Merge pull request #2 from hdzierz/master

Marcus course in R markdown

.gitignore

@@ -9,11 +9,13 @@ tmp/
 *.cnt
 *.fq
 *.fasta
+*.fastq
+*.fastq.gz
 *.bt2
 *.zip
 *.gz
 *.h5
-
+*.bt2
 
 tt/
 .Rproj.user

.travis.yml

@@ -0,0 +1,13 @@
+language: R 
+before_install: 
+  - R --version
+  - RScript -e "library(knitr);"
+  - wget --version
+  - unzip --version
+  - wget --version
+  - unzip -h
+  - bowtie2 -h
+  - run_pipeline.pl -h
+  - pandoc --version
+  - module --version
+

00_AlignerIndices/load_data.sh

@@ -0,0 +1,13 @@
+#!/bin/bash
+
+if [ -f /input/genomic/TrainingData/BBS/gbs_rmd/00_AlignerIndices/GBS_Workshop_Maize.zip ]; 
+then
+    echo "File found";
+    unzip /input/genomic/TrainingData/BBS/gbs_rmd/00_AlignerIndices/GBS_Workshop_Maize.zip
+else
+    echo "File not found. Downloading";
+    wget -O GBS_Workshop_Maize.zip https://www.dropbox.com/sh/idwq4oo3uim31dw/AADW46CCFtxqnI4Kmjh_uAxoa?dl=1;
+    unzip GBS_Workshop_Maize.zip
+fi
+
+

00_AlignerIndices/run.R

@@ -0,0 +1,4 @@
+
+library(knitr)
+
+knit('run.Rmd')

00_AlignerIndices/run.Rmd

@@ -0,0 +1,13 @@
+# Download Maize Index from Dropbox 
+
+- unzip index and delete zip afterwards
+- convert mark down to html to load in browser
+
+
+```{r test-bash, engine='bash'}
+
+./load_data.sh
+
+pandoc run.md -o run.html
+
+```

01_RawSequence/load_data.sh

@@ -0,0 +1,14 @@
+#!/bin/bash
+
+rm -f C08L7ACXX_6_fastq.gz 
+
+if [ -f /input/genomic/TrainingData/BBS/gbs_rmd/01_RawSequence/C08L7ACXX_6_fastq.gz ]; 
+then
+    echo "File found";
+    ln -s /input/genomic/TrainingData/BBS/gbs_rmd/01_RawSequence/C08L7ACXX_6_fastq.gz
+else
+    echo "File not found. Downloading";
+    wget -O C08L7ACXX_6_fastq.gz "https://www.dropbox.com/s/vcrtcqunuxkwz90/C08L7ACXX_6_fastq.gz?dl=1";
+fi
+
+

01_RawSequence/run.R

@@ -0,0 +1,4 @@
+
+library(knitr)
+
+knit('run.Rmd')

01_RawSequence/run.Rmd

@@ -0,0 +1,12 @@
+# Load data
+
+- linking data from input for convenience
+- convert output to html for loading into the browser
+
+
+```{r test-bash, engine='bash'}
+
+./load_data.sh
+pandoc run.md -o run.html
+
+```

02_TagCounts/01_IndividualTagCounts/FastqToTagCounts.xml

@@ -0,0 +1,14 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+ <TasselPipeline>
+    <fork1>
+        <FastqToTagCountPlugin>
+            <i>../../01_RawSequence/</i>
+            <o>./</o>
+            <k>../../50_KeyFiles/GBS_Workshop_Maize_key.txt</k>
+            <e>ApeKI</e>
+            <s>3000000</s>
+            <c>1</c>
+        </FastqToTagCountPlugin>
+    </fork1>
+    <runfork1/>
+</TasselPipeline>

02_TagCounts/01_IndividualTagCounts/run.R

@@ -0,0 +1,4 @@
+
+library(knitr)
+
+knit('run.Rmd')

02_TagCounts/01_IndividualTagCounts/run.Rmd

@@ -0,0 +1,9 @@
+# Count GBS tags
+
+```{r test-bash, engine='bash'}
+module load tassel/3.0
+run_pipeline.pl -configFile FastqToTagCounts.xml
+pandoc run.md -o run.html
+module unload tassel/3.0
+
+```

