Versions Compared

Version Old Version 1 New Version Current
Changes made by

Gregg Randolph

Gregg Randolph

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

GTLCON

Assign taxonomy

Code Block
cd /project/microbiome/data/seq/cu_29april22novaseq5/otu/16S/GTLCON/
salloc --account=microbiome -t 0-08:00 --mem=500G

module load swset/2018.05  
module load 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 /project/microbiome/data_queue/seq/GtlAnalyses/GTLCON_16S_NS5.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 631 of 631 sequences (100.00%)

Convert into useful form:

 

Code Block
cd /project/microbiome/data_queue/seq/GtlAnalyses/
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] }' GTLCON_16S_NS5.sintax > GTLCON_16S_NS5taxonomy.csv

AIR21 

Assign taxonomy

Code Block
cd /project/microbiome/data/seq/cu_29april22novaseq5/otu/16S/AIR21

vsearch --sintax zotus.fa --db /project/microbiome/users/grandol1/ref_db/gg_16s_13.5.fa -tabbedout /project/microbiome/data_queue/seq/GtlAnalyses/AIR21_16S_NS5.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 631 of 631 sequences (100.00%)

Convert into useful form:

 

Code Block
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] }' AIR21_16S_NS5.sintax > AIR21_16S_NS5taxonomy.csv

 

ARG20

Assign taxonomy

Code Block
cd /project/microbiome/data/seq/cu_29april22novaseq5/otu/16S/ARG20

vsearch --sintax zotus.fa --db /project/microbiome/users/grandol1/ref_db/gg_16s_13.5.fa -tabbedout /project/microbiome/data_queue/seq/GtlAnalyses/ARG20_16S_NS5.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 631 of 631 sequences (100.00%)

Convert into useful form:

 

Code Block
cd /project/microbiome/data_queue/seq/GtlAnalyses/
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] }' ARG20_16S_NS5.sintax > ARG20_16S_NS5taxonomy.csv

 

BSAGE21

Assign taxonomy

Code Block
cd /project/microbiome/data/seq/cu_29april22novaseq5/otu/16S/BSAGE21

vsearch --sintax zotus.fa --db /project/microbiome/users/grandol1/ref_db/gg_16s_13.5.fa -tabbedout /project/microbiome/data_queue/seq/GtlAnalyses/BSAGE21_16S_NS5.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 631 of 631 sequences (100.00%)

Convert into useful form:

 

Code Block
cd /project/microbiome/data_queue/seq/GtlAnalyses/
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] }' BSAGE21_16S_NS5.sintax > BSAGE21_16S_NS5taxonomy.csv

 

DRAG21

Assign taxonomy

Code Block
cd /project/microbiome/data/seq/cu_29april22novaseq5/otu/16S/DRAG21

vsearch --sintax zotus.fa --db /project/microbiome/users/grandol1/ref_db/gg_16s_13.5.fa -tabbedout /project/microbiome/data_queue/seq/GtlAnalyses/DRAG21_16S_NS5.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 631 of 631 sequences (100.00%)

Convert into useful form:

 

Code Block
cd /project/microbiome/data_queue/seq/GtlAnalyses/
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] }' DRAG21_16S_NS5.sintax > DRAG21_16S_NS5taxonomy.csv

LIBB19

Assign taxonomy

Code Block
cd /project/microbiome/data/seq/cu_29april22novaseq5/otu/16S/LIBB19

vsearch --sintax zotus.fa --db /project/microbiome/users/grandol1/ref_db/gg_16s_13.5.fa -tabbedout /project/microbiome/data_queue/seq/GtlAnalyses/LIBB19_16S_NS5.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 631 of 631 sequences (100.00%)

Convert into useful form:

 

Code Block
cd /project/microbiome/data_queue/seq/GtlAnalyses/
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] }' LIBB19_16S_NS5.sintax > LIBB19_16S_NS5taxonomy.csv

MAWC21

Assign taxonomy

Code Block
cd /project/microbiome/data/seq/cu_29april22novaseq5/otu/16S/MAWC21

vsearch --sintax zotus.fa --db /project/microbiome/users/grandol1/ref_db/gg_16s_13.5.fa -tabbedout /project/microbiome/data_queue/seq/GtlAnalyses/MAWC21_16S_NS5.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 631 of 631 sequences (100.00%)

Convert into useful form:

 

Code Block
cd /project/microbiome/data_queue/seq/GtlAnalyses/
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] }' MAWC21_16S_NS5.sintax > MAWC21_16S_NS5taxonomy.csv

MULFIRE22

Assign taxonomy

Code Block
cd /project/microbiome/data/seq/cu_29april22novaseq5/otu/16S/MULFIRE22

vsearch --sintax zotus.fa --db /project/microbiome/users/grandol1/ref_db/gg_16s_13.5.fa -tabbedout /project/microbiome/data_queue/seq/GtlAnalyses/MULFIRE22_16S_NS5.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 631 of 631 sequences (100.00%)

Convert into useful form:

 

Code Block
cd /project/microbiome/data_queue/seq/GtlAnalyses/
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] }' MULFIRE22_16S_NS5.sintax > MULFIRE22_16S_NS5taxonomy.csv

OUTLVD

Assign taxonomy

Code Block
cd /project/microbiome/data/seq/cu_29april22novaseq5/otu/16S/OUTLVD

vsearch --sintax zotus.fa --db /project/microbiome/users/grandol1/ref_db/gg_16s_13.5.fa -tabbedout /project/microbiome/data_queue/seq/GtlAnalyses/OUTLVD_16S_NS5.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 631 of 631 sequences (100.00%)

Convert into useful form:

 

Code Block
cd /project/microbiome/data_queue/seq/GtlAnalyses/
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] }' OUTLVD_16S_NS5.sintax > OUTLVD_16S_NS5taxonomy.csv

SM19FIRE

Assign taxonomy

Code Block
cd /project/microbiome/data/seq/cu_29april22novaseq5/otu/16S/SM19FIRE

vsearch --sintax zotus.fa --db /project/microbiome/users/grandol1/ref_db/gg_16s_13.5.fa -tabbedout /project/microbiome/data_queue/seq/GtlAnalyses/SM19FIRE_16S_NS5.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 631 of 631 sequences (100.00%)

Convert into useful form:

 

Code Block
cd /project/microbiome/data_queue/seq/GtlAnalyses/
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] }' SM19FIRE_16S_NS5.sintax > SM19FIRE_16S_NS5taxonomy.csv

SM19HILL

Assign taxonomy

Code Block
cd /project/microbiome/data/seq/cu_29april22novaseq5/otu/16S/SM19HILL

vsearch --sintax zotus.fa --db /project/microbiome/users/grandol1/ref_db/gg_16s_13.5.fa -tabbedout /project/microbiome/data_queue/seq/GtlAnalyses/SM19HILL_16S_NS5.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 631 of 631 sequences (100.00%)

Convert into useful form:

 

Code Block
cd /project/microbiome/data_queue/seq/GtlAnalyses/
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] }' SM19HILL_16S_NS5.sintax > SM19HILL_16S_NS5taxonomy.csv