Análise de dados de proteômica do artigo publicado por Lomate et al. 2018
Pedro Alexander Velasquez-Vasconez e Diego Zanardo Gallan
03/06/2021
1. Carregando os pacotes
library(readxl)
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(reshape)##
## Attaching package: 'reshape'## The following object is masked from 'package:dplyr':
##
## renamelibrary(openxlsx)
library(reshape2)##
## Attaching package: 'reshape2'## The following objects are masked from 'package:reshape':
##
## colsplit, melt, recastlibrary(ggplot2)1. Carregando os dados disponibilizados por Lomate et al. 2018
Early <- read_excel("C:/Users/Alex/Google Drive/Backup_PCacer_28_11_2020/Doutorado/Datos/RNAseq/Lomate-2018/Proteoma_H_armigera_alimentada_com_inibidores_Lomate_etal_2018.xlsx",
sheet = "Early")[,c(2,3,4,5, 12,13,14)];head(Early)## # A tibble: 6 x 7
## Accession Description `Peptides(95%)` `%Coverage` `p-value` `Fold Change`
## <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 Not annot~ Not annotated 907 80.5 0.294 1.37
## 2 ABQ23674.1 very high dens~ 238 78.5 0.00316 0.874
## 3 Not annot~ Not annotated 225 66.8 0.0000916 0.832
## 4 AAZ31061.1 actin 6 [Aedes~ 217 92.1 0.0423 0.953
## 5 AEG78288.1 heat shock pro~ 201 85.9 0.00038 0.819
## 6 EHJ64315.1 H+ transportin~ 150 86.0 0.00418 1.14
## # ... with 1 more variable: Log (Fold Change) <dbl>Mid <- read_excel("C:/Users/Alex/Google Drive/Backup_PCacer_28_11_2020/Doutorado/Datos/RNAseq/Lomate-2018/Proteoma_H_armigera_alimentada_com_inibidores_Lomate_etal_2018.xlsx",
sheet = "Mid")[,c(2,3,4,5, 12,13,14)];head(Mid)## # A tibble: 6 x 7
## Accession Description `Peptides(95%)` `%Coverage` `p-value` `Fold Change`
## <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 Not annot~ Not annotated 793 80.5 4.86e-1 0.943
## 2 Not annot~ Not annotated 254 72.7 6.75e-5 0.307
## 3 ABQ23674.1 very high dens~ 194 81.3 1.89e-3 0.502
## 4 AAZ31061.1 actin 6 [Aedes~ 187 94.7 5.08e-7 2.39
## 5 AEG78288.1 heat shock pro~ 187 90.5 4.03e-2 0.680
## 6 ADD22718.1 arginine kinas~ 114 79.8 2.55e-1 1.17
## # ... with 1 more variable: Log (Fold Change) <dbl>Late <- read_excel("C:/Users/Alex/Google Drive/Backup_PCacer_28_11_2020/Doutorado/Datos/RNAseq/Lomate-2018/Proteoma_H_armigera_alimentada_com_inibidores_Lomate_etal_2018.xlsx",
sheet = "Late")[,c(2,3,4,5, 12,13,14)];head(Late)## # A tibble: 6 x 7
## Accession Description `Peptides(95%)` `%Coverage` `p-value` `Fold Change`
## <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 Not annot~ Not annotated 794 78.4 0.0234 1.20
## 2 ABQ23674.1 very high dens~ 289 83.4 0.00014 1.18
## 3 AAZ31061.1 actin 6 [Aedes~ 215 93.4 0.00358 1.87
## 4 Not annot~ Not annotated 178 62.9 0.0370 1.03
## 5 AEG78288.1 heat shock pro~ 143 86.5 0.00087 0.740
## 6 ADD22718.1 arginine kinas~ 126 79.5 0.0532 1.06
## # ... with 1 more variable: Log (Fold Change) <dbl>2. Filtrando os valores de acordo com o nível de signicância p-value<0.05
Early_sig<- Early[Early$`p-value`<0.05, ]; head(Early_sig)## # A tibble: 6 x 7
## Accession Description `Peptides(95%)` `%Coverage` `p-value` `Fold Change`
## <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 ABQ23674.1 very high dens~ 238 78.5 0.00316 0.874
## 2 Not annot~ Not annotated 225 66.8 0.0000916 0.832
## 3 AAZ31061.1 actin 6 [Aedes~ 217 92.1 0.0423 0.953
## 4 AEG78288.1 heat shock pro~ 201 85.9 0.00038 0.819
## 5 EHJ64315.1 H+ transportin~ 150 86.0 0.00418 1.14
## 6 ADD22718.1 arginine kinas~ 142 77.0 0.00025 1.37
## # ... with 1 more variable: Log (Fold Change) <dbl>Mid_sig<- Mid[Mid$`p-value`<0.05, ]; head(Mid_sig)## # A tibble: 6 x 7
## Accession