Created documentation and updated mkdocs.yml

biopet-autodoc/synchronize_docs.sh

-#!/bin/bash
-
-#Script to document not yet documented tools in biopet
-
-#Declare variables
-BIOPET_DIR=~/biopet
-TOOLS_DIR=$BIOPET_DIR/biopet-tools/src/main/scala/nl/lumc/sasc/biopet/tools
-DOCS_DIR=$BIOPET_DIR/docs/tools
-TEMPLATE=$BIOPET_DIR/biopet-autodoc/tools_doc_template.j2
-BIOPET="java -jar $BIOPET_JAR tool" #Make sure the BIOPET_JAR environment variable is defined!
-
-
-for file in $TOOLS_DIR/*.scala #For loop checking all scala files in the tools section
-do
-  file_no_path=${file##*/}
-  file_no_extension=${file_no_path%.scala}
-  file_with_md=${file_no_extension}.md
-  destfile=$DOCS_DIR/$file_with_md
-  if [ ! -f $destfile ] #Checks if (tool_name).md is already present. Existing files are skipped
-    then
-      eval "$BIOPET $file_no_extension -h 2> help.txt"
-      if grep -Fxq "ERROR: command '$file_no_extension' does not exist in module 'tool'" help.txt
-        then
-          echo "The tool $file_no_extension does not exist in the latest compiled version of biopet"
-        else
-          ./templateparser.py -t "$TEMPLATE" -o "destfile" -N "$file_no_extension" -L "help.txt"
-          echo "$destfile created"
-      
-      fi
-      rm help.txt
-  fi  
-done

biopet-autodoc/templateparser.py

-#! /usr/bin/env python2
-
-#Script to document new tools using a jinja2 template
-from jinja2 import Environment, FileSystemLoader
-import os
-import argparse
-import ast
-import yaml
-
-if __name__ == "__main__":
-    
-    #Block with command line options
-    parser=argparse.ArgumentParser(description="")
-    parser.add_argument("-t", type=str, nargs=1, help="Templatefile to be used")
-    parser.add_argument("-o", type=str, nargs=1, help="output file")
-    parser.add_argument("-N","--tool-name", type=str, nargs=1, help="name of the tool")
-    parser.add_argument("-O", "--tool-output", type=str, nargs='?', default='')
-    parser.add_argument("-R", "--tool-run", type=str, nargs='?', default='')
-    parser.add_argument("-L", "--tool-option-list", type=str, nargs='?', default= '', help="Text file containing the --help output of the tool")
-
-    #parse arguments
-    arguments=parser.parse_args()
-    template=arguments.t[0]
-    output_file=arguments.o[0]
-    tool=dict()
-    tool['name']=arguments.tool_name[0]
-    tool['output']=arguments.tool_output
-    tool['run']=arguments.tool_run
-    help_file=open(arguments.tool_option_list, 'r')
-    tool['option_list']=help_file.read()   #This reads the option list file to a raw string
-
-    # Open jinja2 template and render it with variables
-    j2_env = Environment(loader=FileSystemLoader("/"))
-    rendered = j2_env.get_template(template).render(tool=tool)
-
-    # Write the template results to the output file
-    file=open(output_file, "w")
-    file.seek(0)
-    file.write(rendered)
-    file.close()

biopet-autodoc/tools_doc_template.j2

-# {{tool.name}}
-
-## Introduction
-{{tool.introduction|default('')}} 
-
-## Example
-The help menu:
-~~~
-
-{{tool.option_list|default('')}}
-
-~~~
-
-To run the tool use:
-~~~
-biopet tool {{tool.name}} {{tool.run|default('')}}   
-~~~
-
-
-## Output
-{{tool.output|default('')}}

