<tool id="alfa" name="ALFA" version="0.1.0">
	<description>- Compute and display distribution of reads by genomic categories</description>

	<!-- ALFA requires bedtools suite v2.20.0 and above -->
	<requirements>
    	<requirement type="package">bedtools</requirement>
    	<requirement type="package">samtools</requirement>
    	<requirement type="package" version="1.5.3">matplotlib</requirement>
  	</requirements>

  	<command interpreter="bash">
  		alfa_wrapper.sh ${ALFA_config} $logReport
  	</command>	
	
	<inputs>
		<param name="projectName" value="ALFA" type="text" size="20" label="Project Name">
			<validator type="empty_field" message="Please, specify a name for your project."/>
		</param>

		<section name="annotation" title="INPUT 1: Annotation File (GTF format)" expanded="True">
			<conditional name="annotationSource">
				<param name="annotationSourceSelection" type="select" label="Select the source of your annotated sequence/genome">
					<option value="personal_gtf" selected="true">Personal annotation file (GTF format)</option>
					<option value="index">Stranded and Unstranded Indexes previously generated by ALFA (Index format)</option>
					<option value="built_in_index">Built-in indexes among a list of referenced genome (Index format)</option>
				</param>
				<when value="personal_gtf">
					<param name="annotationFile" type="data" format="Gff, Gtf" label="Select your personal annotation file (GTF format)">
					</param>
				</when>
				<when value="index">
					<param name="strandedIndex" type="data" format="index" label="Select your ALFA stranded index file (index format)"/>
					<param name="unstrandedIndex" type="data" format="index" label="Select your ALFA Unstranded index file (index format)"/>
				</when>
				<when value="built_in_index">
					<param name="built_in_index_prefix" type="select" label="Select Genome">
						<options from_data_table="alfa_indexes">
							<validator type="no_options" message="No indexes are available for the selected input dataset" />
						</options>
					</param>
				</when>
			</conditional>
		</section>

		<section name="reads" title="INPUT 2: Aligned Reads File(s) of the annotated sequence (BAM or BEDGRAPH format)" expanded="True">
			<conditional name="readsType">
				<param name="readsTypeSelection" type="select" label="Select the format of the reads file(s)">
					<option value="bam" selected="true">BAM</option>
					<option value="bedgraph">BEDGRAPH</option>
				</param>
				<when value="bam">
					<repeat name="readsList" title="Reads File" min="1" >
						<param name="readsFile" type="data" format="Bam" label="Select the reads file of your annotated sequence (BAM format)"/>
						<param name="readsLabel" type="text" size="20" value="" label="Label of the reads" optional="True"/>
					</repeat>
				</when>
				<when value="bedgraph">
					<repeat name="readsList" title="Reads File" min="1">
						<param name="readsFile" type="data" format="Bed" label="Select the reads file of your annotated sequence (BEDGRAPH format)"/>
						<param name="readsLabel" type="text" size="20" value="" label="Label of the reads" optional="True"/>
					</repeat>
				</when>
			</conditional>
			<param name="strandness" type="select" label="Select the strandness of your mapped reads dataset">
				<option value="unstranded" selected="true">Unstranded (reads will match genomic features on both forward and reverse strands of the annotated sequence)</option>
				<option value="forward">Forward (reads will match only genomic features on the forward strand of the annotated sequence)</option>
				<option value="reverse">Reverse (reads will match only genomic features on the reverse strand of the annotated sequence)</option>
			</param>
		</section>

		<section name="outputFiles" title="OUTPUT FILES: Choose the output files" expanded="False">
			<param name="plot" type="boolean" truevalue="True" falsevalue="False" checked="True" label="Categories and Biotypes Histograms" help="Plot the nucleotides distribution of the reads per genomic categories and biotypes"/>
			<param name="countFile" type="boolean" truevalue="True" falsevalue="False" checked="True" label="Categories Count File" help="Edit the exact count of nucleotides in the reads per genomic categories and biotypes"/>
			<param name="index" type="boolean" truevalue="True" falsevalue="False" checked="False" label ="Indexes" help="Print the resulting stranded and unstranded indexes from the gtf input file (useful if you plan to run ALFA again with this annotated sequence)"/>
		</section>

