polished bp_scripts

git-svn-id: http://biopieces.googlecode.com/svn/trunk@1420 74ccb610-7750-0410-82ae-013aeee3265d

diff --git a/bp_scripts/clean_reads.sh b/bp_scripts/clean_reads.sh
new file mode 100755 (executable)
index 0000000..6929378
--- /dev/null
+++ b/bp_scripts/clean_reads.sh
@@ -0,0 +1,27 @@
+#!/bin/sh
+
+# Remove adaptor from sequences and trim according to scores.
+# Produces a number of plots during the process.
+
+# Usage: read_fastq -i test.fq | clean_reads.sh | write_fastq -xo clean.fq
+
+#adaptor='TCGTATGCCGTCTTCTGCTTG' # 454 adaptor
+adaptor='AGATCGGAAGACACACGTCT'  # Solexa adaptor
+pid=$$
+
+progress_meter |
+plot_lendist -t post -o 00_remove_adaptor_lendist_seq_before.$pid.ps -k SEQ_LEN |
+find_adaptor -a $adaptor -p |
+plot_histogram -t post -o 01_remove_adaptor_histogram_adaptor_pos.$pid.ps -k ADAPTOR_POS -s num |
+plot_lendist -t post -o 02_remove_adaptor_lendist_adaptor_len.$pid.ps -k ADAPTOR_LEN |
+plot_lendist -t post -o 03_remove_adaptor_lendist_seq_after.$pid.ps -k SEQ_LEN |
+analyze_vals -k ADAPTOR_POS,ADAPTOR_LEN -o 04_remove_adaptor_analyze_vals.$pid.txt |
+clip_adaptor |
+plot_scores -t post -o 04_trim_seq_scores_pretrim.$pid.ps |
+plot_lendist -k SEQ_LEN -t post -o 05_trim_seq_lendist_pretrim.$pid.ps |
+trim_seq |
+grab -e "SEQ_LEN>=30" |
+mean_scores -l |
+grab -e "SCORES_LOCAL_MEAN>=15" |
+plot_scores -t post -o 06_trim_seq_scores_posttrim.$pid.ps |
+plot_lendist -k SEQ_LEN -t post -o 07_trim_seq_lendist_posttrim.$pid.ps

diff --git a/bp_scripts/remove_adaptor_454.sh b/bp_scripts/remove_adaptor_454.sh
index 34013b1ec4c6a06f67daf17123ae14b6ddac0ddd..5088d477000115a4e565b5147f267b3b382c6c09 100755 (executable)
--- a/bp_scripts/remove_adaptor_454.sh
+++ b/bp_scripts/remove_adaptor_454.sh
@@ -2,14 +2,13 @@
 
 # Remove adaptor from sequences and produce a number of plots.
 
-# Usage: read_fastq -i test.fq | remove_adaptor.sh | write_fastq -xo test_no_adaptor.fq
+# Usage: read_fastq -i test.fq | remove_adaptor_454.sh | write_fastq -xo test_no_adaptor.fq
 
 adaptor='TCGTATGCCGTCTTCTGCTTG' # 454 adaptor
 pid=$$
 
-#find_adaptor -a $adaptor |
 plot_lendist -t post -o 00_remove_adaptor_lendist_seq_before.$pid.ps -k SEQ_LEN |
-parallel -k --blocksize 50M --pipe --recend "\n---\n" "nice -n 19 find_adaptor -a $adaptor" |
+find_adaptor -a $adaptor -p |
 plot_histogram -t post -o 01_remove_adaptor_histogram_adaptor_pos.$pid.ps -k ADAPTOR_POS -s num |
 plot_lendist -t post -o 02_remove_adaptor_lendist_adaptor_len.$pid.ps -k ADAPTOR_LEN |
 plot_lendist -t post -o 03_remove_adaptor_lendist_seq_after.$pid.ps -k SEQ_LEN |

diff --git a/bp_scripts/trim_seq.sh b/bp_scripts/trim_seq.sh
index 60839aa59ac2cbd17de087acbaaf3265f916f878..7866c740fcc72f75e21a704d0f472c5508f473a2 100755 (executable)
--- a/bp_scripts/trim_seq.sh
+++ b/bp_scripts/trim_seq.sh
@@ -5,11 +5,11 @@
 
 pid=$$
 
-plot_scores -t post -o trim_seq_scores_pretrim.$pid.ps |
-plot_lendist -k SEQ_LEN -t post -o trim_seq_lendist_pretrim.$pid.ps |
+plot_scores -t post -o 00_trim_seq_scores_pretrim.$pid.ps |
+plot_lendist -k SEQ_LEN -t post -o 01_trim_seq_lendist_pretrim.$pid.ps |
 trim_seq |
 grab -e "SEQ_LEN>=30" |
 mean_scores -l |
 grab -e "SCORES_LOCAL_MEAN>=15" |
-plot_scores -t post -o trim_seq_scores_posttrim.$pid.ps |
-plot_lendist -k SEQ_LEN -t post -o trim_seq_lendist_posttrim.$pid.ps 
+plot_scores -t post -o 02_trim_seq_scores_posttrim.$pid.ps |
+plot_lendist -k SEQ_LEN -t post -o 03_trim_seq_lendist_posttrim.$pid.ps