docs/tools/DownloadNcbiAssembly.md

+# DownloadNcbiAssembly
+
+## Introduction
+ 
+
+## Example
+The help menu:
+~~~
+
+Usage: DownloadNcbiAssembly [options]
+
+  -l <value> | --log_level <value>
+        Level of log information printed. Possible levels: 'debug', 'info', 'warn', 'error'
+  -h | --help
+        Print usage
+  -v | --version
+        Print version
+  -a <file> | --assembly_report <file>
+        refseq ID from NCBI
+  -o <file> | --output <file>
+        output Fasta file
+  --report <file>
+        where to write report from ncbi
+  --nameHeader <string>
+        
+ What column to use from the NCBI report for the name of the contigs.
+ All columns in the report can be used but this are the most common field to choose from:
+ - 'Sequence-Name': Name of the contig within the assembly
+ - 'UCSC-style-name': Name of the contig used by UCSC ( like hg19 )
+ - 'RefSeq-Accn': Unique name of the contig at RefSeq (default for NCBI)
+  --mustHaveOne:<key>=<column_name=regex>
+        This can be used to filter based on the NCBI report, multiple conditions can be given, at least 1 should be true
+  --mustNotHave:<key>=<column_name=regex>
+        This can be used to filter based on the NCBI report, multiple conditions can be given, all should be false
+
+
+~~~
+
+To run the tool use:
+~~~
+biopet tool DownloadNcbiAssembly    
+~~~
+
+
+## Output

docs/tools/FastqFilter.md

+# FastqFilter
+
+## Introduction
+ 
+
+## Example
+The help menu:
+~~~
+
+Usage: FastqFilter [options]
+
+  -l <value> | --log_level <value>
+        Level of log information printed. Possible levels: 'debug', 'info', 'warn', 'error'
+  -h | --help
+        Print usage
+  -v | --version
+        Print version
+  -I <file> | --inputFile <file>
+        Path to input file
+  -o <file> | --output <file>
+        Path to output file
+  --idRegex <file>
+        Regex to match ID
+
+
+~~~
+
+To run the tool use:
+~~~
+biopet tool FastqFilter    
+~~~
+
+
+## Output

docs/tools/FastqSync.md

+# FastqSync
+
+## Introduction
+ 
+
+## Example
+The help menu:
+~~~
+
+
+FastqSync - Sync paired-end FASTQ files.
+
+This tool works with gzipped or non-gzipped FASTQ files. The output
+file will be gzipped when the input is also gzipped.
+      
+Usage: FastqSync [options]
+
+  -l <value> | --log_level <value>
+        Level of log information printed. Possible levels: 'debug', 'info', 'warn', 'error'
+  -h | --help
+        Print usage
+  -v | --version
+        Print version
+  -r <fastq> | --ref <fastq>
+        Reference FASTQ file
+  -i <fastq> | --in1 <fastq>
+        Input FASTQ file 1
+  -j <fastq[.gz]> | --in2 <fastq[.gz]>
+        Input FASTQ file 2
+  -o <fastq[.gz]> | --out1 <fastq[.gz]>
+        Output FASTQ file 1
+  -p <fastq> | --out2 <fastq>
+        Output FASTQ file 2
+
+
+~~~
+
+To run the tool use:
+~~~
+biopet tool FastqSync    
+~~~
+
+
+## Output

docs/tools/FindOverlapMatch.md

+# FindOverlapMatch
+
+## Introduction
+ 
+
+## Example
+The help menu:
+~~~
+
+Usage: FindOverlapMatch [options]
+
+  -l <value> | --log_level <value>
+        Level of log information printed. Possible levels: 'debug', 'info', 'warn', 'error'
+  -h | --help
+        Print usage
+  -v | --version
+        Print version
+  -i <file> | --input <file>
+        Input should be a table where the first row and column have the ID's, those can be different
+  -o <file> | --output <file>
+        default to stdout
+  -c <value> | --cutoff <value>
+        minimum value to report it as pair
+  --use_same_names
+        Do not compare samples with the same name
+  --rowSampleRegex <regex>
+        Samples in the row should match this regex
+  --columnSampleRegex <regex>
+        Samples in the column should match this regex
+
+
+~~~
+
+To run the tool use:
+~~~
+biopet tool FindOverlapMatch    
+~~~
+
+
+## Output

