1.1 Run goseq

Please note that this is using the >8 fold significance data.

pa_go <- load_microbesonline_go(id=208963)

## The species being downloaded is: Pseudomonas aeruginosa UCBPP-PA14 and is being downloaded as 208963.tab.

colnames(pa_go) <- c("ID", "GO")

gff_annot[["name"]] <- as.character(gff_annot[["name"]])
length_go <- merge(gff_annot, pa_go, by.x="name", by.y="ID")
pa_lengths <- unique(length_go[, c("ID", "width")])
pa_go <- length_go[, c("ID", "GO")]

pa_ex_mtwt_up <- pa_sig[["deseq"]][["ups"]][["mt_ex_vs_wt_ex"]]
pa_ex_mtwt_down <- pa_sig[["deseq"]][["downs"]][["mt_ex_vs_wt_ex"]]

pa_st_mtwt_up <- pa_sig[["deseq"]][["ups"]][["mt_st_vs_wt_st"]]
pa_st_mtwt_down <- pa_sig[["deseq"]][["downs"]][["mt_st_vs_wt_st"]]

pa_ex_wtmt_up_goseq <- simple_goseq(sig_genes=pa_ex_mtwt_up, go_db=pa_go, length_db=pa_lengths)

## Using the row names of your table.

## Found 27 genes out of 40 from the sig_genes in the go_db.

## Found 27 genes out of 40 from the sig_genes in the length_db.

## 

## Using manually entered categories.

## Calculating the p-values...

## 'select()' returned 1:1 mapping between keys and columns

## simple_goseq(): Calculating q-values

## Using GO.db to extract terms and categories.

## simple_goseq(): Filling godata with terms, this is slow.

## Testing that go categories are defined.

## Removing undefined categories.

## Gathering synonyms.

## Gathering category definitions.

## simple_goseq(): Making pvalue plots for the ontologies.

pa_ex_wtmt_up_goseq$pvalue_plots$bpp_plot_over

pa_ex_wtmt_down_goseq <- simple_goseq(sig_genes=pa_ex_mtwt_down, go_db=pa_go, length_db=pa_lengths)

## Using the row names of your table.

## Found 18 genes out of 22 from the sig_genes in the go_db.

## Found 18 genes out of 22 from the sig_genes in the length_db.

## Warning in pcls(G): initial point very close to some inequality constraints

## Using manually entered categories.

## Calculating the p-values...

## 'select()' returned 1:1 mapping between keys and columns

## simple_goseq(): Calculating q-values

## Using GO.db to extract terms and categories.

## simple_goseq(): Filling godata with terms, this is slow.

## Testing that go categories are defined.

## Removing undefined categories.

## Gathering synonyms.

## Gathering category definitions.

## simple_goseq(): Making pvalue plots for the ontologies.

pa_ex_wtmt_down_goseq$pvalue_plots$bpp_plot_over

writeme <- write_goseq_data(goseq_result=pa_ex_wtmt_up_goseq, excel="excel/pa_ex_wtmt_up_goseq.xlsx")

## Writing a sheet containing the legend.

## Warning: Removed 1 rows containing missing values (geom_bar).

## Warning: Removed 1 rows containing missing values (geom_bar).

## There was an error generating the BP tree.

## Writing the BP data.

## Loading required namespace: Vennerable

## 
## Attaching package: 'Vennerable'

## The following objects are masked from 'package:topGO':
## 
##     Weights, Weights<-

## Writing the MF data.

## Writing the CC data.

## Finished writing excel file.

writeme <- write_goseq_data(goseq_result=pa_ex_wtmt_down_goseq, excel="excel/pa_ex_wtmt_down_goseq.xlsx")

## Writing a sheet containing the legend.

## Warning: Removed 1 rows containing missing values (geom_bar).

## Warning: Removed 1 rows containing missing values (geom_bar).

## Writing the BP data.

## Writing the MF data.

## Writing the CC data.

## Finished writing excel file.

pa_st_wtmt_up_goseq <- simple_goseq(sig_genes=pa_st_mtwt_up, go_db=pa_go, length_db=pa_lengths)

## Using the row names of your table.

## Found 40 genes out of 61 from the sig_genes in the go_db.

## Found 40 genes out of 61 from the sig_genes in the length_db.

## Using manually entered categories.

## Calculating the p-values...

## 'select()' returned 1:1 mapping between keys and columns

## simple_goseq(): Calculating q-values

## Using GO.db to extract terms and categories.

## simple_goseq(): Filling godata with terms, this is slow.

## Testing that go categories are defined.

## Removing undefined categories.

## Gathering synonyms.

## Gathering category definitions.

## simple_goseq(): Making pvalue plots for the ontologies.

pa_st_wtmt_up_goseq$pvalue_plots$bpp_plot_over

pa_st_wtmt_down_goseq <- simple_goseq(sig_genes=pa_st_mtwt_down, go_db=pa_go, length_db=pa_lengths)

