Skip to end of metadata
Go to start of metadata

You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 6 Next »

/project/microbiome/data_queue/seq/LowReadII/rawdata

salloc --account=microbiome -t 0-06:00

mkdir -p /gscratch/grandol1/LowReadII/rawdata

cd /gscratch/grandol1/LowReadII/rawdata

unpigz --to-stdout /project/microbiome/data_queue/seq/LowReadII/rawdata/Low-Read-II_S1_L001_R1_001.fastq | split -l 1000000 -d --suffix-length=3 --additional-suffix=.fastq - LowReadII_R1_ ;unpigz --to-stdout /project/microbiome/data_queue/seq/LowReadII/rawdata/Low-Read-II_S1_L001_R2_001.fastq | split -l 1000000 -d --suffix-length=3 --additional-suffix=.fastq - LowReadII_R2_

//project/microbiome/data_queue/seq/LowReadII/rawdata/run_parse_count_onSplitInput.pl

cd /project/microbiome/data_queue/seq/LowReadII/rawdata

./run_splitFastq_fwd.sh

./run_splitFastq_rev.sh

./run_aggregate.sh

cd /project/microbiome/data_queue/seq/LowReadII/tfmergedreads

./run_slurm_mergereads.pl

cd /project/microbiome/data_queue/seq/LowReadII/otu

./run_slurm_mkotu.pl

vsearch -sintax OTUFILE -db REFERENCEDATABASE -tabbedout OUTPUT -sintax_cutoff 0.8 -strand both -threads 32

Assign taxonomy

salloc --account=microbiome -t 0-02:00 --mem=500G

module load swset/2018.05  gcc/7.3.0

module load vsearch/2.15.1

vsearch --sintax zotus.fa --db /project/microbiome/users/grandol1/ref_db/gg_16s_13.5.fa -tabbedout LRII.sintax -sintax_cutoff 0.8

Output:

Reading file /project/microbiome/users/grandol1/ref_db/gg_16s_13.5.fa 100%  

1769520677 nt in 1262986 seqs, min 1111, max 2368, avg 1401

Counting k-mers 100% 

Creating k-mer index 100% 

Classifying sequences 100%   

Classified 4038 of 4042 sequences (99.90%)

Convert into useful form:

awk -F "\t" '{OFS=","} NR==1 {print "OTU_ID","SEQS","SIZE","DOMAIN","KINGDOM","PHYLUM","CLASS","ORDER","FAMILY","GENUS","SPECIES"} {gsub(";", ","); gsub("centroid=", ""); gsub("seqs=", ""); gsub("size=", ""); match($4, /d:[^,]+/, d); match($4, /k:[^,]+/, k); match($4, /p:[^,]+/, p); match($4, /c:[^,]+/, c); match($4, /o:[^,]+/, o); match($4, /f:[^,]+/, f); match($4, /g:[^,]+/, g); match($4, /s:[^,]+/, s); print $1, d[0]=="" ? "NA" : d[0], k[0]=="" ? "NA" : k[0], p[0]=="" ? "NA" : p[0], c[0]=="" ? "NA" : c[0], o[0]=="" ? "NA" : o[0], f[0]=="" ? "NA" : f[0], g[0]=="" ? "NA" : g[0], s[0]=="" ? "NA" : s[0] }' LRII.sintax > LRIItaxonomy.csv

  • No labels