Derive Peptide Flycodes by Conducting Random Experiment
2015-04-01, 2015-04-28, 2015-04-29, 2015-04-30, 2015-10-24, 2018-12-17
Abstract
this is a preliminary in-silico experiment to analyze the detectability of a proposed flycode family. it considers the mass range, hydrophobicity and the cycle time of a mass spec device.
Package
NestLink 1.6.0
Contents
The following content is descibed in more detail in Egloff et al. (2018) (under review NMETH-A35040).
library(NestLink)
stopifnot(require(specL))1 Input Pool Frequency
aa_pool_x8 <- c(rep('A', 12), rep('S', 0), rep('T', 12), rep('N', 12),
rep('Q', 12), rep('D', 8), rep('E', 0), rep('V', 12), rep('L', 0),
rep('F', 0), rep('Y', 8), rep('W', 0), rep('G', 12), rep('P', 12))
aa_pool_1_2_9_10 <- c(rep('A', 8), rep('S', 7), rep('T', 7), rep('N', 6),
rep('Q', 6), rep('D', 8), rep('E', 8), rep('V', 9), rep('L', 6),
rep('F', 5), rep('Y', 9), rep('W', 6), rep('G', 15), rep('P', 0))
aa_pool_3_8 <- c(rep('A', 5), rep('S', 4), rep('T', 5), rep('N', 2),
rep('Q', 2), rep('D', 8), rep('E', 8), rep('V', 7), rep('L', 5),
rep('F', 4), rep('Y', 6), rep('W', 4), rep('G', 12), rep('P', 28))2 Sanity Check
table(aa_pool_x8)## aa_pool_x8
## A D G N P Q T V Y
## 12 8 12 12 12 12 12 12 8length(aa_pool_x8)## [1] 100table(aa_pool_1_2_9_10)## aa_pool_1_2_9_10
## A D E F G L N Q S T V W Y
## 8 8 8 5 15 6 6 6 7 7 9 6 9length(aa_pool_1_2_9_10)## [1] 100table(aa_pool_3_8)## aa_pool_3_8
## A D E F G L N P Q S T V W Y
## 5 8 8 4 12 5 2 28 2 4 5 7 4 6length(aa_pool_3_8)## [1] 1003 Compose Peptides
3.1 GPGXXXXXXXX(VR|VSR|VFGIR|VSGER) peptide
replicate(10, compose_GPGx8cTerm(pool=aa_pool_x8))## [1] "GPGNNVTTNVYVFR" "GPGPAVAGNGVVFR" "GPGNVYVQGDNVSGER" "GPGTVAANAGNVFR"
## [5] "GPGQNAQQNAGVFR" "GPGYPQAGANPVSR" "GPGPNQYQAVAVSGER" "GPGTVGPDTGQVSGER"
## [9] "GPGGTGGPNAYVFR" "GPGPDPNPGADVSR"3.2 GPYYXXXXXXYYR peptide
compose_GPx10R(aa_pool_1_2_9_10, aa_pool_3_8)## [1] "GPGGEVEEGPAQR"4 Generate peptides
set.seed(2)
(sample.size <- 3E+04)## [1] 30000peptides.GPGx8cTerm <- replicate(sample.size, compose_GPGx8cTerm(pool=aa_pool_x8))
peptides.GPx10R <- replicate(sample.size, compose_GPx10R(aa_pool_1_2_9_10, aa_pool_3_8))
# write.table(peptides.GPGx8cTerm, file='/tmp/pp.txt')5 Peptide mass
5.1 Compute peptide mass
library(protViz)