		<section name="outputOptions" title="ADVANCED OPTIONS" expanded="False">
			<param name="categoriesDepth" type="select" label="Categories to Display">
				<option value="1">gene | intergenic</option>
				<option value="2">exon | intron | intergenic</option>
				<option value="3" selected="true">5’-UTR | CDS | 3’-UTR | intron | intergenic</option>
				<option value="4">5’-UTR | start_codon | CDS | stop_codon | 3’-UTR | intron | intergenic</option>
			</param>
			<param name="plotFormat" type="select" label="Plot Options: Select graph format" help="Ignore if you did not choose the histograms output file">
				<option value="pdf" selected="true">pdf</option>
				<option value="svg">svg</option>
				<option value="png">png</option>
			</param>
			<conditional name="plotThreshold">
				<param name="plotThresholdChoice" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Plot Options: Modify y axis range of the normalized counts of bio-features" help="Ignore if you did not choose the histograms output file"/>
					<when value="True">
						<param name="yMin" type="float" value="-2.0" label="y min"/>
						<param name="yMax" type="float" value="2.0" label="y max"/>
					</when>
			</conditional>
		</section>
	</inputs>
	
	<outputs>
		<data name="logReport" format="txt" label="${projectName}-Log Report"/>
		<data name="outputPdf" format="pdf" label="${projectName}-BioFeatures Distribution">
			<filter>outputFiles['plot'] is True and outputOptions['plotFormat'] == 'pdf'</filter>
		</data>
		<data name="outputCategoriesPng" format="png" label="${projectName}-Categories Distribution">
			<filter>outputFiles['plot'] is True and outputOptions['plotFormat'] == 'png'</filter>
		</data>
		<data name="outputBiotypesPng" format="png" label="${projectName}-Biotypes Distribution">
			<filter>outputFiles['plot'] is True and outputOptions['plotFormat'] == 'png'</filter>
		</data>
		<data name="outputCategoriesSvg" format="svg" label="${projectName}-Categories Distribution">
			<filter>outputFiles['plot'] is True and outputOptions['plotFormat'] == 'svg'</filter>
		</data>
		<data name="outputBiotypesSvg" format="svg" label="${projectName}-Biotypes Distribution">
			<filter>outputFiles['plot'] is True and outputOptions['plotFormat'] == 'svg'</filter>
		</data>
		<data name="outputCountFile" format="txt" label="${projectName}-Categories Count">
			<filter>outputFiles['countFile'] is True</filter>
		</data>
		<data name="outputStrandedIndex" format="txt" label="${projectName}-Stranded Index">
			<filter>outputFiles['index'] is True</filter>
		</data>
		<data name="outputUnstrandedIndex" format="txt" label="${projectName}-Unstranded Index">
			<filter>outputFiles['index'] is True</filter>
		</data>
	</outputs>

	<configfiles>
		<configfile name="ALFA_config">
			projectName=$projectName

			##__INPUT 1__##
			annotationSource=$annotation.annotationSource['annotationSourceSelection']
			#if str ( $annotation.annotationSource['annotationSourceSelection'] ) == "index"
				annotationFile=None
				strandedIndex=$annotation.annotationSource['strandedIndex']
				unstrandedIndex=$annotation.annotationSource['unstrandedIndex']
			#else if str ( $annotation.annotationSource['annotationSourceSelection'] ) == "built_in_index"
				annotationFile=None
				built_in_index_prefix=$annotation.annotationSource.built_in_index_prefix.fields.prefix
			#else
				annotationFile=$annotation.annotationSource['annotationFile']
				strandedIndex=None
				unstrandedIndex=None
			#end if

			##__INPUT 2__##
			readsType=$reads.readsType['readsTypeSelection']
			#for $i, $r in enumerate ( $reads.readsType['readsList'] ) 
				readsFile[$i]=$r.readsFile
				readsLabel[$i]=$r.readsLabel
			#end for
			strandness=$reads['strandness']

			##__OUTPUT FILES__##
			plotChoice=$outputFiles['plot']
			countFileChoice=$outputFiles['countFile']
			indexChoice=$outputFiles['index']

			outputPdf=$outputPdf
			outputCategoriesPng=$outputCategoriesPng
			outputBiotypesPng=$outputBiotypesPng
			outputCategoriesSvg=$outputCategoriesSvg
			outputBiotypesSvg=$outputBiotypesSvg
			outputCountFile=$outputCountFile
			outputStrandedIndex=$outputStrandedIndex
			outputUnstrandedIndex=$outputUnstrandedIndex

			##__OUTPUT OPTIONS__##
			categoriesDepth=$outputOptions['categoriesDepth']
			plotFormat=$outputOptions['plotFormat']
			plotThresholdChoice=$outputOptions.plotThreshold['plotThresholdChoice']
			#if str ( $outputOptions.plotThreshold['plotThresholdChoice'] ) == "True"
				yMin=$outputOptions.plotThreshold.yMin
				yMax=$outputOptions.plotThreshold.yMax
			#else
				yMin=None
				yMax=None
			#end if
		</configfile>
	</configfiles>

