Difference between revisions of "PSEAE CF.2010"
From Marcotte Lab
(→Gzipped TXT files) |
(→R script for ANOSIM test) |
||
Line 138: | Line 138: | ||
mgroup <- c('C','C','M','D','D','C','C','D','M','M','C','M','C','M','M','D','M','R','R') | 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)</pre> | tbl_morphology_anosim <- anosim(tbl_dist,mgroup)</pre> | ||
+ | |||
+ | === R script for detecting differentially expressed genes == | ||
+ | <pre>library(limma) | ||
+ | library(affy) | ||
+ | |||
+ | ## Read target information | ||
+ | targets <- readTargets("EXP") | ||
+ | affybatch_raw <- ReadAffy(filenames = targets$Filename) | ||
+ | eset_rma <- rma(affybatch_raw) | ||
+ | |||
+ | ## Patient - Splitting P3 | ||
+ | igroup_detail <- factor(targets$Isogenic, levels=c("A","B","Ca","Cb","PAO1","PA14")) | ||
+ | design_igroup_detail <- model.matrix(~0+igroup_detail) | ||
+ | colnames(design_igroup_detail) <- c(levels(igroup_detail)) | ||
+ | |||
+ | fit_igroup_detail <- lmFit(eset_rma, design_igroup_detail) | ||
+ | fit_igroup_detail <- eBayes(fit_igroup_detail) | ||
+ | contrast_igroup_detail <- makeContrasts(B-A,Ca-A,Cb-A,Ca-B,Cb-B,Cb-Ca, | ||
+ | levels=design_igroup_detail) | ||
+ | contrast_fit_igroup_detail <- contrasts.fit(fit_igroup_detail, contrast_igroup_detail) | ||
+ | contrast_fit_igroup_detail <- eBayes(contrast_fit_igroup_detail) | ||
+ | top_B_A <- topTable(contrast_fit_igroup_detail, n=nrow(contrast_fit_igroup_detail), | ||
+ | coef=1, adjust="fdr", resort.by="logFC") | ||
+ | write.table(top_B_A,"DE_between_group/igroup_B_A.top.txt") | ||
+ | top_Ca_A <- topTable(contrast_fit_igroup_detail, n=nrow(contrast_fit_igroup_detail), | ||
+ | coef=2, adjust="fdr", resort.by="logFC") | ||
+ | write.table(top_Ca_A,"DE_between_group/igroup_Ca_A.top.txt") | ||
+ | top_Cb_A <- topTable(contrast_fit_igroup_detail, n=nrow(contrast_fit_igroup_detail), | ||
+ | coef=3, adjust="fdr", resort.by="logFC") | ||
+ | write.table(top_Cb_A,"DE_between_group/igroup_Cb_A.top.txt") | ||
+ | top_Ca_B <- topTable(contrast_fit_igroup_detail, n=nrow(contrast_fit_igroup_detail), | ||
+ | coef=4, adjust="fdr", resort.by="logFC") | ||
+ | write.table(top_Ca_B,"DE_between_group/igroup_Ca_B.top.txt") | ||
+ | top_Cb_B <- topTable(contrast_fit_igroup_detail, n=nrow(contrast_fit_igroup_detail), | ||
+ | coef=5, adjust="fdr", resort.by="logFC") | ||
+ | write.table(top_Cb_B,"DE_between_group/igroup_Cb_B.top.txt") | ||
+ | top_Cb_Ca <- topTable(contrast_fit_igroup_detail, n=nrow(contrast_fit_igroup_detail), | ||
+ | coef=6, adjust="fdr", resort.by="logFC") | ||
+ | write.table(top_Cb_Ca,"DE_between_group/igroup_Cb_Ca.top.txt")</pre> | ||
== Genome/Annotation data == | == Genome/Annotation data == |
Revision as of 16:53, 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 |
Figures
|
|
|
|
|
Supplement Tables
- Table S1. P. aeruginosa strains used in this study MS Excel
- Table S2. Orthologous genes from P. aeruginosa strains PAO1, PA14, PA7, and LESB58 MS Excel
- Table S3. Affymetrix microarray annotation MS Excel
- Table S4. Genes expressed differently in clonal groups MS Excel
- Table S5. Genes expressed differently in ancestors and strain PA14 MS Excel
- Table S6. Genes expressed differently within clonal groups over time MS Excel
Microarray data
CEL files
- http://www.marcottelab.org/users/taejoon/PSEAE_CF/microarray/GSE21966_CEL.zip
- Description for CEL files (gzipped)
- You can also download it from http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE21966 (NCBI GEO)
TXT files
Compressed by gzip.
