From e17af538fca1e46d6fa5563395584e60c01d7bc2 Mon Sep 17 00:00:00 2001 From: martinahansen Date: Thu, 17 Jul 2008 02:56:24 +0000 Subject: [PATCH] cleaning bp_usage git-svn-id: http://biopieces.googlecode.com/svn/trunk@163 74ccb610-7750-0410-82ae-013aeee3265d --- bp_usage/align_seq | 24 -------------------- bp_usage/analyze_bed | 17 -------------- bp_usage/analyze_tags | 23 ------------------- bp_usage/analyze_vals | 19 ---------------- bp_usage/blast_seq | 24 -------------------- bp_usage/blat_seq | 23 ------------------- bp_usage/calc_bit_scores | 18 --------------- bp_usage/complexity_seq | 18 --------------- bp_usage/compute | 19 ---------------- bp_usage/count_seq | 19 ---------------- bp_usage/create_blast_db | 19 ---------------- bp_usage/create_vmatch_index | 19 ---------------- bp_usage/flip_tab | 16 ------------- bp_usage/get_genome_align | 42 ----------------------------------- bp_usage/get_genome_phastcons | 38 ------------------------------- bp_usage/head_records | 18 --------------- bp_usage/length_seq | 19 ---------------- bp_usage/length_vals | 18 --------------- bp_usage/list_biotools | 9 -------- bp_usage/match_seq | 19 ---------------- 20 files changed, 421 deletions(-) delete mode 100644 bp_usage/align_seq delete mode 100644 bp_usage/analyze_bed delete mode 100644 bp_usage/analyze_tags delete mode 100644 bp_usage/analyze_vals delete mode 100644 bp_usage/blast_seq delete mode 100644 bp_usage/blat_seq delete mode 100644 bp_usage/calc_bit_scores delete mode 100644 bp_usage/complexity_seq delete mode 100644 bp_usage/compute delete mode 100644 bp_usage/count_seq delete mode 100644 bp_usage/create_blast_db delete mode 100644 bp_usage/create_vmatch_index delete mode 100644 bp_usage/flip_tab delete mode 100644 bp_usage/get_genome_align delete mode 100644 bp_usage/get_genome_phastcons delete mode 100644 bp_usage/head_records delete mode 100644 bp_usage/length_seq delete mode 100644 bp_usage/length_vals delete mode 100644 bp_usage/list_biotools delete mode 100644 bp_usage/match_seq diff --git a/bp_usage/align_seq b/bp_usage/align_seq deleted file mode 100644 index b361062..0000000 --- a/bp_usage/align_seq +++ /dev/null @@ -1,24 +0,0 @@ -Author: Martin Asser Hansen - Copyright (C) - All rights reserved - -Contact: mail@maasha.dk - -Date: August 2007 - -License: GNU General Public License version 2 (http://www.gnu.org/copyleft/gpl.html) - -Description: Align sequences in stream using Muscle. - -Usage: ... | $script [options] - -Options: [-I | --stream_in=] - Read input from stream file - Default=STDIN -Options: [-O | --stream_out=] - Write output to stream file - Default=STDOUT - -Examples: ... | $script - Aligns all sequences in stream. - -Keys in: SEQ_NAME - name of sequence. -Keys in: Q_ID - used as sequence name if no SEQ_NAME. -Keys in: SEQ - unaligned sequence. - -Keys out: SEQ_NAME - Name of sequence. -Keys out: SEQ - Aligned sequence. -Keys out: ALIGN - Number indicating what alignment this sequence belong to. diff --git a/bp_usage/analyze_bed b/bp_usage/analyze_bed deleted file mode 100644 index ba6eede..0000000 --- a/bp_usage/analyze_bed +++ /dev/null @@ -1,17 +0,0 @@ -Author: Martin Asser Hansen - Copyright (C) - All rights reserved - -Contact: mail@maasha.dk - -Date: August 2007 - -License: GNU General Public License version 2 (http://www.gnu.org/copyleft/gpl.html) - -Description: Analysis BED entries in the stream. - -Usage: ... | $script [options] - -Options: [-I | --stream_in=] - Read input from stream file - Default=STDIN -Options: [-O | --stream_out=] - Write output to file - Default=STDOUT - -Examples: ... | $script - Analyzes all BED entries in