Mercurial > repos > yhoogstrate > unafold
changeset 1:37198dc9311c draft default tip
planemo upload for repository https://github.com/ErasmusMC-Bioinformatics/unafold_galaxy_wrapper commit 3d01452f19416679047a05e4c0a05c15d11f34ea
| author | yhoogstrate |
|---|---|
| date | Wed, 24 Feb 2016 11:46:54 -0500 |
| parents | bf022d3751fa |
| children | |
| files | README.rst datatypes_conf.xml lib/galaxy/datatypes/RNAStructure.py unafold.xml |
| diffstat | 4 files changed, 178 insertions(+), 205 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/README.rst Wed Feb 24 11:46:54 2016 -0500 @@ -0,0 +1,78 @@ +# UNAFold Galaxy wrapper # + +# License # + +UNAFold 3.x ACADEMIC NON-COMMERCIAL USE LICENSE AGREEMENT + +1. UNAFold 3.x is the work of Drs. Nicholas R. Markham and Michael Zuker. The + copyright in UNAFold 3.x is owned by RENSSELAER POLYTECHNIC INSTITUTE. + +2. This is a legal agreement between you, RECIPIENT, and RENSSELAER POLYTECHNIC + INSTITUTE. By accepting, receiving, and using UNAFold 3.x, you agree to be + bound by all of its terms. If you do not agree to all of the terms of this + Agreement, please DO NOT download the software; or, if you have already done + so, please delete all of the source code, documentation and compiled programs + associated with UNAFold 3.x. + +3. UNAFold 3.x is provided to RECIPIENT as source code. RENSSELAER POLYTECHNIC + INSTITUTE grants to RECIPIENT a royalty free, non-exclusive, and non- + transferable license to compile, install, use UNAFold for internal research + only. RECIPIENT acknowledges that UNAFold 3.x is a research tool that is + provided free of charge and only provided "as is." RENSSELAER POLYTECHNIC + INSTITUTE, its faculty, employees, or students, or former employees who have + developed UNAFold 3.x, have no obligation to assist RECIPIENT in its use, + correction, modification, or enhancement and are without any obligation to + provide any updates. RECIPIENT may also offer UNAFold 3.x to the public over + a web server provided the program resides on a server at RECIPIENT's + institution and users are not able to download or modify the program. + +4. The title and copyright to UNAFold 3.x and any associated programs and + documentation shall remain with RENSSELAER POLYTECHNIC INSTITUTE. RECIPIENT + agrees to preserve same. RECIPIENT agrees not to make any copies of UNAFold + except for use in RECIPIENT's laboratory without RENSSELAER POLYTECHNIC + INSTITUTE's prior written permission. Written permission can be obtained by + contacting Rensselaer Polytechnic Institute's Office of Technology + Commercialization by e-mail at burtok2@rpi.edu, or by telephone at 518-276- + 3675. RECIPIENT agrees to place the appropriate copyright notice on any such + copies. + +5. RECIPIENT may not modify UNAFold 3.x, except to fix minor errors, or create + derivative works without RENSSELAER POLYTECHNIC INSTITUTE's permission. + Please send all requests for modification to markhn@rpi.edu and + zukerm@rpi.edu. Errors and bugs that are found should be reported to Nick + Markham and Michael Zuker, whether or not they are corrected. + +6. RECIPIENT shall not distribute UNAFold 3.x to other laboratories within + RECIPIENT's institution. RECIPIENT shall not transfer UNAFold 3.x to another + location or person outside of RECIPIENT's institution without RENSSELAER + POLYTECHNIC INSTITUTE's prior written permission. Please send all requests + for distribution to markhn@rpi.edu and zukerm@rpi.edu. + +7. If RENSSELAER POLYTECHNIC INSTITUTE grants RECIPIENT permission to distribute + UNAFold 3.x, under