## Using the row names of your table.

## Found 101 genes out of 184 from the sig_genes in the go_db.

## Found 101 genes out of 184 from the sig_genes in the length_db.

## Warning in pcls(G): initial point very close to some inequality constraints

## Using manually entered categories.

## Calculating the p-values...

## 'select()' returned 1:1 mapping between keys and columns

## simple_goseq(): Calculating q-values

## Using GO.db to extract terms and categories.

## simple_goseq(): There are no genes with an adj.p < 0.1 using: BH.

## simple_goseq(): Providing genes with raw pvalue < 0.1.

## simple_goseq(): Filling godata with terms, this is slow.

## Testing that go categories are defined.

## Removing undefined categories.

## Gathering synonyms.

## Gathering category definitions.

## simple_goseq(): Making pvalue plots for the ontologies.

pa_st_wtmt_down_goseq$pvalue_plots$bpp_plot_over

writeme <- write_goseq_data(goseq_result=pa_st_wtmt_up_goseq, excel="excel/pa_st_wtmt_up_goseq.xlsx")

## Writing a sheet containing the legend.

## Warning: Removed 1 rows containing missing values (geom_bar).

## Warning: Removed 1 rows containing missing values (geom_bar).

## There was an error generating the BP tree.

## Writing the BP data.

## Writing the MF data.

## Writing the CC data.

## Finished writing excel file.

writeme <- write_goseq_data(goseq_result=pa_st_wtmt_down_goseq, excel="excel/pa_st_wtmt_down_goseq.xlsx")

## Writing a sheet containing the legend.

## Warning: Removed 1 rows containing missing values (geom_bar).

## Warning: Removed 1 rows containing missing values (geom_bar).

## Writing the BP data.

## Writing the MF data.

## Writing the CC data.

## Finished writing excel file.

pa_wt_stex_up <- pa_sig[["deseq"]][["ups"]][["wt_st_vs_wt_ex"]]
pa_wt_stex_down <- pa_sig[["deseq"]][["downs"]][["wt_st_vs_wt_ex"]]

pa_mt_stex_up <- pa_sig[["deseq"]][["ups"]][["mt_st_vs_mt_ex"]]
pa_mt_stex_down <- pa_sig[["deseq"]][["downs"]][["mt_st_vs_mt_ex"]]

pa_wt_stex_up_goseq <- simple_goseq(sig_genes=pa_wt_stex_up, go_db=pa_go, length_db=pa_lengths)

## Using the row names of your table.

## Found 176 genes out of 326 from the sig_genes in the go_db.

## Found 176 genes out of 326 from the sig_genes in the length_db.

## Warning in pcls(G): initial point very close to some inequality constraints

## Using manually entered categories.

## Calculating the p-values...

## 'select()' returned 1:1 mapping between keys and columns

## simple_goseq(): Calculating q-values

## Using GO.db to extract terms and categories.

## simple_goseq(): There are no genes with an adj.p < 0.1 using: BH.

## simple_goseq(): Providing genes with raw pvalue < 0.1.

## simple_goseq(): Filling godata with terms, this is slow.

## Testing that go categories are defined.

## Removing undefined categories.

## Gathering synonyms.

## Gathering category definitions.

## simple_goseq(): Making pvalue plots for the ontologies.

pa_wt_stex_up_goseq$pvalue_plots$bpp_plot_over

pa_wt_stex_down_goseq <- simple_goseq(sig_genes=pa_wt_stex_down, go_db=pa_go, length_db=pa_lengths)

## Using the row names of your table.

## Found 82 genes out of 97 from the sig_genes in the go_db.

## Found 82 genes out of 97 from the sig_genes in the length_db.

## Using manually entered categories.

## Calculating the p-values...

## 'select()' returned 1:1 mapping between keys and columns

## simple_goseq(): Calculating q-values

## Using GO.db to extract terms and categories.

## simple_goseq(): Filling godata with terms, this is slow.

## Testing that go categories are defined.

## Removing undefined categories.

## Gathering synonyms.

## Gathering category definitions.

## simple_goseq(): Making pvalue plots for the ontologies.

pa_wt_stex_down_goseq$pvalue_plots$bpp_plot_over

writeme <- write_goseq_data(goseq_result=pa_wt_stex_up_goseq, excel="excel/pa_wt_stex_up_goseq.xlsx")