Description `Peptides(95%)` `%Coverage` `p-value` `Fold Change`
## <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 Not annot~ Not annotated 254 72.7 6.75e-5 0.307
## 2 ABQ23674.1 very high dens~ 194 81.3 1.89e-3 0.502
## 3 AAZ31061.1 actin 6 [Aedes~ 187 94.7 5.08e-7 2.39
## 4 AEG78288.1 heat shock pro~ 187 90.5 4.03e-2 0.680
## 5 AEB26315.1 heat shock pro~ 108 73.8 1.81e-5 0.709
## 6 EHJ74635.1 putative Spect~ 106 68.4 1.13e-3 0.599
## # ... with 1 more variable: Log (Fold Change) <dbl>Late_sig<- Late[Late$`p-value`<0.05, ]; head(Late_sig)## # A tibble: 6 x 7
## Accession Description `Peptides(95%)` `%Coverage` `p-value` `Fold Change`
## <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 Not annot~ Not annotated 794 78.4 0.0234 1.20
## 2 ABQ23674.1 very high dens~ 289 83.4 0.00014 1.18
## 3 AAZ31061.1 actin 6 [Aedes~ 215 93.4 0.00358 1.87
## 4 Not annot~ Not annotated 178 62.9 0.0370 1.03
## 5 AEG78288.1 heat shock pro~ 143 86.5 0.00087 0.740
## 6 EHJ74635.1 putative Spect~ 103 66.9 0.00423 0.792
## # ... with 1 more variable: Log (Fold Change) <dbl>3. Removendo os peptideos não anotados
Early_sig_anotated<-Early_sig[!(Early_sig$Description=="Not annotated"),]
head(Early_sig_anotated)## # A tibble: 6 x 7
## Accession Description `Peptides(95%)` `%Coverage` `p-value` `Fold Change`
## <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 ABQ23674.1 very high dens~ 238 78.5 0.00316 0.874
## 2 AAZ31061.1 actin 6 [Aedes~ 217 92.1 0.0423 0.953
## 3 AEG78288.1 heat shock pro~ 201 85.9 0.00038 0.819
## 4 EHJ64315.1 H+ transportin~ 150 86.0 0.00418 1.14
## 5 ADD22718.1 arginine kinas~ 142 77.0 0.00025 1.37
## 6 AAL83698.1 translation el~ 128 80.9 0.00108 0.890
## # ... with 1 more variable: Log (Fold Change) <dbl>Mid_sig_anotated<-Mid_sig[!(Mid_sig$Description=="Not annotated"),]
head(Mid_sig_anotated)## # A tibble: 6 x 7
## Accession Description `Peptides(95%)` `%Coverage` `p-value` `Fold Change`
## <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 ABQ23674.1 very high dens~ 194 81.3 1.89e-3 0.502
## 2 AAZ31061.1 actin 6 [Aedes~ 187 94.7 5.08e-7 2.39
## 3 AEG78288.1 heat shock pro~ 187 90.5 4.03e-2 0.680
## 4 AEB26315.1 heat shock pro~ 108 73.8 1.81e-5 0.709
## 5 EHJ74635.1 putative Spect~ 106 68.4 1.13e-3 0.599
## 6 AAL83698.1 translation el~ 103 79.6 4.22e-3 0.704
## # ... with 1 more variable: Log (Fold Change) <dbl>Late_sig_anotated<-Late_sig[!(Late_sig$Description=="Not annotated"),]
head(Late_sig_anotated)## # A tibble: 6 x 7
## Accession Description `Peptides(95%)` `%Coverage` `p-value` `Fold Change`
## <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 ABQ23674.1 very high dens~ 289 83.4 0.00014 1.18
## 2 AAZ31061.1 actin 6 [Aedes~ 215 93.4 0.00358 1.87
## 3 AEG78288.1 heat shock pro~ 143 86.5 0.00087 0.740
## 4 EHJ74635.1 putative Spect~ 103 66.9 0.00423 0.792
## 5 EHJ66053.1 filamin [Danau~ 94 79.0 0.0000733 1.34
## 6 AEB26315.1 heat shock pro~ 92 67.2 0.00823 0.912
## # ... with 1 more variable: Log (Fold Change) <dbl>4. Analysis de abundância de peptideos nas três epocas
Early_e_Mid<-Early_sig_anotated[,1]%>%inner_join(Mid_sig_anotated)## Joining, by = "Accession"Early_e_Late<-Early_sig_anotated[,1]%>%inner_join(Late_sig_anotated)## Joining, by = "Accession"Mid_e_Late<-Mid_sig_anotated[,1]%>%inner_join(Late_sig_anotated)## Joining, by = "Accession"Early_Mid_Late<-Early_e_Mid[,1]%>%inner_join(Late_sig_anotated)## Joining, by = "Accession"Early_Mid_Late## # A tibble: 113 x 7
