Mercurial > repos > iuc > pairtools_dedup
comparison dedup.xml @ 2:74df4a44471b draft
planemo upload for repository https://github.com/open2c/pairtools commit abd18c860877b2100e02019b4b597d6d2569994e
| author | iuc |
|---|---|
| date | Thu, 18 Sep 2025 05:56:33 +0000 |
| parents | c99b93043a7f |
| children | e36bce668b44 |
comparison
equal
deleted
inserted
replaced
| 1:054230c3643d | 2:74df4a44471b |
|---|---|
| 1 <tool id="pairtools_dedup" name="Pairtools dedup" version="@TOOL_VERSION@+galaxy@SUFFIX_VERSION@" profile="23.2" license="MIT"> | 1 <tool id="pairtools_dedup" name="Pairtools dedup" version="@TOOL_VERSION@+galaxy@SUFFIX_VERSION@" profile="@PROFILE_VERSION@" license="MIT"> |
| 2 <description>Find and remove PCR/optical duplicates</description> | 2 <description>Find and remove PCR/optical duplicates</description> |
| 3 <macros> | 3 <macros> |
| 4 <import>macros.xml</import> | 4 <import>macros.xml</import> |
| 5 </macros> | 5 </macros> |
| 6 <expand macro="requirements"/> | 6 <expand macro="requirements"/> |
| 7 <command detect_errors="exit_code"><![CDATA[ | 7 <command detect_errors="exit_code"><![CDATA[ |
| 8 #if $pairs_path.is_of_type('4dn_pairs.gz') or $pairs_path.is_of_type('4dn_pairsam.gz'): | |
| 9 #set $input_link = "input.gz" | |
| 10 #set $output_dedup_pairs_link = "output_dedup_pairs.ga" | |
| 11 #set $output_dups_pairs_link = "output_dups_pairs.gz" | |
| 12 #else | |
| 13 #set $input_link = "input" | |
| 14 #set $output_dedup_pairs_link = "output_dedup_pairs" | |
| 15 #set $output_dups_pairs_link = "output_dups_pairs" | |
| 16 #end if | |
| 17 ln -s '$pairs_path' '$input_link' && | |
| 18 ln -s '$output_dedup_pairs' '$output_dedup_pairs_link' && | |
| 19 ln -s '$output_dups_pairs' '$output_dups_pairs_link' && | |
| 8 pairtools dedup | 20 pairtools dedup |
| 9 '$pairs_path' | 21 '$input_link' |
| 10 -o '$output_dedup_pairs' | 22 -o '$output_dedup_pairs_link' |
| 11 #if $output_dups: | 23 #if $output_dups: |
| 12 --output-dups '$output_dups_pairs' | 24 --output-dups '$output_dups_pairs_link' |
| 13 #end if | 25 #end if |
| 14 $mark_dups | 26 $mark_dups |
| 15 #if $output_stats: | 27 #if $output_stats: |
| 16 --output-stats '$dedup_pairs_stats' | 28 --output-stats '$dedup_pairs_stats' |
| 17 #end if | 29 #end if |
| 30 #if $output_bytile_stats: | |
| 31 --keep-parent-id | |
| 32 --output-bytile-stats '$dedup_bytile_stats' | |
| 33 #end if | |
| 18 --nproc-in \${GALAXY_SLOTS:-4} | 34 --nproc-in \${GALAXY_SLOTS:-4} |
| 19 --nproc-out \${GALAXY_SLOTS:-4} | 35 --nproc-out \${GALAXY_SLOTS:-4} |
| 36 --max-mismatch ${max_mismatch} | |
| 20 ]]></command> | 37 ]]></command> |
| 21 <inputs> | 38 <inputs> |
| 22 <param name="pairs_path" type="data" format="4dn_pairs,4dn_pairsam" label="Input pairs file" help="Input triu-flipped sorted .pairs or .pairsam file"/> | 39 <param name="pairs_path" type="data" format="4dn_pairs,4dn_pairsam,4dn_pairs.gz,4dn_pairsam.gz" label="Input pairs file" help="Input triu-flipped sorted .pairs or .pairsam file"/> |
| 23 <param argument="--mark-dups" type="boolean" truevalue="--mark-dups" falsevalue="" checked="True" label="Duplicate pairs are marked as DD in pair_type and as a duplicate in the SAM entries"/> | 40 <param argument="--mark-dups" type="boolean" truevalue="--mark-dups" falsevalue="" checked="True" label="Duplicate pairs are marked as DD in pair_type and as a duplicate in the SAM entries"/> |
| 24 <param argument="--output-dups" type="boolean" truevalue="--output-dups" falsevalue="" checked="False" label="Output file for duplicate pairs"/> | 41 <param argument="--output-dups" type="boolean" truevalue="--output-dups" falsevalue="" checked="False" label="Output file for duplicate pairs"/> |
| 25 <param argument="--output-stats" type="boolean" truevalue="--output-stats" falsevalue="" checked="False" label="Output file for duplicate statistics"/> | 42 <param argument="--output-stats" type="boolean" truevalue="--output-stats" falsevalue="" checked="False" label="Output file for duplicate statistics"/> |
