Mercurial > repos > chrisw > bamcount_tool_test
changeset 1:78bca99736b0 draft default tip
Uploaded
author | chrisw |
---|---|
date | Tue, 19 Nov 2019 02:59:07 +0000 |
parents | 1f0e3aaaba19 |
children | |
files | bamcount.xml test-data/test.auc.tsv tool_dependencies.xml |
diffstat | 3 files changed, 87 insertions(+), 56 deletions(-) [+] |
line wrap: on
line diff
--- a/bamcount.xml Tue Feb 12 13:42:37 2019 -0500 +++ b/bamcount.xml Tue Nov 19 02:59:07 2019 +0000 @@ -1,84 +1,113 @@ -<tool id="bamcount" name="Summarize coverage from a BAM (bamcount)" version="0.1.0"> +<tool id="bamcount" name="Summarize coverage from a BAM (bamcount)" version="0.2.0"> <requirements> - <requirement type="package" version="0.2.6">bamcount</requirement> + <requirement type="package" version="0.4.0">bamcount</requirement> </requirements> <command detect_errors="exit_code"><![CDATA[ - bamcount "$input1" --threads $threads --coverage --no-head --require-mdz --min-unique-qual $min_uniq_qual --frag-dist bc --bigwig bc --annotation $annotation bc --auc bc --alts bc + bamcount "$input1" --threads $threads --coverage --no-head --min-unique-qual $min_uniq_qual --frag-dist bc --bigwig bc --auc bc --alts bc --junctions bc ]]></command> <inputs> - <param type="data" name="input1" format="bam" /> + <param type="integer" name="threads" value="1" /> + <param type="integer" name="min_uniq_qual" value="10" /> + <param type="file" name="input1" format="bam" /> + <param type="file" name="annotation" format="bed" /> </inputs> <outputs> - <data name="output1" format="auc.tsv" from_work_dir="bc.auc.tsv" /> + <data name="output1" format="txt" from_work_dir="bc.auc.tsv" /> + <data name="output2" format="txt" from_work_dir="bc.alts.tsv" /> + <data name="output3" format="txt" from_work_dir="bc.frags.tsv" /> + <data name="output4" format="txt" from_work_dir="bc.jxs.tsv" /> + <!-- + <data name="output5" format="bed" from_work_dir="bc.all.tsv" /> + <data name="output6" format="bed" from_work_dir="bc.unique.tsv" /> + --> + <data name="output7" format="bigwig" from_work_dir="bc.all.bw" /> + <data name="output8" format="bigwig" from_work_dir="bc.unique.bw" /> </outputs> <tests> <test> <param name="input1" value="test.bam"/> - <output name="output1" file="bc.auc.tsv"/> + <output name="output1" file="test.auc.tsv"/> </test> </tests> <help><![CDATA[ - bamcount 0.2.6 +bamcount 0.4.0 + +BAM and BigWig utility. - BAM and BigWig utility. +Usage: + bamcount <bam> [options] - Usage: - bamcount <bam> [options] +Options: + -h --help Show this screen. + --version Show version. + --threads # of threads to do BAM decompression - Options: - -h --help Show this screen. - --version Show version. - --threads # of threads to do BAM decompression +Extract basic junction information from the BAM, including co-occurrence + --junctions <prefix> Extract jx coordinates, strand, and anchor length, per read + Writes to a TSV file <prefix>.jxs.tsv - Non-reference summaries: - --alts <prefix> Print differing from ref per-base coverages - Writes to a CSV file <prefix>.alts.tsv - --include-softclip Print a record for soft-clipped bases - --include-n Print mismatch records when mismatched read base is N - --print-qual Print quality values for mismatched bases - --delta Print POS field as +/- delta from previous - --require-mdz Quit with error unless MD:Z field exists everywhere it's - expected - --no-head Don't print sequence names and lengths in header +Extract reads from BAM into FASTQ (exclusive of all other modes): + --bam2fastq <prefix> Extract all reads from the passed in BAM and output as FASTQs + Uses prefix to name the fastq(s) + --filter-out SAM bit flags to filter out + --filter-in SAM bit flags to filter in + --re-reverse If read is reversed in alignment, re-reverse it in output + --one-file If you know file is not paired or just want all reads in one file - Coverage and quantification: - --coverage Print per-base coverage (slow but totally worth it) - --auc <prefix> Print per-base area-under-coverage, will generate it for the genome - and for the annotation if --annotation is also passed in - Writes to a TSV file <prefix>.auc.tsv - --bigwig <prefix> Output coverage as BigWig file(s). Writes to <prefix>.all.bw - (also <prefix>.unique.bw when --min-unique-qual is specified). - Requires libBigWig. - --annotation <bed> <prefix> - Path to BED file containing list of regions to sum coverage over - (tab-delimited: chrm,start,end) - --min-unique-qual <int> - Output second bigWig consisting built only from alignments - with at least this mapping quality. --bigwig must be specified. - Also produces second set of annotation sums based on this coverage - if --annotation is enabled - --double-count Allow overlapping ends of PE read to count twice toward - coverage - --num-bases Report total sum of bases in alignments processed (that pass filters) +Non-reference summaries: + --alts <prefix> Print differing from ref per-base coverages + Writes to a CSV file <prefix>.alts.tsv + --include-softclip <prefix> Print a record to the alts CSV for soft-clipped bases + Writes total counts to a separate TSV file <prefix>.softclip.tsv + --only-polya If --include-softclip, only print softclips which are mostly A's or T's + --include-n Print mismatch records when mismatched read base is N + --print-qual Print quality values for mismatched bases + --delta Print POS field as +/- delta from previous + --require-mdz Quit with error unless MD:Z field exists everywhere it's + expected + --no-head Don't print sequence names and lengths in header - Other outputs: - --read-ends Print counts of read starts/ends, if --min-unique-qual is set - then only the alignments that pass that filter will be counted here - Writes to 2 TSV files: <prefix>.starts.tsv, <prefix>.ends.tsv - --frag-dist <prefix> Print fragment length distribution across the genome - Writes to a TSV file <prefix>.frags.tsv - --echo-sam Print a SAM record for each aligned read - --ends Report end coordinate for each read (useful for debugging) - ]]></help> +Coverage and quantification: + --coverage Print per-base coverage (slow but totally worth it) + --auc <prefix> Print per-base area-under-coverage, will generate it for the genome + and for the annotation if --annotation is also passed in + Writes to a TSV file <prefix>.auc.tsv + --bigwig <prefix> Output coverage as BigWig file(s). Writes to <prefix>.all.bw + (also <prefix>.unique.bw when --min-unique-qual is specified). + Requires libBigWig. + --annotation <bed> <prefix> + Path to BED file containing list of regions to sum coverage over + (tab-delimited: chrm,start,end) + --keep-bam-order Output annotation coverage in the order chromosomes appear in the BAM file. + The default is to output annotation coverage in the order chromosomes appear in the BED file. + --min-unique-qual <int> + Output second bigWig consisting built only from alignments + with at least this mapping quality. --bigwig must be specified. + Also produces second set of annotation sums based on this coverage + if --annotation is enabled + --double-count Allow overlapping ends of PE read to count twice toward + coverage + --num-bases Report total sum of bases in alignments processed (that pass filters) + +Other outputs: + --read-ends Print counts of read starts/ends, if --min-unique-qual is set + then only the alignments that pass that filter will be counted here + Writes to 2 TSV files: <prefix>.starts.tsv, <prefix>.ends.tsv + --frag-dist <prefix> Print fragment length distribution across the genome + Writes to a TSV file <prefix>.frags.tsv + --echo-sam Print a SAM record for each aligned read + --ends Report end coordinate for each read (useful for debugging) + --test-polya Lower Poly-A filter minimums for testing (only useful for debugging/testing) + ]]></help> <citations> <citation type="bibtex"> -@misc{githubbamcount, + @misc{githubbamcount, author = {Wilks, Christopher}, year = {2019}, title = {bamcount}, publisher = {GitHub}, journal = {GitHub repository}, - url = {https://github.com/BenLangmead/bamcount}, + url = {https://github.com/ChristopherWilks/bamcount}, }</citation> </citations> </tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/test.auc.tsv Tue Nov 19 02:59:07 2019 +0000 @@ -0,0 +1,2 @@ +ALL_READS_ALL_BASES 3864 +UNIQUE_READS_ALL_BASES 3576
--- a/tool_dependencies.xml Tue Feb 12 13:42:37 2019 -0500 +++ b/tool_dependencies.xml Tue Nov 19 02:59:07 2019 +0000 @@ -1,6 +1,6 @@ <?xml version="1.0"?> <tool_dependency> - <package name="bamcount" version="0.2.6"> - <repository changeset_revision="f02b4483eda2" name="bamcount_test" owner="chrisw" prior_installation_required="False" toolshed="http://testtoolshed.g2.bx.psu.edu" /> + <package name="bamcount" version="0.4.0"> + <repository changeset_revision="cb4c1efac7af" name="bamcount_test" owner="chrisw" prior_installation_required="False" toolshed="http://testtoolshed.g2.bx.psu.edu" /> </package> </tool_dependency>