Mercurial > repos > iuc > pairtools_dedup
changeset 8:914533f3507e draft
planemo upload for repository https://github.com/open2c/pairtools commit d80cc18cb4f1f67065ed77c6225ef9cea906b727
| author | iuc |
|---|---|
| date | Fri, 27 Jun 2025 20:33:05 +0000 |
| parents | c162f3c43442 |
| children | 608ea80cccba |
| files | dedup.xml macros.xml test-data/output_dedup_max_mismatch0_sorted.pairsam test-data/output_dedup_max_mismatch0_sorted.stats test-data/output_dedup_max_parent_id_bytile_sorted.pairsam test-data/output_dedup_max_parent_id_bytile_sorted.stats test-data/output_dedup_max_parent_id_bytile_sorted_tile_dups.stats |
| diffstat | 7 files changed, 2591 insertions(+), 1 deletions(-) [+] |
line wrap: on
line diff
--- a/dedup.xml Mon Mar 10 09:36:35 2025 +0000 +++ b/dedup.xml Fri Jun 27 20:33:05 2025 +0000 @@ -15,14 +15,21 @@ #if $output_stats: --output-stats '$dedup_pairs_stats' #end if + #if $output_bytile_stats: + --keep-parent-id + --output-bytile-stats '$dedup_bytile_stats' + #end if --nproc-in \${GALAXY_SLOTS:-4} --nproc-out \${GALAXY_SLOTS:-4} + --max-mismatch ${max_mismatch} ]]></command> <inputs> <param name="pairs_path" type="data" format="4dn_pairs,4dn_pairsam" label="Input pairs file" help="Input triu-flipped sorted .pairs or .pairsam file"/> <param argument="--mark-dups" type="boolean" truevalue="--mark-dups" falsevalue="" checked="True" label="Duplicate pairs are marked as DD in pair_type and as a duplicate in the SAM entries"/> <param argument="--output-dups" type="boolean" truevalue="--output-dups" falsevalue="" checked="False" label="Output file for duplicate pairs"/> <param argument="--output-stats" type="boolean" truevalue="--output-stats" falsevalue="" checked="False" label="Output file for duplicate statistics"/> + <param argument="--max-mismatch" type="integer" value="3" min="0" label="Maximum number of mismatches. Pairs with both sides mapped within this distance "bp" from each other are considered duplicates."/> + <param argument="--output-bytile-stats" type="boolean" truevalue="--output-bytile-stats" falsevalue="" checked="False" label="Output file for optical duplicate statistics for datasets with original Illumina-generated read IDs."/> </inputs> <outputs> <data name="output_dedup_pairs" format_source="pairs_path" label="${tool.name} on ${on_string}: Deduplicated Pairs"/> @@ -32,8 +39,12 @@ <data name="dedup_pairs_stats" format="tabular" label="${tool.name} on ${on_string}: Deduplicated stats"> <filter>output_stats</filter> </data> + <data name="dedup_bytile_stats" format="tabular" label="${tool.name} on ${on_string}: By-tile stats"> + <filter>output_bytile_stats</filter> + </data> </outputs> <tests> + <!--Test 01 with default parameters--> <test expect_num_outputs="1"> <param name="pairs_path" value="output_sorted_pairs.pairsam"/> @@ -55,6 +66,25 @@ <output name="output_dedup_pairs" file="output_dedup_pairs_markdups.pairsam" lines_diff="20"/> <output name="dedup_pairs_stats" file="output_dedup_pairs.stats" lines_diff="20"/> </test> + <!--Test 04 mark_dups and output_stats enabled, max_mismatch set to 0--> + <test expect_num_outputs="2"> + <param name="pairs_path" value="output_sorted_pairs.pairsam"/> + <param name="mark_dups" value="true"></param> + <param name="output_stats" value="true"></param> + <param name="max_mismatch" value="0"></param> + <output name="output_dedup_pairs" file="output_dedup_max_mismatch0_sorted.pairsam" lines_diff="20"/> + <output name="dedup_pairs_stats" file="output_dedup_max_mismatch0_sorted.stats" lines_diff="20"/> + </test> + <!--Test 05 mark_dups and output_stats + bytile_stats enabled--> + <test expect_num_outputs="3"> + <param name="pairs_path" value="output_sorted_pairs.pairsam"/> + <param name="mark_dups" value="true"></param> + <param name="output_stats" value="true"></param> + <param name="output_bytile_stats" value="true"></param> + <output name="output_dedup_pairs" file="output_dedup_max_parent_id_bytile_sorted.pairsam" lines_diff="20"/> + <output name="dedup_pairs_stats" file="output_dedup_max_parent_id_bytile_sorted.stats" lines_diff="20"/> + <output name="dedup_bytile_stats" file="output_dedup_max_parent_id_bytile_sorted_tile_dups.stats" lines_diff="20"/> + </test> </tests> <help><