(smp.peptide <- compose_GPGx8cTerm(aa_pool_x8))## [1] "GPGPDDTDTYGVFR"parentIonMass(smp.peptide)## [1] 1496.665pim.GPGx8cTerm <- unlist(lapply(peptides.GPGx8cTerm, function(x){parentIonMass(x)}))
pim.GPx10R <- unlist(lapply(peptides.GPx10R, function(x){parentIonMass(x)}))
pim.iRT <- unlist(lapply(as.character(iRTpeptides$peptide), function(x){parentIonMass(x)}))5.2 Draw parent ion mass histogram
(pim.min <- min(pim.GPGx8cTerm, pim.GPx10R))## [1] 1037.512(pim.max <- max(pim.GPGx8cTerm, pim.GPx10R))## [1] 1890.877(pim.breaks <- seq(round(pim.min - 1) , round(pim.max + 1) , length=75))## [1] 1037.000 1048.554 1060.108 1071.662 1083.216 1094.770 1106.324 1117.878
## [9] 1129.432 1140.986 1152.541 1164.095 1175.649 1187.203 1198.757 1210.311
## [17] 1221.865 1233.419 1244.973 1256.527 1268.081 1279.635 1291.189 1302.743
## [25] 1314.297 1325.851 1337.405 1348.959 1360.514 1372.068 1383.622 1395.176
## [33] 1406.730 1418.284 1429.838 1441.392 1452.946 1464.500 1476.054 1487.608
## [41] 1499.162 1510.716 1522.270 1533.824 1545.378 1556.932 1568.486 1580.041
## [49] 1591.595 1603.149 1614.703 1626.257 1637.811 1649.365 1660.919 1672.473
## [57] 1684.027 1695.581 1707.135 1718.689 1730.243 1741.797 1753.351 1764.905
## [65] 1776.459 1788.014 1799.568 1811.122 1822.676 1834.230 1845.784 1857.338
## [73] 1868.892 1880.446 1892.000hist(pim.GPGx8cTerm, breaks=pim.breaks, probability = TRUE,
col='#1111AAAA', xlab='peptide mass [Dalton]', ylim=c(0, 0.006))
hist(pim.GPx10R, breaks=pim.breaks,
probability = TRUE, add=TRUE, col='#11AA1188')
abline(v=pim.iRT, col='grey')
legend("topleft", c('GPGx8cTerm', 'GPx10R', 'iRT'),
fill=c('#1111AAAA', '#11AA1133', 'grey'))
6 Hydrophobicity
6.1 Compute Hydrophobicity value using SSRC
the SSRC model, see Krokhin et al. (2004), is implemented as ssrc function in
protViz.
For a sanity check we apply the ssrc function
to a real world LC-MS run peptideStd consits of a digest of the
FETUIN_BOVINE
protein (400 amol) shipped with specL Panse et al. (2015).
library(specL)
ssrc <- sapply(peptideStd, function(x){ssrc(x$peptideSequence)})
rt <- unlist(lapply(peptideStd, function(x){x$rt}))
plot(ssrc, rt); abline(ssrc.lm <- lm(rt ~ ssrc), col='red');
legend("topleft", paste("spearman", round(cor(ssrc, rt, method='spearman'),2)))
here we apply ssrc to the simulated flycodes and iRT peptides Escher et al. (2012).
