Mercurial > repos > cjav > smalt
changeset 2:ead9eab0bc4c draft default tip
Uploaded
| author | takadonet |
|---|---|
| date | Thu, 16 Jan 2014 14:32:05 -0500 |
| parents | b857363cc1db |
| children | |
| files | smalt/smalt_check.sh smalt/smalt_check.xml smalt/smalt_index.sh smalt/smalt_index.xml smalt/smalt_map.sh smalt/smalt_map.xml smalt/smalt_sample.sh smalt/smalt_sample.xml tool_conf.xml tool_dependencies.xml tools/smalt_wrapper.py tools/smalt_wrapper.xml tools/tool-data/smalt_index.loc.sample tools/tool_data_table_conf.xml.sample |
| diffstat | 14 files changed, 662 insertions(+), 523 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/smalt/smalt_check.sh Thu Jan 16 14:32:05 2014 -0500 @@ -0,0 +1,24 @@ +#/bin/bash + + +#determine if we were given 1 or 2 fastq files +if [ $# -eq 3 ] || [ $# -eq 2 ]; then + #get the output file name + output=$1 + + #remove it from the arguments list + shift + + smalt check $@ > $output + + #remove header file + sed -i -e "1d" $output + +else + #unknown arguments given + exit 1 +fi + + + +exit 0 \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/smalt/smalt_check.xml Thu Jan 16 14:32:05 2014 -0500 @@ -0,0 +1,68 @@ +<tool id="smalt_check" name="smalt check" version="0.0.2" > + <requirements> + <requirement type="package" version="1.0">smalt</requirement> + </requirements> + + <command interpreter="bash"> + smalt_check.sh $output + #if $singlePaired.sPaired == "single": + $singlePaired.sInput1 + #elif $singlePaired.sPaired == "paired": + $singlePaired.pInput1 $singlePaired.pInput2 + #elif $singlePaired.sPaired == "matePairs": + $singlePaired.mInput1 $singlePaired.mInput2 + #end if + + + </command> + + <description>Determine number of reads in fastq(s) and if they are mate-pair</description> + + <inputs> + <conditional name="singlePaired"> + <param name="sPaired" type="select" label="Is this library mate-paired?"> + <option value="single">Single-end</option> + <option value="paired">Paired-end</option> + <option value="matePairs">MatePairs</option> + </param> + <when value="single"> + <param name="sInput1" type="data" format="fastq" label="Single end illumina fastq file" optional="false"/> + </when> + <when value="paired"> + <param name="pInput1" type="data" format="fastq,fastqsanger,fastqillumina,fastqsolexa" label="Forward FASTQ file" help="Must have ASCII encoded quality scores"/> + <param name="pInput2" type="data" format="fastq,fastqsanger,fastqillumina,fastqsolexa" label="Reverse FASTQ file" help="File format must match the Forward FASTQ file"/> + </when> + <when value="matePairs"> + <param name="mInput1" type="data" format="fastq,fastqsanger,fastqillumina,fastqsolexa" label="Forward FASTQ file" help="Must have ASCII encoded quality scores"/> + <param name="mInput2" type="data" format="fastq,fastqsanger,fastqillumina,fastqsolexa" label="Reverse FASTQ file" help="File format must match the Forward FASTQ file"/> + </when> + </conditional> + + </inputs> + + <outputs> + <data format="tabular" name="output" /> + </outputs> + <stdio> + <exit_code range="1" level="fatal" description="Unknown argument given." /> + <exit_code range="2:" level="fatal" description="Unknown error." /> + </stdio> + +<help> + +**What it does** + +Check FASTA/FASTQ read files. If <mate_file> is specified, the reads are in pairs. + +------ + +Please cite the website "http://www.sanger.ac.uk/resources/software/smalt/". + + + + +</help> + + +</tool> +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/smalt/smalt_index.sh Thu Jan 16 14:32:05 2014 -0500 @@ -0,0 +1,30 @@ +#/bin/bash + +#smalt_index.sh $output $output2 $reference $k $s + + +#get first output file name and remove it from argument list +output1=$1 +shift +#get second output file name and remove it from argument list +output2=$1 +shift + +#get reference file path +reference=$1; +shift + +#get working directory so we can find the output files +CUR_DIR=`pwd` + + +#run script +#options need to be put in front of last two arguments otherwise will error out +smalt index $@ 'temp' $reference + + +#move output files to their names so Galaxy can see the results +mv "$CUR_DIR/temp.smi" "$output1" +mv "$CUR_DIR/temp.sma" "$output2" + +exit 0 \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/smalt/smalt_index.xml Thu Jan 16 14:32:05 2014 -0500 @@ -0,0 +1,64 @@ +<tool id="smalt_index" name="smalt index" version="0.0.2"> + <requirements> + <requirement type="package" version="1.0">smalt</requirement> + </requirements> + + <command interpreter="bash"> + smalt_index.sh "$output" "$output2" "$reference" + #if $k: + -k "$k" + #end if + + #if $s: + -s "$s" + #end if + + </command> + + <description>Index a reference </description> + + <inputs> + <param name="reference" type="data" format="fasta" label="Fasta reference file"/> + <param name="k" type="integer" value="13" label="K-mer size" help="Specifies the word length. [wordlen] is an integer within the limits. between 2 and less then 20. The default word length is 13"/> + <param name="s" type="text" label="Stepsiz" help="Specifies how many bases are skipped between indexed words."