scripts/metaSpades_command.txt
Version 1

_p_RNAinVAL/_I_03_Omics/_S_02_metagenome_resp/_A_07_allReads_meta-assembly/

SEEK ID: https://fairdomhub.org/data_files/4764?version=1

Filename: scripts/metaSpades_command.txt  Download

Format: Plain text document

Size: 2.68 KB

# metaSPAdes v3.13.0 de novo assembly of DNA seq reads from all gut content samples
# @bufo

cd /DATA/markop/CPB_metaSpades
mkdir output
mkdir input

cp /STORK_ngs/NGS_mpe_2018_CPB-gut-metagenome_DNAseq/original_data_pt1/*.fq.gz ./input
cp /STORK_ngs/NGS_mpe_2018_CPB-gut-metagenome_DNAseq/original_data_pt2/*.fq.gz ./input
gunzip ./input/*.gz

#combine all DNA reads into two files
cat ./input/*_1.fq > ./input/CPB_metaDNA_1.fq
cat ./input/*_2.fq > ./input/CPB_metaDNA_2.fq


#used pipeline for cleaning reads suggested here: http://seqanswers.com/forums/showthread.php?p=204724#post204724
#Trim adapters
/DATA/markop/bbmap/bbduk.sh -Xmx230g in=./input/CPB_metaDNA_1.fq in2=./input/CPB_metaDNA_2.fq out=./input/trimmed.fq ktrim=r k=23 mink=11 hdist=1 ref=/DATA/markop/bbmap/resources/adapters.fa tbo tpe maxns=0 trimq=20 qtrim=r maq=12

rm -rf ./input/RI0*.fq
rm -rf ./input/CPB_metaDNA*.fq

#Remove small contaminants
/DATA/markop/bbmap/bbduk.sh -Xmx230g in=./input/trimmed.fq out=./input/filtered.fq k=31 ref=/DATA/markop/bbmap/resources/sequencing_artifacts.fa.gz,/DATA/markop/bbmap/resources/phix174_ill.ref.fa.gz

rm ./input/trimmed.fq

#Error-correct 1
/DATA/markop/bbmap/bbmerge.sh -Xmx230g in=./input/filtered.fq out=./input/ecco.fq ecco mix vstrict adapters=default

#Error-correct 2
#used parameters that were suggested by Brian Bushnell here: http://seqanswers.com/forums/archive/index.php/t-72901.html and https://www.biostars.org/p/225338/
/DATA/markop/bbmap/clumpify.sh -Xmx200g in=./input/ecco.fq out=./input/eccc.fq ecc passes=6 minid=0.98

#Error-correct 3
/DATA/markop/bbmap/tadpole.sh -Xmx200g in=./input/eccc.fq out=./input/ecct.fq ecc

rm ./input/filtered.fq
rm ./input/ecco.fq

#Merge
/DATA/markop/bbmap/bbmerge.sh -Xmx200g in=./input/ecct.fq out=./input/merged.fq outu=./input/unmerged.fq rem k=62 extend2=50 adapters=default

# rm ./input/ecct.fq

#Split unmerged into two files
/DATA/markop/bbmap/reformat.sh in=./input/unmerged.fq out1=./input/unmerged_1.fq out2=./input/unmerged_2.fq overwrite=true

rm ./input/unmerged.fq

#run metaSPAdes
# k 127 gave out-of-mem error code (-6)
python /home/administrator/SPAdes-3.13.0-Linux/bin/spades.py --meta -k 21,41,71,101 -m 230 -t 32 -o output -1 ./input/unmerged_1.fq -2 ./input/unmerged_2.fq -s ./input/merged.fq

# python /home/administrator/SPAdes-3.13.0-Linux/bin/spades.py --continue -o ./output
# I changed the params.txt to omit k-mer assembly 127

#Evaluate
/DATA/markop/bbmap/stats.sh -Xmx200g in=./output/contigs.fasta

#filter contigs
/DATA/markop/bbmap/reformat.sh in=./output/contigs.fasta out=./output/contigs1to5k.fasta minlength=1000 maxlength=5999
/DATA/markop/bbmap/reformat.sh in=./output/contigs.fasta out=./output/contigs5kup.fasta minlength=5000



help Creators and Submitter
Creator
Submitter
Activity

Views: 1148   Downloads: 38

Created: 12th Nov 2021 at 23:07

Last updated: 12th Nov 2021 at 23:07

help Tags
help Attributions

None

Version History

Version 1 (earliest) Created 12th Nov 2021 at 23:07 by Marko Petek

No revision comments

Powered by
(v.1.18.0)