| 43 <param argument="--max-mismatch" type="integer" value="3" min="0" label="Maximum number of mismatches. Pairs with both sides mapped within this distance "bp" from each other are considered duplicates."/> | |
| 44 <param argument="--output-bytile-stats" type="boolean" truevalue="--output-bytile-stats" falsevalue="" checked="False" label="Output file for optical duplicate statistics for datasets with original Illumina-generated read IDs."/> | |
| 45 <param name="compress_output" type="boolean" truevalue=".gz" falsevalue="" checked="false" label="Compress output files" /> | |
| 26 </inputs> | 46 </inputs> |
| 27 <outputs> | 47 <outputs> |
| 28 <data name="output_dedup_pairs" format_source="pairs_path" label="${tool.name} on ${on_string}: Deduplicated Pairs"/> | 48 <data name="output_dedup_pairs" label="${tool.name} on ${on_string}: Deduplicated Pairs" format_source="pairs_path" /> |
| 29 <data name="output_dups_pairs" format_source="pairs_path" label="${tool.name} on ${on_string}: Duplicate Pairs"> | 49 <data name="output_dups_pairs" label="${tool.name} on ${on_string}: Duplicate Pairs" format_source="pairs_path" > |
| 30 <filter>output_dups</filter> | 50 <filter>output_dups</filter> |
| 31 </data> | 51 </data> |
| 32 <data name="dedup_pairs_stats" format="tabular" label="${tool.name} on ${on_string}: Deduplicated stats"> | 52 <data name="dedup_pairs_stats" format="tabular" label="${tool.name} on ${on_string}: Deduplicated stats"> |
| 33 <filter>output_stats</filter> | 53 <filter>output_stats</filter> |
| 34 </data> | 54 </data> |
| 55 <data name="dedup_bytile_stats" format="tabular" label="${tool.name} on ${on_string}: By-tile stats"> | |
| 56 <filter>output_bytile_stats</filter> | |
| 57 </data> | |
| 35 </outputs> | 58 </outputs> |
| 36 <tests> | 59 <tests> |
| 37 <!--Test 01 with default parameters--> | 60 <!--Test 01 with default parameters--> |
| 38 <test expect_num_outputs="1"> | 61 <test expect_num_outputs="1"> |
| 39 <param name="pairs_path" value="output_sorted_pairs.pairsam"/> | 62 <param name="pairs_path" ftype="4dn_pairsam" value="output_sorted_pairs.pairsam"/> |
| 40 <output name="output_dedup_pairs" file="output_dedup_pairs.pairsam" lines_diff="20"/> | 63 <output name="output_dedup_pairs" file="output_dedup_pairs.pairsam" ftype="4dn_pairsam" lines_diff="20" /> |
| 41 </test> | 64 </test> |
| 42 <!--Test 02 mark_dups enabled and output_dups--> | 65 <!--Test 02 with default parameters and compressed output--> |
| 66 <test expect_num_outputs="1"> | |
| 67 <param name="pairs_path" ftype="4dn_pairsam" value="output_sorted_pairs.pairsam"/> | |
| 68 <param name="compress_output" value="true"/> | |
| 69 <output name="output_dedup_pairs" file="output_dedup_pairs.pairsam" ftype="4dn_pairsam" decompress="true" lines_diff="20"/> | |
| 70 </test> | |
| 71 <!--Test 03 with default parameters and compressed iput--> | |
| 72 <test expect_num_outputs="1"> | |
| 73 <param name="pairs_path" ftype="4dn_pairsam" value="output_sorted_pairs.pairsam.gz"/> | |
| 74 <output name="output_dedup_pairs" file="output_dedup_pairs.pairsam" ftype="4dn_pairsam" lines_diff="20"/> | |
| 75 </test> | |
| 76 <!--Test 04 mark_dups enabled and output_dups--> | |
| 43 <test expect_num_outputs="2"> | 77 <test expect_num_outputs="2"> |
| 44 <param name="pairs_path" value="output_sorted_pairs.pairsam"/> | 78 <param name="pairs_path" ftype="4dn_pairsam" value="output_sorted_pairs.pairsam"/> |
| 45 <param name="mark_dups" value="true"></param> | 79 <param name="mark_dups" value="true"></param> |
| 46 <param name="output_dups" value="true"></param> | 80 <param name="output_dups" value="true"></param> |