Paragraph 6, RECIPIENT shall only export UNAFold 3.x or + any part thereof, directly or indirectly, to any country where such export or + reexport is authorized in full compliance with the laws of the United States + of America. + +8. RECIPENT shall cite the following publications in any abstract, paper, or + presentation referencing UNAFold: + +a. N. Markham & M. Zuker. (2003) DINAMelt web server for nucleic acid melting + prediction. Nucleic Acids Res. 33:W577-W581. + +9. RECIPIENT acknowledges that as UNAFold 3.x is a research tool and provided + free of charge, it is only provided "as is." RENSSELAER POLYTECHNIC + INSTITUTE, its faculty, employees, or students, have no obligation to assist + RECIPIENT in its use, correction, modification, or enhancement and are + without any obligation to provide any updates. + +10. RENSSELAER POLYTECHNIC INSTITUTE MAKES NO REPRESENTATIONS AND EXTENDS NO + WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED. THERE ARE NO EXPRESS OR + IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS OF UNAFold 3.x FOR A + PARTICULAR PURPOSE, OR THAT THE USE OF UNAFold 3.x WILL NOT INFRINGE ANY + PATENT, COPYRIGHT, TRADEMARK, TRADE SECRET, OR OTHER INTELLECTUAL PROPERTY + RIGHTS OF ANOTHER PARTY, OR ANY OTHER EXPRESS OR IMPLIED WARRANTIES. + RENSSELAER POLYTECHNIC INSTITUTE WILL NOT BE LIABLE TO RECIPIENT FOR ANY + CLAIMS OR DAMAGES ARISING FROM YOUR RECIPIENT'S OF UNAFold 3.x, ANY CLAIM + FOR ANY LOSS OR INTERRUPTION OF BUSINESS, OR FOR ANY INDIRECT, SPECIAL, OR + CONSEQUENTIAL DAMAGES OF ANY KIND. \ No newline at end of file
--- a/datatypes_conf.xml Tue Jun 16 11:21:12 2015 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,25 +0,0 @@ -<?xml version="1.0"?> -<datatypes> - <datatype_files> - <datatype_file name="RNAStructure.py"/> - </datatype_files> - - <registration> - <datatype - extension="ct" - type="galaxy.datatypes.RNAStructure:ConnectivityTable" - display_in_upload="True" - subclass="True" - description="ConnectivityTable format is a text-based column wise format for storing both an RNA sequence and its corresponding 2D structure." /> - <datatype - extension="rnaml" - type="galaxy.datatypes.RNAStructure:RNAML" - display_in_upload="True" - subclass="True" - description="RNAML: a standard syntax for exchanging RNA information." - url="http://www.ncbi.nlm.nih.gov/pubmed/12088144" /> - </registration> - - <sniffers> - </sniffers> -</datatypes>
--- a/lib/galaxy/datatypes/RNAStructure.py Tue Jun 16 11:21:12 2015 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,132 +0,0 @@ -import logging -log = logging.getLogger(__name__) - -from galaxy import util -import galaxy -import galaxy.model -import galaxy.datatypes -import galaxy.datatypes.data - -from galaxy.datatypes.metadata import MetadataElement - -from galaxy.datatypes.sequence import Sequence -from galaxy.datatypes.tabular import Tabular -from galaxy.datatypes.xml import GenericXml - -from galaxy.datatypes.data import Data - - -import re - -class DotBracket ( Sequence ): - edam_format = "format_1457" - file_ext = "dbn" - - sequence_regexp = re.compile( "^[ACGTURYKMSWBDHVN]*" ) - structure_regexp = re.compile( "^[\(\)\.]