Mercurial > repos > davide-albanese > qiime_1_6_0
annotate check_id_map.xml @ 4:51eb500d6526 draft
check_id_map minor fix
author | Davide Albanese <davide.albanese@gmail.com> |
---|---|
date | Sat, 09 Mar 2013 22:27:31 +0100 |
parents | 3e5da170ffdd |
children | 60b88c61566f |
rev | line source |
---|---|
4
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
1 <!-- Author: Davide Albanese - Fondazione Edmud Mach, 2013 --> |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
2 |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
3 <tool id="check_id_map" name="Check ID Map" version="1.6.0-2"> |
0 | 4 <description> |
5 Checks user's metadata mapping file for required data, valid | |
6 format | |
7 </description> | |
8 <requirements> | |
4
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
9 <requirement type="binary">check_id_map.py</requirement> |
0 | 10 </requirements> |
4
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
11 <command> |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
12 check_id_map.py |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
13 |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
14 -m $mapping_fp |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
15 |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
16 #if str($char_replace): |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
17 -c $char_replace |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
18 #end if |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
19 |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
20 #if $not_barcoded: |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
21 -b |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
22 #end if |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
23 |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
24 #if $variable_len_barcodes: |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
25 -B |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
26 #end if |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
27 |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
28 #if $disable_primer_check: |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
29 -p |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
30 #end if |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
31 |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
32 #if str($added_demultiplex_field): |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
33 -j $added_demultiplex_field |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
34 #end if |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
35 ; |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
36 rm `basename $mapping_fp .txt`'.html' |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
37 ; |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
38 rm overlib.js |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
39 ; |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
40 mv `basename $mapping_fp .txt`'.log' $out_log |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
41 ; |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
42 mv `basename $mapping_fp .txt`'_corrected.txt' $out_txt |
0 | 43 </command> |
44 <inputs> | |
45 <param name="mapping_fp" label="Metadata mapping file" optional="False" type="data" format="tabular"/> | |
4
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
46 |
0 | 47 <param name="char_replace" value="_" label="Character used to replace invalid characters found in the mapping file. Must be a valid character (alphanumeric, period, or underscore)" optional="False" type="text"/> |
48 | |
49 <param name="not_barcoded" label="Set if barcodes are not present. BarcodeSequence header still required" selected="False" type="boolean"/> | |
50 | |
51 <param name="variable_len_barcodes" label="Set if variable length barcodes are present to suppress warnings about barcodes of unequal length" selected="False" type="boolean"/> | |
52 | |
53 <param name="disable_primer_check" label="Set to disable checks for primers. LinkerPrimerSequence header still required" selected="False" type="boolean"/> | |
54 | |
55 <param name="added_demultiplex_field" label="Use to add a field to use in the mapping file as additional demultiplexing (can be used with or without barcodes). All combinations of barcodes/primers and the these fields must be unique. The fields must contain values that can be parsed from the fasta labels such as 'plate=R_2008_12_09'. In this case, 'plate' would be the column header and 'R_2008_12_09' would be the field data (minus quotes) in the mapping file. To use the run prefix from the fasta label, such as '>FLP3FBN01ELBSX', where 'FLP3FBN01' is generated from the run ID, use '-j run_prefix' and set the run prefix to be used as the data under the column header 'run_prefix'" optional="False" type="text" value=""/> | |
56 </inputs> | |
57 <outputs> | |
58 <data format="txt" name="out_log" label="${tool.name} on ${mapping_fp.name}"/> | |
59 <data format="tabular" name="out_txt" label="Corrected ${mapping_fp.name}"/> | |
60 </outputs> | |
4
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
61 <help> |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
62 Check ID Map checks:: |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
63 |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
64 1. The BarcodeSequence, LinkerPrimerSequences, and ReversePrimer fields |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
65 have valid IUPAC DNA characters, and BarcodeSequence characters |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
66 are non-degenerate (error) |
0 | 67 |
4
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
68 2. The SampleID, BarcodeSequence, LinkerPrimerSequence, and Description |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
69 headers are present (error) |
0 | 70 |
4
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
71 3. There are not duplicate header fields (error) |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
72 |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
73 4. There are not duplicate barcodes (error) |
0 | 74 |
4
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
75 5. Barcodes are of the same length. Suppressed when |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
76 variable_len_barcode flag is passed (warning) |
0 | 77 |
4
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
78 6. The headers do not contain invalid characters (alphanumeric and |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
79 underscore only) (warning) |
0 | 80 |
4
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
81 7. The data fields do not contain invalid characters (alphanumeric, |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
82 underscore, space, and +-%./:,; characters) (warning) |
0 | 83 |
4
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
84 8. SampleID fields are MIENS compliant (only alphanumeric |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
85 and . characters). (warning) |
0 | 86 |
4
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
87 9. There are no duplicates when the primer and variable length |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
88 barcodes are appended (error) |
0 | 89 |
4
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
90 10. There are no duplicates when barcodes and added demultiplex |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
91 fields (-j option) are combined (error) |
0 | 92 |
4
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
93 11. Data fields are not found beyond the Description column (warning) |
0 | 94 |
4
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
95 Details about the metadata mapping file format can be found here: |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
96 http://www.qiime.org/documentation/file_formats.html#metadata-mapping-files |
0 | 97 |
4
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
98 Errors and warnings are saved to a log file. Errors can be caused |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
99 by problems with the headers, invalid characters in barcodes or |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
100 primers, or by duplications in SampleIDs or barcodes. |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
101 |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
102 Warnings can arise from invalid characters and variable length |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
103 barcodes that are not specified with the --variable_len_barcode. |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
104 Warnings will contain a reference to the cell (row,column) that |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
105 the warning arose from. |
0 | 106 |
4
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
107 In addition to the log file, a 'corrected_mapping' file will be |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
108 created. Any invalid characters will be replaced with '.' |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
109 characters in the SampleID fields (to enforce MIENS compliance) |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
110 and text in other data fields will be replaced with the character |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
111 specified by the -c parameter, which is an underscore '_' by |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
112 default. |
0 | 113 |
4
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
114 If pooled primers are used, separate with a comma. For instance, |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
115 a pooled set of three 27f primers (used to increase taxonomic |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
116 coverage) could be specified in the LinkerPrimerSequence fields as |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
117 such: |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
118 AGGGTTCGATTCTGGCTCAG,AGAGTTTGATCCTGGCTTAG,AGAATTTGATCTTGGTTCAG |
51eb500d6526
check_id_map minor fix
Davide Albanese <davide.albanese@gmail.com>
parents:
3
diff
changeset
|
119 </help> |
0 | 120 </tool> |