/> + + + </inputs> + + <outputs> + <data name="output" label="SMI" /> + <data name="output2" label="SMA" /> + </outputs> + <stdio> + <exit_code range="1:" level="fatal" description="Unknown error" /> + </stdio> + + <help> + +**What it does** + +Generates an index of k-mer words for the genomic reference sequences. The words are of fixed length <wordlen> and are sampled at equidistant steps <stepsiz> bases apart. The reference sequences are provided in a single file <reference_file> in FASTA or FASTQ format. Two binary files are output. The file <index_name>.sma contains the reference sequences in compressed form. The file <index_name>.smi contains the k-mer word index. + + +------ + +Please cite the website "http://www.sanger.ac.uk/resources/software/smalt/". + +------ + + -k <wordlen> + Specifies the word length. <wordlen> is an integer within the limits + 2 < wordlen <= 20. The default word length is 13. + + -s <stepsiz> + Specifies how many bases are skipped between indexed words. With '-s 1' + every k-mer word along the reference sequences is indexed. With '-s 2' + every other word is indexed etc. By default the step size is set equal + to the word length (tiling words). + + + </help> + + +</tool> +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/smalt/smalt_map.sh Thu Jan 16 14:32:05 2014 -0500 @@ -0,0 +1,42 @@ +#/bin/bash + + +smi=$1 +shift +sma=$1 +shift + +#get working directory so we can find the output files +CUR_DIR=`pwd` + + +cp "$smi" "$CUR_DIR/temp.smi" +cp "$sma" "$CUR_DIR/temp.sma" + +#determine if we have 1 or 2 +num_inputs=$1 +shift + +inputs=() + +#determine how many fasta/fastq were given. Needs to be provided by user +if [ $num_inputs -eq 1 ]; then + inputs+=$1 + shift +elif [ $num_inputs -eq 2 ]; then + inputs+=$1 + shift + inputs+=' ' + inputs+=$1 + shift +else + exit 1 +fi +smalt map $@ 'temp' $inputs + +#remove index files +rm "$CUR_DIR/temp.smi" +rm "$CUR_DIR/temp.sma" + + +exit 0 \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/smalt/smalt_map.xml Thu Jan 16 14:32:05 2014 -0500 @@ -0,0 +1,292 @@ +<tool id="smalt_map" name="smalt map" version="0.0.2" > + <requirements> + <requirement type="package" version="1.0">smalt</requirement> + </requirements> + + <command interpreter="bash"> + smalt_map.sh $smi $sma + + #if $singlePaired.sPaired == "single": + 1 $singlePaired.sInput1 + #elif $singlePaired.sPaired == "paired": + 2 $singlePaired.pInput1 $singlePaired.pInput2 + #elif $singlePaired.sPaired == "matePairs": + 2 $singlePaired.mInput1 $singlePaired.mInput2 + #end if + + -o $output + + #if $outformat: + -f "$outformat" + #end if + + #if $threads: + -n "$threads" + #end if + + + #if $mincover: + -c "$mincover" + #end if + + #if $scordiff: + -d "$scordiff" + #end if + + #if $insfil: + -g "$insfil" + #end if + + #if $insertmax: + -i "$insertmax" + #end if + + #if $insertmin: + -j "$insertmin" + #end if + + #if $minscor: + -m "$minscor" + #end if + + #if $minbasq: + -q "$minbasq" + #end if + + #if $seed: + -r "$seed" + #end if + + #if $sw_weighted: + -w + #end if + + #if $search_harder: + -x + #end if + + #if $minid: + -y "$minid" + #end if + + </command> + + <description>Map query reads (FASTA/FASTQ) format onto the reference sequences</description> + + <inputs> + <conditional name="singlePaired"> + <param name="sPaired" type="select" label="Is this library mate-paired?"> + <option value="single">Single-end</option> + <option value="paired">Paired-end</option> + <option value="matePairs">MatePairs</option> + </param> + <when value="single"> + <param name="sInput1" type="data" format="fastq" label="Single end illumina fastq file" optional="false"/> + </when> + <when value="paired"> + <param name="pInput1" type="data" format="fastq,fastqsanger,fastqillumina,fastqsolexa" label="Forward FASTQ file" help="Must have ASCII encoded quality scores"/> + <param name="pInput2" type="data" format="fastq,fastqsanger,fastqillumina,fastqsolexa" label="Reverse FASTQ file" help="File format must match the Forward FASTQ file"/> + </when> + <when value="matePairs"> + <param name="mInput1" type="data" format="fastq,fastqsanger,fastqillumina,fastqsolexa" label="Forward FASTQ file" help="Must have ASCII encoded quality scores"/> + <param name="mInput2" type="data" format="fastq,fastqsanger,fastqillumina,fastqsolexa" label="Reverse FASTQ file" help="File format must match the Forward FASTQ file"/> + </when> + </conditional> + + <param name="threads" type="text" format="integer" value="2" label="Number of threads to use" help="The order of the reads in the input files is not preserved for the output unless '-O' is also specified"/> + <param name="smi" type="data" label="SMI index" help=""/> + <param name="sma" type="data" label="SMA index" help=""/> + + <param name="mincover" type="text" label="Mincover" help="Only consider mappings where the k-mer word seeds cover the query read to a minimum extent"/> + <param name="scordiff" type="text" label="Scordiff" help="Set a threshold of the Smith-Waterman alignment score relative to the maximum score"/> + <param name="outformat" type="select" label="Format" help=""> + <option value="cigar">cigar</option> + <option value="sam">sam</option> + <option value="samsoft">samsoft</option> + <option value="ssaha">ssaha</option> + </param> + <param name="insfil" type="data" optional="true" label="Distribution insert sizes " help="Use the distribution of insert sizes stored in the file [insfil]. Thisfile is in ASCII format and can be generated using the 'sample'"/> + <param name="insertmax" type="text" label="Maximum insert size (only in paired-end mode). " help="Maximum insert size (only in paired-end mode). The default is 500."/> + <param name="insertmin" type="text" label="Minimum insert size (only in paired-end mode). " help="Minimum insert size (only in paired-end mode). The default is 0."/> + <param name="pairtype" type="select" optional="true" label="Pair Type" help="Type of read pair library"> + <option value="se">Illumina single-end</option> + <option value="pe">Illumina paired-end (short inserts)</option> + <option value="mp">Illumina mate-pair library (long inserts)</option> + <option value="pp">Mate-pair sequenced on the same strand</option> + </param> + + <param name="minscor" type="text" label="Sets an absolute threshold of the Smith-Waterman scores." help="Mappings with scores below that threshold will not be reported. The default is < minscor > = < wordlen > + < stepsiz > - 1"/> + + <param name="minbasq" type="text" label="Sets a base quality threshold (0 <= minbasq <= 10, default 0)" help="K-mer words of the read with nucleotides that have a base quality below this threshold are not looked up in the hash index."