the stream. - diff --git a/bp_usage/analyze_tags b/bp_usage/analyze_tags deleted file mode 100644 index 553a852..0000000 --- a/bp_usage/analyze_tags +++ /dev/null @@ -1,23 +0,0 @@ -Author: Martin Asser Hansen - Copyright (C) - All rights reserved - -Contact: mail@maasha.dk - -Date: May 2008 - -License: GNU General Public License version 2 (http://www.gnu.org/copyleft/gpl.html) - -Description: Analyze sequence tags in the stream from sequence or BED records resulting in a tag length and clone count distribution. - -Usage: ... | $script [options] - -Options: [-I | --stream_in=] - Read input from stream file - Default=STDIN -Options: [-O | --stream_out=] - Write output to file - Default=STDOUT - -Examples: ... | $script - Analyzes all entries with SEQ in the stream. - -Keys in: Q_ID/SEQ_NAME - Identifier with clone/read count: ID00001_123 (123 is the clone count). -Keys in: SEQ/BED_LEN - Sequence. - -Keys out: TAG_LEN - Length of sequence tags. -Keys out: TAG_COUNT - Number of tags with a given TAG_LEN. -Keys out: TAG_CLONES - Total clones or reads for all tags (TAG_COUNT) of TAG_LEN. diff --git a/bp_usage/analyze_vals b/bp_usage/analyze_vals deleted file mode 100644 index 175be88..0000000 --- a/bp_usage/analyze_vals +++ /dev/null @@ -1,19 +0,0 @@ -Author: Martin Asser Hansen - Copyright (C) - All rights reserved - -Contact: mail@maasha.dk - -Date: January 2008 - -License: GNU General Public License version 2 (http://www.gnu.org/copyleft/gpl.html) - -Description: Determine type, count, min, max, sum and mean for values in stream. - -Usage: ... | analyze_vals [options] - -Options: [-x | --no_stream] - Do not emit records. -Options: [-k | --keys=] - Comma separated list of keys. -Options: [-I | --stream_in=] - Read input from stream file - Default=STDIN -Options: [-O | --stream_out=] - Write output to stream file - Default=STDOUT - -Examples: ... | analyze_vals -x - Analyses all values in stream. -Examples: ... | analyze_vals -x -k CHR_BEG,SCORE - Analyses selected values in stream. diff --git a/bp_usage/blast_seq b/bp_usage/blast_seq deleted file mode 100644 index 3c75c76..0000000 --- a/bp_usage/blast_seq +++ /dev/null @@ -1,24 +0,0 @@ -Author: Martin Asser Hansen - Copyright (C) - All rights reserved - -Contact: mail@maasha.dk - -Date: September 2007 - -License: GNU General Public License version 2 (http://www.gnu.org/copyleft/gpl.html) - -Description: BLAST sequences in stream against a specified database. - -Usage: ... | blast_seq [options] - -Options: [-d | --database=] - Path to database. -Options: [-g | --genome=] - Choose genome instead of database. -Options: [-p | --program= - blastn|blastp|tblastn|blastx|tblastx - Default=guessed! -Options: [-e | --e_val=] - Expectation value - Default=10 -Options: [-f | --filter] - Filter low complexity sequence - Default=OFF -Options: [-F | --no_filter] - Disable low complexity filter - Default -Options: [-c | --cpus=] - Number of CPUs to use - Default=1 -Options: [-I | --stream_in=] - Read input from stream file - Default=STDIN -Options: [-O | --stream_out=] - Write output to stream file - Default=STDOUT - -Examples: ... | blast_seq -d my_database - BLAST sequences in stream against custom database. -Examples: ... | blast_seq -g hg18 - BLAST sequences in stream against hg18. diff --git a/bp_usage/blat_seq b/bp_usage/blat_seq deleted file mode 100644 index 4c4f382..0000000 --- a/bp_usage/blat_seq +++ /dev/null @@ -1,23 +0,0 @@ -Author: Martin Asser Hansen - Copyright (C) - All rights reserved - -Contact: mail@maasha.dk - -Date: August 2007 - -License: GNU General Public License version 2 (http://www.gnu.org/copyleft/gpl.html) - -Description: BLAT sequences in stream against a specified genome. - -Usage: ... | $script [options] -g - -Options: [-g | --genome= ] - BLAT against genome. -Options: [-c | --ooc] - Use overused tile file (faster, but less sensitive). -Options: [-t | --tile_size=] - Size of match that triggers an alignment - Default=11 -Options: [-s | --step_size=] - Spacing between tiles - Default=tile_size -Options: [-m | --min_identity=] - Minimum sequence identity in percent - Default=90 -Options: [-M | --min_score=] - Minimum score - Default=0 -Options: [-o | --one_off=] - Allows one mismatch in tile - Default=0 -Options: [-I | --stream_in=] - Read input from stream file - Default=STDIN -Options: [-O | --stream_out=] - Write output to stream file - Default=STDOUT - -Examples: ... | $script -g hg18 - BLAT sequences in stream against hg18. diff --git a/bp_usage/calc_bit_scores b/bp_usage/calc_bit_scores deleted file mode 100644 index 34f5334..0000000 --- a/bp_usage/calc_bit_scores +++ /dev/null @@ -1,18 +0,0 @@ -Author: Martin Asser Hansen - Copyright (C) - All rights reserved - -Contact: mail@maasha.dk - -Date: March 2008 - -License: GNU General Public License version 2 (http://www.gnu.org/copyleft/gpl.html) - -Description: Calculate the bit score for each position based on an alignment in the stream. - -Usage: ... | $script [options] - -Options: [-I | --stream_in=] - Read input from stream file - Default=STDIN -Options: [-O | --stream_out=] - Write output to stream file - Default=STDOUT - -Examples: ... | $script - Output a bitscore for each column in the alignment. - -Keys out: V0, V1, V2, Vn - Bit score for each position. diff --git a/bp_usage/complexity_seq b/bp_usage/complexity_seq deleted file mode 100644 index 09724b9..0000000 --- a/bp_usage/complexity_seq +++ /dev/null @@ -1,18 +0,0 @@ -Author: Martin Asser Hansen - Copyright (C) - All rights reserved - -Contact: mail@maasha.dk - -Date: May 2008 - -License: GNU General Public License version 2 (http://www.gnu.org/copyleft/gpl.html) - -Description: Generates an index calculated as the most common di-residue over the sequence length for all sequences in stream. An index higher than 0.4 indicates low complexity sequence. - -Usage: ... | $script [options] - -Options: [-I | --stream_in=] - Read input from stream file - Default=STDIN -Options: [-O | --stream_out=] - Write output to file - Default=STDOUT - -Examples: ... | $script - Analyzes all sequences in stream. - -Keys out: SEQ_COMPLEXITY - Calculated complexity index. diff --git a/bp_usage/compute b/bp_usage/compute deleted file mode 100644 index ea32c6c..0000000 --- a/bp_usage/compute +++ /dev/null @@ -1,19 +0,0 @@ -Author: Martin Asser Hansen - Copyright (C) - All rights reserved - -Contact: mail@maasha.dk - -Date: February 2008 - -License: GNU General Public License version 2 (http://www.gnu.org/copyleft/gpl.html) - -Description: Performs computations on records in stream. - -Usage: ... | $script [options] - -Options: [-e | --eval=] - Evaluate extression. -Options: [-I | --stream_in=] - Read input from stream file - Default=STDIN -Options: [-O | --stream_out=] - Write output to file - Default=STDOUT - -Examples: ... | $script -e 'CHR_BEG = 50' - Set CHR_BEG to 50 in all records. -Examples: ... | $script -e 'CHR_BEG = CHR_BEG - 50' - Substracts 50 from CHR_BEG in all records. -Examples: ... | $script -e 'CHR_END = CHR_END + BED_LEN' - Adds BED_LEN to CHR_END in all records. diff --git a/bp_usage/count_seq b/bp_usage/count_seq deleted file mode 100644 index 2b4bb7a..0000000 --- a/bp_usage/count_seq +++ /dev/null @@ -1,19 +0,0 @@ -Author: Martin Asser Hansen - Copyright (C) - All