From fcd35967162c131af84550267a146384d105d16a Mon Sep 17 00:00:00 2001
From: sajvanderzeeuw <s.a.j.van_der_zeeuw@lumc.nl>
Date: Thu, 5 Nov 2015 16:49:34 +0100
Subject: [PATCH] changes in docs 0.5.0 carp
---
docs/pipelines/carp.md | 144 +++++++++++++++++++++++++++++++++++-
docs/pipelines/flexiprep.md | 22 +++---
2 files changed, 152 insertions(+), 14 deletions(-)
diff --git a/docs/pipelines/carp.md b/docs/pipelines/carp.md
index e869bb1b5..c39535f9e 100644
--- a/docs/pipelines/carp.md
+++ b/docs/pipelines/carp.md
@@ -11,7 +11,7 @@ Carp is a pipeline for analyzing ChIP-seq NGS data. It uses the BWA MEM aligner
The layout of the sample configuration for Carp is basically the same as with our other multi sample pipelines, for example:
-~~~
+~~~ json
{
"samples": {
"sample_X": {
@@ -58,19 +58,155 @@ While optional settings are:
As with other pipelines in the Biopet suite, Carp can be run by specifying the pipeline after the `pipeline` subcommand:
-~~~
+~~~ bash
java -jar </path/to/biopet.jar> pipeline carp -config </path/to/config.json> -qsub -jobParaEnv BWA -run
~~~
If you already have the `biopet` environment module loaded, you can also simply call `biopet`:
-~~~
+~~~ bash
biopet pipeline carp -config </path/to/config.json> -qsub -jobParaEnv BWA -run
~~~
-It is also a good idea to specify retries (we recomend `-retry 4` up to `-retry 8`) so that cluster glitches do not interfere
+It is also a good idea to specify retries (we recommend `-retry 4` up to `-retry 8`) so that cluster glitches do not interfere
with your pipeline runs.
+## Example output
+
+```bash
+.
+├── Carp.summary.json
+├── report
+│  ├── alignmentSummary.png
+│  ├── alignmentSummary.tsv
+│  ├── ext
+│  │  ├── css
+│  │  │  ├── bootstrap_dashboard.css
+│  │  │  ├── bootstrap.min.css
+│  │  │  ├── bootstrap-theme.min.css
+│  │  │  └── sortable-theme-bootstrap.css
+│  │  ├── fonts
+│  │  │  ├── glyphicons-halflings-regular.ttf
+│  │  │  ├── glyphicons-halflings-regular.woff
+│  │  │  └── glyphicons-halflings-regular.woff2
+│  │  └── js
+│  │  ├── bootstrap.min.js
+│  │  ├── jquery.min.js
+│  │  └── sortable.min.js
+│  ├── Files
+│  │  └── index.html
+│  ├── index.html
+│  ├── insertsize.png
+│  ├── insertsize.tsv
+│  ├── QC_Bases_R1.png
+│  ├── QC_Bases_R1.tsv
+│  ├── QC_Bases_R2.png
+│  ├── QC_Bases_R2.tsv
+│  ├── QC_Reads_R1.png
+│  ├── QC_Reads_R1.tsv
+│  ├── QC_Reads_R2.png
+│  ├── QC_Reads_R2.tsv
+│  ├── Samples
+│  │  ├── 10_Input_2
+│  │  │  ├── Alignment
+│  │  │  │  ├── index.html
+│  │  │  │  ├── insertsize.png
+│  │  │  │  ├── insertsize.tsv
+│  │  │  │  ├── wgs.png
+│  │  │  │  └── wgs.tsv
+│  │  │  ├── Files
+│  │  │  │  └── index.html
+│  │  │  ├── index.html
+│  │  │  └── Libraries
+│  │  │  ├── 3307
+│  │  │  │  ├── Alignment
+│  │  │  │  │  ├── index.html
+│  │  │  │  │  ├── insertsize.png
+│  │  │  │  │  ├── insertsize.tsv