## Writing a sheet containing the legend.

## Warning: Removed 1 rows containing missing values (geom_bar).

## Warning: Removed 1 rows containing missing values (geom_bar).

## Writing the BP data.

## Writing the MF data.

## Writing the CC data.

## Finished writing excel file.

writeme <- write_goseq_data(goseq_result=pa_wt_stex_down_goseq, excel="excel/pa_wt_stex_down_goseq.xlsx")

## Writing a sheet containing the legend.

## Warning: Removed 1 rows containing missing values (geom_bar).

## Warning: Removed 1 rows containing missing values (geom_bar).

## Writing the BP data.

## Writing the MF data.

## Writing the CC data.

## Finished writing excel file.

pa_mt_stex_up_goseq <- simple_goseq(sig_genes=pa_mt_stex_up, go_db=pa_go, length_db=pa_lengths)

## Using the row names of your table.

## Found 49 genes out of 61 from the sig_genes in the go_db.

## Found 49 genes out of 61 from the sig_genes in the length_db.

## Using manually entered categories.

## Calculating the p-values...

## 'select()' returned 1:1 mapping between keys and columns

## simple_goseq(): Calculating q-values

## Using GO.db to extract terms and categories.

## simple_goseq(): Filling godata with terms, this is slow.

## Testing that go categories are defined.

## Removing undefined categories.

## Gathering synonyms.

## Gathering category definitions.

## simple_goseq(): Making pvalue plots for the ontologies.

pa_mt_stex_up_goseq$pvalue_plots$bpp_plot_over

pa_mt_stex_down_goseq <- simple_goseq(sig_genes=pa_mt_stex_down, go_db=pa_go, length_db=pa_lengths)

## Using the row names of your table.

## Found 6 genes out of 6 from the sig_genes in the go_db.

## Found 6 genes out of 6 from the sig_genes in the length_db.

## Using manually entered categories.

## Calculating the p-values...

## 'select()' returned 1:1 mapping between keys and columns

## simple_goseq(): Calculating q-values

## Using GO.db to extract terms and categories.

## simple_goseq(): There are no genes with an adj.p < 0.1 using: BH.

## simple_goseq(): Providing genes with raw pvalue < 0.1.

## simple_goseq(): Filling godata with terms, this is slow.

## Testing that go categories are defined.

## Removing undefined categories.

## Gathering synonyms.

## Gathering category definitions.

## simple_goseq(): Making pvalue plots for the ontologies.

pa_mt_stex_down_goseq$pvalue_plots$bpp_plot_over

writeme <- write_goseq_data(goseq_result=pa_mt_stex_up_goseq, excel="excel/pa_mt_stex_up_goseq.xlsx")

## Writing a sheet containing the legend.

## Warning: Removed 1 rows containing missing values (geom_bar).

## Warning: Removed 1 rows containing missing values (geom_bar).

## Writing the BP data.

## Writing the MF data.

## Writing the CC data.

## Finished writing excel file.

writeme <- write_goseq_data(goseq_result=pa_mt_stex_down_goseq, excel="excel/pa_mt_stex_down_goseq.xlsx")

## Writing a sheet containing the legend.

## Warning: Removed 1 rows containing missing values (geom_bar).

## Warning: Removed 1 rows containing missing values (geom_bar).

## Writing the BP data.

## Writing the MF data.

## No data survived to be written for the CC ontology.

## Finished writing excel file.

pander::pander(sessionInfo())

R version 3.5.1 (2018-07-02)

Platform: x86_64-pc-linux-gnu (64-bit)

locale: LC_CTYPE=en_US.utf8, LC_NUMERIC=C, LC_TIME=en_US.utf8, LC_COLLATE=en_US.utf8, LC_MONETARY=en_US.utf8, LC_MESSAGES=en_US.utf8, LC_PAPER=en_US.utf8, LC_NAME=C, LC_ADDRESS=C, LC_TELEPHONE=C, LC_MEASUREMENT=en_US.utf8 and LC_IDENTIFICATION=C

attached base packages: grid, parallel, stats, graphics, grDevices, utils, datasets, methods and base

other attached packages: Vennerable(v.3.1.0.9000), Rgraphviz(v.2.24.0), graph(v.1.58.0), BiocGenerics(v.0.26.0), SparseM(v.1.77), topGO(v.2.32.0) and hpgltools(v.2018.03)

