diff --git a/READ_THIS b/READ_THIS new file mode 100644 index 0000000000000000000000000000000000000000..5f3a34a5941e231403eb410cd6012a9fb90af9db --- /dev/null +++ b/READ_THIS @@ -0,0 +1 @@ +There are a number of useful scripts on /projet/genosol/work/script on the migale server. I chmod 777 the access to all of my files . diff --git a/bwa b/bwa new file mode 100644 index 0000000000000000000000000000000000000000..110d827188a17cf4551d52ce84cb5af4ffe506f1 --- /dev/null +++ b/bwa @@ -0,0 +1,11 @@ +conda activate bwa-0.7.17 + +bwa index -a bwtsw solca_95p200bp.fasta +bwa aln -t 8 [SCAFFOLD.fasta] R1.gz | awk '{if($3!="*"){print $0}}' > OUT1.sai +bwa aln -t 8 [SCAFFOLD.fasta] R2.gz| awk '{if($3!="*"){print $0}}' > OUT2.sai +bwa sampe [SCAFFOLD.fasta] OUT1.sai OUT2.sai R1.gz R2.gz > OUT.sam +samtools view -F 4 -Sb OUT.sam | samtools sort > OUT.bam +samtools depth OUT.bam > temp.depthmore +samtools idxstats OUT.bam > reads_per_scaffold.txt + +conda deactivate diff --git a/kaiju b/kaiju new file mode 100644 index 0000000000000000000000000000000000000000..9a7095da2007b3e5e4bf674f2612811605181ff2 --- /dev/null +++ b/kaiju @@ -0,0 +1,12 @@ +conda activate kaiju-1.7.3 +##for multiple files +conda activate kaiju-1.7.2 +for i in {1..10} +do +kaiju -i *"$i"*R1*.fastq.gz -j *"$i"*R2*.fastq.gz -t /db/outils/kaiju-1.7.0/nr/nodes.dmp -f /db/outils/kaiju-1.7.0/nr/kaiju_db_nr.fmi -z 6 -o fraggenescan_"$i"_kaijuNR + +#add Taxon names +addTaxonNames -t /db/outils/kaiju-1.7.0/nr/nodes.dmp -n /db/outils/kaiju-1.7.0/nr/names.dmp -i fraggenescan_"$i"_kaijuNR -r superkingdom,genus,species -o kaiju_"$i"_names.out +kaijuReport -t /db/outils/kaiju-1.7.0/nr/nodes.dmp -n /db/outils/kaiju-1.7.0/nr/names.dmp -i fraggenescan_"$i"_kaijuNR -l superkingdom,phylum,class,family,genus -r genus -o kaiju.out.summary_"$i"_3.txt +kaijuReport -t /db/outils/kaiju-1.7.0/nr/nodes.dmp -n /db/outils/kaiju-1.7.0/nr/names.dmp -i fraggenescan.kaijuNR -p -r genus -o kaiju.out.summary_"$i"_4.txt +done diff --git a/mapping.sh b/mapping.sh new file mode 100644 index 0000000000000000000000000000000000000000..65272e73664d0806fb507a39de034f71b5d5affe --- /dev/null +++ b/mapping.sh @@ -0,0 +1,18 @@ + + +mkdir mapXXb1meg +cd mapXXb1meg/ +cp ../solcab1_95id200bp.fasta solcab1_95id200bp.fasta +bwa index -a bwtsw solcab1_95id200bp.fasta +bwa aln -t 8 solcab1_95id200bp.fasta ../*XX*R1*.fastq.gz | awk '{if($3!="*"){print $0}}' > OUT1.sai +bwa aln -t 8 solcab1_95id200bp.fasta ../*XX*R2*.fastq.gz | awk '{if($3!="*"){print $0}}' > OUT2.sai +bwa sampe solcab1_95id200bp.fasta OUT1.sai OUT2.sai ../*XX*R1*.fastq.gz ../*XX*R2*.fastq.gz > OUT.sam +samtools view -F 4 -Sb OUT.sam | samtools sort > OUT.bam +samtools depth OUT.bam > temp.depthmore +samtools idxstats OUT.bam > reads_per_scaffoldXXb1meg.txt +#Use for Tablet view +samtools view -F 4 -bS OUT.sam -t solcab1_95id200bp.fasta | samtools sort > OUT_tablet.bam +samtools sort OUT_tablet.bam -o sorted.bam +samtools index sorted.bam + +rm -fr OUT1.sai OUT2.sai OUT.sam OUT.bam temp.depthmore diff --git a/megahit_metaG b/megahit_metaG new file mode 100644 index 0000000000000000000000000000000000000000..be341e74cbbcf83f4f81023dcf4d97c2d7f8b045 --- /dev/null +++ b/megahit_metaG @@ -0,0 +1,4 @@ +conda activate megahit-1.2.9 +##Yes, its that simple +megahit -1 R1.fastq.gz -2 R2.fastq.gz -o [OUTPUT] +conda deactivate diff --git a/mget_mput b/mget_mput new file mode 100644 index 0000000000000000000000000000000000000000..5a508df5dc82aadb3791e36b1cf338a8238157b1 --- /dev/null +++ b/mget_mput @@ -0,0 +1,15 @@ +sftp username@server << EOT +#example +cd /backup/SOLCA/mRNA +mput RNA*-mRNA* +bye +EOT + + + +sftp username@server << EOT +#example +cd /backup/SOLCA/mRNA +mget *67*split* +bye +EOT diff --git a/simka b/simka new file mode 100644 index 0000000000000000000000000000000000000000..a63dc576f4247923f6c8b6a5c854be3b125e75eb --- /dev/null +++ b/simka @@ -0,0 +1,20 @@ +# creates liste of the samples. +ls *subset* > temp +#creates right format for SIMKA +awk -v var=$(pwd) '{print "id"NR": "var"/"$0}' temp > liste +conda activate simka-1.5.2 +### Kmersize can be optimized for the sample, default is 21, tmp files can be kept, but is not necessary. +[location]/bin/simka -in [liste] -out simka_out -out-tmp simka_temp -keep-tmp -kmer-size 30 -nb-cores 4 -max-reads [number] + +### R script to make figure +### REMOVE FIRST ; IN CSV FILES!!!! +a<-as.matrix(read.table("file.csv",sep=";",header=T)) +#list +rownames(a)<- c("samplename1","samplename2") +colnames(a)<- c("samplename1","samplename2") +#plot +heatmap(a,trace="none", Rowv=F) +#print plot +pdf("name.pdf", width=15, height=15) +heatmap(a,trace="none", Rowv=F) +dev.off() diff --git a/sortmerna b/sortmerna new file mode 100644 index 0000000000000000000000000000000000000000..0dada9b113ecf814c037f70f2d7a12e98d91ec9f --- /dev/null +++ b/sortmerna @@ -0,0 +1,9 @@ +###in case of conda enviroment. Check version when first using the software (conda info --envs | grep [NAME SOFTWARE]) +conda activate sortmerna-4.2.0 + +###Check location databes if migale is not used +sortmerna -threads 8 -v --reads [FASTQ OR .GZ] --paired_in --aligned FILE_NAME.extendedFrags-rRNA --other FILE_NAME.extendedFrags-mRNA --fastx --ref/usr/local/genome/src/sortmerna-2.0/rRNA_databases/rfam-5s-database-id98.fasta,/projet/mig/work/orue/SORTMERNA_index/index/rfam-5s:/usr/local/genome/src/sortmerna-2.0/rRNA_databases/rfam-5.8s-database-id98.fasta,/projet/mig/work/orue/SORTMERNA_index/index/rfam-5.8s:/usr/local/genome/src/sortmerna-2.0/rRNA_databases/silva-arc-16s-id95.fasta,/projet/mig/work/orue/SORTMERNA_index/index/silva-arc-16s-id95:/usr/local/genome/src/sortmerna-2.0/rRNA_databases/silva-arc-23s-id98.fasta,/projet/mig/work/orue/SORTMERNA_index/index/silva-arc-23s-id98:/usr/local/genome/src/sortmerna-2.0/rRNA_databases/silva-bac-16s-id90.fasta,/projet/mig/work/orue/SORTMERNA_index/index/silva-bac-16s-id90:/usr/local/genome/src/sortmerna-2.0/rRNA_databases/silva-bac-23s-id98.fasta,/projet/mig/work/orue/SORTMERNA_index/index/silva-bac-23s-id98:/usr/local/genome/src/sortmerna-2.0/rRNA_databases/silva-euk-18s-id95.fasta,/projet/mig/work/orue/SORTMERNA_index/index/silva-euk-18s-id95:/usr/local/genome/src/sortmerna-2.0/rRNA_databases/silva-euk-28s-id98.fasta,/projet/mig/work/orue/SORTMERNA_index/index/silva-euk-28s-id98 + +conda deactivate + +