1输入池频率

aa_pool_x8 < - c(代表(' A ', 12),代表(“S”,0),代表(“T”,12),代表(' N ', 12),代表(“问”,12),代表(' D ', 8),代表(“E”,0),代表(“V”,12),代表(“L”,0),代表(“F”,0),代表(' Y ', 8),代表(' W ', 0),代表(“G”,12),代表(“P”,12))aa_pool_1_2_9_10 < - c(代表(' A ', 8),代表(“S”,7),代表(“T”,7),代表(' N ', 6),代表(“问”,6),代表(' D ', 8),代表(“E”,8),代表(“V”,9),代表(‘L’,6),代表(“F”,5),代表(' Y ', 9),代表(“W”,6),代表(“G”,15),代表(“P”,0))aa_pool_3_8 < - c(代表(' A ', 5),代表(“S”,4),代表(“T”,5),代表(' N ', 2),代表(“问”,2),代表(' D ', 8),代表(“E”,8),代表(“V”,7),代表(‘L’,5),代表(“F”,4),代表(' Y ', 6),代表(“W”,4),代表(“G”,12),代表(“P”,28岁))

2完整性检查

表(aa_pool_x8)

## A D G N P Q T V Y ## 12 12 12 12 12 12 12 12 12 12 8

长度(aa_pool_x8)

## [1] 100

表(aa_pool_1_2_9_10)

A D E F G L N Q S T V W Y ## 8 8 5 15 6 6 6 7 7 9 6 9 9 9

长度(aa_pool_1_2_9_10)

## [1] 100

表(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 6

长度(aa_pool_3_8)

## [1] 100

3.合成肽

复制(10,compose_GPGx8cTerm(池= aa_pool_x8))

##[1]“gpggdvaypqnvfgir”“gpggttvyqvyvsger”“gpgnnqgyggpvfr”“gpgynaaqqvpvfgir”##[5]“gpgtgtdygnnvsr”“gpgtatnptttvfr”“gpgqddpgtqtvsr”“gpgtnvgdaaqvsr”##[9]“gpgvggqvqntvfgir”“gpgaayvvattvfgir”

compose_GPx10R (aa_pool_1_2_9_10 aa_pool_3_8)

## [1] " gpywwtfdggygr "

4生成肽

set.seed(2)(样本。尺寸<- 3E+04)

## [1] 30000

肽。GPGx8cTerm <- replication (sample。size, compose_GPGx8cTerm(池=aa_pool_x8))多肽。GPx10R <- replication (sample。size, compose_GPx10R(aa_pool_1_2_9_10, aa_pool_3_8)) # write.table(肽。GPGx8cTerm文件=“/ tmp / pp.txt”)

5肽质量

图书馆(protViz (smp)。- compose_GPGx8cTerm(aa_pool_x8))

## [1] " gpgpddtdtygvfr "

parentIonMass (smp.peptide)

## [1] 1496.665

pim。GPGx8cTerm <- unlist(lapply(肽。GPGx8cTerm, function(x){parentIonMass(x)}))GPx10R <- unlist(lapply(肽。GPx10R, function(x){parentIonMass(x)}))iRT <- unlist(lapply(as.character(iRTpeptides$peptide)， function(x){parentIonMass(x)}))

(pim。Min <- Min (pim。GPGx8cTerm, pim.GPx10R))

## [1] 1037.512

(pim。Max <- Max (pim。GPGx8cTerm, pim.GPx10R))

## [1] 1890.877

(pim。断点<- seq(round(pim。Min - 1)，圆(pim。Max + 1)，长度=75))

## [9] 1129.432 1140.986 1152.541 1164.095 1187.203 1198.757 1210.311 ## [17] 1221.865 1233.419 1244.973 1279.681 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 ## [49] 1591.5951603.149 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 1892.000

嘘(pim。GPGx8cTerm休息= pim。，概率= TRUE, col='#1111AAAA'， xlab='肽质量[Dalton]'， ylim=c(0,0.006)) hist(pim.;GPx10R休息= pim。break，概率=TRUE, add=TRUE, col='#11AA1188') abline(v=pim。红外热成像,坳=传奇“灰色”)(“topleft”,c(‘GPGx8cTerm’,‘GPx10R’,红外热成像),填补= c(“# 1111 aaaa级”,“# 11 aa1133”,“灰色”))