hyd.GPGx8cTerm <- ssrc(peptides.GPGx8cTerm)
hyd.GPx10R <- ssrc(peptides.GPx10R)
hyd.iRT <- ssrc(as.character(iRTpeptides$peptide))
(hyd.min <- min(hyd.GPGx8cTerm, hyd.GPx10R))## [1] -7.63055(hyd.max <- max(hyd.GPGx8cTerm, hyd.GPx10R))## [1] 65.12112hyd.breaks <- seq(round(hyd.min - 1) , round(hyd.max + 1) , length=75)6.2 Draw hydrophobicity histogram
hist(hyd.GPGx8cTerm, breaks = hyd.breaks, probability = TRUE,
col='#1111AAAA', xlab='hydrophobicity',
ylim=c(0, 0.06),
main='Histogram')
hist(hyd.GPx10R, breaks = hyd.breaks, probability = TRUE, add=TRUE, col='#11AA1188')
abline(v=hyd.iRT, col='grey')
legend("topleft", c('GPGx8cTerm', 'GPx10R', 'iRT'), fill=c('#1111AAAA', '#11AA1133', 'grey'))
7 Quality Control (QC)
7.1 QC of composed peptides
7.1.1 Input
round(table(aa_pool_x8)/length(aa_pool_x8), 2)## aa_pool_x8
## A D G N P Q T V Y
## 0.12 0.08 0.12 0.12 0.12 0.12 0.12 0.12 0.087.1.2 Output
peptide2aa <- function(seq, from=4, to=4+8){
unlist(lapply(seq, function(x){strsplit(substr(x, from, to), '')}))
}
peptides.GPGx8cTerm.aa <- peptide2aa(peptides.GPGx8cTerm)
round(table(peptides.GPGx8cTerm.aa)/length(peptides.GPGx8cTerm.aa), 2)## peptides.GPGx8cTerm.aa
## A D G N P Q T V Y
## 0.11 0.07 0.11 0.11 0.11 0.11 0.11 0.22 0.07peptides.GPx10R.aa <- peptide2aa(peptides.GPx10R, from=3, to=12)
round(table(peptides.GPx10R.aa)/length(peptides.GPx10R.aa), 2)## peptides.GPx10R.aa
## A D E F G L N P Q S T V W Y
## 0.06 0.08 0.08 0.04 0.13 0.05 0.04 0.17 0.04 0.05 0.06 0.08 0.05 0.077.2 Count GP patterns
sample.size ## [1] 30000length(grep('^GP(.*)GP(.*)R$', peptides.GPGx8cTerm))## [1] 6319length(grep('^GP(.*)GP(.*)R$', peptides.GPx10R))## [1] 59597.3 Compute AA frequency table
count the peptides having the same AA composition
sample.size ## [1] 30000table(table(tt<-unlist(lapply(peptides.GPGx8cTerm,
function(x){paste(sort(unlist(strsplit(x, ''))), collapse='')}))))##
## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 16 17
## 9541 3606 1607 792 427 204 104 50 34 20 6 5 6 2 1 1# write.table(tt, file='GPGx8cTerm.txt')
table(table(unlist(lapply(peptides.GPx10R,
function(x){paste(sort(unlist(strsplit(x, ''))), collapse='')}))))##
## 1 2 3 4 5
## 24844 2104 265 32 5the NestLink function plot_in_silico_LCMS_map graphs
the LC-MS maps.
par(mfrow=c(2, 2))
h <- NestLink:::.plot_in_silico_LCMS_map(peptides.GPGx8cTerm, main='GPGx8cTerm')
h <- NestLink:::.plot_in_silico_LCMS_map(peptides.GPx10R, main='GPx10R')
8 Session info
Here is the output of the sessionInfo() commmand.
## R version 4.0.3 (2020-10-10)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 18.04.5 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.12-bioc/R/lib/libRblas.so
## LAPACK: /home/biocbuild/bbs-3.12-bioc/R/lib/libRlapack.so
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_US.UTF-8 LC_COLLATE=C
## [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8
## [7] LC_PAPER=en_US.UTF-8 LC_NAME=C
## [9] LC_ADDRESS=C LC_TELEPHONE=C
## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
