manifest <- readr::read_table(
"/media/hutianlong/b8986a7a-0c13-db4b-81c7-7b26cebbb183/16s_deblur_type6/16s-manifest.tsv",
col_names = TRUE)
manifest
setwd("/media/hutianlong/b8986a7a-0c13-db4b-81c7-7b26cebbb183/16s_deblur_type6")
for (i in 1:nrow(manifest)){
comstr1 <- paste("vsearch --fastq_mergepairs ",
manifest[i,2],
" --reverse ",
manifest[i,3],
" --fastqout ",
manifest[i,1],
".fq ",
" --relabel ",
manifest[i,1],
".",
sep="")
#comstr2 <- paste("gzip ",manifest[i,1],".fq",sep="")
print(comstr1)
system(comstr1)
#print(comstr2)
#system(comstr2)
}
mkdir ./2_merged
mv *.fq ./2_merged
cat ./2_merged/*.fq >> ./all.fq
My sequences look like following:
GTGYCAGCMGCCGCGGTAAmysequenceAAACTCAAAKRAATTGACGGCC
GGCCGYCAATTYMTTTRAGTTTmysequenceTTACCGCGGCKGCTGRCAC
cutadapt -a TTACCGCGGCKGCTGRCAC \
-a AAACTCAAAKRAATTGACGGCC \
-g GGCCGYCAATTYMTTTRAGTTT \
-g GTGYCAGCMGCCGCGGTAA \
-o all_trimmed2.fq \
-j 10 \
all_trimmed.fq
vsearch --fastx_filter ./all_trimmed.fq \
--fastq_maxee_rate 0.01 \
--fastaout ./filtered.fa
vsearch --derep_fulllength ./filtered.fa \
--sizeout --minuniquesize 2 \
--output ./uniques.fa
vsearch --cluster_unoise uniques.fa \
--centroids zotus.fa \
--uc uc_zotus.uc \
--log unoise_log.txt \
--threads 14
vsearch --uchime3_denovo zotus.fa \
--nonchimeras zotus_nochime.fa \
--fasta_width 0 \
--relabel zotu \
--xsize \
--log unchime3_log.txt
vsearch --usearch_global filtered.fa \
--db zotus_nochime.fa \
--id 0.97 \
--otutabout unoise3_zotu_table.txt \
--biomout unoise3_zotu_table.biom \
--threads 14 \
--log otutab_log.txt