@@ -19,9 +19,9 @@

                 minimum_mapq = 0L,

                 concordant_only = FALSE, unique_only = FALSE,

                 primary_only = FALSE, ignore_duplicates = FALSE,

-                min_depth = 0L, variant_strand = 0L,

+                min_depth = 0L, variant_strand = 0L, variant_pct = 0,

                 ignore_query_Ns = FALSE,

-                indels = FALSE, include_soft_clips = 0L,

+                indels = FALSE, min_softclip = 0L, max_softclip = 0L,

                 exon_iit = NULL, IIT_BPPARAM = NULL,

                 xs = FALSE, read_pos = FALSE,

                 min_base_quality = 0L, noncovered = FALSE, nm = FALSE)

@@ -52,6 +52,8 @@

     only positions where a variant was seen on at least one strand, and

     2 requires the variant be seen on both strands. Setting this to 1

     is a good way to save resources.}

+  \item{variant_pct}{The minimum alternate allele fraction

+    for a variant to be reported for a strand.} 

   \item{ignore_query_Ns}{Whether to ignore the N base pairs when

     counting. Can save a lot of resources when processing low quality data.}

   \item{indels}{Whether to return indel counts. The \code{ref} and

@@ -60,7 +62,8 @@

     always spans the sequence in \code{ref}; so e.g. a deletion extends

     one nt upstream of the actual deleted sequence.

   }

-  \item{include_soft_clips}{Maximum length of soft clips that are

+  \item{min_softclip, max_softclip}{

+    Minimum and maximum length of soft clips that are

     considered for counting. Soft-clipping is often useful (for GSNAP at

     least) during alignment, and it should be preserved in the

     output. However, soft clipping can preferentially occur in regions

@@ -28,7 +28,7 @@

 }

 \arguments{

   \item{genome}{A \code{GmapGenome} object, or something coercible to one.}

-  \item{which}{A \code{RangesList} or something coercible to

+  \item{which}{A \code{IntegerRangesList} or something coercible to

     one that limits the tally to that range or set of ranges. By

     default, the entire genome is processed.

   }

@@ -22,7 +22,9 @@

                 min_depth = 0L, variant_strand = 0L,

                 ignore_query_Ns = FALSE,

                 indels = FALSE, include_soft_clips = 0L,

-                exon_iit = NULL, IIT_BPPARAM = NULL)

+                exon_iit = NULL, IIT_BPPARAM = NULL,

+                xs = FALSE, read_pos = FALSE,

+                min_base_quality = 0L, noncovered = FALSE, nm = FALSE)

 }

 \arguments{

   \item{genome}{A \code{GmapGenome} object, or something coercible to one.}

@@ -74,6 +76,20 @@

     generating the iit file from an R object. Ignored if \code{exon_iit}

     is a character vector or \code{NULL}

   }

+  \item{xs}{Whether to tabulate reads by XS tag, the aligner's best

+    guess about the strand of transcription.

+  }

+  \item{read_pos}{Whether to tabulate by read position.

+  }

+  \item{min_base_quality}{Minimum base quality cutoff. Calls of lower

+    quality are not counted, except in the total raw depth.

+  }

+  \item{noncovered}{

+    Whether to report zero tallies, where there is no coverage.

+  }

+  \item{nm}{

+    Whether to tally by NM tag, the number of mismatches for a read.

+  }

 }

 \seealso{

   \code{\link{bam_tally}}

@@ -22,7 +22,7 @@

                 min_depth = 0L, variant_strand = 0L,

                 ignore_query_Ns = FALSE,

                 indels = FALSE, include_soft_clips = 0L,

-                cds_iit = NULL, IIT_BPPARAM = NULL)

+                exon_iit = NULL, IIT_BPPARAM = NULL)

 }

 \arguments{

   \item{genome}{A \code{GmapGenome} object, or something coercible to one.}

@@ -22,7 +22,7 @@

                 min_depth = 0L, variant_strand = 0L,

                 ignore_query_Ns = FALSE,

                 indels = FALSE, include_soft_clips = 0L,

-                count_xs = FALSE, noncovered = FALSE)

+                cds_iit = NULL, IIT_BPPARAM = NULL)

 }

 \arguments{

   \item{genome}{A \code{GmapGenome} object, or something coercible to one.}

@@ -65,15 +65,16 @@

     of discordance with the reference, and if those clipped regions are

     ignored during counting, the allele fraction is misestimated.