+│  │  │  │  │  ├── wgs.png
+│  │  │  │  │  └── wgs.tsv
+│  │  │  │  ├── index.html
+│  │  │  │  └── QC
+│  │  │  │  ├── fastqc_R1_duplication_levels.png
+│  │  │  │  ├── fastqc_R1_kmer_profiles.png
+│  │  │  │  ├── fastqc_R1_per_base_quality.png
+│  │  │  │  ├── fastqc_R1_per_base_sequence_content.png
+│  │  │  │  ├── fastqc_R1_per_sequence_gc_content.png
+│  │  │  │  ├── fastqc_R1_per_sequence_quality.png
+│  │  │  │  ├── fastqc_R1_qc_duplication_levels.png
+│  │  │  │  ├── fastqc_R1_qc_kmer_profiles.png
+│  │  │  │  ├── fastqc_R1_qc_per_base_quality.png
+│  │  │  │  ├── fastqc_R1_qc_per_base_sequence_content.png
+│  │  │  │  ├── fastqc_R1_qc_per_sequence_gc_content.png
+│  │  │  │  ├── fastqc_R1_qc_per_sequence_quality.png
+│  │  │  │  ├── fastqc_R1_qc_sequence_length_distribution.png
+│  │  │  │  ├── fastqc_R1_sequence_length_distribution.png
+│  │  │  │  └── index.html
+│  │  │  └── index.html
+│  │  ├── 11_GR_2A
+│  │  │  ├── Alignment
+│  │  │  │  ├── index.html
+│  │  │  │  ├── insertsize.png
+│  │  │  │  ├── insertsize.tsv
+│  │  │  │  ├── wgs.png
+│  │  │  │  └── wgs.tsv
+│  │  │  ├── alignmentSummary.png
+│  │  │  ├── alignmentSummary.tsv
+│  │  │  ├── Files
+│  │  │  │  └── index.html
+│  │  │  ├── index.html
+│  │  │  └── Libraries
+│  │  │  ├── 3307
+│  │  │  │  ├── Alignment
+│  │  │  │  │  ├── index.html
+│  │  │  │  │  ├── insertsize.png
+│  │  │  │  │  ├── insertsize.tsv
+│  │  │  │  │  ├── wgs.png
+│  │  │  │  │  └── wgs.tsv
+│  │  │  │  ├── index.html
+│  │  │  │  └── QC
+│  │  │  │  ├── fastqc_R1_duplication_levels.png
+│  │  │  │  ├── fastqc_R1_kmer_profiles.png
+│  │  │  │  ├── fastqc_R1_per_base_quality.png
+│  │  │  │  ├── fastqc_R1_per_base_sequence_content.png
+│  │  │  │  ├── fastqc_R1_per_sequence_gc_content.png
+│  │  │  │  ├── fastqc_R1_per_sequence_quality.png
+│  │  │  │  ├── fastqc_R1_qc_duplication_levels.png
+│  │  │  │  ├── fastqc_R1_qc_kmer_profiles.png
+│  │  │  │  ├── fastqc_R1_qc_per_base_quality.png
+│  │  │  │  ├── fastqc_R1_qc_per_base_sequence_content.png
+│  │  │  │  ├── fastqc_R1_qc_per_sequence_gc_content.png
+│  │  │  │  ├── fastqc_R1_qc_per_sequence_quality.png
+│  │  │  │  ├── fastqc_R1_qc_sequence_length_distribution.png
+│  │  │  │  ├── fastqc_R1_sequence_length_distribution.png
+│  │  │  │  └── index.html
+│  │  │  ├── 3385
+│  │  │  │  ├── Alignment
+│  │  │  │  │  ├── index.html
+│  │  │  │  │  ├── insertsize.png
+│  │  │  │  │  ├── insertsize.tsv
+│  │  │  │  │  ├── wgs.png
+│  │  │  │  │  └── wgs.tsv
+│  │  │  │  ├── index.html
+│  │  │  │  └── QC
+│  │  │  │  ├── fastqc_R1_duplication_levels.png
+│  │  │  │  ├── fastqc_R1_kmer_profiles.png
+│  │  │  │  ├── fastqc_R1_per_base_quality.png
+│  │  │  │  ├── fastqc_R1_per_base_sequence_content.png
+│  │  │  │  ├── fastqc_R1_per_sequence_gc_content.png
+│  │  │  │  ├── fastqc_R1_per_sequence_quality.png
