometry.range:\n+ #set $range +=\n+ #end for\n+\n+ --read-geometry ${read_geometry.geometry}[]\n+ ln -s "$geneMap" ./geneMap.${geneMap.ext} &&\n+ #end if\n+ \n+ ]]>\n+ </token>\n+\n+\n+ <xml name="stranded">\n+ <param name="strandedness" type="select" label="Specify the strandedness of the reads">\n+ <option value="U" selected="True">Not stranded (U)</option>\n+ <option value="SF">read comes from the forward strand (SF)</option>\n+ <option value="SR">read comes from the reverse strand (SR)</option>\n+ </param>\n+ </xml>\n+ <xml name="orient">\n+ <param name="orientation" type="select" label="Relative orientation of reads within a pair">\n+ <option value="M">Mates are oriented in the same direction (M = matching)</option>\n+ <option value="O">Mates are oriented away from each other (O = outward)</option>\n+ <option value="I" selected="True">Mates are oriented toward each other (I = inward)</option>\n+ </param>\n+ </xml>\n+ <xml name="index">\n+ <conditional name="refTranscriptSource">\n+ <param name="TranscriptSource" type="select" label="Select a reference transcriptome from your history or use a built-in index?" help="Built-ins were indexed using default options">\n+ <option value="indexed">Use a built-in index</option>\n+ <option value="history" selected="True">Use one from the history</option>\n+ </param>\n+ <when value="indexed">\n+ '..b' ${adv.noGammaDraw}\n+ #if str($adv.numBootstraps):\n+ --numBootstraps \'${adv.numBootstraps}\'\n+ #end if\n+ ${adv.bootstrapReproject}\n+ #if $adv.thinningFactor:\n+ --thinningFactor \'${adv.thinningFactor}\'\n+ #end if\n+ ${adv.perTranscriptPrior}\n+ --sigDigits \'${adv.sigDigits}\'\n+ #if $adv.vbPrior:\n+ --vbPrior \'${adv.vbPrior}\'\n+ #end if\n+ ${adv.writeOrphanLinks}\n+ ${adv.writeUnmappedNames}\n+ -o ./output\n+ ]]>\n+ </token>\n+ <token name="@qmerge@"><![CDATA[\n+ #import re\n+\n+ #for $counter, $input_data in enumerate($quantfiles):\n+ rank_of_series=$counter\n+ mkdir ${counter}.quantmerge &&\n+ ln -s $input_data.quants ${counter}.quantmerge/quant.sf &&\n+ #end for\n+ salmon quantmerge\n+ --quants *.quantmerge\n+ --names\n+ #for $counter, $input_data in enumerate($quantfiles):\n+ #if $input_data.names and re.sub(\' \', \'\', \'$input_data.names\') != \'\':\n+ \'${input_data.names}\'\n+ #else:\n+ #set $identifier=re.sub(\'[^\\w\\-\\s]\', \'_\', str($input_data.quants.element_identifier))\n+ "$identifier"\n+ #end if\n+ #end for\n+ --column \'${column}\'\n+ ${genes}\n+ #if $missing:\n+ --missing \'${missing}\'\n+ #end if\n+ -o qmergeout.tab\n+ ]]>\n+ </token>\n+ <token name="@salmonhelp@"><![CDATA[\n+ Salmon is a lightweight method for quantifying transcript abundance from RNA\xe2\x80\x93seq reads, combining a dual-phase parallel inference algorithm and feature-rich bias models with an ultra-fast read mapping procedure.\n+\n+ The salmon package contains 4 tools:\n+\n+ * Index: creates a salmon index\n+\n+ * Quant: quantifies a sample (Reads or mapping-based)\n+\n+ * Alevin: Single-cell analysis\n+\n+ * Quantmerge: Merges multiple quantifications into a single file\n+\n+ Galaxy divides these four into three separate tools in the IUC toolshed:\n+\n+ * Salmon quant\n+\n+ * Salmon quantmerge\n+\n+ * Alevin\n+ ]]>\n+ </token>\n+ <token name="@alevinhelp@"><![CDATA[\n+ Alevin is a tool \xe2\x80\x94 integrated with the salmon software \xe2\x80\x94 that introduces a family of algorithms for quantification and analysis of 3\xe2\x80\x99 tagged-end single-cell sequencing data. Currently alevin supports the following two major droplet based single-cell protocols:\n+\n+ * Drop-seq\n+\n+ * 10x-Chromium v1/2/3\n+\n+ Alevin works under the same indexing scheme (as salmon) for the reference, and consumes the set of FASTA/Q files(s) containing the Cellular Barcode(CB) + Unique Molecule identifier (UMI) in one read file and the read sequence in the other. Given just the transcriptome and the raw read files, alevin generates a cell-by-gene count matrix (in a fraction of the time compared to other tools).\n+\n+ Alevin works in two phases. In the first phase it quickly parses the read file containing the CB and UMI information to generate the frequency distribution of all the observed CBs, and creates a lightweight data-structure for fast-look up and correction of the CB. In the second round, alevin utilizes the read-sequences contained in the files to map the reads to the transcriptome, identify potential PCR/sequencing errors in the UMIs, and performs hybrid de-duplication while accounting for UMI collisions. Finally, a post-abundance estimation CB whitelisting procedure is done and a cell-by-gene count matrix is generated.\n+\n+ For further information regarding the tool and its optional parameters, visit the `Alevin <https://salmon.readthedocs.io/en/latest/alevin.html?highlight=alevin>`__ and `Salmon <https://salmon.readthedocs.io/en/latest/index.html>`__ wikis.\n+ ]]>\n+ </token>\n+</macros>\n' |