   }

-  \item{count_xs}{Whether to tabulate the +/- values of the XS tag,

-    often output by RNA-seq aligners to indicate the strand of

-    transcription.

-  }

-  \item{noncovered}{Whether to output rows for positions without any

-    coverage.

+  \item{exon_iit}{An object which indicates the exons to be used for

+    tallying codons (a character value indicating an existing .iit file, a

+    \code{GRangesList} of exons by gene or a \code{TxDb} object from which

+    to make such a \code{GRangesList}) or \code{NULL} indicating no

+    codon-level tallying should be done.}

+  \item{IIT_BPPARAM}{A \code{BiocParallelParam} object to use when

+    generating the iit file from an R object. Ignored if \code{exon_iit}

+    is a character vector or \code{NULL}

   }

 }

-

 \seealso{

   \code{\link{bam_tally}}

 }

@@ -21,7 +21,8 @@

                 primary_only = FALSE, ignore_duplicates = FALSE,

                 min_depth = 0L, variant_strand = 0L,

                 ignore_query_Ns = FALSE,

-                indels = FALSE, include_soft_clips = 0L)

+                indels = FALSE, include_soft_clips = 0L,

+                count_xs = FALSE, noncovered = FALSE)

 }

 \arguments{

   \item{genome}{A \code{GmapGenome} object, or something coercible to one.}

@@ -64,6 +65,13 @@

     of discordance with the reference, and if those clipped regions are

     ignored during counting, the allele fraction is misestimated.

   }

+  \item{count_xs}{Whether to tabulate the +/- values of the XS tag,

+    often output by RNA-seq aligners to indicate the strand of

+    transcription.

+  }

+  \item{noncovered}{Whether to output rows for positions without any

+    coverage.

+  }

 }

 \seealso{

@@ -21,7 +21,7 @@

                 primary_only = FALSE, ignore_duplicates = FALSE,

                 min_depth = 0L, variant_strand = 0L,

                 ignore_query_Ns = FALSE,

-                indels = FALSE)

+                indels = FALSE, include_soft_clips = 0L)

 }

 \arguments{

   \item{genome}{A \code{GmapGenome} object, or something coercible to one.}

@@ -57,6 +57,13 @@

     always spans the sequence in \code{ref}; so e.g. a deletion extends

     one nt upstream of the actual deleted sequence.

   }

+  \item{include_soft_clips}{Maximum length of soft clips that are

+    considered for counting. Soft-clipping is often useful (for GSNAP at

+    least) during alignment, and it should be preserved in the

+    output. However, soft clipping can preferentially occur in regions

+    of discordance with the reference, and if those clipped regions are

+    ignored during counting, the allele fraction is misestimated.

+  }

 }

 \seealso{

@@ -14,16 +14,14 @@

 }

 \usage{

-  BamTallyParam(genome, which = RangesList(),

+  BamTallyParam(genome, which = GRanges(),

                 desired_read_group = NULL,

-                read_pos_breaks = NULL,

-                high_base_quality = 0L,

                 minimum_mapq = 0L,

                 concordant_only = FALSE, unique_only = FALSE,

                 primary_only = FALSE, ignore_duplicates = FALSE,

                 min_depth = 0L, variant_strand = 0L,

                 ignore_query_Ns = FALSE,

-                indels = TRUE)

+                indels = FALSE)