rights reserved - -Contact: mail@maasha.dk - -Date: August 2007 - -License: GNU General Public License version 2 (http://www.gnu.org/copyleft/gpl.html) - -Description: Count sequences in stream. - -Usage: ... | count_seq [options] - -Options: [-x | --no_stream] - Do not emit records. -Options: [-o | --data_out=] - Write result to file. -Options: [-I | --stream_in=] - Read input from stream file - Default=STDIN -Options: [-O | --stream_out=] - Write output to file - Default=STDOUT - -Examples: ... | count_seq -x -o count.txt - Output records count to 'count.txt'. - diff --git a/bp_usage/create_blast_db b/bp_usage/create_blast_db deleted file mode 100644 index 13bec4c..0000000 --- a/bp_usage/create_blast_db +++ /dev/null @@ -1,19 +0,0 @@ -Author: Martin Asser Hansen - Copyright (C) - All rights reserved - -Contact: mail@maasha.dk - -Date: September 2007 - -License: GNU General Public License version 2 (http://www.gnu.org/copyleft/gpl.html) - -Description: Create a BLAST database from sequences in stream for use with BLAST. - -Usage: ... | create_blast_db [options] - -Options: [-x | --no_stream] - Do not emit records. -Options: [-d | --database=] - Path and name of database to create. -Options: [-I | --stream_in=] - Read input from stream file - Default=STDIN -Options: [-O | --stream_out=] - Write output to stream file - Default=STDOUT - -Examples: ... | create_blast_db -x -d /tmp/fly - diff --git a/bp_usage/create_vmatch_index b/bp_usage/create_vmatch_index deleted file mode 100644 index 10119ff..0000000 --- a/bp_usage/create_vmatch_index +++ /dev/null @@ -1,19 +0,0 @@ -Author: Martin Asser Hansen - Copyright (C) - All rights reserved - -Contact: mail@maasha.dk - -Date: January 2008 - -License: GNU General Public License version 2 (http://www.gnu.org/copyleft/gpl.html) - -Description: Create a vmatch index using mkvtree from sequences in stream for use with vmatch. - -Usage: ... | $script [options] - -Options: [-x | --no_stream] - Do not emit records. -Options: [-i | --index_name=] - Directory name to contain index files. -Options: [-p | --prefix_length=] - Minimum prefix that can be matched - Default=guessed -Options: [-I | --stream_in=] - Read input from stream file - Default=STDIN -Options: [-O | --stream_out=] - Write output to stream file - Default=STDOUT - -Examples: ... | $script -x -i /tmp/fly diff --git a/bp_usage/flip_tab b/bp_usage/flip_tab deleted file mode 100644 index deae82b..0000000 --- a/bp_usage/flip_tab +++ /dev/null @@ -1,16 +0,0 @@ -Author: Martin Asser Hansen - Copyright (C) - All rights reserved - -Contact: mail@maasha.dk - -Date: June 2008 - -License: GNU General Public License version 2 (http://www.gnu.org/copyleft/gpl.html) - -Description: Flip table records so rows becomes columns and visa versa. - -Usage: ... | $script [options] - -Options: [-I | --stream_in=] - Read input from stream file - Default=STDIN -Options: [-O | --stream_out=] - Write output to stream file - Default=STDOUT - -Examples: ... | $script - Flip rows and columns. diff --git a/bp_usage/get_genome_align b/bp_usage/get_genome_align deleted file mode 100644 index 80dd010..0000000 --- a/bp_usage/get_genome_align +++ /dev/null @@ -1,42 +0,0 @@ -Author: Martin Asser Hansen - Copyright (C) - All rights reserved - -Contact: mail@maasha.dk - -Date: April 2008 - -License: GNU General Public License version 2 (http://www.gnu.org/copyleft/gpl.html) - -Description: Extract alignment from multiple genome alignment either explicitly or using BED/PSL/BLAST entries in stream. - -Usage: $script [options] -g -Usage: ... | $script [options] -g - -Options: [-g | --genome=] - Genome to get alignment