Mercurial > repos > mvdbeek > mismatch_frequencies
annotate mismatch_frequencies.xml @ 19:f7da7f3e2c98
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
| author | mvdbeek |
|---|---|
| date | Sun, 24 May 2015 11:12:24 -0400 |
| parents | e3d950e52e38 |
| children | 11a1dae1ab8e |
| rev | line source |
|---|---|
|
19
f7da7f3e2c98
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents:
18
diff
changeset
|
1 <tool id="mismatch_frequencies" name="Mismatch Frequencies" version="0.0.8" hidden="false" > |
| 12 | 2 <description>Analyze mismatch frequencies in BAM/SAM alignments</description> |
| 3 <requirements> | |
| 13 | 4 <requirement type="package" version="0.7.7">pysam</requirement> |
| 12 | 5 <requirement type="package" version="0.14.1">pandas</requirement> |
| 17 | 6 <requirement type="package" version="1.2.1">matplotlib</requirement> |
| 12 | 7 </requirements> |
| 8 <command interpreter="python">mismatch_frequencies.py --input | |
| 9 #for i in $rep | |
| 10 "$i.input_file" | |
| 11 #end for | |
| 12 --name | |
| 13 #for i in $rep | |
| 14 "$i.input_file.name" | |
| 15 #end for | |
| 16 --output_pdf $output_pdf --output_tab $output_tab --min $min_length --max $max_length | |
| 17 --n_mm $number_of_mismatches | |
| 18 --five_p $five_p | |
| 19 --three_p $three_p | |
|
19
f7da7f3e2c98
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents:
18
diff
changeset
|
20 --expanded_output_tab $expanded_tab |
|
f7da7f3e2c98
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents:
18
diff
changeset
|
21 --possible_mismatches $possible_mismatches |
| 12 | 22 </command> |
| 23 <inputs> | |
| 16 | 24 <repeat name="rep" title="alignment files"> |
| 25 <param name="input_file" type="data" format="bam,sam" label="Alignment file" help="The input alignment file(s) for which to analyze the mismatches."/> | |
| 12 | 26 </repeat> |
| 27 <param name="number_of_mismatches" label="Maximum number of allowed mismatches per read" help="Discard reads with more than the chosen number of mismatches from the frequency calculation" type="integer" value="3"/> | |
|
19
f7da7f3e2c98
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents:
18
diff
changeset
|
28 <param name="possible_mismatches" label="Specify mismatches that should be counted" help="Ignores mismatches that are not listed" type="text" value="AC AG AT CA CG CT GA GC GT TA TC TG"> |
|
f7da7f3e2c98
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents:
18
diff
changeset
|
29 <validator type="expression" message="Allowed values are AGCTN, seperated by space.">len([False for char in value if not char in " AGCTN"]) == 0</validator> |
|
f7da7f3e2c98
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents:
18
diff
changeset
|
30 </param> |
| 12 | 31 <param name="min_length" label="Minumum read length to analyse" type="integer" value="21"/> |
| 32 <param name="max_length" label="Maximum read length to analyse" type="integer" value="21"/> | |
| 33 <param name="five_p" label="Ignore mismatches in the first N nucleotides of a read" type="integer" value="0"/> | |
| 34 <param name="three_p" label="Ignore mismatches in the last N nucleotides of a read" help="useful to discriminate between tailing events and editing events" type="integer" value="3"/> | |
|
19
f7da7f3e2c98
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents:
18
diff
changeset
|
35 <param help="Output expanded tabular format" label="Nucleotide mismatches per reference sequence" name="expanded" type="select"> |
|
f7da7f3e2c98
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents:
18
diff
changeset
|
36 <option select="true" value="false">No</option> |
|
f7da7f3e2c98
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents:
18
diff
changeset
|
37 <option value="expanded">Yes</option> |
|
f7da7f3e2c98
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents:
18
diff
changeset
|
38 </param> |
| 12 | 39 </inputs> |
| 40 <outputs> | |
| 41 <data format="tabular" name="output_tab" /> | |
|
19
f7da7f3e2c98
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents:
18
diff
changeset
|
42 <data format="fasta" name="expanded_tab"> |
|
f7da7f3e2c98
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents:
18
diff
changeset
|
43 <filter> expanded == "expanded"</filter> |
|
f7da7f3e2c98
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents:
18
diff
changeset
|
44 </data> |
| 12 | 45 <data format="pdf" name="output_pdf" /> |
| 46 </outputs> | |
| 47 <tests> | |
| 48 <test> | |
| 49 <param name="rep_0|input_file" value="3mismatches_ago2ip_s2.bam" ftype="bam" /> | |
| 18 | 50 <param name="rep_1|input_file" value="3mismatches_ago2ip_ovary.bam" ftype="bam" /> |
| 12 | 51 <param name="number_of_mismatches" value="1" /> |
| 52 <param name="min_length" value="21" /> | |
| 53 <param name="max_length" value="21" /> | |
| 18 | 54 <param name="three_p" value="0" /> |
| 55 <param name="five_p" value="0" /> | |
| 56 <output name="tabular" file="mismatch.tab" ftype="tabular"/> | |
| 57 <!-- | |
| 58 <output name="pdf" file="mismatch.pdf" ftype="pdf"/> | |
| 59 --> | |
| 60 </test> | |
| 61 </tests> | |
| 62 <help> | |
| 63 | |
| 64 .. class:: infomark | |
| 65 | |
| 66 | |
| 67 ***What it does*** | |
| 68 | |
| 69 This tool reconstitues for each aligned read of an alignment file in SAM/BAM format whether | |
| 70 a mismatch is annotated in the MD tag, and if that is the case counts the identity of the | |
| 71 mismatch relative to the reference sequence. The output is a PDF document with the calculated | |
| 72 frequency for each mismatch that occured relative to the total number of valid reads and a table | |
| 73 with the corresponding values. Read length can be limited to a specific read length, and 5 prime and | |
| 74 3 prime-most nucleotides of a read can be ignored. | |
| 75 | |
| 76 ---- | |
| 77 | |
| 78 .. class:: warningmark | |
| 79 | |
| 80 ***Warning*** | |
| 81 | |
| 82 This tool skips all read that have insertions and has been tested only with bowtie and bowtie2 | |
| 83 generated alignment files. | |
| 84 | |
| 85 Written by Marius van den Beek, m.vandenbeek at gmail . com | |
| 86 </help> | |
|
19
f7da7f3e2c98
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents:
18
diff
changeset
|
87 <citations> |
|
f7da7f3e2c98
planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents:
18
diff
changeset
|
88 </citations> |
| 12 | 89 </tool> |