|
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 function usage()
|
|
|
20 {
|
|
|
21 echo "Solexa-Quality BoxPlot plotter"
|
|
|
22 echo "Generates a solexa quality score box-plot graph "
|
|
|
23 echo
|
|
|
24 echo "Usage: $0 [-i INPUT.TXT] [-t TITLE] [-p] [-o OUTPUT]"
|
|
|
25 echo
|
|
|
26 echo " [-p] - Generate PostScript (.PS) file. Default is PNG image."
|
|
|
27 echo " [-i INPUT.TXT] - Input file. Should be the output of \"solexa_quality_statistics\" program."
|
|
|
28 echo " [-o OUTPUT] - Output file name. default is STDOUT."
|
|
|
29 echo " [-t TITLE] - Title (usually the solexa file name) - will be plotted on the graph."
|
|
|
30 echo
|
|
|
31 exit
|
|
|
32 }
|
|
|
33
|
|
|
34 #
|
|
|
35 # 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
|
|
|
36 # As produced by "solexa_quality_statistics" program
|
|
|
37
|
|
|
38 TITLE="" # default title is empty
|
|
|
39 FILENAME=""
|
|
|
40 OUTPUTTERM="set term png size 2048,768" # default output terminal is "PNG"
|
|
|
41 OUTPUTFILE="/dev/stdout" # Default output file is simply "stdout"
|
|
|
42 while getopts ":t:i:o:ph" Option
|
|
|
43 do
|
|
|
44 case $Option in
|
|
|
45 # w ) CMD=$OPTARG; FILENAME="PIMSLogList.txt"; TARGET="logfiles"; ;;
|
|
|
46 t ) TITLE="for $OPTARG" ;;
|
|
|
47 i ) FILENAME=$OPTARG ;;
|
|
|
48 o ) OUTPUTFILE="$OPTARG" ;;
|
|
|
49 p ) OUTPUTTERM="set term postscript enhanced color \"Helvetica\" 8" ;;
|
|
|
50 h ) usage ;;
|
|
|
51 * ) echo "unrecognized argument. use '-h' for usage information."; exit -1 ;;
|
|
|
52 esac
|
|
|
53 done
|
|
|
54 shift $(($OPTIND - 1))
|
|
|
55
|
|
|
56
|
|
|
57 if [ "$FILENAME" == "" ]; then
|
|
|
58 usage
|
|
|
59 fi
|
|
|
60
|
|
|
61 if [ ! -r "$FILENAME" ]; then
|
|
|
62 echo "Error: can't open input file ($1)." >&2
|
|
|
63 exit 1
|
|
|
64 fi
|
|
|
65
|
|
|
66 #Read number of cycles from the stats file (each line is a cycle, minus the header line)
|
|
|
67 #But for the graph, I want xrange to reach (num_cycles+1), so I don't subtract 1 now.
|
|
|
68 NUM_CYCLES=$(cat "$FILENAME" | wc -l)
|
|
|
69
|
|
|
70 GNUPLOTCMD="
|
|
|
71 $OUTPUTTERM
|
|
|
72 set boxwidth 0.8
|
|
|
73 set size 1,1
|
|
|
74 set key Left inside
|
|
|
75 set xlabel \"read position\"
|
|
|
76 set ylabel \"Quality Score (Solexa Scale: 40=Highest, -15=Lowest)\"
|
|
|
77 set title \"Quality Scores $TITLE\"
|
|
|
78 #set auto x
|
|
|
79 set bars 4.0
|
|
|
80 set xrange [ 0: $NUM_CYCLES ]
|
|
|
81 set yrange [-15:45]
|
|
|
82 set y2range [-15:45]
|
|
|
83 set xtics 1
|
|
|
84 set x2tics 1
|
|
|
85 set ytics 2
|
|
|
86 set y2tics 2
|
|
|
87 set tics out
|
|
|
88 set grid ytics
|
|
|
89 set style fill empty
|
|
|
90 plot '$FILENAME' using 1:7:11:12:9 with candlesticks lt 1 lw 1 title 'Quartiles' whiskerbars, \
|
|
|
91 '' using 1:8:8:8:8 with candlesticks lt -1 lw 2 title 'Medians'
|
|
|
92 "
|
|
|
93
|
|
|
94 echo "$GNUPLOTCMD" | gnuplot > "$OUTPUTFILE"
|