- RAW data, before pre-processing
- RMA pre-processing, PM corrected
- RMA pre-processing, Quantile normalized
- RMA pre-processing, ExpressSet
- MAS5 pre-processing, ExpressSet
- MAS5 pre-processing, P/M/A calls
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$Sample,mode='character') affybatch_raw <- ReadAffy(filenames=files_vector,sampleNames=samples_vector) save(affybatch_raw, file=paste(dataset_name,'.affybatch_raw', sep='')) write.table(intensity(affybatch_raw), file=paste(dataset_name,'.raw.txt', sep='')) affybatch_corrected <- bg.correct(affybatch_raw, method='rma') save(affybatch_corrected, file=paste(dataset_name,'.affybatch_corrected', sep='')) write.table(intensity(affybatch_corrected), file=paste(dataset_name,'.corrected.txt', sep='')) affybatch_normalized <- normalize(affybatch_corrected, method='quantiles') save(affybatch_normalized, file=paste(dataset_name,'.affybatch_normalized',sep='')) write.table(intensity(affybatch_normalized), file=paste(dataset_name,'.norm.txt', sep='')) eset_rma <- rma(affybatch_raw) save(eset_rma, file=paste(dataset_name,'.eset_rma',sep='')) write.exprs(eset_rma, file=paste(dataset_name,'.eset_rma.txt',sep=''))
R script for ANOSIM test
library(vegan) tbl <- read.table('Huse2010_GSE21966.gene_mean.txt',header=T,row.names='Gene') t_tbl <- t(tbl) tbl_dist <- as.dist(1-cor(as.matrix(tbl),method='spearman')) igroup <- c('A','A','A','A','A','B','B','B','B','B','B','B','Ca','Ca','Cb','Cb','Cb','R','R') tbl_igroup_anosim <- anosim(tbl_dist,igroup) tgroup <- c('E','M','M','M','L','E','M','M','M','L','L','L','E','L','E','M','L','R','R') tbl_time_anosim <- anosim(tbl_dist,tgroup) mgroup <- c('C','C','M','D','D','C','C','D','M','M','C','M','C','M','M','D','M','R','R') tbl_morphology_anosim <- anosim(tbl_dist,mgroup)
= R script for detecting differentially expressed genes
library(limma) library(affy) ## Read target information targets <- readTargets("EXP") affybatch_raw <- ReadAffy(filenames = targets$Filename) eset_rma <- rma(affybatch_raw) ## Patient - Splitting P3 igroup_detail <- factor(targets$Isogenic, levels=c("A","B","Ca","Cb","PAO1","PA14")) design_igroup_detail <- model.matrix(~0+igroup_detail) colnames(design_igroup_detail) <- c(levels(igroup_detail)) fit_igroup_detail <- lmFit(eset_rma, design_igroup_detail) fit_igroup_detail <- eBayes(fit_igroup_detail) contrast_igroup_detail <- makeContrasts(B-A,Ca-A,Cb-A,Ca-B,Cb-B,Cb-Ca, levels=design_igroup_detail) contrast_fit_igroup_detail <- contrasts.fit(fit_igroup_detail, contrast_igroup_detail) contrast_fit_igroup_detail <- eBayes(contrast_fit_igroup_detail) top_B_A <- topTable(contrast_fit_igroup_detail, n=nrow(contrast_fit_igroup_detail), coef=1, adjust="fdr", resort.by="logFC") write.table(top_B_A,"DE_between_group/igroup_B_A.top.txt") top_Ca_A <- topTable(contrast_fit_igroup_detail, n=nrow(contrast_fit_igroup_detail), coef=2, adjust="fdr", resort.by="logFC") write.table(top_Ca_A,"DE_between_group/igroup_Ca_A.top.txt") top_Cb_A <- topTable(contrast_fit_igroup_detail, n=nrow(contrast_fit_igroup_detail), coef=3, adjust="fdr", resort.by="logFC") write.table(top_Cb_A,"DE_between_group/igroup_Cb_A.top.txt") top_Ca_B <- topTable(contrast_fit_igroup_detail, n=nrow(contrast_fit_igroup_detail), coef=4, adjust="fdr", resort.by="logFC") write.table(top_Ca_B,"DE_between_group/igroup_Ca_B.top.txt") top_Cb_B <- topTable(contrast_fit_igroup_detail, n=nrow(contrast_fit_igroup_detail), coef=5, adjust="fdr", resort.by="logFC") write.table(top_Cb_B,"DE_between_group/igroup_Cb_B.top.txt") top_Cb_Ca <- topTable(contrast_fit_igroup_detail, n=nrow(contrast_fit_igroup_detail), coef=6, adjust="fdr", resort.by="logFC") write.table(top_Cb_Ca,"DE_between_group/igroup_Cb_Ca.top.txt")
Genome/Annotation data
All data were downloaded from http://www.pseudomonas.com on November, 23, 2009.
- P. aeruginosa PAO1
- Genomic DNA, Transcripts, Proteins, Annotation(TSV)
- Reciprocal BLAST best-hits: PA14, PA7, LESB58, Summary
- P. aeruginosa PA14
- P. aeruginosa PA7
- P. aeruginosa LESB58