loaded via a namespace (and not attached): colorspace(v.1.3-2), selectr(v.0.4-1), rprojroot(v.1.3-2), qvalue(v.2.12.0), htmlTable(v.1.12), XVector(v.0.20.0), GenomicRanges(v.1.32.4), base64enc(v.0.1-3), rstudioapi(v.0.7), roxygen2(v.6.0.1), ggrepel(v.0.8.0), bit64(v.0.9-7), AnnotationDbi(v.1.42.1), xml2(v.1.2.0), codetools(v.0.2-15), splines(v.3.5.1), robustbase(v.0.93-1.1), geneplotter(v.1.58.0), knitr(v.1.20), Formula(v.1.2-3), Rsamtools(v.1.32.2), annotate(v.1.58.0), GO.db(v.3.6.0), cluster(v.2.0.7-1), geneLenDataBase(v.1.16.0), compiler(v.3.5.1), httr(v.1.3.1), backports(v.1.1.2), assertthat(v.0.2.0), Matrix(v.1.2-14), lazyeval(v.0.2.1), acepack(v.1.4.1), htmltools(v.0.3.6), prettyunits(v.1.0.2), tools(v.3.5.1), bindrcpp(v.0.2.2), gtable(v.0.2.0), glue(v.1.3.0), GenomeInfoDbData(v.1.1.0), reshape2(v.1.4.3), dplyr(v.0.7.6), Rcpp(v.0.12.17), Biobase(v.2.40.0), Biostrings(v.2.48.0), nlme(v.3.1-137), rtracklayer(v.1.40.3), iterators(v.1.0.10), stringr(v.1.3.1), openxlsx(v.4.1.0), rvest(v.0.3.2), devtools(v.1.13.6), XML(v.3.98-1.12), DEoptimR(v.1.0-8), directlabels(v.2018.05.22), zlibbioc(v.1.26.0), scales(v.0.5.0), hms(v.0.4.2), RBGL(v.1.56.0), SummarizedExperiment(v.1.10.1), RColorBrewer(v.1.1-2), yaml(v.2.1.19), curl(v.3.2), goseq(v.1.32.0), memoise(v.1.1.0), gridExtra(v.2.3), pander(v.0.6.2), ggplot2(v.3.0.0), biomaRt(v.2.36.1), rpart(v.4.1-13), latticeExtra(v.0.6-28), stringi(v.1.2.3), RSQLite(v.2.1.1), genefilter(v.1.62.0), S4Vectors(v.0.18.3), foreach(v.1.4.4), checkmate(v.1.8.5), GenomicFeatures(v.1.32.0), zip(v.1.0.0), BiocParallel(v.1.14.2), GenomeInfoDb(v.1.16.0), rlang(v.0.2.1), pkgconfig(v.2.0.1), commonmark(v.1.5), matrixStats(v.0.53.1), bitops(v.1.0-6), evaluate(v.0.11), lattice(v.0.20-35), purrr(v.0.2.5), bindr(v.0.1.1), labeling(v.0.3), GenomicAlignments(v.1.16.0), htmlwidgets(v.1.2), bit(v.1.1-14), tidyselect(v.0.2.4), plyr(v.1.8.4), magrittr(v.1.5), DESeq2(v.1.20.0), R6(v.2.2.2), IRanges(v.2.14.10), Hmisc(v.4.1-1), DelayedArray(v.0.6.1), DBI(v.1.0.0), mgcv(v.1.8-24), pillar(v.1.3.0), foreign(v.0.8-70), withr(v.2.1.2), survival(v.2.42-6), RCurl(v.1.95-4.11), nnet(v.7.3-12), tibble(v.1.4.2), crayon(v.1.3.4), rmarkdown(v.1.10), progress(v.1.2.0), locfit(v.1.5-9.1), data.table(v.1.11.4), blob(v.1.1.1), digest(v.0.6.15), xtable(v.1.8-2), tidyr(v.0.8.1), stats4(v.3.5.1), munsell(v.0.5.0), BiasedUrn(v.1.07) and quadprog(v.1.5-5)

message(paste0("This is hpgltools commit: ", get_git_commit()))

## If you wish to reproduce this exact build of hpgltools, invoke the following:

## > git clone http://github.com/abelew/hpgltools.git

## > git reset c730ef178f8e57bbf3819e21cf5e6cfe879e6328

## R> packrat::restore()

## This is hpgltools commit: Fri Jul 13 17:21:39 2018 -0400: c730ef178f8e57bbf3819e21cf5e6cfe879e6328

this_save <- paste0(gsub(pattern="\\.Rmd", replace="", x=rmd_file), "-v", ver, ".rda.xz")
message(paste0("Saving to ", this_save))

## Saving to 03_differential_expression-v20171019.rda.xz

tmp <- sm(saveme(filename=this_save))