*" ) - - def set_meta( self, dataset, **kwd ): - """ - Set the number of sequences and the number of data lines - in dataset. - """ - if self.max_optional_metadata_filesize >= 0 and dataset.get_size() > self.max_optional_metadata_filesize: - dataset.metadata.data_lines = None - dataset.metadata.sequences = None - dataset.metadata.seconday_structures = None - return - - data_lines = 0 - sequences = 0 - - for line in file( dataset.file_name ): - line = line.strip() - data_lines += 1 - - if line and line.startswith( '>' ): - sequences += 1 - - dataset.metadata.data_lines = data_lines - dataset.metadata.sequences = sequences - - def sniff(self, filename): - """ - The format is as follows, although it remains unclear whether - the Dot-Bracket format may contain multiple sequences per file: - - >sequenceName1 - CCCaaaGGG - (((...))) - >sequenceName2 - GGGuuuCCC - (((...))) - """ - - i = 0 - pairs = False - - with open( filename ) as handle: - for line in handle: - line = line.strip() - - state = i % 3 - - if state == 0:#header line - if(line[0] != '>'): - return False - elif state == 1:#sequence line - if not sequence_regexp.match(line.upper()): - return False - else: - sequence_size = len(line) - elif state == 2:#dot-bracket structure line - if (sequence_size != len(line)) or (not structure_regexp.match(line)): - return False - - i += 1 - return True - -class ConnectivityTable( Tabular ): - edam_format = "format_3309" - file_ext = "ct" - - header_regexp = re.compile( "^[0-9]+" + "(?:\t|[ ]+)" + "[^ \t]+") - structure_regexp = re.compile( "^[0-9]+" + "(?:\t|[ ]+)" + "[ACGTURYKMSWBDHVN]+" + "(?:\t|[ ]+)" + "[^\t]+" + "(?:\t|[ ]+)" + "[^\t]+" + "(?:\t|[ ]+)" + "[^\t]+" + "(?:\t|[ ]+)" + "[^\t]+") - - def __init__(self, **kwd): - Tabular.__init__( self, **kwd ) - - self.columns = 6 - self.column_names = ['base_index', 'base', 'neighbor_left', 'neighbor_right', 'partner', 'natural_numbering'] - self.column_types = ['int', 'str', 'int', 'int', 'int', 'int'] - - def set_meta( self, dataset, **kwd ): - data_lines = 0 - - for line in file( dataset.file_name ): - data_lines += 1 - - dataset.metadata.data_lines = data_lines - - def sniff(self, filename): - - filename = filename.file_name - - i = 0 - with open( filename ) as handle: - for line in handle: - line = line.strip() - - if(i == 0): - if not self.header_regexp.match(line): - return False - else: - if not self.structure_regexp.match(line.upper()): - return False - i += 1 - return True - - -class RNAML( GenericXml ): - edam_format = "format_3311" - file_ext = "rnaml"
--- a/unafold.xml Tue Jun 16 11:21:12 2015 -0400 +++ b/unafold.xml Wed Feb 24 11:46:54 2016 -0500 @@ -1,34 +1,54 @@ <?xml version="1.0"?> -<tool id="unafold" name="UNAFold" version="1.0.0"> +<tool id="unafold" name="UNAFold" version="1.1.0"> <description>UNAFold RNA and DNA structure prediction</description> - + <requirements> <requirement type="package" version="3.8">unafold</requirement> </requirements> - + <stdio> <regex match="mv: cannot stat ..: No such file or directory" source="stderr" level="fatal" description="Could not find CT output file\n" /> </stdio> - + <version_command>UNAFold.pl --version</version_command> - - <command> + + <command><![CDATA[ + #if str($input_source.select_fasta) == "false" + echo ">Sequence" > "input.fasta" && + echo "${input_source.input_sequence}" >> "input.fasta" && + #end if + UNAFold.pl -n $n.a -t $temp - #if $n.a == "DNA" -N $sodium -M $magnesium #end if + + #if str($input_source.select_fasta) == "false" + "input.fasta" + #else + "${input_source.input_file}" + #end if + && - $input_file && - output=\$(ls | grep \.ct | sort -r | head -n 1) && + output=\$(ls | grep \.ct | sort -r | head -n 1) && + mv "\$output" "$output_ct" - </command> - + ]]></command> + <inputs> - <param format="fasta" name="input_file" type="data" label="Input sequence (FASTA)"/> + <conditional name="input_source"> + <param name="select_fasta" type="boolean" truevalue="true" falsevalue="false" label="Input