diff --git a/README.md b/README.md
index 003fea17ffb0efec87598e912a7be40108eda132..9fae089959a5ccaef570d3a5b52b9ba8e3cdfbed 100644
--- a/README.md
+++ b/README.md
@@ -31,22 +31,26 @@ _Good idea to include screenshots or GIFs (see ttygif or Asciinema)_
### Conda _(prior!)_ ###
Download and install **Conda**: [Latest Miniconda Installer](https://docs.conda.io/en/latest/miniconda.html#latest-miniconda-installer-links)
-1. Donwload conda installer _(i.e. for Miniconda3 with Python 3.9 on Linux-64-bit)_:
+1. Donwload conda installer _(i.e. for Miniconda3 with Python 3.9 on MacOSX-64-bit)_:
```shel
-wget https://repo.anaconda.com/miniconda/Miniconda3-py39_4.10.3-Linux-x86_64.sh
+wget https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-x86_64.sh
```
+
2. Install conda using installer bash script:
_Follow the prompts on the installer screens_
```shell
-bash Miniconda3-latest-Linux-x86_64.sh
+bash Miniconda3-latest-MacOSX-x86_64.sh
```
+
3. Remove conda installer:
+```shell
+rm Miniconda3-latest-MacOSX-x86_64.sh
```
-rm Miniconda3-latest-Linux-x86_64.sh
-```
+
4. Restart shell, close and reopen new terminal window
### Snakemake _(prior!)_ ###
+
Install **Snakemake** using Conda package management system
_Follow the prompts on the installer screens_
```shell
@@ -54,29 +58,41 @@ conda install -c bioconda -c conda-forge snakemake
```
### RQCP ###
-Download _or_ clone the **Reads Quality Control Pipeline** project
+
+**Download** _OR_ clone the **Reads Quality Control Pipeline** project
#### Download ####
-1. Download source code archive (_zip_, **tar.gz**, _tar.bz2_, _tar_): [RQCP on GitLab](https://gitlab.com/ird_transvihmi/Reads_Quality_Control_Pipeline)
+- Download source code archive (_zip_, **tar.gz**, _tar.bz2_, _tar_): [RQCP on GitLab](https://gitlab.com/ird_transvihmi/Reads_Quality_Control_Pipeline)
+```shel
+wget https://gitlab.com/ird_transvihmi/Reads_Quality_Control_Pipeline/-/archive/main/Reads_Quality_Control_Pipeline-main.tar.gz -O ~/Desktop/
+```
+
+_alternatively_:
-2. Extract and remove the the archive (i.e. tar.gz):
+- Extract and remove the the archive (i.e. tar.gz):
```shell
-tar -xzvf path/to/archive/Reads_Quality_Control_Pipeline.tar.gz
-rm path/to/archive/Reads_Quality_Control_Pipeline.tar.gz
+tar -xzvf path/to/archive/Reads_Quality_Control_Pipeline-main.tar.gz
+rm path/to/archive/Reads_Quality_Control_Pipeline-main.tar.gz
+mv ~/Desktop/Reads_Quality_Control_Pipeline-main ~/Desktop/Reads_Quality_Control_Pipeline
+cd ~/Desktop/Reads_Quality_Control_Pipeline
```
#### Clone ####
-Clone with **SSH** when you want to authenticate only one time
+
+- Clone with **SSH** when you want to authenticate only one time
Authenticate with GitLab by following the instructions in the [SSH documentation](https://docs.gitlab.com/ee/ssh/index.html)
```shell
-git clone git@gitlab.com:ird_transvihmi/Reads_Quality_Control_Pipeline.git path/to/workdir/
+git clone git@gitlab.com:ird_transvihmi/Reads_Quality_Control_Pipeline.git
+
+cd Reads_Quality_Control_Pipeline
```
Clone with **HTTPS** when you want to authenticate each time you perform an operation between your computer and GitLab
```shell
-git clone https://gitlab.com/ird_transvihmi/Reads_Quality_Control_Pipeline.git path/to/workdir/
+git clone https://gitlab.com/ird_transvihmi/Reads_Quality_Control_Pipeline.git
+cd Reads_Quality_Control_Pipeline
```
#### Difference between download and clone ####
@@ -191,8 +207,8 @@ You can also ask for new databases, for genomes references not yet included, to
5. Call me to `+33.(0)4.67.41.55.xx` (No don't please _O\_o_!)
## Roadmap ##
-Finish documentation about "terminal" and "results"
Add a wiki !
