# HG changeset patch # User Davide Albanese # Date 1362864451 -3600 # Node ID 51eb500d652647b4aa0983ba5ed8a0bfd0dce517 # Parent 3e5da170ffdd20e381f8a98b4c6384c7f6c15a9a check_id_map minor fix diff -r 3e5da170ffdd -r 51eb500d6526 check_id_map.xml --- a/check_id_map.xml Sat Mar 09 22:05:13 2013 +0100 +++ b/check_id_map.xml Sat Mar 09 22:27:31 2013 +0100 @@ -1,47 +1,49 @@ - - + + + Checks user's metadata mapping file for required data, valid format - qiime + check_id_map.py - check_id_map.py - - -m $mapping_fp - - #if str($char_replace): - -c $char_replace - #end if - - #if $not_barcoded: - -b - #end if - - #if $variable_len_barcodes: - -B - #end if - - #if $disable_primer_check: - -p - #end if - - #if str($added_demultiplex_field): - -j $added_demultiplex_field - #end if - ; - rm `basename $mapping_fp .txt`'.html' - ; - rm overlib.js - ; - mv `basename $mapping_fp .txt`'.log' $out_log - ; - mv `basename $mapping_fp .txt`'_corrected.txt' $out_txt + + check_id_map.py + + -m $mapping_fp + + #if str($char_replace): + -c $char_replace + #end if + + #if $not_barcoded: + -b + #end if + + #if $variable_len_barcodes: + -B + #end if + + #if $disable_primer_check: + -p + #end if + + #if str($added_demultiplex_field): + -j $added_demultiplex_field + #end if + ; + rm `basename $mapping_fp .txt`'.html' + ; + rm overlib.js + ; + mv `basename $mapping_fp .txt`'.log' $out_log + ; + mv `basename $mapping_fp .txt`'_corrected.txt' $out_txt - + @@ -56,64 +58,63 @@ - - -Check ID Map checks:: + + Check ID Map checks:: + + 1. The BarcodeSequence, LinkerPrimerSequences, and ReversePrimer fields + have valid IUPAC DNA characters, and BarcodeSequence characters + are non-degenerate (error) -1. The BarcodeSequence, LinkerPrimerSequences, and ReversePrimer fields - have valid IUPAC DNA characters, and BarcodeSequence characters - are non-degenerate (error) + 2. The SampleID, BarcodeSequence, LinkerPrimerSequence, and Description + headers are present (error) -2. The SampleID, BarcodeSequence, LinkerPrimerSequence, and Description - headers are present (error) - -3. There are not duplicate header fields (error) - -4. There are not duplicate barcodes (error) + 3. There are not duplicate header fields (error) + + 4. There are not duplicate barcodes (error) -5. Barcodes are of the same length. Suppressed when - variable_len_barcode flag is passed (warning) + 5. Barcodes are of the same length. Suppressed when + variable_len_barcode flag is passed (warning) -6. The headers do not contain invalid characters (alphanumeric and - underscore only) (warning) + 6. The headers do not contain invalid characters (alphanumeric and + underscore only) (warning) -7. The data fields do not contain invalid characters (alphanumeric, - underscore, space, and +-%./:,; characters) (warning) + 7. The data fields do not contain invalid characters (alphanumeric, + underscore, space, and +-%./:,; characters) (warning) -8. SampleID fields are MIENS compliant (only alphanumeric - and . characters). (warning) + 8. SampleID fields are MIENS compliant (only alphanumeric + and . characters). (warning) -9. There are no duplicates when the primer and variable length - barcodes are appended (error) + 9. There are no duplicates when the primer and variable length + barcodes are appended (error) -10. There are no duplicates when barcodes and added demultiplex - fields (-j option) are combined (error) - -11. Data fields are not found beyond the Description column (warning) + 10. There are no duplicates when barcodes and added demultiplex + fields (-j option) are combined (error) -Details about the metadata mapping file format can be found here: -http://www.qiime.org/documentation/file_formats.html#metadata-mapping-files + 11. Data fields are not found beyond the Description column (warning) -Errors and warnings are saved to a log file. Errors can be caused -by problems with the headers, invalid characters in barcodes or -primers, or by duplications in SampleIDs or barcodes. + Details about the metadata mapping file format can be found here: + http://www.qiime.org/documentation/file_formats.html#metadata-mapping-files -Warnings can arise from invalid characters and variable length -barcodes that are not specified with the --variable_len_barcode. -Warnings will contain a reference to the cell (row,column) that -the warning arose from. + Errors and warnings are saved to a log file. Errors can be caused + by problems with the headers, invalid characters in barcodes or + primers, or by duplications in SampleIDs or barcodes. + + Warnings can arise from invalid characters and variable length + barcodes that are not specified with the --variable_len_barcode. + Warnings will contain a reference to the cell (row,column) that + the warning arose from. -In addition to the log file, a 'corrected_mapping' file will be -created. Any invalid characters will be replaced with '.' -characters in the SampleID fields (to enforce MIENS compliance) -and text in other data fields will be replaced with the character -specified by the -c parameter, which is an underscore '_' by -default. + In addition to the log file, a 'corrected_mapping' file will be + created. Any invalid characters will be replaced with '.' + characters in the SampleID fields (to enforce MIENS compliance) + and text in other data fields will be replaced with the character + specified by the -c parameter, which is an underscore '_' by + default. -If pooled primers are used, separate with a comma. For instance, -a pooled set of three 27f primers (used to increase taxonomic -coverage) could be specified in the LinkerPrimerSequence fields as -such: -AGGGTTCGATTCTGGCTCAG,AGAGTTTGATCCTGGCTTAG,AGAATTTGATCTTGGTTCAG - + If pooled primers are used, separate with a comma. For instance, + a pooled set of three 27f primers (used to increase taxonomic + coverage) could be specified in the LinkerPrimerSequence fields as + such: + AGGGTTCGATTCTGGCTCAG,AGAGTTTGATCCTGGCTTAG,AGAATTTGATCTTGGTTCAG +