Difference between revisions of "PSEAE CF.2010"

From Marcotte Lab
Jump to: navigation, search
(CEL files)
(Microarray data)
Line 34: Line 34:
 
* [http://www.marcottelab.org/users/taejoon/PSEAE_CF/microarray/Huse2010_GSE21966.eset_mas5.txt.gz MAS5 pre-processing, ExpressSet]
 
* [http://www.marcottelab.org/users/taejoon/PSEAE_CF/microarray/Huse2010_GSE21966.eset_mas5.txt.gz MAS5 pre-processing, ExpressSet]
 
* [http://www.marcottelab.org/users/taejoon/PSEAE_CF/microarray/Huse2010_GSE21966.calls_mas5.txt.gz MAS5 pre-processing, P/M/A calls]
 
* [http://www.marcottelab.org/users/taejoon/PSEAE_CF/microarray/Huse2010_GSE21966.calls_mas5.txt.gz MAS5 pre-processing, P/M/A calls]
 +
 +
=== Probe mapping to PAO1 ===
 +
A BASH shell script to run exonerate:
 +
<pre>EXONERATE="/home/taejoon/bin64/exonerate"
 +
PROBE_FILE="PSEAE_1.affy_probes.fasta"
 +
 +
GENOME_DIR="/home/taejoon/pkgenome.data/PCAP"
 +
TARGET_NAME="PSEAE_PAO1.NC_002516.fna"
 +
 +
GENOME_FILE="$GENOME_DIR/$TARGET_NAME"
 +
GENOME_MAP_FILE=${PROBE_FILE/%fasta/$TARGET_NAME.exonerate}
 +
echo "$PROBE_FILE vs. $GENOME_FILE"
 +
echo "#PROBE_FILE : $PROBE_FILE" > $GENOME_MAP_FILE
 +
echo "#GENOME_FILE : $GENOME_FILE" >> $GENOME_MAP_FILE
 +
$EXONERATE -m affine:local -Q dna -T dna --showvulgar no --showcigar no --showalignment no \
 +
--ryo "%qi %ti %tS %qab %qae %tab %tae %et %ei %es %em %s %C\n " $PROBE_FILE $GENOME_FILE >> $GENOME_MAP_FILE
 +
 +
TARGET_NAME="PSEAE_PAO1.PCAP20091123.dna.fasta"
 +
CDNA_FILE="$GENOME_DIR/$TARGET_NAME"
 +
CDNA_MAP_FILE=${PROBE_FILE/%fasta/$TARGET_NAME.exonerate}
 +
echo "$PROBE_FILE vs. $CDNA_FILE"
 +
echo "#PROBE_FILE : $PROBE_FILE" > $CDNA_MAP_FILE
 +
echo "#CDNA_FILE : $CDNA_FILE" >> $CDNA_MAP_FILE
 +
$EXONERATE -m affine:local -Q dna -T dna --showvulgar no --showcigar no --showalignment no \
 +
--ryo "%qi %ti %tS %qab %qae %tab %tae %et %ei %es %em %s %C\n " $PROBE_FILE $CDNA_FILE >> $CDNA_MAP_FILE</pre>
 +
 +
* [http://www.marcottelab.org/users/taejoon/PSEAE_CF/microarray/PSEAE_1.affy_probes.PSEAE_PAO1.PCAP20091123.dna.fasta.exonerate.gz Exonerate output against PAO1 transcripts]
 +
* [http://www.marcottelab.org/users/taejoon/PSEAE_CF/microarray/PSEAE_1.affy_probes.PSEAE_PAO1.PCAP20091123.dna.fasta.probeset.gz ProbeSet - PAO1 gene mapping]
 +
* [http://www.marcottelab.org/users/taejoon/PSEAE_CF/microarray/PSEAE_1.affy_probes.PSEAE_PAO1.PCAP20091123.dna.fasta.probeset_log.gz Log for bad probesets]
  
 
=== R script for preprocessing ===
 
=== R script for preprocessing ===
Line 65: Line 94:
 
             file=paste(dataset_name,'.eset_rma.txt',sep=''))</pre>
 
             file=paste(dataset_name,'.eset_rma.txt',sep=''))</pre>
  
=== Probe mapping to PAO1 ===
+
=== R script for ANOSIM test ===
A BASH shell script to run exonerate:
+
<pre>library(vegan)
<pre>EXONERATE="/home/taejoon/bin64/exonerate"
+
tbl <- read.table('Huse2010_GSE21966.gene_mean.txt',header=T,row.names='Gene')
PROBE_FILE="PSEAE_1.affy_probes.fasta"
+
t_tbl <- t(tbl)
  