/> + + <param name="seed" type="text" label="If the there are multiple mappings with the same best alignment score report one picked at random." help="is an integer >= 0 used to seed the pseudo-random genarator."/> + + <param name="sw_weighted" type="boolean" label="Smith-Waterman scores are complexity weighted."/> + + <param name="search_harder" type="boolean" label="This flag triggers a more exhaustive search for alignments at the cost of decreased speed" help="In paired-end mode each mate is mapped independently. (By default the mate with fewer hits in the hash index is mapped first and the vicinity is searched for mappings of its mate.)"/> + + <param name="minid" type="text" label="Sets an identity threshold for a mapping to be reported (default: 0)." help="specifies the number of exactly matching nucleotides either as + a positive integer or as a fraction of the read length (>= 1.0)."/> + + </inputs> + + + <outputs> + <data name="output" format="cigar" > + <change_format> + <when input="outformat" value="cigar" format="cigar"/> + <when input="outformat" value="sam" format="sam"/> + <when input="outformat" value="samsoft" format="samsoft"/> + <when input="outformat" value="ssaha" format="ssaha"/> + </change_format> + </data> + </outputs> + <stdio> + <exit_code range="1:" level="fatal" description="Unknown error" /> + <regex match="Command line error" + source="stdout" + level="fatal" + description="You cannot do that!! What were you thinking!" /> + <regex match="ERROR" + source="stderr" + level="fatal" + description="You cannot do that!! What were you thinking!" /> + + </stdio> + +<help> + + +**What it does** + +SMALT is a pairwise sequence alignment program for the experimentingcient mapping of DNA sequencing reads onto genomic reference sequences. It uses a combination of short-word hashing and dynamic programming. Most types of sequencing platforms are supported including paired-end sequencing reads. + + +------ + + +**Know what you are doing** + +.. class:: warningmark + +There is no such thing (yet) as an automated gearshift in short read mapping. It is all like stick-shift driving in San Francisco. In other words = running this tool with default parameters will probably not give you meaningful results. A way to deal with this is to **understand** the parameters by carefully reading the `documentation`__ and experimenting. Fortunately, Galaxy makes experimenting easy. + + .. __: http://www.sanger.ac.uk/resources/software/smalt/ + +------ + +**Input formats** + +SMALT accepts files in Sanger FASTQ format (galaxy type *fastqsanger*). Use the FASTQ Groomer to prepare your files. + +------ + + +Please cite the website "http://www.sanger.ac.uk/resources/software/smalt/". + +------ + + + -a + Output explicit alignments along with the mappings. + + -c <mincover> + Only consider mappings where the k-mer word seeds cover the query read to + a minimum extent. If <mincover> is an integer or floating point > 1.0, at + least this many bases of the read must be covered by k-mer word seeds. If + <mincover> is a floating point <= 1.0, it specifies the fraction of the + query read length that must be covered by k-mer word seeds. This option + is only valid in conjunction with the '-x' flag. + + -d <scordiff> + Set a threshold of the Smith-Waterman alignment score relative to the + maximum score. All mappings are reported that have Smith-Waterman scores + within <scorediff> of the maximum score. Mappings with scores lower than + this value are skipped. This option has no effect when paired reads are + mapped. + <scorediff> is an integer. If set to 0 (default) only mappings with the + best score are reported. Reads with multiple best mappings are reported + as unmapped. If set to a value < 0, report all alignments with scores + above the threshold specified with the '-m <minscor>' option. + + -f <format> + Specifies the output format. <format> can be either 'cigar' (default), + 'sam' (samtools.sourceforge.net, hard clipped), 'samsoft' (sam output + using soft clipping) or 'ssaha' (ssaha2 default output format). + + -g <insfil> + Use the distribution of insert sizes stored in the file <insfil>. This + file is in ASCII format and can be generated using the 'sample' task see + 'smalt sample -H' for help). + + -H + Print these instructions. + + -i <insertmax> + Maximum insert size (only in paired-end mode). The default is 500. + + -j <insertmin> + Minimum insert size (only in paired-end mode). The default is 0. + + -l <pairtyp> + Type of read pair library. <pairtyp> can be either 'pe', i.e. for + the Illumina paired-end library for short inserts. 'mp' for the Illumina mate-pair library for long inserts or + 'pp' for mates sequenced on the same strand + + + -m <minscor> + Sets an absolute threshold of the Smith-Waterman scores. Mappings with + scores below that threshold will not be reported. The default is + <minscor> = <wordlen> + <stepsiz> - 1 + + -n <nthreads> + Run smalt using mutiple threads. <nthread> is the number of additional + threads forked from the main thread. The order of the reads in the + input files is not preserved for the output unless '-O' is also specified. + + -o <oufilnam> + Write mapping output (e.g. SAM lines) to a separate file. If this option + is not specified, mappings are written to standard output together with + other messages. + + -O + Output mappings in the order of the reads in the input files when using + multiple threads (option '-n <nthreads>'). + + -p + Report partial alignments if they are complementary on the read (split + reads). + + -q <minbasq> + Sets a base quality threshold (0 <= minbasq <= 10, default 0). + K-mer words of the read with nucleotides that have a base quality below + this threshold are not looked up in the hash index. + + -r <seed> + If the there are multiple mappings with the same best alignment score + report one picked at random. This is relevant only in paired-end mode or + with the option -d 0 (the default). + <seed> is an integer >= 0 used to seed the pseudo-random genarator. With + <seed> = 0 a seed is derived from the current calendar time. Without this + option (the default) reads with multiple best mappings are reported as + unmapped. + + -w + Smith-Waterman scores are complexity weighted. + + -x + This flag triggers a more exhaustive search for alignments at the cost + of decreased speed. In paired-end mode each mate is mapped independently. + (By default the mate with fewer hits in the hash index is mapped first + and the vicinity is searched for mappings of its mate.) + + -y <minid> + Sets an identity threshold for a mapping to be reported (default: 0). + <minid> specifies the number of exactly matching nucleotides either as + a positive integer or as a fraction of the read length (<= 1.0). + +</help> + + +</tool> +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/smalt/smalt_sample.sh Thu Jan 16 14:32:05 2014 -0500 @@ -0,0 +1,42 @@ +#/bin/bash + + +smi=$1 +shift +sma=$1 +shift + +#get working directory so we can find the output files +CUR_DIR=`pwd` + + +cp "$smi" "$CUR_DIR/temp.smi" +cp "$sma" "$CUR_DIR/temp.sma" + +#determine if we have 1 or 2 +num_inputs=$1 +shift + +inputs=() + +#determine how many fasta/fastq were given. Needs to be provided by user +if [ $num_inputs -eq 1 ]; then + inputs+=$1 + shift +elif [ $num_inputs -eq 2 ]; then + inputs+=$1 + shift + inputs+=' ' + inputs+=$1 + shift +else + exit 1 +fi +smalt sample $@ 'temp' $inputs + +#remove index files +rm "$CUR_DIR/temp.smi" +rm "$CUR_DIR/temp.sma" + + +exit 0 \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/smalt/smalt_sample.xml Thu Jan 16 14:32:05 2014 -0500 @@ -0,0 +1,74 @@ +<tool id="smalt_sample" name="smalt sample" version="0.0.2" > + <requirements> + <requirement type="package" version="1.0">smalt</requirement> + </requirements> + + <command interpreter="bash"> + smalt_sample.sh "$smi" "$sma" + + 2 "$mInput1" "$mInput2" + + -o "$output" + + #if $threads: + -n "$threads" + #end if + + #if $minscor: + -m "$minscor" + #end if + + #if $minbasq: + -q "$minbasq" + #end if + + #if $num_reads: + -u "$num_reads" + #end if + + </command> + + <description>Sample insert size distribution for paired reads.</description> + + <inputs> + <param name="mInput1" type="data" format="fastq,fastqsanger,fastqillumina,fastqsolexa" label="Forward FASTQ file" help="Must have ASCII encoded quality scores"/> + <param name="mInput2" type="data" format="fastq,fastqsanger,fastqillumina,fastqsolexa" label="Reverse FASTQ file" help="File format must match the Forward FASTQ file"/> + <param name="smi" type="data" label="SMI index" help=""/> + <param name="sma" type="data" label="SMA index" help=""/> + + <param name="threads" type="text" format="integer" value="2" label="Number of threads to use" help="The order of the reads in the input files is not preserved for the output unless '-O' is also specified"/> + <param name="minscor" type="text" label="Sets an absolute threshold of the Smith-Waterman scores." help="Mappings with scores below that threshold will not be reported. The default is < minscor > = < wordlen > + < stepsiz > - 1"/> + <param name="minbasq" type="text" label="Sets a base quality threshold (0 <= minbasq <= 10, default 0)" help="K-mer words of the read with nucleotides that have a base quality below this threshold are not looked up in the hash index."/> + + <param name="num_reads" type="integer" value="100" label="Map only every [num_reads]-th read pair" help="Default 100"/> + </inputs> + + <outputs> + <data format="cigar" name="output" /> + </outputs> + <stdio> + <exit_code range="1:" level="fatal" description="Unknown error" /> + </stdio> + +<help> + +**What it does** + + Sample insert size distribution for paired reads. A subset of the read + pairs is aligned with a reference in order to derrive the distribution of + insert sizes. The reference sequences and index are read from the files + [index_name.sma and [index_name].smi created by the 'index' task + + +------ + +Please cite the website "http://www.sanger.ac.uk/resources/software/smalt/". + + + + +</help> + + +</tool> +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_conf.xml Thu Jan 16 14:32:05 2014 -0500 @@ -0,0 +1,8 @@ +<?xml version="1.0"?> +<toolbox> + <section name="Smalt Tools" id="smalt"> + <label text="Smalt Tools" id="smalt_tools" /> + <tool file="smalt/tools/smalt/smalt_check.xml" /> + <tool file="smalt/tools/smalt/smalt_index.xml" /> + </section> +</toolbox>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_dependencies.xml Thu Jan 16 14:32:05 2014 -0500 @@ -0,0 +1,18 @@ +<?xml version="1.0"?> +<tool_dependency> + <package name="smalt" version="1.0"> + <install version="1.0"> + <actions> + <action type="download_by_url" target_filename="smalt-0.7.5.tar.gz">http://downloads.sourceforge.net/project/smalt/smalt-0.7.5.tar.gz</action> + <action type="shell_command">./configure --prefix=$INSTALL_DIR</action> + <action type="make_install"></action> + <action type="set_environment"> + <environment_variable name="PATH" action="prepend_to">$INSTALL_DIR/bin</environment_variable> + <environment_variable name="PATH" action="prepend_to">$INSTALL_DIR/share</environment_variable> + </action> + </actions> + </install> + <readme> + </readme> + </package> +</tool_dependency>
