<?xml version="1.0"?>
<tool id="edu.tamu.cpt.mist3" name="MIST v3" version="19.1.0.0">
	<description>Multiple Interrelated Sequence doT plotter.</description>
	<macros>
		<import>macros.xml</import>
		<import>cpt-macros.xml</import>
	</macros>
	<requirements>
		<requirement type="package" version="2.7">python</requirement>
                <requirement type="package" version="1.76">biopython</requirement>
		<requirement type="package" version="8.0.192">openjdk</requirement>
		<requirement type="package" version="7.0.8_68">imagemagick</requirement>
		<requirement type="package" version="9.18">ghostscript</requirement>
	</requirements>
	<command detect_errors="aggressive">
$__tool_directory__/mist3.py
#set repeat_var_1 = '" "'.join([ str($var) for $var in $fasta_files ])
--window "${window}"
--zoom "${zoom}"
--matrix "${matrix}"
--files_path $output.files_path
--plot_type $plot_type

"$repeat_var_1"
> $output
</command>
	<inputs>
		<param help="Sequences to plot" label="file" name="fasta_files" type="data" format="fasta" multiple="True"/>

		<param name="plot_type" label="Plot Type" type="select">
			<option value="complete">[complete] Complete NxN plot</option>
			<option value="1vn">[1vN] 1 genome versus the rest</option>
			<option value="2up">[2up] Compare two genomes (see help)</option>
		</param>

		<param help="How zoomed in the image is" label="zoom" name="zoom" type="integer" value="50" min="5"/>

		<param help="Window Size" label="window" name="window" type="integer" value="10" min="5"/>

		<param label="Comparison Matrix" name="matrix" type="select">
			<option value="blosum62">Blosum62</option>
			<option selected="True" value="edna">Extended DNA</option>
			<option value="ednaorig">Extended DNA (Original)</option>
			<option value="pam250">Pam 250</option>
			<option value="protidentity">Protein Identity</option>
		</param>

	</inputs>
	<outputs>
		<data format="html" name="output" />
	</outputs>
	<tests>
		<test>
			<param name="fasta_files" value="mist3_in.fasta"/>
			<param name="plot_type" value="complete"/>
			<param name="zoom" value="100"/>
			<param name="window" value="20"/>
			<param name="matrix" value="edna"/>
			<output name="output" ftype="html">
				<assert_contents>
					<has_text text="Mist Results"/>
					<has_text text="Each section of mist output is now clickable to view a higher resolution version of that subsection"/>
				</assert_contents>
			</output>
		</test>
	</tests>
	<help>
Multiple Interrlated Sequence doTplotter
========================================

Uses a stripped down vesion of Gepard (Dr. Jan Krumsiek/HelmholtzZentrum/IBIS) for dot plotting.

Plot Types
----------

There are three main plot types:

- **complete** does an N x N plot of each genome versus every other genome
- **1vN** The first genome in the list is compared to each other genome
- **2up** two-genome comparison

	- If you provide TWO files and are using a protein comparison matrix, then the invidual 
		protein sequences of both files will be compared in a "complete" style plot.
	- Otherwise, the first two genomes encountered will be compared.

Options
-------

**Zoom**

Be careful with this option. It represents the number of bases to plot in
a single pixel. For large genomes, this can mean very large images, and
should be lowered appropriately. For a value of 50, 50 bases would be
considered a single pixel in the output image. For a 1 Mbp genome comparison
(say 5 x 200-kb phages), this would result in a 20,000 pixel image.

</help>
	<citations>
		<expand macro="citation/gepard" />
		<expand macro="citation/mijalisrasche" />
                <citation type="bibtex">
			@unpublished{galaxyTools,
				author = {A. Criscione},
				title = {CPT Galaxy Tools},
				year = {2019-2021},
				note = {https://github.com/tamu-cpt/galaxy-tools/}
			}
                        </citation>
	</citations>
</tool>