| 47 <output name="output_dedup_pairs" file="output_dedup_pairs_markdups.pairsam" lines_diff="20"/> | 81 <output name="output_dedup_pairs" file="output_dedup_pairs_markdups.pairsam" ftype="4dn_pairsam" lines_diff="20"/> |
| 48 <output name="output_dups_pairs" file="output_dups_pairs_markdups.pairsam" lines_diff="20"/> | 82 <output name="output_dups_pairs" file="output_dups_pairs_markdups.pairsam" ftype="4dn_pairsam" lines_diff="20"/> |
| 49 </test> | 83 </test> |
| 50 <!--Test 03 mark_dups and output_stats enabled--> | 84 <!--Test 05 mark_dups and output_stats enabled--> |
| 51 <test expect_num_outputs="2"> | 85 <test expect_num_outputs="2"> |
| 52 <param name="pairs_path" value="output_sorted_pairs.pairsam"/> | 86 <param name="pairs_path" ftype="4dn_pairsam" value="output_sorted_pairs.pairsam"/> |
| 53 <param name="mark_dups" value="true"></param> | 87 <param name="mark_dups" value="true"></param> |
| 54 <param name="output_stats" value="true"></param> | 88 <param name="output_stats" value="true"></param> |
| 55 <output name="output_dedup_pairs" file="output_dedup_pairs_markdups.pairsam" lines_diff="20"/> | 89 <output name="output_dedup_pairs" file="output_dedup_pairs_markdups.pairsam" ftype="4dn_pairsam" lines_diff="20"/> |
| 56 <output name="dedup_pairs_stats" file="output_dedup_pairs.stats" lines_diff="20"/> | 90 <output name="dedup_pairs_stats" file="output_dedup_pairs.stats" ftype="tabular" lines_diff="20"/> |
| 91 </test> | |
| 92 <!--Test 06 mark_dups and output_stats enabled, max_mismatch set to 0--> | |
| 93 <test expect_num_outputs="2"> | |
| 94 <param name="pairs_path" ftype="4dn_pairsam" value="output_sorted_pairs.pairsam"/> | |
| 95 <param name="mark_dups" value="true"></param> | |
| 96 <param name="output_stats" value="true"></param> | |
| 97 <param name="max_mismatch" value="0"></param> | |
| 98 <output name="output_dedup_pairs" file="output_dedup_max_mismatch0_sorted.pairsam" ftype="4dn_pairsam" lines_diff="20"/> | |
| 99 <output name="dedup_pairs_stats" file="output_dedup_max_mismatch0_sorted.stats" ftype="tabular" lines_diff="20"/> | |
| 100 </test> | |
| 101 <!--Test 07 mark_dups and output_stats + bytile_stats enabled--> | |
| 102 <test expect_num_outputs="3"> | |
| 103 <param name="pairs_path" ftype="4dn_pairsam" value="output_sorted_pairs.pairsam"/> | |
| 104 <param name="mark_dups" value="true"></param> | |
| 105 <param name="output_stats" value="true"></param> | |
| 106 <param name="output_bytile_stats" value="true"></param> | |
| 107 <output name="output_dedup_pairs" file="output_dedup_max_parent_id_bytile_sorted.pairsam" ftype="4dn_pairsam" lines_diff="20"/> | |
| 108 <output name="dedup_pairs_stats" file="output_dedup_max_parent_id_bytile_sorted.stats" ftype="tabular" lines_diff="20"/> | |
| 109 <output name="dedup_bytile_stats" file="output_dedup_max_parent_id_bytile_sorted_tile_dups.stats" ftype="tabular" lines_diff="20"/> | |
| 110 </test> | |
| 111 <!--Test 08 mark_dups and output_stats + bytile_stats enabled, compress output--> | |
| 112 <test expect_num_outputs="3"> | |
| 113 <param name="pairs_path" ftype="4dn_pairsam" value="output_sorted_pairs.pairsam"/> | |
| 114 <param name="mark_dups" value="true"></param> | |
| 115 <param name="output_stats" value="true"></param> | |
| 116 <param name="compress_output" value="true"></param> | |
| 117 <param name="output_bytile_stats" value="true"></param> | |
| 118 <output name="output_dedup_pairs" file="output_dedup_max_parent_id_bytile_sorted.pairsam" ftype="4dn_pairsam" decompress="true" lines_diff="20"/> | |
| 119 <output name="dedup_pairs_stats" file="output_dedup_max_parent_id_bytile_sorted.stats" ftype="tabular" decompress="true" lines_diff="20"/> | |
| 120 <output name="dedup_bytile_stats" file="output_dedup_max_parent_id_bytile_sorted_tile_dups.stats" ftype="tabular" decompress="true" lines_diff="20"/> | |
| 57 </test> | 121 </test> |
| 58 </tests> | 122 </tests> |
| 59 <help><