updated for new 75B sample analysis

Author: dacb

12.persistent_otus

@@ -15,7 +15,7 @@ EOF
 
 #head -1 $IN | awk '{ for (i = 2; i <= NF; ++i) print $i }' | sort -n | awk '{ printf("\t\t%s,\n", $1); }' >> $SQL
 #awk -F'\t' -v otu_table="$otu_table" '{ if (line >= 1) { printf("\t\tROUND((%s / (SELECT SUM(%s) FROM %s)) * 100, 2) AS \"%s.%s\",\n", $1, $1, otu_table, $2, $3); } ++line; }' $SAMPLE_INFO_SUBSET >> $SQL
-awk -F'\t' -v otu_table="$otu_table" '{ if (line >= 1) { printf("\t\t%s\",\n", $1); } ++line; }' $SAMPLE_INFO_SUBSET >> $SQL
+awk -F'\t' -v otu_table="$otu_table" '{ if (line >= 1) { printf("\t\t%s,\n", $1); } ++line; }' $SAMPLE_INFO_SUBSET >> $SQL
 
 cat << EOF >> $SQL
 		sequence

13.figures.R

@@ -10,7 +10,7 @@ library(RColorBrewer)
 library(ggplot2)
 #library(reshape)
 
-columns_to_use <- 29
+columns_to_use <- 30
 
 pdf("./13.figures.heatmap.pdf")
 

14.diversity

@@ -0,0 +1,5 @@
+#!/bin/bash
+
+source globals
+
+R --no-save < $0.R

14.diversity.R

@@ -0,0 +1,34 @@
+library(vegan)
+#source("http://www.jennajacobs.org/R/rarefaction.txt")
+source("rarefaction.txt")
+
+columns_to_use <- 29
+
+d <- read.table("variableO2_illumina_analyses.xls", header=T, row.names=1, sep="\t")
+
+raw_otus <- d[,1:columns_to_use]
+
+dmat <- t(raw_otus)
+
+H <- diversity(dmat)
+
+write.table(H, file="14.Shannon_Weaver.alpha.tab", quote=F, sep="\t")
+
+z <- betadiver(dmat, "z")
+
+print(z)
+
+#write.table(z, file="14.beta.tab", quote=F, sep="\t")
+
+rf <- rarefy(dmat, min(rowSums(dmat)))
+
+print(rf)
+
+pdf("14.rarefaction.pdf")
+rfc <- rarefaction(dmat)
+
+rfc$richness
+rfc$SE
+rfc$subsample
+
+write.table(rfc$richness, file="14.richness.tab", quote=F, sep="\t")

EXECUTE

@@ -1,6 +1,6 @@
 #!/bin/bash
 
-JOBS="0.setup 1.quality_filter 2.dereplication 3.abundance_sort 4.cluster 5.chimera 6.number_otus 7.map 8.make_table 9.classify 10.database 11.join_to_RDP_class 12.persistent_otus 13.figures"
+JOBS="0.setup 1.quality_filter 2.dereplication 3.abundance_sort 4.cluster 5.chimera 6.number_otus 7.map 8.make_table 9.classify 10.database 11.join_to_RDP_class 12.persistent_otus 13.figures 14.diversity"
 
 update_dependent=0
 

data/082214MC27Fillumina-mapping2.txt

@@ -12,5 +12,5 @@ O2_5A_15	CGTGAGAC	AGRGTTTGATCMTGGCTCAG	Ill27Fbar13	082214MC27Fillumina	O2_5A_15
 O2_5B_15	CGTGATAA	AGRGTTTGATCMTGGCTCAG	Ill27Fbar14	082214MC27Fillumina	O2_5B_15
 O2_5C_15	CGTGGGAC	AGRGTTTGATCMTGGCTCAG	Ill27Fbar15	082214MC27Fillumina	O2_5C_15
 O2_75A_15	CGTAACCA	AGRGTTTGATCMTGGCTCAG	Ill27Fbar1	082214MC27Fillumina	O2_75A_15
-O2_75B_15	CGTAAGAA	AGRGTTTGATCMTGGCTCAG	Ill27Fbar2	082214MC27Fillumina	O2_75B_15
+O2_75B_15_ignore	CGTAAGAA	AGRGTTTGATCMTGGCTCAG	Ill27Fbar2	082214MC27Fillumina	O2_75B_15_ignore
 O2_75C_15	CGTACCCA	AGRGTTTGATCMTGGCTCAG	Ill27Fbar3	082214MC27Fillumina	O2_75C_15

globals

@@ -13,12 +13,12 @@ CLFRJAR=$RDPT/classifier.jar
 HOST=`mysql_host`
 DB=variableO2_illumina_analyses
 
-RUNS="082214MC27Fillumina 070314MC27Fillumina"
+RUNS="082214MC27Fillumina 070314MC27Fillumina 100814MC27Fillumina"
 PRIMER=AGRGTTTGATCMTGGCTCAG
 
 TRUNCLEN=492
 MAXEE=0.5
-CLUSTER_IDENT=0.97
+CLUSTER_IDENT=0.95
 
 SAMPLE_INFO=sample_info.xls
 SAMPLE_INFO_SUBSET=sample_info.subset.xls

sample_info.subset.xls

@@ -27,4 +27,5 @@ O2_5A_15	5A	15
 O2_5B_15	5B	15
 O2_5C_15	5C	15
 O2_75A_15	75A	15
+O2_75B_15	75B	15
 O2_75C_15	75C	15