02_TagCounts/02_MergedTagCounts/MergeTagCounts.xml

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+ <TasselPipeline>
+    <fork1>
+        <MergeMultipleTagCountPlugin>
+            <i>../01_IndividualTagCounts</i>
+            <o>./GBS_Workshop_Maize.cnt</o>
+            <c>5</c>
+        </MergeMultipleTagCountPlugin>
+    </fork1>
+    <runfork1/>
+</TasselPipeline>

02_TagCounts/02_MergedTagCounts/run.R

@@ -0,0 +1,4 @@
+
+library(knitr)
+
+knit('run.Rmd')

02_TagCounts/02_MergedTagCounts/run.Rmd

@@ -0,0 +1,10 @@
+# Merge tag count files
+
+```{r test-bash, engine='bash'}
+module load tassel/3.0
+run_pipeline.pl -configFile MergeTagCounts.xml
+module unload tassel/3.0
+
+pandoc run.md -o run.html
+
+```

02_TagCounts/03_TagCountToFastq/TagCountToFastq.xml

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+ <TasselPipeline>
+    <fork1>
+        <TagCountToFastqPlugin>
+            <i>../02_MergedTagCounts/GBS_Workshop_Maize.cnt</i>
+            <o>./GBS_Workshop_Maize.fq</o>
+            <c>5</c>
+        </TagCountToFastqPlugin>
+    </fork1>
+    <runfork1/>
+</TasselPipeline>

02_TagCounts/03_TagCountToFastq/run.R

@@ -0,0 +1,4 @@
+
+library(knitr)
+
+knit('run.Rmd')

02_TagCounts/03_TagCountToFastq/run.Rmd

@@ -0,0 +1,11 @@
+# Convert to Fastq
+
+```{r test-bash, engine='bash'}
+
+module load tassel/3.0
+run_pipeline.pl -configFile TagCountToFastq.xml
+module unload tassel/3.0
+
+pandoc run.md -o run.html
+
+```

03_SAM/run.R

@@ -0,0 +1,4 @@
+
+library(knitr)
+
+knit('run.Rmd')

03_SAM/run.Rmd

@@ -0,0 +1,9 @@
+# Align GBS tags to reference genome
+
+```{r test-bash, engine='bash'}
+
+module load bowtie2/2.2.5
+bowtie2 -M 4 -p 15 --very-sensitive-local -x ../00_AlignerIndices/GBS_Workshop_Maize  -U ../02_TagCounts/03_TagCountToFastq/GBS_Workshop_Maize.fq -S GBS_Workshop_Maize.sam
+module unload bowtie2/2.2.5
+
+```

04_TOPM/SAMConverter.xml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+ <TasselPipeline>
+    <fork1>
+        <SAMConverterPlugin>
+            <i>../03_SAM/GBS_Workshop_Maize.sam</i>
+            <o>./GBS_Workshop_Maize.topm</o>
+        </SAMConverterPlugin>
+    </fork1>
+    <runfork1/>
+</TasselPipeline>

04_TOPM/SAMConverter2.xml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+ <TasselPipeline>
+    <fork1>
+        <SAMConverterPlugin>
+            <i>&lt;(samtools view -h ../03_SAM/GBS_Workshop_Maize.bam)</i>
+            <o>./GBS_Workshop_Maize.topm</o>
+        </SAMConverterPlugin>
+    </fork1>
+    <runfork1/>
+</TasselPipeline>

04_TOPM/run.R

@@ -0,0 +1,4 @@
+
+library(knitr)
+
+knit('run.Rmd')

04_TOPM/run.Rmd

@@ -0,0 +1,9 @@
+# Convert sam tags to tags on physical map (TOPM)
+
+```{r test-bash, engine='bash'}
+
+module load tassel/3.0
+run_pipeline.pl -configFile SAMConverter.xml
+module unload tassel/3.0
+
+```

