Commit 8abb86ba authored by ziegenhain@bio.lmu.de's avatar ziegenhain@bio.lmu.de
Browse files

smaller fixes incl nReadsBC and better RAM usage estimation

parent 3ef7abb1
Loading
Loading
Loading
Loading
+5 −0
Original line number Diff line number Diff line
@@ -160,5 +160,10 @@ if($pbcread ne "NA") {

print "Raw reads: $total \nFiltered reads: $filtered \n\n";

$RAM=11330+$filtered*0.000192;
$RAM=int($RAM);

print "Make sure you have approximately $RAM Mb RAM available";

`$pigz -f -p $threads $cdnareadout`;
`$pigz -f -p $threads $bcreadoutfull`;

preprocess_splitseq.pl

100644 → 100755
+0 −0

File mode changed from 100644 to 100755.

+2 −2
Original line number Diff line number Diff line
@@ -33,8 +33,8 @@ option_list = list(
              help="End position of UMI barcode in the read", metavar="integer"),
  make_option(c("--subsamp"), type="character", default="0",
              help="Number of reads for downsampling.", metavar="character"),
  make_option(c("--nReadsBC"), type="character", default="100",
              help="Retain cells with atleast N reads.", metavar="character"),
  make_option(c("--nReadsBC"), type="integer", default="100",
              help="Retain cells with atleast N reads.", metavar="integer"),
  make_option(c("--hamming"), type="character", default=0,
                          help="Hamming distance filter", metavar="integer"),
  make_option(c("--XCbin"), type="character", default=0,
+2 −2
Original line number Diff line number Diff line
@@ -3,7 +3,7 @@
# Pipeline to run UMI-seq analysis from fastq to read count tables.
# Authors: Swati Parekh &  Christoph Ziegenhain
# Contact: sparekh@age.mpg.de or christoph.ziegenhain@ki.se or hellmann@bio.lmu.de
vers=0.0.6b
vers=0.0.6c
function check_opts() {
    value=$1
    name=$2
@@ -57,7 +57,7 @@ Make sure you have 3-4 times more disk space to your input fastq files.
				   defined barcodes as a text file with a list of barcodes without headers (e.g. ATGCCAAT). Default: Adaptive cell barcode selection
				   We highly reccomend to provide expected number of barcodes for Drop-seq protocol.
	-N  <nReadsperCell>	 : Keep the cell barcodes with atleast "-N <int>" number of reads. Default: 100
				   Cells with less than "-N <int>" number of total reads are removed.
				   Cells with less than "-N <int>" number of total reads are removed. Only considered in automatic cell barcode selection.
	-d  <downsampling>	 : Number of reads to downsample to. This value can be a fixed number of reads (e.g. 10000) or a desired range (e.g. 10000-20000).
				   Barcodes with less than <d> will not be reported. 0 means adaptive downsampling. Default: 0.
	-x  <STARparams>	 : Additional STAR mapping parameters. Optional. e.g. "--outFilterMismatchNoverLmax 0.2 --quantMode TranscriptomeSAM".