docs/tools/GvcfToBed.md

+# GvcfToBed
+
+## Introduction
+ 
+
+## Example
+The help menu:
+~~~
+
+Usage: GvcfToBed [options]
+
+  -l <value> | --log_level <value>
+        Level of log information printed. Possible levels: 'debug', 'info', 'warn', 'error'
+  -h | --help
+        Print usage
+  -v | --version
+        Print version
+  -I <file> | --inputVcf <file>
+        Input vcf file
+  -O <file> | --outputBed <file>
+        Output bed file
+  --invertedOutputBed <file>
+        Output bed file
+  -S <sample> | --sample <sample>
+        Sample to consider. Will take first sample on alphabetical order by default
+  --minGenomeQuality <int>
+        Minimum genome quality to consider
+
+
+~~~
+
+To run the tool use:
+~~~
+biopet tool GvcfToBed    
+~~~
+
+
+## Output

docs/tools/MergeTables.md

+# MergeTables
+
+## Introduction
+ 
+
+## Example
+The help menu:
+~~~
+
+
+MergeTables - Tabular file merging based on feature ID equality.
+      
+Usage: MergeTables [options] [<input_tables> ...]
+
+  -l <value> | --log_level <value>
+        Level of log information printed. Possible levels: 'debug', 'info', 'warn', 'error'
+  -h | --help
+        Print usage
+  -v | --version
+        Print version
+  -i <idx1>,<idx2>, ... | --id_column_index <idx1>,<idx2>, ...
+        Index of feature ID column from each input file (1-based)
+  -a <idx> | --value_column_index <idx>
+        Index of column from each input file containing the value to merge (1-based)
+  -o <path> | --output <path>
+        Path to output file (default: '-' <stdout>)
+  -n <name> | --id_column_name <name>
+        Name of feature ID column in the output merged file (default: feature)
+  -N <name> | --column_names <name>
+        Name of feature ID column in the output merged file (default: feature)
+  -e <ext> | --strip_extension <ext>
+        Common extension of all input tables to strip (default: empty string)
+  -m <value> | --num_header_lines <value>
+        The number of header lines present in all input files (default: 0; no header)
+  -f <value> | --fallback <value>
+        The string to use when a value for a feature is missing in one or more sample(s) (default: '-')
+  -d <value> | --delimiter <value>
+        The character used for separating columns in the input files (default: '\t')
+  <input_tables> ...
+        Input tables to merge
+
+This tool merges multiple tab-delimited files and outputs a single
+tab delimited file whose columns are the feature IDs and a single
+column from each input files.
+
+Note that in each input file there must not be any duplicate features.
+If there are, the tool will only keep one and discard the rest.
+      
+
+
+~~~
+
+To run the tool use:
+~~~
+biopet tool MergeTables    
+~~~
+
+
+## Output

docs/tools/PrefixFastq.md

+# PrefixFastq
+
+## Introduction
+ 
+
+## Example
+The help menu:
+~~~
+
+INFO  [2017-03-22 10:07:55,583] [PrefixFastq$] - Start
+Usage: PrefixFastq [options]
+
+  -l <value> | --log_level <value>
+        Level of log information printed. Possible levels: 'debug', 'info', 'warn', 'error'
+  -h | --help
+        Print usage
+  -v | --version
+        Print version
+  -i <file> | --input <file>
+        
+  -o <file> | --output <file>
+        
+  -s <prefix seq> | --seq <prefix seq>
+        
+
+
+~~~
+
+To run the tool use:
+~~~
+biopet tool PrefixFastq    
+~~~
+
+
+## Output

docs/tools/SageCountFastq.md

+# SageCountFastq
+
+## Introduction
+ 
+
+## Example
+The help menu:
+~~~
+
+Usage: SageCountFastq [options]
+
+  -l <value> | --log_level <value>
+        Level of log information printed. Possible levels: 'debug', 'info', 'warn', 'error'
+  -h | --help
+        Print usage
+  -v | --version
+        Print version
+  -I <file> | --input <file>
+        
+  -o <file> | --output <file>
+        
+
+
+~~~
+
+To run the tool use:
+~~~
+biopet tool SageCountFastq    
+~~~
+
+
+## Output