6疏水性

library(specL) ssrc <- sapply(peptideStd，函数(x){ssrc(x$peptideSequence)}) rt <- unlist(lapply(peptideStd，函数(x){x$rt}) plot(ssrc, rt);abline(中心。Lm <- Lm (rt ~ ssrc)， col='red');Legend ("topleft"， paste("spearman"， round(cor(ssrc, rt, method='spearman')，2))))

海德拉巴。GPGx8cTerm <- ssrc(peptides.GPGx8cTerm) hyd。GPx10R <- ssrc(peptide .GPx10R) hyd。iRT <- ssrc(as.character(iRTpeptides$peptide)) (hyd。Min <- Min (hyd。GPGx8cTerm, hyd.GPx10R))

## [1] -7.63055

(海德拉巴。Max <- Max (hyd。GPGx8cTerm, hyd.GPx10R))

## [1] 65.12112

海德拉巴。中断<- seq(round(hyd. round)。Min - 1)，圆(hyd。Max + 1)，长度=75)

嘘(海德拉巴。GPGx8cTerm, breaks = hyd。，概率= TRUE, col='#1111AAAA'， xlab='疏水性'，ylim=c(0,0.06)， main='直方图')hist(hyd。GPx10R，断点= hyd。break，概率=TRUE, add=TRUE, col='#11AA1188')红外热成像,坳=传奇“灰色”)(“topleft”,c(‘GPGx8cTerm’,‘GPx10R’,红外热成像),填补= c(“# 1111 aaaa级”,“# 11 aa1133”,“灰色”))

7质量控制(QC)

轮(表(aa_pool_x8) /长度(aa_pool_x8), 2)

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 0.08

peptide2aa <- function(seq, from=4, to=4+8){unlist(lapply(seq, function(x){strsplit(substr(x, from, to)， ")}))} peptides.GPGx8cTerm。aa <- peptide2aa(peptids . gpgx8cterm) round(table(peptids . gpgx8cterm .aa)/length(peptids . gpgx8cterm .aa)， 2)

# # peptides.GPGx8cTerm。A D G N P Q T V Y ## 0.11 0.07 0.11 0.11 0.11 0.11 0.22 0.07

peptides.GPx10R。Aa <- peptide2aa(肽。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 0.07

sample.size

## [1] 30000

长度(grep (' ^ GP (. *) GP (. *) R美元”,peptides.GPGx8cTerm))

## [1] 6319

长度(grep (' ^ GP (. *) GP (. *) R美元”,peptides.GPx10R))

## [1] 5959

sample.size

## [1] 30000

表(表(tt < -unlist(拉普兰人(肽。GPGx8cTerm、功能(x){粘贴(排序(unlist (strsplit (x)))),崩溃=)}))))

## ## 12 34 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 11

#写。table(tt, file='GPGx8cTerm.txt') table(unlist(lapply(peptides. txt))GPx10R、功能(x){粘贴(排序(unlist (strsplit (x)))),崩溃=)}))))

## ## 1 2 3 4 5 ## 24844 2104 265 32 5

par(mfrow=c(2,2)) h <- NestLink:::. plot_in_silico_lcms_map(多肽。GPGx8cTerm, main='GPGx8cTerm') h <- NestLink:::. plot_in_silico_lcms_map(多肽。GPx10R主要=“GPx10R”)

