Target Decoy approach

1 Pyrococcus

source('https://statomics.github.io/SGA2020/assets/EvalTargetDecoys.R')
library(mzID)
mzIdMsgfPlus<-mzID("~/Dropbox/proteomicsShortcourse/pda2019/data/identification/pyrococcusMSGF+.mzid")

## reading pyrococcusMSGF+.mzid... DONE!

1.1 PPplots

decoyPlots <- evalTargetDecoys(mzIdMsgfPlus, decoy="isdecoy", score="ms-gf:specevalue", log10=TRUE)

## Warning: Removed 9387 rows containing missing values (geom_point).

decoyPlots

## $ppPlot

## 
## $histogram

## 
## $ppPlotZoom

## Warning: Removed 9387 rows containing missing values (geom_point).

## 
## $histogramZoom

## 
## $together

2 Information on the package version

sessionInfo()

## R version 4.0.2 (2020-06-22)
## Platform: x86_64-apple-darwin17.0 (64-bit)
## Running under: macOS Catalina 10.15.7
## 
## Matrix products: default
## BLAS:   /Library/Frameworks/R.framework/Versions/4.0/Resources/lib/libRblas.dylib
## LAPACK: /Library/Frameworks/R.framework/Versions/4.0/Resources/lib/libRlapack.dylib
## 
## locale:
## [1] C/UTF-8/C/C/C/C
## 
## attached base packages:
## [1] parallel  stats4    stats     graphics  grDevices utils     datasets 
## [8] methods   base     
## 
## other attached packages:
##  [1] ggpubr_0.4.0                shiny_1.5.0                
##  [3] ggplot2_3.3.2               dplyr_1.0.2                
##  [5] mzR_2.22.0                  Rcpp_1.0.5                 
##  [7] mzID_1.26.0                 msqrob2_0.0.1              
##  [9] lme4_1.1-23                 Matrix_1.2-18              
## [11] QFeatures_0.99.3            MultiAssayExperiment_1.14.0
## [13] SummarizedExperiment_1.18.2 DelayedArray_0.14.1        
## [15] matrixStats_0.57.0          Biobase_2.48.0             
## [17] GenomicRanges_1.40.0        GenomeInfoDb_1.24.2        
## [19] IRanges_2.22.2              S4Vectors_0.26.1           
## [21] BiocGenerics_0.34.0        
## 
## loaded via a namespace (and not attached):
##  [1] minqa_1.2.4             colorspace_1.4-1        ggsignif_0.6.0         
##  [4] ellipsis_0.3.1          rio_0.5.16              rprojroot_1.3-2        
##  [7] XVector_0.28.0          farver_2.0.3            remotes_2.2.0          
## [10] fansi_0.4.1             codetools_0.2-16        splines_4.0.2          
## [13] ncdf4_1.17              doParallel_1.0.15       knitr_1.30             
## [16] jsonlite_1.7.1          nloptr_1.2.2.2          broom_0.7.1            
## [19] BiocManager_1.30.10     compiler_4.0.2          backports_1.1.10       
## [22] assertthat_0.2.1        fastmap_1.0.1           lazyeval_0.2.2         
## [25] limma_3.44.3            cli_2.0.2               later_1.1.0.1          
## [28] htmltools_0.5.0         prettyunits_1.1.1       tools_4.0.2            
## [31] gtable_0.3.0            glue_1.4.2              GenomeInfoDbData_1.2.3 
## [34] carData_3.0-4           cellranger_1.1.0        vctrs_0.3.4            
## [37] nlme_3.1-149            iterators_1.0.12        stringr_1.4.0          
## [40] xfun_0.18               ps_1.4.0                openxlsx_4.2.2         
## [43] mime_0.9                lifecycle_0.2.0         statmod_1.4.34         
## [46] rstatix_0.6.0           XML_3.99-0.5            zlibbioc_1.34.0        
## [49] MASS_7.3-53             scales_1.1.1            hms_0.5.3              
## [52] promises_1.1.1          ProtGenerics_1.20.0     AnnotationFilter_1.12.0
## [55] yaml_2.2.1              curl_4.3                stringi_1.5.3          
## [58] foreach_1.5.0           boot_1.3-25             pkgbuild_1.1.0         
## [61] zip_2.1.1               rlang_0.4.7             pkgconfig_2.0.3        
## [64] bitops_1.0-6            evaluate_0.14           lattice_0.20-41        
## [67] purrr_0.3.4             labeling_0.3            cowplot_1.1.0          
## [70] processx_3.4.4          tidyselect_1.1.0        plyr_1.8.6             
## [73] magrittr_1.5            R6_2.4.1                generics_0.0.2         
## [76] pillar_1.4.6            haven_2.3.1             foreign_0.8-80         
## [79] withr_2.3.0             MsCoreUtils_1.1.8       abind_1.4-5            
## [82] RCurl_1.98-1.2          tibble_3.0.3            crayon_1.3.4           
## [85] car_3.0-10              rmarkdown_2.4           grid_4.0.2             
## [88] readxl_1.3.1            data.table_1.13.0       callr_3.4.4            
## [91] forcats_0.5.0           digest_0.6.25           xtable_1.8-4           
## [94] tidyr_1.1.2             httpuv_1.5.4            munsell_0.5.0

