Mercurial > repos > miller-lab > genome_diversity
annotate find_intervals.xml @ 6:626b714f72bb
add gd_ploteig
| author | Richard Burhans <burhans@bx.psu.edu> |
|---|---|
| date | Tue, 10 Apr 2012 13:51:19 -0400 |
| parents | 7a94f11fe71f |
| children | e29f4d801bb0 |
| rev | line source |
|---|---|
| 0 | 1 <tool id="gd_find_intervals" name="Find remarkable" version="1.0.0"> |
| 2 <description>genomic intervals</description> | |
| 3 | |
| 4 <command interpreter="python"> | |
|
4
7a94f11fe71f
change output.extra_files_path to output.files_path
Richard Burhans <burhans@bx.psu.edu>
parents:
0
diff
changeset
|
5 find_intervals.py "$input" "$input.metadata.dbkey" "$output" "$output.files_path" |
| 0 | 6 |
| 7 #if $override_metadata.choice == "0" | |
| 8 "$input.metadata.ref" "$input.metadata.rPos" | |
| 9 #else | |
| 10 "$override_metadata.ref_col" "$override_metadata.rpos_col" | |
| 11 #end if | |
| 12 | |
| 13 "$score_col" "$shuffles" | |
| 14 | |
| 15 #if $cutoff.type == 'percentage' | |
| 16 "$cutoff.cutoff_pct" | |
| 17 #else | |
| 18 "=$cutoff.cutoff_val" | |
| 19 #end if | |
| 20 | |
| 21 "$out_format" | |
| 22 </command> | |
| 23 | |
| 24 <inputs> | |
| 25 <param name="input" type="data" format="tabular" label="Input"> | |
| 26 <validator type="unspecified_build" message="This dataset does not have a reference species and cannot be used with this tool" /> | |
| 27 </param> | |
| 28 | |
| 29 <param name="score_col" type="data_column" data_ref="input" numerical="true" label="Column with score"/> | |
| 30 | |
| 31 <conditional name="cutoff"> | |
| 32 <param name="type" type="select" label="Cutoff type"> | |
| 33 <option value="percentage">percentage</option> | |
| 34 <option value="value">value</option> | |
| 35 </param> | |
| 36 <when value="percentage"> | |
| 37 <param name="cutoff_pct" type="float" value="95" min="0" max="100" label="Percentage cutoff"/> | |
| 38 </when> | |
| 39 <when value="value"> | |
| 40 <param name="cutoff_val" type="float" value="0.0" label="Value cutoff"/> | |
| 41 </when> | |
| 42 </conditional> | |
| 43 | |
| 44 <param name="shuffles" type="integer" min="0" value="0" label="Number of randomizations"/> | |
| 45 | |
| 46 <param name="out_format" type="select" format="integer" label="Report SNPs"> | |
| 47 <option value="0" selected="true">No</option> | |
| 48 <option value="1">Yes</option> | |
| 49 </param> | |
| 50 | |
| 51 <conditional name="override_metadata"> | |
| 52 <param name="choice" type="select" format="integer" label="Choose columns"> | |
| 53 <option value="0" selected="true">No, get columns from metadata</option> | |
| 54 <option value="1" >Yes, choose columns</option> | |
| 55 </param> | |
| 56 <when value="0" /> | |
| 57 <when value="1"> | |
| 58 <param name="ref_col" type="data_column" data_ref="input" numerical="false" label="Column with reference chromosome"/> | |
| 59 <param name="rpos_col" type="data_column" data_ref="input" numerical="true" label="Column with reference position"/> | |
| 60 </when> | |
| 61 </conditional> | |
| 62 </inputs> | |
| 63 | |
| 64 <outputs> | |
| 65 <data name="output" format="interval"> | |
| 66 <change_format> | |
| 67 <when input="out_format" value="1" format="bigwigpos" /> | |
| 68 </change_format> | |
| 69 </data> | |
| 70 </outputs> | |
| 71 | |
| 72 <tests> | |
| 73 <test> | |
| 74 <param name="input" value="test_in/sample.wsf" ftype="wsf" /> | |
| 75 <param name="score_col" value="5" /> | |
| 76 <param name="type" value="value" /> | |
| 77 <param name="cutoff_val" value="700.0" /> | |
| 78 <param name="shuffles" value="10" /> | |
| 79 <param name="out_format" value="0" /> | |
| 80 <param name="choice" value="0" /> | |
| 81 | |
| 82 <output name="output" file="test_out/find_intervals/find_intervals.interval" /> | |
| 83 </test> | |
| 84 </tests> | |
| 85 | |
| 86 <help> | |
| 87 **What it does** | |
| 88 | |
| 89 The user selects a SNP table and specifies the columns containing (1) | |
| 90 chromosome, (2) position, (3) scores (such as an Fst-value for the SNP), (4) | |
| 91 a percentage or raw score for the "cutoff" and (5) the number of times the | |
| 92 data should be randomized (only intervals with score exceeding the maximum for | |
| 93 the randomized data are reported). If a percentage (e.g. 95%) is specified | |
| 94 for #3, then that percentile of the scores is used as the cutoff; this may | |
| 95 not work well if many SNPs have the same score. The program subtracts the | |
| 96 cutoff from every score, then finds genomic intervals (i.e., consecutive runs | |
| 97 of SNPs) whose total score cannot be increased by adding or subtracting one | |
| 98 or more SNPs at the ends of the interval. | |
| 99 </help> | |
| 100 </tool> |