8会话信息

的输出sessionInfo ()commmand。

## R版本4.2.1(2022-06-23)##平台:x86_64-pc-linux-gnu(64位)##运行在Ubuntu 20.04.5 LTS ## ##矩阵产品:默认## BLAS: /home/biocbuild/bbs-3.16-bioc/R/lib/libRblas。/home/biocbuild/bbs-3.16-bioc/R/lib/libRlapack。所以## ## 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_phone = c# # [11] LC_MEASUREMENT=en_US。UTF-8 LC_IDENTIFICATION=C ## ##附加的基本包:## [1]stats4 stats graphics grDevices utils datasets methods ##[8]基础## ##其他附加包:# # # # [1] specL_1.32.0 seqinr_4.2-16 [3] RSQLite_2.2.18 DBI_1.1.3 # # [5] knitr_1.40 scales_1.2.1 # # [7] ggplot2_3.3.6 NestLink_1.14.0 # # [9] ShortRead_1.56.0 GenomicAlignments_1.34.0 # # [11] SummarizedExperiment_1.28.0 Biobase_2.58.0 # # [13] MatrixGenerics_1.10.0 matrixStats_0.62.0 # # [15] Rsamtools_2.14.0 GenomicRanges_1.50.0 # # [17] BiocParallel_1.32.0 protViz_0.7.3 # # [19] gplots_3.1.3 Biostrings_2.66.0 # # [21] GenomeInfoDb_1.34.0 XVector_0.38.0 # # [23] IRanges_2.32.0 S4Vectors_0.36.0 # # [25]ExperimentHub_2.6.0 AnnotationHub_3.6.0 ## [27] BiocFileCache_2.6.0 dbplyr_2.2.1 ## [29] BiocGenerics_0.44.0 BiocStyle_2.26.0 ## ## loaded via a namespace (and not attached): ## [1] colorspace_2.0-3 deldir_1.0-6 ## [3] hwriter_1.3.2.1 ellipsis_0.3.2 ## [5] farver_2.1.1 bit64_4.0.5 ## [7] interactiveDisplayBase_1.36.0 AnnotationDbi_1.60.0 ## [9] fansi_1.0.3 codetools_0.2-18 ## [11] splines_4.2.1 cachem_1.0.6 ## [13] ade4_1.7-20 jsonlite_1.8.3 ## [15] png_0.1-7 shiny_1.7.3 ## [17] BiocManager_1.30.19 compiler_4.2.1 ## [19] httr_1.4.4 assertthat_0.2.1 ## [21] Matrix_1.5-1 fastmap_1.1.0 ## [23] cli_3.4.1 later_1.3.0 ## [25] htmltools_0.5.3 tools_4.2.1 ## [27] gtable_0.3.1 glue_1.6.2 ## [29] GenomeInfoDbData_1.2.9 dplyr_1.0.10 ## [31] rappdirs_0.3.3 Rcpp_1.0.9 ## [33] jquerylib_0.1.4 vctrs_0.5.0 ## [35] nlme_3.1-160 xfun_0.34 ## [37] stringr_1.4.1 mime_0.12 ## [39] lifecycle_1.0.3 gtools_3.9.3 ## [41] MASS_7.3-58.1 zlibbioc_1.44.0 ## [43] promises_1.2.0.1 parallel_4.2.1 ## [45] RColorBrewer_1.1-3 yaml_2.3.6 ## [47] curl_4.3.3 memoise_2.0.1 ## [49] sass_0.4.2 latticeExtra_0.6-30 ## [51] stringi_1.7.8 BiocVersion_3.16.0 ## [53] highr_0.9 caTools_1.18.2 ## [55] filelock_1.0.2 rlang_1.0.6 ## [57] pkgconfig_2.0.3 bitops_1.0-7 ## [59] evaluate_0.17 lattice_0.20-45 ## [61] purrr_0.3.5 labeling_0.4.2 ## [63] bit_4.0.4 tidyselect_1.2.0 ## [65] magrittr_2.0.3 bookdown_0.29 ## [67] R6_2.5.1 magick_2.7.3 ## [69] generics_0.1.3 DelayedArray_0.24.0 ## [71] pillar_1.8.1 withr_2.5.0 ## [73] mgcv_1.8-41 KEGGREST_1.38.0 ## [75] RCurl_1.98-1.9 tibble_3.1.8 ## [77] crayon_1.5.2 interp_1.1-3 ## [79] KernSmooth_2.23-20 utf8_1.2.2 ## [81] rmarkdown_2.17 jpeg_0.1-9 ## [83] grid_4.2.1 blob_1.2.3 ## [85] digest_0.6.30 xtable_1.8-4 ## [87] httpuv_1.6.6 munsell_0.5.0 ## [89] bslib_0.4.0