##
## attached base packages:
## [1] stats4 parallel stats graphics grDevices utils datasets
## [8] methods base
##
## other attached packages:
## [1] specL_1.24.0 seqinr_4.2-4
## [3] RSQLite_2.2.1 DBI_1.1.0
## [5] knitr_1.30 scales_1.1.1
## [7] ggplot2_3.3.2 NestLink_1.6.0
## [9] ShortRead_1.48.0 GenomicAlignments_1.26.0
## [11] SummarizedExperiment_1.20.0 Biobase_2.50.0
## [13] MatrixGenerics_1.2.0 matrixStats_0.57.0
## [15] Rsamtools_2.6.0 GenomicRanges_1.42.0
## [17] GenomeInfoDb_1.26.0 BiocParallel_1.24.0
## [19] protViz_0.6.8 gplots_3.1.0
## [21] Biostrings_2.58.0 XVector_0.30.0
## [23] IRanges_2.24.0 S4Vectors_0.28.0
## [25] ExperimentHub_1.16.0 AnnotationHub_2.22.0
## [27] BiocFileCache_1.14.0 dbplyr_1.4.4
## [29] BiocGenerics_0.36.0 BiocStyle_2.18.0
##
## loaded via a namespace (and not attached):
## [1] nlme_3.1-150 bitops_1.0-6
## [3] bit64_4.0.5 progress_1.2.2
## [5] RColorBrewer_1.1-2 httr_1.4.2
## [7] tools_4.0.3 R6_2.5.0
## [9] KernSmooth_2.23-17 mgcv_1.8-33
## [11] colorspace_1.4-1 ade4_1.7-16
## [13] withr_2.3.0 prettyunits_1.1.1
## [15] tidyselect_1.1.0 bit_4.0.4
## [17] curl_4.3 compiler_4.0.3
## [19] DelayedArray_0.16.0 labeling_0.4.2
## [21] bookdown_0.21 caTools_1.18.0
## [23] rappdirs_0.3.1 stringr_1.4.0
## [25] digest_0.6.27 rmarkdown_2.5
## [27] jpeg_0.1-8.1 pkgconfig_2.0.3
## [29] htmltools_0.5.0 highr_0.8
## [31] fastmap_1.0.1 rlang_0.4.8
## [33] shiny_1.5.0 farver_2.0.3
## [35] generics_0.0.2 hwriter_1.3.2
## [37] gtools_3.8.2 dplyr_1.0.2
## [39] RCurl_1.98-1.2 magrittr_1.5
## [41] GenomeInfoDbData_1.2.4 Matrix_1.2-18
## [43] Rcpp_1.0.5 munsell_0.5.0
## [45] lifecycle_0.2.0 stringi_1.5.3
## [47] yaml_2.2.1 MASS_7.3-53
## [49] zlibbioc_1.36.0 grid_4.0.3
## [51] blob_1.2.1 promises_1.1.1
## [53] crayon_1.3.4 lattice_0.20-41
## [55] splines_4.0.3 hms_0.5.3
## [57] magick_2.5.0 pillar_1.4.6
## [59] codetools_0.2-16 glue_1.4.2
## [61] BiocVersion_3.12.0 evaluate_0.14
## [63] latticeExtra_0.6-29 BiocManager_1.30.10
## [65] vctrs_0.3.4 png_0.1-7
## [67] httpuv_1.5.4 gtable_0.3.0
## [69] purrr_0.3.4 assertthat_0.2.1
## [71] xfun_0.18 mime_0.9
## [73] xtable_1.8-4 later_1.1.0.1
## [75] tibble_3.0.4 AnnotationDbi_1.52.0
## [77] memoise_1.1.0 ellipsis_0.3.1
## [79] interactiveDisplayBase_1.28.0References
Egloff, Pascal, Iwan Zimmermann, Fabian M. Arnold, Cedric A. J. Hutter, Damien Damien Morger, Lennart Opitz, Lucy Poveda, et al. 2018. “Engineered Peptide Barcodes for In-Depth Analyses of Binding Protein Ensembles.” bioRxiv. https://doi.org/10.1101/287813.
Escher, C., L. Reiter, B. MacLean, R. Ossola, F. Herzog, J. Chilton, M. J. MacCoss, and O. Rinner. 2012. “Using iRT, a normalized retention time for more targeted measurement of peptides.” Proteomics 12 (8): 1111–21.
Krokhin, O. V., R. Craig, V. Spicer, W. Ens, K. G. Standing, R. C. Beavis, and J. A. Wilkins. 2004. “An improved model for prediction of retention times of tryptic peptides in ion pair reversed-phase HPLC: its application to protein peptide mapping by off-line HPLC-MALDI MS.” Mol. Cell Proteomics 3 (9): 908–19.
Panse, C., C. Trachsel, J. Grossmann, and R. Schlapbach. 2015. “specL–an R/Bioconductor package to prepare peptide spectrum matches for use in targeted proteomics.” Bioinformatics 31 (13): 2228–31.