3 Uniprot

3.1 Data

mzIdUni <- mzID("~/Dropbox/proteomicsShortcourse/pda2019/data/identification/pyroUniprot.mzid")

## reading pyroUniprot.mzid... DONE!

3.2 MSGF+

plotsUniMsgf <- evalTargetDecoys(mzIdUni,decoy =  "isdecoy", score = "ms-gf:specevalue", log10 = TRUE)

## Warning: Removed 10503 rows containing missing values (geom_point).

plotsUniMsgf$together

3.3 Xtandem

plotsUniXtandem <- evalTargetDecoys(mzIdMsgfPlusUni,decoy =  "isdecoy", score = "x!tandem:expect", log10 = TRUE)

## Warning: Removed 9324 rows containing missing values (geom_point).

plotsUniXtandem$together

3.4 omssa

plotsUniOmssa <- evalTargetDecoys(mzIdUni,decoy =  "isdecoy", score = "omssa:evalue", log10 = TRUE)

## Warning: Removed 9535 rows containing missing values (geom_point).

plotsUniOmssa$together

3.5 PeptideShaker

plotsUniShaker <- evalTargetDecoys(mzIdUni,decoy =  "isdecoy", score = "peptideshaker psm score", log10 = FALSE)

## Warning: Removed 11604 rows containing missing values (geom_point).

plotsUniShaker$together

4 Swissprot

4.1 Data

mzIdSwiss <- mzID("~/Dropbox/proteomicsShortcourse/pda2019/data/identification/pyroSwissprot.mzid")

## reading pyroSwissprot.mzid... DONE!

4.2 MSGF+

plotsSwissMsgf <- evalTargetDecoys(mzIdSwiss,decoy =  "isdecoy", score = "ms-gf:specevalue", log10 = TRUE)

## Warning: Removed 5127 rows containing missing values (geom_point).

plotsSwissMsgf$together

4.3 Xtandem

plotsSwissXtandem <- evalTargetDecoys(mzIdSwiss,decoy =  "isdecoy", score = "x!tandem:expect", log10 = TRUE)

## Warning: Removed 4951 rows containing missing values (geom_point).

plotsSwissXtandem$together

4.4 omssa

plotsSwissOmssa <- evalTargetDecoys(mzIdSwiss,decoy =  "isdecoy", score = "omssa:evalue", log10 = TRUE)

## Warning: Removed 4089 rows containing missing values (geom_point).

plotsSwissOmssa$together

4.5 PeptideShaker

plotsSwissShaker <- evalTargetDecoys(mzIdSwiss,decoy =  "isdecoy", score = "peptideshaker psm score", log10 = FALSE)

## Warning: Removed 5558 rows containing missing values (geom_point).

plotsSwissShaker$together