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 1.22.0
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] "GPGNQANQTGAVSGER" "GPGGTTQQQAYVSR" "GPGGNVVTAQAVSR" "GPGVTGPADNNVSGER"
## [5] "GPGNTADVTPNVSR" "GPGTPPNQGDVVSR" "GPGTNYQGTDPVSR" "GPGPAQDPTDTVSR"
## [9] "GPGPVATDQGPVSR" "GPGNYPATDTGVSR"3.2 GPYYXXXXXXYYR peptide
compose_GPx10R(aa_pool_1_2_9_10, aa_pool_3_8)## [1] "GPGTETEDPPAGR"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 4.4.1 (2024-06-14)
## Platform: x86_64-pc-linux-gnu
## Running under: Ubuntu 24.04.1 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.20-bioc/R/lib/libRblas.so
## LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.12.0
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_GB 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
##
## time zone: America/New_York
## tzcode source: system (glibc)
##
## attached base packages:
## [1] stats4 stats graphics grDevices utils datasets methods
## [8] base
##
## other attached packages:
## [1] specL_1.40.0 seqinr_4.2-36
## [3] RSQLite_2.3.7 DBI_1.2.3
## [5] knitr_1.48 scales_1.3.0
## [7] ggplot2_3.5.1 NestLink_1.22.0
## [9] ShortRead_1.64.0 GenomicAlignments_1.42.0
## [11] SummarizedExperiment_1.36.0 Biobase_2.66.0
## [13] MatrixGenerics_1.18.0 matrixStats_1.4.1
## [15] Rsamtools_2.22.0 GenomicRanges_1.58.0
## [17] BiocParallel_1.40.0 protViz_0.7.9
## [19] gplots_3.2.0 Biostrings_2.74.0
## [21] GenomeInfoDb_1.42.0 XVector_0.46.0
## [23] IRanges_2.40.0 S4Vectors_0.44.0
## [25] ExperimentHub_2.14.0 AnnotationHub_3.14.0
## [27] BiocFileCache_2.14.0 dbplyr_2.5.0
## [29] BiocGenerics_0.52.0 BiocStyle_2.34.0
##
## loaded via a namespace (and not attached):
## [1] bitops_1.0-9 deldir_2.0-4 rlang_1.1.4
## [4] magrittr_2.0.3 ade4_1.7-22 compiler_4.4.1
## [7] mgcv_1.9-1 png_0.1-8 vctrs_0.6.5
## [10] pwalign_1.2.0 pkgconfig_2.0.3 crayon_1.5.3
## [13] fastmap_1.2.0 magick_2.8.5 labeling_0.4.3
## [16] caTools_1.18.3 utf8_1.2.4 rmarkdown_2.29
## [19] UCSC.utils_1.2.0 tinytex_0.54 purrr_1.0.2
## [22] bit_4.5.0 xfun_0.49 zlibbioc_1.52.0
## [25] cachem_1.1.0 jsonlite_1.8.9 blob_1.2.4
## [28] highr_0.11 DelayedArray_0.32.0 jpeg_0.1-10
## [31] parallel_4.4.1 R6_2.5.1 bslib_0.8.0
## [34] RColorBrewer_1.1-3 jquerylib_0.1.4 Rcpp_1.0.13-1
## [37] bookdown_0.41 splines_4.4.1 Matrix_1.7-1
## [40] tidyselect_1.2.1 abind_1.4-8 yaml_2.3.10
## [43] codetools_0.2-20 hwriter_1.3.2.1 curl_5.2.3
## [46] lattice_0.22-6 tibble_3.2.1 withr_3.0.2
## [49] KEGGREST_1.46.0 evaluate_1.0.1 pillar_1.9.0
## [52] BiocManager_1.30.25 filelock_1.0.3 KernSmooth_2.23-24
## [55] generics_0.1.3 BiocVersion_3.20.0 munsell_0.5.1
## [58] gtools_3.9.5 glue_1.8.0 tools_4.4.1
## [61] interp_1.1-6 grid_4.4.1 latticeExtra_0.6-30
## [64] AnnotationDbi_1.68.0 colorspace_2.1-1 nlme_3.1-166
## [67] GenomeInfoDbData_1.2.13 cli_3.6.3 rappdirs_0.3.3
## [70] fansi_1.0.6 S4Arrays_1.6.0 dplyr_1.1.4
## [73] gtable_0.3.6 sass_0.4.9 digest_0.6.37
## [76] SparseArray_1.6.0 farver_2.1.2 memoise_2.0.1
## [79] htmltools_0.5.8.1 lifecycle_1.0.4 httr_1.4.7
## [82] mime_0.12 MASS_7.3-61 bit64_4.5.2References
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.