3
|
1 #!/bin/sh
|
|
2
|
|
3 # FASTX-toolkit - FASTA/FASTQ preprocessing tools.
|
|
4 # Copyright (C) 2009 A. Gordon (gordon@cshl.edu)
|
|
5 #
|
|
6 # This program is free software: you can redistribute it and/or modify
|
|
7 # it under the terms of the GNU Affero General Public License as
|
|
8 # published by the Free Software Foundation, either version 3 of the
|
|
9 # License, or (at your option) any later version.
|
|
10 #
|
|
11 # This program is distributed in the hope that it will be useful,
|
|
12 # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
13 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
14 # GNU Affero General Public License for more details.
|
|
15 #
|
|
16 # You should have received a copy of the GNU Affero General Public License
|
|
17 # along with this program. If not, see <http://www.gnu.org/licenses/>.
|
|
18
|
|
19 usage()
|
|
20 {
|
|
21 echo "FASTA/Q Nucleotide Distribution Plotter"
|
|
22 echo
|
|
23 echo "Usage: $0 [-i INPUT.TXT] [-t TITLE] [-p] [-o OUTPUT]"
|
|
24 echo
|
|
25 echo " [-p] - Generate PostScript (.PS) file. Default is PNG image."
|
|
26 echo " [-i INPUT.TXT] - Input file. Should be the output of \"fastx_quality_statistics\" program."
|
|
27 echo " [-o OUTPUT] - Output file name. default is STDOUT."
|
|
28 echo " [-t TITLE] - Title - will be plotted on the graph."
|
|
29 echo
|
|
30 exit
|
|
31 }
|
|
32
|
|
33 #
|
|
34 # Input Data columns: #pos cnt min max sum mean Q1 med Q3 IQR lW rW A_Count C_Count G_Count T_Count N_Count
|
|
35 # As produced by "fastq_quality_statistics" program
|
|
36
|
|
37 TITLE="" # default title is empty
|
|
38 FILENAME=""
|
|
39 OUTPUTTERM="set term png size 1048,768" # default output terminal is "PNG"
|
|
40 OUTPUTFILE="/dev/stdout" # Default output file is simply "stdout"
|
|
41 while getopts ":t:i:o:ph" Option
|
|
42 do
|
|
43 case $Option in
|
|
44 t ) TITLE="for $OPTARG" ;;
|
|
45 i ) FILENAME=$OPTARG ;;
|
|
46 o ) OUTPUTFILE="$OPTARG" ;;
|
|
47 p ) OUTPUTTERM="set term postscript enhanced color \"Helvetica\" 8" ;;
|
|
48 h ) usage ;;
|
|
49 * ) echo "unrecognized argument. use '-h' for usage information."; exit -1 ;;
|
|
50 esac
|
|
51 done
|
|
52 shift $(($OPTIND - 1))
|
|
53
|
|
54
|
|
55 if [ -z "$FILENAME" ]; then
|
|
56 usage
|
|
57 fi
|
|
58
|
|
59 if [ ! -r "$FILENAME" ]; then
|
|
60 echo "Error: can't open input file ($1)." >&2
|
|
61 exit 1
|
|
62 fi
|
|
63
|
|
64 GNUPLOTCMD="
|
|
65 $OUTPUTTERM
|
|
66 set boxwidth 0.75 absolute
|
|
67 set size 1,1
|
|
68 set style fill solid 1.00 border -1
|
|
69 set xlabel \"read position\"
|
|
70 set title \"Nucleotides distribution $TITLE\"
|
|
71 set ylabel \"% of total (per read position)\"
|
|
72 #set grid noxtics nomxtics ytics nomytics noztics nomztics \
|
|
73 # nox2tics nomx2tics noy2tics nomy2tics nocbtics nomcbtics
|
|
74 #set grid layerdefault linetype 0 linewidth 1.000, linetype 0 linewidth 1.000
|
|
75 set key outside right top vertical Left reverse enhanced autotitles columnhead nobox
|
|
76 set key invert samplen 4 spacing 1 width 0 height 0
|
|
77 set style histogram rowstacked
|
|
78 set style data histograms
|
|
79 set noytics
|
|
80 set xtics 1
|
|
81 set yrange [ 0.00000 : 100.000 ] noreverse nowriteback
|
|
82
|
|
83 plot '$FILENAME' using (100.*column(13)/column(18)):xtic(1) title \"A\" lt rgb \"#5050ff\", \
|
|
84 '' using (100.*column(14)/column(18)) title \"C\" lt rgb \"#e00000\", \
|
|
85 '' using (100.*column(15)/column(18)) title \"G\" lt rgb \"#00c000\", \
|
|
86 '' using (100.*column(16)/column(18)) title \"T\" lt rgb \"#e6e600\", \
|
|
87 '' using (100.*column(17)/column(18)) title \"N\" lt rgb \"pink\"
|
|
88 "
|
|
89
|
|
90 echo "$GNUPLOTCMD" | gnuplot > "$OUTPUTFILE"
|