from FASTA file" selected="false" /> + + <when value="true"> + <param format="fasta" name="input_file" type="data" label="Input sequence (FASTA)"/> + </when> + <when value="false"> + <param name="input_sequence" type="text" label="Input sequence"/> + </when> + </conditional> <conditional name="n"> <param name="a" type="select" label="Nucleic Acid Type"> @@ -46,55 +66,87 @@ <param name="temp" type="integer" size="3" value="37" min="0" max="100" label="Temperature (°C)"/> </inputs> - + <outputs> - <data format="ct" name="output_ct" label="${tool.name} on ${input_file.hid}: ${input_file.name}"/> + <data format="ct" name="output_ct" label="${tool.name}"/> </outputs> - + <tests> <test> + <param name="select_fasta" value="true" /> <param name="input_file" value="test1_input.fa" ftype="fasta" /> <param name="temp" value="37" /> <output name="output_ct" file="test1_output.ct" /> </test> + <test> + <param name="select_fasta" value="false" /> + <param name="input_sequence" value="GGGGGaaaCCCCC" /> + <param name="temp" value="37" /> + + <output name="output_ct" file="test1_output.ct" lines_diff="2" /><!-- Sequence name (header) differs --> + </test> </tests> - <help> - Usage: UNAFold.pl [options] file [file] + <help><![CDATA[ +``Usage: UNAFold.pl [options] file [file]`` + +``Options:`` +``-V, --version`` + +``-h, --help`` + +``-n, --NA=(RNA | DNA) (defaults to RNA)`` + +``-t, --temp=<temperature> (defaults to 37)`` + +``-N, --sodium=<[Na+] in M> (defaults to 1)`` + +``-M, --magnesium=<[Mg++] in M> (defaults to 0)`` + +``-p, --polymer`` + +``-C, --Ct=<total strand concentration>`` + +``-I, --noisolate`` + +``-m, --maxbp=<maximum basepair distance>`` + +``-c, --constraints=<name of constraints file> (defaults to prefix.aux)`` + +``-P, --percent=<energy increment percent> (defaults to 5)`` + +``-W, --window=<window size> (default set by sequence length)`` - Options: - -V, --version - -h, --help - -n, --NA=(RNA | DNA) (defaults to RNA) - -t, --temp=<temperature> (defaults to 37) - -N, --sodium=<[Na+] in M> (defaults to 1) - -M, --magnesium=<[Mg++] in M> (defaults to 0) - -p, --polymer - -C, --Ct=<total strand concentration> - -I, --noisolate - -m, --maxbp=<maximum basepair distance> - -c, --constraints=<name of constraints file> (defaults to prefix.aux) - -P, --percent=<energy increment percent> (defaults to 5) - -W, --window=<window size> (default set by sequence length) - -X, --max=<maximum number of foldings> (defaults to 100) - --ann=(none | p-num | ss-count) (defaults to none) - --mode=(auto | bases | lines) (defaults to auto) - --label=<base numbering frequency> - --rotate=<structure rotation angle> - --run-type=(text | html) (defaults to text) - --model=(EM | PF) (defaults to EM) - --circular - Obscure options: - --allpairs - --maxloop=<maximum bulge/interior loop size> (defaults to 30) - --nodangle - --simple - --prefilter=<filter value> +``-X, --max=<maximum number of foldings> (defaults to 100)`` + +``--ann=(none | p-num | ss-count) (defaults to none)`` + +``--mode=(auto | bases | lines) (defaults to auto)`` + +``--label=<base numbering frequency>`` + +``--rotate=<structure rotation angle>`` + +``--run-type=(text | html) (defaults to text)`` + +``--model=(EM | PF) (defaults to EM)`` - Report bugs to markhn@rpi.edu - </help> - +``--circular`` + +``Obscure options:`` + +``--allpairs`` + +``--maxloop=<maximum bulge/interior loop size> (defaults to 30)`` + +``--nodangle`` + +``--simple`` + +``--prefilter=<filter value>`` + ]]></help> + <citations> <citation type="doi">10.1007/978-1-60327-429-6_1</citation> </citations>