05_TBT/01_IndividualTBT/SeqToTBTHDF5Plugin.xml

@@ -0,0 +1,15 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+ <TasselPipeline>
+    <fork1>
+        <SeqToTBTHDF5Plugin>
+            <i>../../01_RawSequence</i>
+            <k>../../50_KeyFiles/GBS_Workshop_Maize_key.txt</k>
+            <e>ApeKI</e>
+            <o>./GBS_Workshop_Maize.h5</o>
+            <s>100000000</s>
+            <L>GBS_Workshop_MaizeTBTHDF5_Log.txt</L>
+            <t>../../02_TagCounts/02_MergedTagCounts/GBS_Workshop_Maize.cnt</t>
+        </SeqToTBTHDF5Plugin>
+    </fork1>
+    <runfork1/>
+</TasselPipeline>

05_TBT/01_IndividualTBT/run.R

@@ -0,0 +1,4 @@
+
+library(knitr)
+
+knit('run.Rmd')

05_TBT/01_IndividualTBT/run.Rmd

@@ -0,0 +1,10 @@
+# Match tags to samples 
+
+
+```{r test-bash, engine='bash'}
+
+module load tassel/3.0
+run_pipeline.pl -configFile SeqToTBTHDF5Plugin.xml
+module unload tassel/3.0
+
+```

05_TBT/04_PivotMergedTaxaTBT/PivotTaxaTBTHDF5.xml

@@ -0,0 +1,12 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+ <TasselPipeline>
+    <fork1>
+        <ModifyTBTHDF5Plugin>
+            <o>../01_IndividualTBT/GBS_Workshop_Maize.h5</o>
+            <p>./PivotTaxaTBTHDF5.h5</p>
+            <L>./PivotTaxaTBTHDF5.log</L>
+            <c></c>
+        </ModifyTBTHDF5Plugin>
+    </fork1>
+    <runfork1/>
+</TasselPipeline>

05_TBT/04_PivotMergedTaxaTBT/run.R

@@ -0,0 +1,4 @@
+
+library(knitr)
+
+knit('run.Rmd')

05_TBT/04_PivotMergedTaxaTBT/run.Rmd

@@ -0,0 +1,10 @@
+# Pivot the tbt to prepare for SNP calling 
+
+
+```{r test-bash, engine='bash'}
+
+module load tassel/3.0
+run_pipeline.pl  -configFile ./PivotTaxaTBTHDF5.xml
+module unload tassel/3.0
+
+```

06_HapMap/SNP_Caller.xml

@@ -0,0 +1,16 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+ <TasselPipeline>
+    <fork1>
+        <TagsToSNPByAlignmentPlugin>
+            <i>../05_TBT/04_PivotMergedTaxaTBT/PivotTaxaTBTHDF5.h5</i>
+            <o>./SNP_Caller</o>
+            <m>../04_TOPM/GBS_Workshop_Maize.topm</m>
+            <mnF>0.8</mnF>
+            <mnMAF>0.02</mnMAF>
+            <mnMAC>100000</mnMAC>
+            <s>9</s>
+            <e>10</e>
+        </TagsToSNPByAlignmentPlugin>
+    </fork1>
+    <runfork1/>
+</TasselPipeline>

06_HapMap/run.R

@@ -0,0 +1,4 @@
+
+library(knitr)
+
+knit('run.Rmd')

06_HapMap/run.Rmd

@@ -0,0 +1,23 @@
+# Call SNPs
+
+
+```{r test-bash, engine='bash'}
+
+if [! -d /output/genomic/TrainingData/BBS/gbs_rmd/06_HapMap/SNP_Caller];
+then
+    mkdir -p  /output/genomic/TrainingData/BBS/gbs_rmd/06_HapMap/SNP_Caller
+fi
+
+if [! -L 06_HapMap];
+then
+    ln -s  /output/genomic/TrainingData/BBS/gbs_rmd/06_HapMap
+fi
+
+module load tassel/3.0
+run_pipeline.pl -configFile ./SNP_Caller.xml
+module unload tassel/3.0
+
+pandoc run.md -o run.html
+
+
+```