+Finish documentation about "terminal" and "results"
Add new features
## Contributing ##
diff --git a/config/config.yaml b/config/config.yaml
index fa3036426e43740606475eea2edaf62f687589ff..3439dc259110e4fe30f99ce659c3d80adc9ebb17 100644
--- a/config/config.yaml
+++ b/config/config.yaml
@@ -34,11 +34,11 @@ datasets:
#- 'sickle-trim_single-end'
#- 'fastq-join_single-end'
#- 'fastq-join_paired-end'
- #- 'all_merged'
+ #- 'all_merged_single-end'
## CUTADAPT ------------------------------------------------------------------------------------------
cutadapt:
- length: '75' # Discard reads shorter than length, after trim
+ length: '35' # Discard reads shorter than length, after trim
kits: # Sequence of an adapter ligated to the 3' end of the first read
truseq: 'AGATCGGAAGAGC' # Illumina TruSeq / ScriptSeq based kits libraries
nextera: 'CTGTCTCTTATACACATC' # Illumina Nextera / TruSight based kits libraries
@@ -59,17 +59,17 @@ sickle-trim:
#- 'illumina' # if illumina (CASAVA 1.3 to 1.7)
#- 'solexa' # if solexa (CASAVA < 1.3)
quality: '30' # phred score limit
- length: '75' # read length limit, after trim
+ length: '35' # read length limit, after trim
## FASTQ-JOIN ----------------------------------------------------------------------------------------
fastq-join:
- percent: '5' # N-percent maximum difference (default: 8)
- overlap: '25' # N-minimum overlap (default: 6)
+ percent: '8' # N-percent maximum difference (default: 8)
+ overlap: '6' # N-minimum overlap (default: 6)
## FASTQSCREEN ---------------------------------------------------------------------------------------
fastq-screen:
config: 'config/fastq-screen.conf' # path to the fastq-screen configuration file
- subset: '1000' # Don't use the whole sequence file, but create a temporary dataset of this specified number of read (default: '100000', set '0' for all dataset)
+ subset: '10000' # Don't use the whole sequence file, but create a temporary dataset of this specified number of read (default: '100000', set '0' for all dataset)
aligner:
- 'bwa' # Burrows-Wheeler Aligner, for mapping low-divergent sequences against a large reference genome
#- 'bowtie' # Bowtie, an ultrafast, memory-efficient short read aligner
diff --git a/config/fastq-screen.conf b/config/fastq-screen.conf
index 7cff70c5395d170567a97ff44d56faa57e7ec102..2a6f366e17f9269f7fb3122ed18b7ef4a0266c50 100644
--- a/config/fastq-screen.conf
+++ b/config/fastq-screen.conf
@@ -48,15 +48,15 @@ THREADS 1
##
##----------
## Human h38
-DATABASE Human resources/databases/bwa/Human/Homo_sapiens_h38
+#DATABASE Human resources/databases/bwa/Human/Homo_sapiens_h38
#DATABASE Human resources/databases/bowtie2/Human/Homo_sapiens_h38
##
## Mouse m39
-DATABASE Mouse resources/databases/bwa/Mouse/Mus_musculus_m39
+#DATABASE Mouse resources/databases/bwa/Mouse/Mus_musculus_m39
#DATABASE Mouse resources/databases/bowtie2/Mouse/Mus_musculus_m39
##
## Arabidopsis thaliana - sequence from NCBI: ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/001/735/GCF_000001735.3_TAIR10/GCF_000001735.3_TAIR10_genomic.fna.gz
-DATABASE Arabidopsis resources/databases/bwa/Arabidopsis/Arabidopsis_thaliana_t10
+#DATABASE Arabidopsis resources/databases/bwa/Arabidopsis/Arabidopsis_thaliana_t10
#DATABASE Arabidopsis resources/databases/bowtie2/Arabidopsis/Arabidopsis_thaliana_t10
##
## Ecoli - sequence available from EMBL accession U00096.2
@@ -78,15 +78,15 @@ DATABASE Vectors resources/databases/bwa/Vectors/UniVec_wo_phi-X174
##
##-----------
## Gorilla g4
-DATABASE Gorilla resources/databases/bwa/Gorilla/Gorilla_gorilla_g4
+#DATABASE Gorilla resources/databases/bwa/Gorilla/Gorilla_gorilla_g4
#DATABASE Gorilla resources/databases/bowtie2/Gorilla/Gorilla_gorilla_g4
##
## Chimpanzee
-DATABASE Chimpanzee resources/databases/bwa/Chimpanzee/Pan_troglodytes_t3
+#DATABASE Chimpanzee resources/databases/bwa/Chimpanzee/Pan_troglodytes_t3
#DATABASE Chimpanzee resources/databases/bowtie2/Chimpanzee/Pan_troglodytes_t3
##
## Bat 10
-DATABASE Bat resources/databases/bwa/Bat/Pteropus_vampyrus_v1
+#DATABASE Bat resources/databases/bwa/Bat/Pteropus_vampyrus_v1
#DATABASE Bat resources/databases/bowtie2/Bat/Pteropus_vampyrus_v1
##
## HIV - HXB2