 }

 \arguments{

   \item{genome}{A \code{GmapGenome} object, or something coercible to one.}

@@ -33,11 +31,6 @@

   }

   \item{desired_read_group}{The name of the read group to which to limit

     the tallying; if not NULL, must be a single, non-NA string.}

-  \item{read_pos_breaks}{The breaks, like those passed to \code{\link{cut}}

-    for aggregating the per-read position counts. If \code{NULL}, no per-cycle

-    counts are returned.}

-  \item{high_base_quality}{The minimum mapping quality for a

-    read to be counted as high quality.}

   \item{minimum_mapq}{Minimum mapping quality for a read to be counted

     at all.}

   \item{concordant_only}{Consider only what gnsap

@@ -14,14 +14,16 @@

 }

 \usage{

-  BamTallyParam(genome, which = RangesList(), read_pos_breaks = NULL,

+  BamTallyParam(genome, which = RangesList(),

+                desired_read_group = NULL,

+                read_pos_breaks = NULL,

                 high_base_quality = 0L,

                 minimum_mapq = 0L,

                 concordant_only = FALSE, unique_only = FALSE,

                 primary_only = FALSE, ignore_duplicates = FALSE,

                 min_depth = 0L, variant_strand = 0L,

                 ignore_query_Ns = FALSE,

-                indels = FALSE)

+                indels = TRUE)

 }

 \arguments{

   \item{genome}{A \code{GmapGenome} object, or something coercible to one.}

@@ -29,6 +31,8 @@

     one that limits the tally to that range or set of ranges. By

     default, the entire genome is processed.

   }

+  \item{desired_read_group}{The name of the read group to which to limit

+    the tallying; if not NULL, must be a single, non-NA string.}

   \item{read_pos_breaks}{The breaks, like those passed to \code{\link{cut}}

     for aggregating the per-read position counts. If \code{NULL}, no per-cycle

     counts are returned.}

@@ -54,7 +58,12 @@

     is a good way to save resources.}

   \item{ignore_query_Ns}{Whether to ignore the N base pairs when

     counting. Can save a lot of resources when processing low quality data.}

-  \item{indels}{Whether to return indel counts; not supported yet.}

+  \item{indels}{Whether to return indel counts. The \code{ref} and

+    \code{alt} columns in the returned \code{VRanges} conform to VCF

+    conventions; i.e., the first base upstream is included. The range

+    always spans the sequence in \code{ref}; so e.g. a deletion extends

+    one nt upstream of the actual deleted sequence.

+  }

 }

 \seealso{

@@ -14,7 +14,7 @@

 }

 \usage{

-  BamTallyParam(genome, which = RangesList(), cycle_breaks = NULL,

+  BamTallyParam(genome, which = RangesList(), read_pos_breaks = NULL,

                 high_base_quality = 0L,

                 minimum_mapq = 0L,

                 concordant_only = FALSE, unique_only = FALSE,

@@ -29,8 +29,8 @@

     one that limits the tally to that range or set of ranges. By

     default, the entire genome is processed.

   }

-  \item{cycle_breaks}{The breaks, like those passed to \code{\link{cut}}

-    for aggregating the per-cycle counts. If \code{NULL}, no per-cycle

+  \item{read_pos_breaks}{The breaks, like those passed to \code{\link{cut}}

+    for aggregating the per-read position counts. If \code{NULL}, no per-cycle

     counts are returned.}

   \item{high_base_quality}{The minimum mapping quality for a

     read to be counted as high quality.}

@@ -18,7 +18,7 @@

                 high_base_quality = 0L,

                 minimum_mapq = 0L,

                 concordant_only = FALSE, unique_only = FALSE,

-                primary_only = FALSE,

+                primary_only = FALSE, ignore_duplicates = FALSE,

                 min_depth = 0L, variant_strand = 0L,

                 ignore_query_Ns = FALSE,

                 indels = FALSE)

@@ -41,6 +41,9 @@

   }

   \item{unique_only}{Consider only the uniquly mapped reads.}

   \item{primary_only}{Consider only primary pairs.}

+  \item{ignore_duplicates}{Whether to ignore the reads flagged as

+    PCR/optical duplicates.