+│  │  │  │  ├── fastqc_R1_qc_duplication_levels.png
+│  │  │  │  ├── fastqc_R1_qc_kmer_profiles.png
+│  │  │  │  ├── fastqc_R1_qc_per_base_quality.png
+│  │  │  │  ├── fastqc_R1_qc_per_base_sequence_content.png
+│  │  │  │  ├── fastqc_R1_qc_per_sequence_gc_content.png
+│  │  │  │  ├── fastqc_R1_qc_per_sequence_quality.png
+│  │  │  │  ├── fastqc_R1_qc_sequence_length_distribution.png
+│  │  │  │  ├── fastqc_R1_sequence_length_distribution.png
+│  │  │  │  └── index.html
+│  │  │  └── index.html
+```
+
## Getting Help
If you have any questions on running Carp, suggestions on how to improve the overall flow, or requests for your favorite ChIP-seq related program to be added, feel free to post an issue to our issue tracker at [https://git.lumc.nl/biopet/biopet/issues](https://git.lumc.nl/biopet/biopet/issues).
diff --git a/docs/pipelines/flexiprep.md b/docs/pipelines/flexiprep.md
index 83d2dd6db..c47732029 100644
--- a/docs/pipelines/flexiprep.md
+++ b/docs/pipelines/flexiprep.md
@@ -1,17 +1,18 @@
# Flexiprep
## Introduction
-Flexiprep is our quality control pipeline. This pipeline checks for possible barcode contamination, clips reads, trims reads and runs
-the <a href="http://www.bioinformatics.babraham.ac.uk/projects/fastqc/" target="_blank">Fastqc</a> tool.
-Adapter clipping is performed by <a href="https://github.com/marcelm/cutadapt" target="_blank">Cutadapt</a>.
-For quality trimming we use <a href="https://github.com/najoshi/sickle" target="_blank">Sickle</a>.
-Flexiprep works on `.fastq` files.
+Flexiprep is a quality control pipeline. This pipeline checks for possible barcode contamination, clips reads, trims reads and
+ runs [FASTQC](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/).
+Adapter clipping is performed by [Cutadapt](https://github.com/marcelm/cutadapt).
+For quality trimming we use [Sickle](https://github.com/najoshi/sickle).
+Flexiprep only works on `.fastq` files.
## Example
To get the help menu:
-~~~
+
+``` bash
java -jar </path/to/biopet.jar> pipeline Flexiprep -h
Arguments for Flexiprep:
@@ -21,17 +22,18 @@ Arguments for Flexiprep:
-library,--libid <libid> Library ID
-config,--config_file <config_file> JSON config file(s)
-DSC,--disablescatter Disable all scatters
-~~~
+```
Note that the pipeline also works on unpaired reads where one should only provide R1.
To start the pipeline (remove `-run` for a dry run):
-~~~bash
+
+``` bash
java -jar Biopet-0.2.0.jar pipeline Flexiprep -run -outDir myDir \
-R1 myFirstReadPair -R2 mySecondReadPair -sample mySampleName \
-library myLibname -config mySettings.json
-~~~
+```
## Configuration and flags
@@ -64,7 +66,7 @@ The pipeline also outputs 2 Fastqc runs one before and one after quality control
### Example output
-~~~
+~~~ bash
.
├── mySample_01.qc.summary.json
├── mySample_01.qc.summary.json.out
--
GitLab