	<tests>
		<test>
			<param name="alfa_toy" />
			<section name="annotation">
				<conditional name="annotationSource">
					<param name="annotationSourceSelection" value="personal_gtf" />
					<param name="annotationFile" value="alfa_toy.gtf" ftype="gtf" />
				</conditional>
			</section>
			<section name="reads">
				<conditional name="readsType">
					<param name="readsTypeSelection" value="bam" />
					<repeat name="readsList">
						<param name="readsFile" value="alfa_toy.bam" ftype="bam" />
						<param name="readsLabel" value="alfa_toy" />
					</repeat>
					<param name="strandness" value="unstranded" />
				</conditional>
			</section>
			<section name="outputFiles">
				<param name="plot" value="True" />
				<param name="countFile" value="True" />
				<param name="index" value="True" />
			</section>
			<section name="outputOptions">
				<param name="categoriesDepth" value="3" />
				<param name="plotFormat" value="pdf" />
				<conditional name="plotThreshold">
					<param name="plotThresholdChoice" value="False" />
				</conditional>
			</section>
			<output name="outputPdf" file="alfa_toy-Biofeatures Distribution.pdf" ftype="pdf" />
			<output name="outputCountFile" file="alfa_toy.categories_count" ftype="txt" />
			<output name="outputStrandedIndex" file="alfa_toy.stranded.index" ftype="txt" />
			<output name="outputUnstrandedIndex" file="alfa_toy.unstranded.index" ftype="txt" />
			<assert_stdout>
				<has_text text="### End of the program" />
			</assert_stdout>
		</test>
	</tests>

	<help>
**ALFA acronym**

- Annotation.Landscape.For.Aligned reads

----

**What it does**

	| ALFA provides a global overview of features distribution composing New Generation Sequencing dataset(s). 
	|
 	| Given a set of aligned reads (BAM files) and an annotation file (GTF format), the tool produces plots of the raw and normalized distributions of those reads among genomic categories (stop codon, 5'-UTR, CDS, intergenic, etc.) and biotypes (protein coding genes, miRNA, tRNA, etc.). Whatever the sequencing technique, whatever the organism.

----

**Official documentation of the tool**


- https://github.com/biocompibens/ALFA

----

**Detailed example**

- https://github.com/biocompibens/ALFA#detailed-example

----

**Nota Bene**

1. **Input 1: Annotation File**


	| ALFA requires as first input an annotation file (sequence, genome...) in gtf format in order to generate indexes that will be used in a 2nd step of the program.
	| Indexes are files which list all the coordinates of all categories (stop codon, 5'-UTR, CDS, intergenic...) and biotypes (protein coding genes, miRNA, tRNA, ...) encountered in the annotated sequence.
	
.. class:: warningmark

Gtf File must be sorted.

.. class:: infomark

Generation of indexes from an annotation file may be time consuming (i.e ~10min for the human genome). Thus, ALFA allows the user to submit directly indexes generated in previous runs.

2. **Input 2: Reads**

	| ALFA requires as second input a single or a set of mapped reads file(s) in either bam or bedgraph format. These files are required to intersect the coordinates of the mapped reads with the associated categories and biotypes on the annotated sequence.
	| The strandness option determines which strand of the annotated sequence will be taken into account during this intersection.

.. class:: warningmark

Bam or Bedgraph file(s) must be sorted.

<!--
.. class:: warningmark

For oriented reads (either matching the forward strand or the reverse strand), 'forward' or 'reverse' strandness must be selected.

.. class:: warningmark

For paired-end or non-oriented reads, 'unstranded' strandness must be selected.
-->

3. **Output files**

	| The result of the intersection is a count file displaying the count of nucleotides in the reads for each genomic categories and biotypes. From this count file, plots of the raw and normalized distributions of the reads among these categories are generated.
	| In the output files section, the user can choose what kind of files he desires as ALFA output. Categories Count File and Plots are proposed by default. 

.. class:: infomark

The user can also select the 'indexes' option as output. This option is interesting if you plan to run ALFA again with the same submitted annotation file. *See Nota Bene/Input 1: Annotation File for more information.*


- `How the plots look like`_

.. _How the plots look like: https://github.com/biocompibens/ALFA#plots

- `How they are generated`_ 

.. _How they are generated: https://github.com/biocompibens/ALFA#detailed-example

----

**ALFA Developpers**

	| Benoît Noël and Mathieu Bahin: *compbio team, Institut de Biologie de l'Ecole Normale Supérieure de Paris*


     </help>

     <citations>
     	<citation type="bibtex">@MISC{
     		author="Benoît Noël and Mathieu Bahin"
     		title="ALFA: Annotation Landscape For Aligned reads"
     		crossref="https://github.com/biocompibens/ALFA"
     		institution="Institut de Biologie de l'Ecole Normale Supérieure de Paris"
     		}
     	</citation>
     </citations>
</tool>