docs/tools/SeqStat.md

+# SeqStat
+
+## Introduction
+ 
+
+## Example
+The help menu:
+~~~
+
+
+SeqStat - Summarize FastQ
+      
+Usage: SeqStat [options]
+
+  -l <value> | --log_level <value>
+        Level of log information printed. Possible levels: 'debug', 'info', 'warn', 'error'
+  -h | --help
+        Print usage
+  -v | --version
+        Print version
+  -i <fastq> | --fastq <fastq>
+        FastQ file to generate stats from
+  -o <json> | --output <json>
+        File to write output to, if not supplied output go to stdout
+
+
+~~~
+
+To run the tool use:
+~~~
+biopet tool SeqStat    
+~~~
+
+
+## Output

docs/tools/SquishBed.md

+# SquishBed
+
+## Introduction
+ 
+
+## Example
+The help menu:
+~~~
+
+Usage: SquishBed [options]
+
+  -l <value> | --log_level <value>
+        Level of log information printed. Possible levels: 'debug', 'info', 'warn', 'error'
+  -h | --help
+        Print usage
+  -v | --version
+        Print version
+  -I <file> | --input <file>
+        
+  -o <file> | --output <file>
+        
+  -s | --strandSensitive
+        
+
+
+~~~
+
+To run the tool use:
+~~~
+biopet tool SquishBed    
+~~~
+
+
+## Output

docs/tools/SummaryToTsv.md

+# SummaryToTsv
+
+## Introduction
+ 
+
+## Example
+The help menu:
+~~~
+
+Usage: SummaryToTsv [options]
+
+  -l <value> | --log_level <value>
+        Level of log information printed. Possible levels: 'debug', 'info', 'warn', 'error'
+  -h | --help
+        Print usage
+  -v | --version
+        Print version
+  -s <file> | --summary <file>
+        
+  -o <file> | --outputFile <file>
+        
+  -p <string> | --path <string>
+        
+String that determines the values extracted from the summary. Should be of the format:
+<header_name>=<namespace>:<lower_namespace>:<even_lower_namespace>...
+      
+  -m <root|sample|lib> | --mode <root|sample|lib>
+        
+Determines on what level to aggregate data.
+root: at the root level
+sample: at the sample level
+lib: at the library level
+      
+
+
+~~~
+
+To run the tool use:
+~~~
+biopet tool SummaryToTsv    
+~~~
+
+
+## Output

docs/tools/ValidateFastq.md

+# ValidateFastq
+
+## Introduction
+ 
+
+## Example
+The help menu:
+~~~
+
+INFO  [2017-03-22 10:08:01,355] [ValidateFastq$] - Start
+Usage: ValidateFastq [options]
+
+  -l <value> | --log_level <value>
+        Level of log information printed. Possible levels: 'debug', 'info', 'warn', 'error'
+  -h | --help
+        Print usage
+  -v | --version
+        Print version
+  -i <file> | --fastq1 <file>
+        
+  -j <file> | --fastq2 <file>
+        
+
+
+~~~
+
+To run the tool use:
+~~~
+biopet tool ValidateFastq    
+~~~
+
+
+## Output

docs/tools/ValidateVcf.md

+# ValidateVcf
+
+## Introduction
+ 
+
+## Example
+The help menu:
+~~~
+
+INFO  [2017-03-22 10:08:02,092] [ValidateVcf$] - Start
+Usage: ValidateVcf [options]
+
+  -l <value> | --log_level <value>
+        Level of log information printed. Possible levels: 'debug', 'info', 'warn', 'error'
+  -h | --help
+        Print usage
+  -v | --version
+        Print version
+  -i <file> | --inputVcf <file>
+        Vcf file to check
+  -R <file> | --reference <file>
+        Reference fasta to check vcf file against
+  --disableFail
+        Do not fail on error. The tool will still exit when encountering an error, but will do so with exit code 0
+
+
+~~~
+
+To run the tool use:
+~~~
+biopet tool ValidateVcf    
+~~~
+
+
+## Output