--- a/tools/smalt_wrapper.py Wed Feb 13 13:23:09 2013 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,195 +0,0 @@ -#!/usr/bin/env python - -""" -Runs Smalt on single-end or paired-end data. -Produces a SAM file containing the mappings. -Works with Smalt version 0.7.1. - -usage: smalt_wrapper.py [options] - -See below for options -""" - -import optparse, os, shutil, subprocess, sys, tempfile - -def stop_err( msg ): - sys.stderr.write( '%s\n' % msg ) - sys.exit() - -def __main__(): - #Parse Command Line - parser = optparse.OptionParser() - parser.add_option( '-t', '--threads', dest='threads', help='The number of threads to use' ) - parser.add_option( '-r', '--ref', dest='ref', help='The reference genome to use or index' ) - parser.add_option( '-f', '--input1', dest='fastq', help='The (forward) fastq file to use for the mapping' ) - parser.add_option( '-F', '--input2', dest='rfastq', help='The reverse fastq file to use for mapping if paired-end data' ) - parser.add_option( '-u', '--output', dest='output', help='The file to save the output (SAM format)' ) - parser.add_option( '-g', '--genAlignType', dest='genAlignType', help='The type of pairing (single or paired)' ) - parser.add_option( '-p', '--params', dest='params', help='Parameter setting to use (pre_set or full)' ) - parser.add_option( '-s', '--fileSource', dest='fileSource', help='Whether to use a previously indexed reference sequence or one form history (indexed or history)' ) - parser.add_option( '-x', '--exhaustiveSearch', dest='exhaustiveSearch', help='This flag triggers a more exhaustive search for alignments at the cost of decreased speed' ) - parser.add_option( '-c', '--minCover', dest='minCover', help='Only consider mappings where the k-mer word seeds cover the query read to a minimum extent' ) - parser.add_option( '-d', '--scorDiff', dest='scorDiff', help='Set a threshold of the Smith-Waterman alignment score relative to the maximum score' ) - parser.add_option( '-i', '--insertMax', dest='insertMax', help='Maximum insert size (Only in paired-end mode)' ) - parser.add_option( '-j', '--insertMin', dest='insertMin', help='Minimum insert size (Only in paired-end mode)' ) - parser.add_option( '-l', '--pairTyp', dest='pairTyp', help='Type of read pair library, can be either pe, mp or pp' ) - parser.add_option( '-m', '--minScor', dest='minScor', help='Sets an absolute threshold of the Smith-Waterman scores' ) - parser.add_option( '-a', '--partialAlignments', dest='partialAlignments', help='Report partial alignments if they are complementary on the read (split reads)' ) - parser.add_option( '-q', '--minBasq', dest='minBasq', help='Sets a base quality threshold (0 <= minbasq <= 10, default 0)' ) - parser.add_option( '-e', '--seed', dest='seed', help='If <seed> >= 0 report an alignment selected at random where there are multiple mappings with the same best alignment score. With <seed> = 0 (default) a seed is derived from the current calendar time. If <seed> < 0 reads with multiple best mappings are reported as "not mapped".' ) - parser.add_option( '-w', '--complexityWeighted', dest='complexityWeighted', help='Smith-Waterman scores are complexity weighted' ) - parser.add_option( '-y', '--minId', dest='minId', help='Sets an identity threshold for a mapping to be reported' ) - parser.add_option( '-D', '--dbkey', dest='dbkey', help='Dbkey for reference genome' ) - parser.add_option( '-X', '--do_not_build_index', dest='do_not_build_index', action='store_true', help="Don't build index" ) - parser.add_option( '-H', '--suppressHeader', dest='suppressHeader', help='Suppress header' ) - (options, args) = parser.parse_args() - - # output version # of tool - try: - tmp = tempfile.NamedTemporaryFile().name - tmp_stdout = open( tmp, 'wb' ) - proc = subprocess.Popen( args='smalt 2>&1', shell=True, stdout=tmp_stdout ) - tmp_stdout.close() - returncode = proc.wait() - stdout = None - for line in open( tmp_stdout.name, 'rb' ): - if line.lower().find( 'version' ) >= 0: - stdout = line.strip() - break - if stdout: - sys.stdout.write( 'SMALT %s\n' % stdout ) - else: - raise Exception - except: - sys.stdout.write( 'Could not determine SMALT version\n' ) - - fastq = options.fastq - if options.rfastq: - rfastq = options.rfastq - - # make temp directory for placement of indices - tmp_index_dir = tempfile.mkdtemp() - tmp_dir = tempfile.mkdtemp() - # index if necessary - if options.fileSource == 'history' and not options.do_not_build_index: - ref_file = tempfile.NamedTemporaryFile( dir=tmp_index_dir ) - ref_file_name = ref_file.name - ref_file.close() - os.symlink( options.ref, ref_file_name ) - cmd1 = 'smalt index %s %s' % ( ref_file_name, ref_file_name ) - try: - tmp = tempfile.NamedTemporaryFile( dir=tmp_index_dir ).name - tmp_stderr = open( tmp, 'wb' ) - proc = subprocess.Popen( args=cmd1, shell=True, cwd=tmp_index_dir, stderr=tmp_stderr.fileno() ) - returncode = proc.wait() - tmp_stderr.close() - # get stderr, allowing for case where it's very large - tmp_stderr = open( tmp, 'rb' ) - stderr = '' - buffsize = 1048576 - try: - while True: - stderr += tmp_stderr.read( buffsize ) - if not stderr or len( stderr ) % buffsize != 0: - break - except OverflowError: - pass - tmp_stderr.close() - if returncode != 0: - raise Exception, stderr - except Exception, e: - # clean up temp dirs - if os.path.exists( tmp_index_dir ): - shutil.rmtree( tmp_index_dir ) - if os.path.exists( tmp_dir ): - shutil.rmtree( tmp_dir ) - stop_err( 'Error indexing reference sequence. ' + str( e ) ) - else: - ref_file_name = options.ref - - # set up aligning and generate aligning command options - if options.params == 'pre_set': - aligning_cmds = '-n %s ' % ( options.threads ) - gen_alignment_cmds = '' - else: - if options.exhaustiveSearch == 'true': - exhaustiveSearch = '-x' - minCover = '-c %s' % options.minCover - else: - exhaustiveSearch = '' - minCover = '' - if options.partialAlignments == 'true': - partialAlignments = '-x' - else: - partialAlignments = '' - if options.complexityWeighted == 'true': - complexityWeighted = '-w' - else: - complexityWeighted = '' - aligning_cmds = '-d %s -m %s -q %s -r %s -y %s' % \ - ( options.scorDiff, options.minScor, options.minBasq, options.seed, options.minId ) - if options.genAlignType == 'paired': - gen_alignment_cmds = '-i %s -j %s -l %s' % ( options.insertMax, options.insertMin, options.pairTyp ) - else: - gen_alignment_cmds = '' - # prepare actual aligning and generate aligning commands - if options.genAlignType == 'paired': - cmd = 'smalt map %s %s -o %s %s %s ' % ( aligning_cmds, gen_alignment_cmds, options.output, ref_file_name, fastq, rfastq ) - else: - cmd = 'smalt map %s -o %s %s %s ' % ( aligning_cmds, options.output, ref_file_name, fastq ) - # perform alignments - buffsize = 1048576 - try: - # need to nest try-except in try-finally to handle 2.4 - try: - # align - try: - tmp = tempfile.NamedTemporaryFile( dir=tmp_dir ).name - tmp_stderr = open( tmp, 'wb' ) - proc = subprocess.Popen( args=cmd, shell=True, cwd=tmp_dir, stderr=tmp_stderr.fileno() ) - returncode = proc.wait() - tmp_stderr.close() - # get stderr, allowing for case where it's very large - tmp_stderr = open( tmp, 'rb' ) - stderr = '' - try: - while True: - stderr += tmp_stderr.read( buffsize ) - if not stderr or len( stderr ) % buffsize != 0: - break - except OverflowError: - pass - tmp_stderr.close() - if returncode != 0: - raise Exception, stderr - except Exception, e: - raise Exception, 'Error aligning sequence. ' + str( e ) - # remove header if necessary - if options.suppressHeader == 'true': - tmp_out = tempfile.NamedTemporaryFile( dir=tmp_dir) - tmp_out_name = tmp_out.name - tmp_out.close() - try: - shutil.move( options.output, tmp_out_name ) - except Exception, e: - raise Exception, 'Error moving output file before removing headers. ' + str( e ) - fout = file( options.output, 'w' ) - for line in file( tmp_out.name, 'r' ): - if not ( line.startswith( '@HD' ) or line.startswith( '@SQ' ) or line.startswith( '@RG' ) or line.startswith( '@PG' ) or line.startswith( '@CO' ) ): - fout.write( line ) - fout.close() - # check that there are results in the output file - if os.path.getsize( options.output ) > 0: - sys.stdout.write( 'SMALT run on %s-end data' % options.genAlignType ) - else: - raise Exception, 'The output file is empty. You may simply have no matches, or there may be an error with your input file or settings.' - except Exception, e: - stop_err( 'The alignment failed.\n' + str( e ) ) - finally: - # clean up temp dir - if os.path.exists( tmp_index_dir ): - shutil.rmtree( tmp_index_dir ) - if os.path.exists( tmp_dir ): - shutil.rmtree( tmp_dir ) - -if __name__=="__main__": __main__()
--- a/tools/smalt_wrapper.xml Wed Feb 13 13:23:09 2013 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,291 +0,0 @@ -<tool id="smalt_wrapper" name="SMALT" version="0.0.1"> - <requirements> - <requirement type="package" version="0.7.1">smalt</requirement> - </requirements> - <description>maps query reads onto the reference sequences</description> - <command interpreter="python"> - smalt_wrapper.py - --threads="4" - - ## reference source - --fileSource=$genomeSource.refGenomeSource - #if $genomeSource.refGenomeSource == "history": - ##build index on the fly - --ref="${genomeSource.ownFile}" - --dbkey=$dbkey - #else: - ##use precomputed indexes - --ref="${genomeSource.indices.fields.path}" - --do_not_build_index - #end if - - ## input file(s) - --input1=$paired.input1 - #if $paired.sPaired == "paired": - --input2=$paired.input2 - #end if - - ## output file - --output=$output - - ## run parameters - --genAlignType=$paired.sPaired - --params=$params.source_select - #if $params.source_select != "pre_set": - --scorDiff=$params.scorDiff - #if $paired.sPaired == "paired": - --insertMax=$params.insertMax - --insertMin=$params.insertMin - --pairTyp=$params.pairTyp - #end if - --minScor=$params.minScor - --partialAlignments=$params.partialAlignments - --minBasq=$params.minBasq - --seed=$params.seed - --complexityWeighted=$params.complexityWeighted - --exhaustiveSearch=$params.cExhaustiveSearch.exhaustiveSearch - #if $params.cExhaustiveSearch.exhaustiveSearch == "true" - --minCover=$params.cExhaustiveSearch.minCover - #end if - --minId=$params.minId - #end if - - ## suppress output SAM header - --suppressHeader=$suppressHeader - </command> - <inputs> - <conditional name="genomeSource"> - <param name="refGenomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?"> - <option value="indexed">Use a built-in index</option> - <option value="history">Use one from the history</option> - </param> - <when value="indexed"> - <param name="indices" type="select" label="Select a reference genome"> - <options from_data_table="smalt_indexes"> - <filter type="sort_by" column="2" /> - <validator type="no_options" message="No indexes are available" /> - </options> - </param> - </when> - <when value="history"> - <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select a reference from history" /> - </when> - </conditional> - <conditional name="paired"> - <param name="sPaired" type="select" label="Is this library mate-paired?"