from. -Options: [-c | --chr=] - Chromosome with requested alignment. -Options: [-b | --beg=] - Begin position of alignment (first residue=1). -Options: [-e | --end=] - End position of alignment. -Options: [-l | --len=] - Length of alignment. -Options: [-s | --strand=] - Strand - Default=+ -Options: [-I | --stream_in=] - Read input from stream file - Default=STDIN -Options: [-O | --stream_out=] - Write output to stream file - Default=STDOUT - -Examples: $script -g hg18 -c chr1 -b 1 -e 10 - Get the first 10 nucleotides multiz alignment of human genome chr1. -Examples: $script -g hg18 -c chr1 -b 1 -l 10 - Get the first 10 nucleotides multiz alignment of human genome chr1. -Examples: ... | $script -g mm8 -s '-' - Get the reverse complement alignment of mouse BED/PSL/BLAST entries. - -Keys in: REC_TYPE - Optional record type (BED, PSL, or BLAST). -Keys in: CHR - Chromosome (for use with BED record type). -Keys in: CHR_BEG - Chromosome begin. -Keys in: CHR_END - Chromosome end. -Keys in: S_ID - Chromosome (for use with PSL and BLAST record type). -Keys in: S_BEG - Chromosome begin (for use with PSL and BLAST record type). -Keys in: S_END - Chromosome end (for use with PSL and BLAST record type). -Keys in: STRAND - Sequence strand. - -Keys out: ALIGN - Alignment number that this entry belongs to. -Keys out: CHR - Chromosome. -Keys out: CHR_BEG - Chromosome begin. -Keys out: CHR_END - Chromosome end. -Keys out: STRAND - Strand. -Keys out: SEQ - Sequence. -Keys out: ALIGN_LEN - Sequence length. diff --git a/bp_usage/get_genome_phastcons b/bp_usage/get_genome_phastcons deleted file mode 100644 index ad6621a..0000000 --- a/bp_usage/get_genome_phastcons +++ /dev/null @@ -1,38 +0,0 @@ -Author: Martin Asser Hansen - Copyright (C) - All rights reserved - -Contact: mail@maasha.dk - -Date: February 2009 - -License: GNU General Public License version 2 (http://www.gnu.org/copyleft/gpl.html) - -Description: Extract phastcons scores from a genome either explicitly or using BED/PSL/BLAST entries in stream. - -Usage: $script [options] -g -Usage: ... | $script [options] -g - -Options: [-g | --genome=] - Genome to get phastcons scores from. -Options: [-c | --chr=] - Chromosome with requested scores. -Options: [-b | --beg=] - Begin position of interval (first residue=1). -Options: [-e | --end=] - End position of interval. -Options: [-l | --len=] - Length of interval. -Options: [-f | --flank=] - Include flanking region. -Options: [-I | --stream_in=] - Read input from stream file - Default=STDIN -Options: [-O | --stream_out=] - Write output to stream file - Default=STDOUT - -Examples: $script -g hg18 -c chr1 -b 1 -e 10 - Get the first 10 phastcons scores from human genome chr1. -Examples: $script -g hg18 -c chr1 -b 1 -l 10 - Get the first 10 phastcons scores from human genome chr1. -Examples: ... | $script -g mm8 -f 50 - Get phastcons scores including 50nt flanks of mouse BED/PSL/BLAST entries. - -Keys in: REC_TYPE - Optional record type (BED, PSL, or BLAST). -Keys in: CHR - Chromosome (for use with BED record type). -Keys in: CHR_BEG - Chromosome begin. -Keys in: CHR_END - Chromosome end. -Keys in: S_ID - Chromosome (for use with PSL and BLAST record type). -Keys in: S_BEG - Chromosome begin (for use with PSL and BLAST record type). -Keys in: S_END - Chromosome end (for use with PSL and BLAST record type). - -Keys out: CHR - Chromosome. -Keys out: CHR_BEG - Chromosome begin. -Keys out: CHR_END - Chromosome end. -Keys out: PHASTCONS - Comma separated list of phastcons scores. diff --git a/bp_usage/head_records b/bp_usage/head_records deleted file mode 100644 index e47def6..0000000 --- a/bp_usage/head_records +++ /dev/null @@ -1,18 +0,0 @@ -Author: Martin Asser Hansen - Copyright (C) - All rights reserved - -Contact: mail@maasha.dk - -Date: August 2007 - -License: GNU General Public License version 2 (http://www.gnu.org/copyleft/gpl.html) - -Description: Emit the first records in stream. - -Usage: ... | head_records - -Options: [-n | --num=] - Number of records to emit - Default=10 -Options: [-I | --stream_in=] - Read input from stream file - Default=STDIN -Options: [-O | --stream_out=] - Write output to stream file - Default=STDOUT - -Examples: ... | head_records -n 40 - Emit the 40 first records from the stream. - diff --git a/bp_usage/length_seq b/bp_usage/length_seq deleted file mode 100644 index 01983ba..0000000 --- a/bp_usage/length_seq +++ /dev/null @@ -1,19 +0,0 @@ -Author: Martin Asser Hansen - Copyright (C) - All rights reserved - -Contact: mail@maasha.dk - -Date: August 2007 - -License: GNU General Public License version 2 (http://www.gnu.org/copyleft/gpl.html) - -Description: Determines the length of each sequence in stream - and a total length. - -Usage: ... | length_seq [options] - -Options: [-x | --no_stream] - Do not emit records. -Options: [-o | --data_out=] - Write result to file. -Options: [-I | --stream_in=] - Read input from stream file - Default=STDIN -Options: [-O | --stream_out=] - Write output to file - Default=STDOUT - -Examples: ... | length_seq -x -o length.txt - Output total length to 'length.txt'. - diff --git a/bp_usage/length_vals b/bp_usage/length_vals deleted file mode 100644 index a72080c..0000000 --- a/bp_usage/length_vals +++ /dev/null @@ -1,18 +0,0 @@ -Author: Martin Asser Hansen - Copyright (C) - All rights reserved - -Contact: mail@maasha.dk - -Date: August 2007 - -License: GNU General Public License version 2 (http://www.gnu.org/copyleft/gpl.html) - -Description: Determine the length of the value for given keys. - -Usage: ... | length_vals [options] - -Options: [-k | --keys=] - Comma separated list of keys. -Options: [-I | --stream_in=] - Read input from stream file - Default=STDIN -Options: [-O | --stream_out=] - Write output to stream file - Default=STDOUT - -Examples: ... | length_vals -k SEQ - Determine the length of all SEQ values. -Examples: ... | length_vals -k HIT,PATTERN - Determine the length of all HIT and PATTERN values. diff --git a/bp_usage/list_biotools b/bp_usage/list_biotools deleted file mode 100644 index 6e675be..0000000 --- a/bp_usage/list_biotools +++ /dev/null @@ -1,9 +0,0 @@ -Author: Martin Asser Hansen - Copyright (C) - All rights reserved - -Contact: mail@maasha.dk - -Date: January 2008 - -License: GNU General Public License version 2 (http://www.gnu.org/copyleft/gpl.html) - -Description: List the description of all biotools. diff --git a/bp_usage/match_seq b/bp_usage/match_seq deleted file mode 100644 index e443d5d..0000000 --- a/bp_usage/match_seq +++ /dev/null @@ -1,19 +0,0 @@ -Author: Martin Asser Hansen - Copyright (C) - All rights reserved - -Contact: mail@maasha.dk - -Date: August 2007 - -License: GNU General Public License version 2 (http://www.gnu.org/copyleft/gpl.html) - -Description: Find all matches between the first two sequences in stream - or all self-self matches if only one sequence is found. - -Usage: ... | match_seq [options] - -Options: [-w | --word_size=] - Minimum match size - Default=20 -Options: [-d | --direction=] - Match direction: both|forward|reverse - Default=both -Options: [-I | --stream_in=] - Read input from stream file - Default=STDIN -Options: [-O | --stream_out=] - Write output to stream file - Default=STDOUT - -Examples: ... | match_seq -w 25 -d forward - -- 2.39.5