+  }

   \item{min_depth}{The minimum number of reads overlapping a position for

     it to be counted.}

   \item{variant_strand}{The number of strands on which a variant must be

@@ -14,8 +14,8 @@

 }

 \usage{

-  BamTallyParam(which = RangesList(), cycle_breaks = NULL,

-                high_quality_cutoff = 0L,

+  BamTallyParam(genome, which = RangesList(), cycle_breaks = NULL,

+                high_base_quality = 0L,

                 minimum_mapq = 0L,

                 concordant_only = FALSE, unique_only = FALSE,

                 primary_only = FALSE,

@@ -24,6 +24,7 @@

                 indels = FALSE)

 }

 \arguments{

+  \item{genome}{A \code{GmapGenome} object, or something coercible to one.}

   \item{which}{A \code{RangesList} or something coercible to

     one that limits the tally to that range or set of ranges. By

     default, the entire genome is processed.

@@ -31,7 +32,7 @@

   \item{cycle_breaks}{The breaks, like those passed to \code{\link{cut}}

     for aggregating the per-cycle counts. If \code{NULL}, no per-cycle

     counts are returned.}

-  \item{high_quality_cutoff}{The minimum mapping quality for a

+  \item{high_base_quality}{The minimum mapping quality for a

     read to be counted as high quality.}

   \item{minimum_mapq}{Minimum mapping quality for a read to be counted

     at all.}

new file mode 100644

@@ -0,0 +1,58 @@

+\name{BamTallyParam-class}

+\Rdversion{1.1}

+\docType{class}

+\alias{BamTallyParam-class}

+\alias{coerce,BamTallyParam,list-method}

+\alias{as.list,BamTallyParam-method}

+\alias{BamTallyParam}

+

+\title{Class \code{"BamTallyParam"}}

+\description{

+  A \code{BamTallyParam} object stores parameters for

+  \code{\link{bam_tally}}. The function of the same name serves as its

+  constructor. 

+}

+

+\usage{

+  BamTallyParam(which = RangesList(), cycle_breaks = NULL,

+                high_quality_cutoff = 0L,

+                minimum_mapq = 0L,

+                concordant_only = FALSE, unique_only = FALSE,

+                primary_only = FALSE,

+                min_depth = 0L, variant_strand = 0L,

+                ignore_query_Ns = FALSE,

+                indels = FALSE)

+}

+\arguments{

+  \item{which}{A \code{RangesList} or something coercible to

+    one that limits the tally to that range or set of ranges. By

+    default, the entire genome is processed.

+  }

+  \item{cycle_breaks}{The breaks, like those passed to \code{\link{cut}}

+    for aggregating the per-cycle counts. If \code{NULL}, no per-cycle

+    counts are returned.}

+  \item{high_quality_cutoff}{The minimum mapping quality for a

+    read to be counted as high quality.}

+  \item{minimum_mapq}{Minimum mapping quality for a read to be counted

+    at all.}

+  \item{concordant_only}{Consider only what gnsap

+    calls \dQuote{concordant} alignments.

+  }

+  \item{unique_only}{Consider only the uniquly mapped reads.}

+  \item{primary_only}{Consider only primary pairs.}

+  \item{min_depth}{The minimum number of reads overlapping a position for

+    it to be counted.}

+  \item{variant_strand}{The number of strands on which a variant must be

+    seen for it to be counted. This means that a value of 0 will report

+    reference alleles in addition to variants. A value of 1 will report

+    only positions where a variant was seen on at least one strand, and

+    2 requires the variant be seen on both strands. Setting this to 1

+    is a good way to save resources.}

+  \item{ignore_query_Ns}{Whether to ignore the N base pairs when

+    counting. Can save a lot of resources when processing low quality data.}

+  \item{indels}{Whether to return indel counts; not supported yet.}

+}

+

+\seealso{

+  \code{\link{bam_tally}}

+}