GENOME_DIR="/home/taejoon/pkgenome.data/PCAP"
+
tbl_dist <-  as.dist(1-cor(as.matrix(tbl),method='spearman'))
TARGET_NAME="PSEAE_PAO1.NC_002516.fna"
+
igroup <- c('A','A','A','A','A','B','B','B','B','B','B','B','Ca','Ca','Cb','Cb','Cb','R','R')
 +
tbl_igroup_anosim <- anosim(tbl_dist,igroup)
  
GENOME_FILE="$GENOME_DIR/$TARGET_NAME"
+
tgroup <- c('E','M','M','M','L','E','M','M','M','L','L','L','E','L','E','M','L','R','R')
GENOME_MAP_FILE=${PROBE_FILE/%fasta/$TARGET_NAME.exonerate}
+
tbl_time_anosim <- anosim(tbl_dist,tgroup)
echo "$PROBE_FILE vs. $GENOME_FILE"
+
echo "#PROBE_FILE : $PROBE_FILE" > $GENOME_MAP_FILE
+
echo "#GENOME_FILE : $GENOME_FILE" >> $GENOME_MAP_FILE
+
$EXONERATE -m affine:local -Q dna -T dna --showvulgar no --showcigar no --showalignment no \
+
--ryo "%qi %ti %tS %qab %qae %tab %tae %et %ei %es %em %s %C\n " $PROBE_FILE $GENOME_FILE >> $GENOME_MAP_FILE
+
  
TARGET_NAME="PSEAE_PAO1.PCAP20091123.dna.fasta"
+
mgroup <- c('C','C','M','D','D','C','C','D','M','M','C','M','C','M','M','D','M','R','R')
CDNA_FILE="$GENOME_DIR/$TARGET_NAME"
+
tbl_morphology_anosim <- anosim(tbl_dist,mgroup)</pre>
CDNA_MAP_FILE=${PROBE_FILE/%fasta/$TARGET_NAME.exonerate}
+
echo "$PROBE_FILE vs. $CDNA_FILE"
+
echo "#PROBE_FILE : $PROBE_FILE" > $CDNA_MAP_FILE
+
echo "#CDNA_FILE : $CDNA_FILE" >> $CDNA_MAP_FILE
+
$EXONERATE -m affine:local -Q dna -T dna --showvulgar no --showcigar no --showalignment no \
+
--ryo "%qi %ti %tS %qab %qae %tab %tae %et %ei %es %em %s %C\n " $PROBE_FILE $CDNA_FILE >> $CDNA_MAP_FILE</pre>
+
 
+
* [http://www.marcottelab.org/users/taejoon/PSEAE_CF/microarray/PSEAE_1.affy_probes.PSEAE_PAO1.PCAP20091123.dna.fasta.exonerate.gz Exonerate output against PAO1 transcripts]
+
* [http://www.marcottelab.org/users/taejoon/PSEAE_CF/microarray/PSEAE_1.affy_probes.PSEAE_PAO1.PCAP20091123.dna.fasta.probeset.gz ProbeSet - PAO1 gene mapping]
+
* [http://www.marcottelab.org/users/taejoon/PSEAE_CF/microarray/PSEAE_1.affy_probes.PSEAE_PAO1.PCAP20091123.dna.fasta.probeset_log.gz Log for bad probesets]
+
  
 
== Genome/Annotation data ==
 
== Genome/Annotation data ==

Revision as of 14:19, 8 September 2010

Web supplement for 'Huse HK, Kwon T, Zlosnik JEA, Speert DP, Marcotte EM, Whiteley M, Parallel evolution in Pseudomonas aeruginosa over 39,000 generations in vivo, mBIO, :in press (2010) PubMed '

Contents

Supplement Tables

  • Table S1. Strains
  • Table S2. P. aeruginosa orthologs
  • Table S3. Affymetrix microarray annotation
  • Table S4. P. aeruginosa annotation
  • Table S5. Differentially expressed genes between progenitors
  • Table S6. Differentially expressed genes within isogenic groups (compared to each progenitor/first strain).
  • Table S7. Differentially expressed genes between isogenic groups.
  • Table S8. Functional enrichment data for Table S7
  • Table S9. Functional enrichment data for Table S6

