add in fastq screen config to docker

docker/NGS_QC/Dockerfile

@@ -4,4 +4,5 @@ RUN conda config --add channels conda-forge
 RUN conda create -n ngsqc kraken2 kaiju fastp fastqc multiqc
 # context dir needs to be repo root
 ADD NGS_QC/docker/ep.sh /ep.sh
+ADD NGS_QC/docker/fastq_screen.conf /etc/fastq_screen.conf
 ENTRYPOINT [ "/ep.sh" ]

docker/NGS_QC/fastq_screen.conf

@@ -0,0 +1,113 @@
+# This is a configuration file for fastq_screen
+############
+## Threads #
+############
+## Bowtie can be made to run across multiple CPU cores to
+## speed up your searches. Set this value to the number
+## of cores you want to use for your searches.
+THREADS		24
+
+##############
+## Databases #
+##############
+## This section allows you to configure multiple databases
+## to search against in your screen.  For each database
+## you need to provide a database name (which can't contain
+## spaces) and the location of the bowtie indices which 
+## you created for that database.
+## 
+## The default entries shown below are only suggested examples
+## you can add as many DATABASE sections as you like, and you
+## can comment out or remove as many of the existing entries
+## as you like.
+
+
+
+#########
+## Human - sequences available from
+## ftp://ftp.ensembl.org/pub/current/fasta/homo_sapiens/dna/
+DATABASE	Human	/fdb/fastq_screen/FastQ_Screen_Genomes/Human/Homo_sapiens.GRCh38
+
+
+
+#########
+## Mouse - sequence available from
+## ftp://ftp.ensembl.org/pub/current/fasta/mus_musculus/dna/
+DATABASE	Mouse	/fdb/fastq_screen/FastQ_Screen_Genomes/Mouse/Mus_musculus.GRCm38
+
+
+
+#########
+## Rat - sequence available from
+## ftp://ftp.ensembl.org/pub/current/fasta/rattus_norvegicus/dna/
+DATABASE	Rat	/fdb/fastq_screen/FastQ_Screen_Genomes/Rat/Rnor_6.0 
+
+
+
+############
+# Drosophila
+DATABASE	Drosophila	/fdb/fastq_screen/FastQ_Screen_Genomes/Drosophila/BDGP6
+
+
+
+#########
+## Worm
+DATABASE	Worm	/fdb/fastq_screen/FastQ_Screen_Genomes/Worm/Caenorhabditis_elegans.WBcel235
+
+
+
+#########
+## Yeast - sequence available from
+## ftp://ftp.ensembl.org/pub/current/fasta/saccharomyces_cerevisiae/dna/
+DATABASE	Yeast	/fdb/fastq_screen/FastQ_Screen_Genomes/Yeast/Saccharomyces_cerevisiae.R64-1-1
+
+
+
+#########
+## Arabidopsis - sequences available from 
+DATABASE	Arabidopsis	     /fdb/fastq_screen/FastQ_Screen_Genomes/Arabidopsis/Arabidopsis_thaliana.TAIR10
+
+
+
+#########
+## Ecoli
+## Sequence available from EMBL accession U00096.2
+DATABASE	Ecoli	/fdb/fastq_screen/FastQ_Screen_Genomes/E_coli/Ecoli
+
+
+
+##########
+##rRNA - In house custom database
+DATABASE rRNA /fdb/fastq_screen/FastQ_Screen_Genomes/rRNA/GRCm38_rRNA 
+
+
+
+##############
+# Mitochondria
+DATABASE	MT	/fdb/fastq_screen/FastQ_Screen_Genomes/Mitochondria/mitochondria
+
+
+
+########
+## PhiX - sequence available from Refseq accession NC_001422.1
+DATABASE	PhiX	     /fdb/fastq_screen/FastQ_Screen_Genomes/PhiX/phi_plus_SNPs
+
+
+
+##############
+# Lambda
+DATABASE Lambda	/fdb/fastq_screen/FastQ_Screen_Genomes/Lambda/Lambda
+
+
+
+##########
+## Vector - Sequence taken from the UniVec database
+## http://www.ncbi.nlm.nih.gov/VecScreen/UniVec.html
+DATABASE	Vectors	/fdb/fastq_screen/FastQ_Screen_Genomes/Vectors/Vectors
+
+
+
+############
+## Adapters - sequence derived from the FastQC contaminats file
+## www.bioinformatics.bbsrc.ac.uk/projects/fastqc/
+DATABASE	Adapters	/fdb/fastq_screen/FastQ_Screen_Genomes/Adapters/Contaminants