docs/tools/VcfWithVcf.md

+# VcfWithVcf
+
+## Introduction
+ 
+
+## Example
+The help menu:
+~~~
+
+INFO  [2017-03-22 10:08:02,817] [VcfWithVcf$] - Init phase
+Usage: VcfWithVcf [options]
+
+  -l <value> | --log_level <value>
+        Level of log information printed. Possible levels: 'debug', 'info', 'warn', 'error'
+  -h | --help
+        Print usage
+  -v | --version
+        Print version
+  -I <file> | --inputFile <file>
+        
+  -o <file> | --outputFile <file>
+        
+  -s <file> | --secondaryVcf <file>
+        
+  -R <file> | --reference <file>
+        
+  -f <field> or <input_field:output_field> or <input_field:output_field:method> | --field <field> or <input_field:output_field> or <input_field:output_field:method>
+         If only <field> is given, the field's identifier in the output VCF will be identical to <field>.
+ By default we will return all values found for a given field.
+ For INFO fields with type R or A we will take the respective alleles present in the input file.
+ If a <method> is supplied, a method will be applied over the contents of the field.
+ In this case, all values will be considered.
+ The following methods are available:
+   - max   : takes maximum of found value, only works for numeric (integer/float) fields
+   - min   : takes minimum of found value, only works for numeric (integer/float) fields
+   - unique: takes only unique values 
+  --match <Boolean>
+        Match alternative alleles; default true
+
+
+~~~
+
+To run the tool use:
+~~~
+biopet tool VcfWithVcf    
+~~~
+
+
+## Output

mkdocs.yml

@@ -22,21 +22,37 @@ pages:
     - Toucan (Annotation): 'pipelines/toucan.md'
 - Tools:
     - AnnotateVcfWithBed: 'tools/AnnotateVcfWithBed.md'
-    - SamplesTsvToConfig: 'tools/SamplesTsvToConfig.md'
-    - BedToInterval: 'tools/bedtointerval.md'
+    - BaseCounter: 'tools/BaseCounter.md'
     - BastyGenerateFasta: 'tools/BastyGenerateFasta.md'
-    - BedToInterval: 'tools/bedtointerval.md'
-    - BedtoolsCoverageToCounts: 'tools/bedtoolscoveragetocounts.md'
+    - BedToInterval: 'tools/BedToInterval.md'
+    - BedtoolsCoverageToCounts: 'tools/BedtoolsCoverageToCounts.md'
     - BiopetFlagstat: 'tools/BiopetFlagstat.md'
     - CheckAllelesVcfInBam: 'tools/CheckAllelesVcfInBam.md'
+    - DownloadNcbiAssembly: 'tools/DownloadNcbiAssembly.md'
     - ExtractAlignedFastq: 'tools/ExtractAlignedFastq.md'
+    - FastqFilter: 'tools/FastqFilter.md'
     - FastqSplitter: 'tools/FastqSplitter.md'
+    - FastqSync: 'tools/FastqSync.md'
+    - FindOverlapMatch: 'tools/FindOverlapMatch.md'
     - FindRepeatsPacBio: 'tools/FindRepeatsPacBio.md'
+    - GvcfToBed: 'tools/GvcfToBed.md'
+    - MergeAlleles: 'tools/MergeAlleles.md'
+    - MergeTables: 'tools/MergeTables.md'
     - MpileupToVcf: 'tools/MpileupToVcf.md'
-    - Sagetools: 'tools/sagetools.md'
-    - WipeReads: 'tools/WipeReads.md'
+    - PrefixFastq: 'tools/PrefixFastq.md'
+    - SageCountFastq: 'tools/SageCountFastq.md'
+    - sagetools: 'tools/sagetools.md'
+    - SamplesTsvToConfig: 'tools/SamplesTsvToConfig.md'
+    - SeqStat: 'tools/SeqStat.md'
+    - SquishBed: 'tools/SquishBed.md'
+    - SummaryToTsv: 'tools/SummaryToTsv.md'
+    - ValidateFastq: 'tools/ValidateFastq.md'
+    - ValidateVcf: 'tools/ValidateVcf.md'
     - VcfFilter: 'tools/VcfFilter.md'
+    - VcfToTsv: 'tools/VcfToTsv.md'
+    - VcfWithVcf: 'tools/VcfWithVcf.md'
     - VepNormalizer: 'tools/VepNormalizer.md'
+    - WipeReads: 'tools/WipeReads.md'
 - Release notes:
     - 0.7.0: 'releasenotes/release_notes_0.7.0.md'
     - 0.6.0: 'releasenotes/release_notes_0.6.0.md'