# HG changeset patch # User chrisw # Date 1574132347 0 # Node ID 78bca99736b0ea5a4452ff925ff2655718c1eb23 # Parent 1f0e3aaaba194990acfb39aec1b2d74092aefd18 Uploaded diff -r 1f0e3aaaba19 -r 78bca99736b0 bamcount.xml --- 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 @@ - + - bamcount + bamcount - + + + + - + + + + + + + - + [options] - Usage: - bamcount [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 Extract jx coordinates, strand, and anchor length, per read + Writes to a TSV file .jxs.tsv - Non-reference summaries: - --alts Print differing from ref per-base coverages - Writes to a CSV file .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 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 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 .auc.tsv - --bigwig Output coverage as BigWig file(s). Writes to .all.bw - (also .unique.bw when --min-unique-qual is specified). - Requires libBigWig. - --annotation - Path to BED file containing list of regions to sum coverage over - (tab-delimited: chrm,start,end) - --min-unique-qual - 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 Print differing from ref per-base coverages + Writes to a CSV file .alts.tsv + --include-softclip Print a record to the alts CSV for soft-clipped bases + Writes total counts to a separate TSV file .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: .starts.tsv, .ends.tsv - --frag-dist Print fragment length distribution across the genome - Writes to a TSV file .frags.tsv - --echo-sam Print a SAM record for each aligned read - --ends Report end coordinate for each read (useful for debugging) - ]]> +Coverage and quantification: + --coverage Print per-base coverage (slow but totally worth it) + --auc 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 .auc.tsv + --bigwig Output coverage as BigWig file(s). Writes to .all.bw + (also .unique.bw when --min-unique-qual is specified). + Requires libBigWig. + --annotation + 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 + 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: .starts.tsv, .ends.tsv + --frag-dist Print fragment length distribution across the genome + Writes to a TSV file .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) + ]]> -@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}, } diff -r 1f0e3aaaba19 -r 78bca99736b0 test-data/test.auc.tsv --- /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 diff -r 1f0e3aaaba19 -r 78bca99736b0 tool_dependencies.xml --- 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 @@ - - + +