Microarray data

CEL files

Gzipped TXT files

Probe mapping to PAO1

A BASH shell script to run exonerate:

EXONERATE="/home/taejoon/bin64/exonerate"
PROBE_FILE="PSEAE_1.affy_probes.fasta"

GENOME_DIR="/home/taejoon/pkgenome.data/PCAP"
TARGET_NAME="PSEAE_PAO1.NC_002516.fna"

GENOME_FILE="$GENOME_DIR/$TARGET_NAME"
GENOME_MAP_FILE=${PROBE_FILE/%fasta/$TARGET_NAME.exonerate}
echo "$PROBE_FILE vs. $GENOME_FILE"
echo "#PROBE_FILE : $PROBE_FILE" > $GENOME_MAP_FILE
echo "#GENOME_FILE : $GENOME_FILE" >> $GENOME_MAP_FILE
$EXONERATE -m affine:local -Q dna -T dna --showvulgar no --showcigar no --showalignment no \
--ryo "%qi %ti %tS %qab %qae %tab %tae %et %ei %es %em %s %C\n " $PROBE_FILE $GENOME_FILE >> $GENOME_MAP_FILE

TARGET_NAME="PSEAE_PAO1.PCAP20091123.dna.fasta"
CDNA_FILE="$GENOME_DIR/$TARGET_NAME"
CDNA_MAP_FILE=${PROBE_FILE/%fasta/$TARGET_NAME.exonerate}
echo "$PROBE_FILE vs. $CDNA_FILE"
echo "#PROBE_FILE : $PROBE_FILE" > $CDNA_MAP_FILE
echo "#CDNA_FILE : $CDNA_FILE" >> $CDNA_MAP_FILE
$EXONERATE -m affine:local -Q dna -T dna --showvulgar no --showcigar no --showalignment no \
--ryo "%qi %ti %tS %qab %qae %tab %tae %et %ei %es %em %s %C\n " $PROBE_FILE $CDNA_FILE >> $CDNA_MAP_FILE

R script for preprocessing

dataset_name <- 'Huse2010_GSE21966'
library(affy)

exp_table <- read.table(file="EXP",header=T,stringsAsFactors=FALSE,sep="\t")
files_vector <- as.vector(exp_table$Filename,mode='character')
samples_vector <- as.vector(exp_table$Sample,mode='character')
affybatch_raw <- ReadAffy(filenames=files_vector,sampleNames=samples_vector)

save(affybatch_raw, file=paste(dataset_name,'.affybatch_raw', sep=''))
write.table(intensity(affybatch_raw),
            file=paste(dataset_name,'.raw.txt', sep=''))

affybatch_corrected <- bg.correct(affybatch_raw, method='rma')
save(affybatch_corrected,
            file=paste(dataset_name,'.affybatch_corrected', sep=''))
write.table(intensity(affybatch_corrected),
            file=paste(dataset_name,'.corrected.txt', sep=''))

affybatch_normalized <- normalize(affybatch_corrected, method='quantiles')
save(affybatch_normalized,
            file=paste(dataset_name,'.affybatch_normalized',sep=''))
write.table(intensity(affybatch_normalized),
            file=paste(dataset_name,'.norm.txt', sep=''))

eset_rma <- rma(affybatch_raw)
save(eset_rma, file=paste(dataset_name,'.eset_rma',sep=''))
write.exprs(eset_rma,
            file=paste(dataset_name,'.eset_rma.txt',sep=''))

R script for ANOSIM test

library(vegan)
tbl <- read.table('Huse2010_GSE21966.gene_mean.txt',header=T,row.names='Gene')
t_tbl <- t(tbl)

tbl_dist <-  as.dist(1-cor(as.matrix(tbl),method='spearman'))
igroup <- c('A','A','A','A','A','B','B','B','B','B','B','B','Ca','Ca','Cb','Cb','Cb','R','R')
tbl_igroup_anosim <- anosim(tbl_dist,igroup)

tgroup <- c('E','M','M','M','L','E','M','M','M','L','L','L','E','L','E','M','L','R','R')
tbl_time_anosim <- anosim(tbl_dist,tgroup)

mgroup <- c('C','C','M','D','D','C','C','D','M','M','C','M','C','M','M','D','M','R','R')
tbl_morphology_anosim <- anosim(tbl_dist,mgroup)

Genome/Annotation data

All data were downloaded from http://www.pseudomonas.com on November, 23, 2009.