> - <option value="single">Single-end</option> - <option value="paired">Paired-end</option> - </param> - <when value="single"> - <param name="input1" type="data" format="fastqsanger" label="FASTQ file" help="FASTQ with Sanger-scaled quality values (fastqsanger)" /> - </when> - <when value="paired"> - <param name="input1" type="data" format="fastqsanger" label="Forward FASTQ file" help="FASTQ with Sanger-scaled quality values (fastqsanger)" /> - <param name="input2" type="data" format="fastqsanger" label="Reverse FASTQ file" help="FASTQ with Sanger-scaled quality values (fastqsanger)" /> - </when> - </conditional> - <conditional name="params"> - <param name="source_select" type="select" label="Smalt settings to use" help="For most mapping needs use Commonly Used settings. If you want full control use Full Parameter List"> - <option value="pre_set">Commonly Used</option> - <option value="full">Full Parameter List</option> - </param> - <when value="pre_set" /> - <when value="full"> - <conditional name="cExhaustiveSearch"> - <param name="exhaustiveSearch" type="boolean" truevalue="true" falsevalue="false" checked="no" label="Do exhaustive search? (map -x)" help="This flag triggers a more exhaustive search for alignments at the cost of decreased speed." /> - <when value="true"> - <param name="minCover" type="float" value="0" label="Minimum cover (map -c)" help="Only consider mappings where the k-mer word seeds cover the query read to a minimum extent." /> - </when> - <when value="no" /> - </conditional> - <param name="scorDiff" type="integer" value="0" label="Score diff (map -d)" help="Set a threshold of the Smith-Waterman alignment score relative to the maximum score." /> - <param name="insertMax" type="integer" value="500" label="Maximum insert size (map -i)" help="Only in paired-end mode." /> - <param name="insertMin" type="integer" value="0" label="Minimum insert size (map -j)" help="Only in paired-end mode." /> - <param name="pairTyp" type="text" size="2" value="pe" label="Type of read pair library (map -l)" help="Can be either 'pe', 'mp' or 'pp'." /> - <param name="minScor" type="integer" value="0" label="Minimum score (map -m)" help="Sets an absolute threshold of the Smith-Waterman scores." /> - <param name="partialAlignments" type="boolean" truevalue="true" falsevalue="false" checked="no" label="Partial alignments (map -p)" help="Report partial alignments if they are complementary on the read (split reads)." /> - <param name="minBasq" type="integer" value="0" label="Base quality threshold (map -q)" help="Sets a base quality threshold (0 <= minbasq <= 10, default 0)." /> - <param name="seed" type="integer" value="0" label="Seed (map -r)" help="See below." /> - <param name="complexityWeighted" type="boolean" truevalue="true" falsevalue="false" checked="no" label="Complexity weighted (map -w)" help="Smith-Waterman scores are complexity weighted." /> - <param name="minId" type="float" value="0" label="Identity threshold (map -y)" help="Sets an identity threshold for a mapping to be reported." /> - </when> - </conditional> - <param name="suppressHeader" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Suppress the header in the output SAM file" help="Smalt produces SAM with several lines of header information" /> - </inputs> - <outputs> - <data format="sam" name="output" label="${tool.name} on ${on_string}: mapped reads"> - <actions> - <conditional name="genomeSource.refGenomeSource"> - <when value="indexed"> - <action type="metadata" name="dbkey"> - <option type="from_data_table" name="smalt_indexes" column="1"> - <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/> - <filter type="param_value" ref="genomeSource.indices" column="0"/> - </option> - </action> - </when> - <when value="history"> - <action type="metadata" name="dbkey"> - <option type="from_param" name="genomeSource.ownFile" param_attribute="dbkey" /> - </action> - </when> - </conditional> - </actions> - </data> - </outputs> - <help> - -**What it does** - -SMALT is a pairwise sequence alignment program for the experimentingcient mapping of DNA sequencing reads onto genomic reference sequences. It uses a combination of short-word hashing and dynamic programming. Most types of sequencing platforms are supported including paired-end sequencing reads. - ------- - -Please cite the website "http://www.sanger.ac.uk/resources/software/smalt/". - ------- - -**Know what you are doing** - -.. class:: warningmark - -There is no such thing (yet) as an automated gearshift in short read mapping. It is all like stick-shift driving in San Francisco. In other words = running this tool with default parameters will probably not give you meaningful results. A way to deal with this is to **understand** the parameters by carefully reading the `documentation`__ and experimenting. Fortunately, Galaxy makes experimenting easy. - - .. __: http://www.sanger.ac.uk/resources/software/smalt/ - ------- - -**Input formats** - -SMALT accepts files in Sanger FASTQ format (galaxy type *fastqsanger*). Use the FASTQ Groomer to prepare your files. - ------- - -**A Note on Built-in Reference Genomes** - -The default variant for all genomes is "Full", defined as all primary chromosomes (or scaffolds/contigs) including mitochondrial plus associated unmapped, plasmid, and other segments. When only one version of a genome is available in this tool, it represents the default "Full" variant. Some genomes will have more than one variant available. The "Canonical Male" or sometimes simply "Canonical" variant contains the primary chromosomes for a genome. For example a human "Canonical" variant contains chr1-chr22, chrX, chrY, and chrM. The "Canonical Female" variant contains the primary chromosomes excluding chrY. - ------- - -**Outputs** - -The output is in SAM format. - -------- - -**SMALT parameter list** - -This is an exhaustive list of SMALT options: - -For **map**:: - - -a - Output explicit alignments along with the mappings. - - -c <mincover> - Only consider mappings where the k-mer word seeds cover the query read to - a minimum extent. If <mincover> is an integer or floating point > 1.0, at - least this many bases of the read must be covered by k-mer word seeds. If - <mincover> is a floating point <= 1.0, it specifies the fraction of the - query read length that must be covered by k-mer word seeds. This option - is only valid in conjunction with the '-x' flag. - - -d <scordiff> - Set a threshold of the Smith-Waterman alignment score relative to the - maximum score. When mapping single reads, all alignments are reported - that have Smith-Waterman scores within <scorediff> of the maximum. - Mappings with lower scores are skipped. If <scorediff> is set to to a - value < 0, all alignments are printed that have scores above the - threshold specified with the '-m <minscor>' option. - For paired reads, only a value of 0 is supported. With the option '-d 0' - all aligments (pairings) with the best score are output. By default - (without the option '-d 0') single reads/mates with multiple best mappings - are reported as 'not mapped'. - - -f <format> - Specifies the output format. <format> can be either 'bam', 'cigar', 'gff', - 'sam' (default), 'samsoft' or 'ssaha'. Optional extension 'sam:nohead,clip' - (see manual) - - -F <inform> - Specifies the input format. <inform> can be either 'fastq' (default), - 'sam' or 'bam' (see: samtools.sourceforge.net). SAM and BAM formats - require additional libraries to be installed. - - -g <insfil> - Use the distribution of insert sizes stored in the file <insfil>. This - file is in ASCII format and can be generated using the 'sample' task see - 'smalt sample -H' for help). - - -H - Print these instructions. - - -i <insertmax> - Maximum insert size (only in paired-end mode). The default is 500. - - -j <insertmin> - Minimum insert size (only in paired-end mode). The default is 0. - - -l <pairtyp> - Type of read pair library. <pairtyp> can be either 'pe', i.e. for - the Illumina paired-end library for short inserts (|--> <--|). 'mp' - for the Illumina mate-pair library for long inserts (<--| |-->) or - 'pp' for mates sequenced on the same strand (|--> |-->). 'pe' is the - default. - - -m <minscor> - Sets an absolute threshold of the Smith-Waterman scores. Mappings with - scores below that threshold will not be reported. The default is - <minscor> = <wordlen> + <stepsiz> - 1 - - -n <nthreads> - Run smalt using mutiple threads. <nthread> is the number of additional - threads forked from the main thread. The order of the reads in the - input files is not preserved for the output unless '-O' is also specified. - - -o <oufilnam> - Write mapping output (e.g. SAM lines) to a separate file. If this option - is not specified, mappings are written to standard output together with - other messages. - - -O - Output mappings in the order of the reads in the input files when using - multiple threads (option '-n <nthreads>'). - - -p - Report partial alignments if they are complementary on the read (split - reads). - - -q <minbasq> - Sets a base quality threshold (0 <= minbasq <= 10, default 0). - K-mer words of the read with nucleotides that have a base quality below - this threshold are not looked up in the hash index. - - -r <seed> - If <seed> >= 0 report an alignment selected at random where there are - multiple mappings with the same best alignment score. With <seed> = 0 - (default) a seed is derived from the current calendar time. If <seed> - < 0 reads with multiple best mappings are reported as 'not mapped'. - - -T <tmp_dir> - Write temporary files to directory <tmp_dir> (used with input files in - SAM/BAM format). - - -w - Smith-Waterman scores are complexity weighted. - - -x - This flag triggers a more exhaustive search for alignments at the cost - of decreased speed. In paired-end mode each mate is mapped independently. - (By default the mate with fewer hits in the hash index is mapped first - and the vicinity is searched for mappings of its mate.) - - -y <minid> - Sets an identity threshold for a mapping to be reported (default: 0). - <minid> specifies the number of exactly matching nucleotides either as - a positive integer or as a fraction of the read length (<= 1.0). - - </help> -</tool> - -
--- a/tools/tool-data/smalt_index.loc.sample Wed Feb 13 13:23:09 2013 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,29 +0,0 @@ -#This is a sample file distributed with Galaxy that enables tools -#to use a directory of Smalt indexed sequences data files. You will need -#to create these data files and then create a smalt_index.loc file -#similar to this one (store it in this directory) that points to -#the directories in which those files are stored. The smalt_index.loc -#file has this format (longer white space characters are TAB characters): -# -#<unique_build_id> <dbkey> <display_name> <file_path> -# -#So, for example, if you had phiX indexed stored in -#/depot/data2/galaxy/phiX/base/, -#then the smalt_index.loc entry would look like this: -# -#phiX174 phiX phiX Pretty /depot/data2/galaxy/phiX/base/phiX.fa -# -#and your /depot/data2/galaxy/phiX/base/ directory -#would contain hg19.fa.* files: -# -#-rw-r--r-- 1 cborroto universe 527388 2005-09-13 10:12 phix.fa.sma -#-rw-r--r-- 1 cborroto universe 269808 2005-09-13 10:12 phiX.fa.smi -# -#Your smalt_index.loc file should include an entry per line for each -#index set you have stored. The "file" in the path does not actually -#exist, but it is the prefix for the actual index files. For example: -# -#phiX174 phiX phiX174 /depot/data2/galaxy/phiX/base/phiX.fa -#hg18canon hg18 hg18 Canonical /depot/data2/galaxy/hg18/base/hg18canon.fa -#hg18full hg18 hg18 Full /depot/data2/galaxy/hg18/base/hg18full.fa -
--- a/tools/tool_data_table_conf.xml.sample Wed Feb 13 13:23:09 2013 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,8 +0,0 @@ -<!-- Use the file tool_data_table_conf.xml.oldlocstyle if you don't want to update your loc files as changed in revision 4550:535d276c92bc--> -<tables> - <!-- Locations of indexes in the BWA mapper format --> - <table name="smalt_indexes" comment_char="#"> - <columns>value, dbkey, name, path</columns> - <file path="tool-data/smalt_index.loc" /> - </table> -</tables>