## Accession Description `Peptides(95%)` `%Coverage` `p-value` `Fold Change`
## <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 ABQ23674.1 very high den~ 289 83.4 1.4 e-4 1.18
## 2 AAZ31061.1 actin 6 [Aede~ 215 93.4 3.58e-3 1.87
## 3 AEG78288.1 heat shock pr~ 143 86.5 8.7 e-4 0.740
## 4 EHJ64315.1 H+ transporti~ 87 84.5 3.02e-6 0.486
## 5 AAL83698.1 translation e~ 78 70.1 3.3 e-4 1.46
## 6 AEB26315.1 heat shock pr~ 92 67.2 8.23e-3 0.912
## 7 NP_001037~ protein disul~ 58 88.1 1.2 e-4 0.789
## 8 BAM19807.1 unknown unsec~ 70 85.6 1.38e-2 1.63
## 9 ADF45669.1 translational~ 49 80.5 1.18e-6 0.705
## 10 BAM17768.1 paramyosin [P~ 80 67.0 2.09e-3 0.829
## # ... with 103 more rows, and 1 more variable: Log (Fold Change) <dbl>5. Organizando os peptideos diferencialmente abundantes dos três tratamentos em uma única tabela
a<-Early_Mid_Late[,1]%>%inner_join(Early_sig_anotated[,c(1,7)])%>%
unique()## Joining, by = "Accession"b<-Early_Mid_Late[,1]%>%inner_join(Mid_sig_anotated[,c(1,7)])%>%
unique()## Joining, by = "Accession"c<-Early_Mid_Late[,1]%>%inner_join (Late_sig_anotated[,c(1,7)])%>%
unique()## Joining, by = "Accession"ab<-full_join(a,b, by = "Accession")
df<-full_join(ab,c,by = "Accession")
names(df)<-c("Accession","Early","Mid", "Late")
df<-melt(df, id.vars = 1)
df<-unique(df)%>%inner_join(Early[,1:2])## Joining, by = "Accession"head(df)## Accession variable value
## 1 ABQ23674.1 Early -0.05844210
## 2 AAZ31061.1 Early -0.02080922
## 3 AEG78288.1 Early -0.08681964
## 4 EHJ64315.1 Early 0.05765239
## 5 AAL83698.1 Early -0.05062564
## 6 AEB26315.1 Early -0.04632465
## Description
## 1 very high density lipoprotein [Helicoverpa zea]
## 2 actin 6 [Aedes aegypti]
## 3 heat shock protein 70 [Agrotis ipsilon]
## 4 H+ transporting ATP synthase beta subunit isoform 2 [Danaus plexippus]
## 5 translation elongation factor 2 [Spodoptera exigua]
## 6 heat shock protein [Helicoverpa armigera]6. Selecionando as proteinas potencialmente envolvidas na adaptação da Helicoverpa armgiera à alimentação com inibidores de peptidase de Capiscum annuum
#write.xlsx(df, 'C:/Users/Alex/Google Drive/Backup_PCacer_28_11_2020/Doutorado/Datos/RNAseq/Lomate-2018/df1.xlsx')
genes_resposta<-read_excel("C:/Users/Alex/Google Drive/Backup_PCacer_28_11_2020/Doutorado/Datos/RNAseq/Lomate-2018/df1.xlsx",
sheet = "Genes_Resposta")
genes_resposta## # A tibble: 12 x 2
## Accession Description
## <chr> <chr>
## 1 XP_004516876.1 heat shock protein 70
## 2 NP_001040146.1 translation elongation factor 2
## 3 BAM19446.1 heat shock protein
## 4 NP_001040460.1 heat shock protein 70
## 5 XP_004926654.1 eukaryotic translation initiation factor 3 subunit B
## 6 NP_001166724.1 trypsin-like protease
## 7 Q962R1.1 trypsin-like protease
## 8 XP_004925737.1 diverged serine protease
## 9 XP_004923167.1 elongation factor 1 gamma
## 10 ACU09495.1 chymotrypsin-like protease
## 11 AAF70499.1 chaperonin
## 12 NP_001040478.1 glutathione S-transferase 16df2<-as.data.frame(df)%>%inner_join(as.data.frame(genes_resposta), by = "Accession")
df2## Accession variable value
## 1 XP_004516876.1 Early 0.17258616
## 2 NP_001040146.1 Early 0.13479269
## 3 BAM19446.1 Early -0.14980118
## 4 NP_001040460.1 Early -0.05152901
## 5 XP_004926654.1 Early 0.60589836
## 6 NP_001166724.1 Early 0.30976333
## 7 Q962R1.1 Early -0.04392794
## 8 XP_004925737.1 Early -0.13131213
## 9 XP_004923167.1 Early -0.15406634
## 10 ACU09495.1 Early 0.36300051
## 11 AAF70499.1 Early 0.38064262
## 12 NP_001040478.1 Early 0.09335017
## 13 XP_004516876.1 Mid 0.25510741
## 14 NP_001040146.1 Mid 0.14886898
## 15 BAM19446.1 Mid 0.24067659
## 16 NP_001040460.1 Mid 0.05621384
## 17 XP_004926654.1 Mid 0.12509050
## 18 NP_001166724.1 Mid -0.46471479
## 19 Q962R1.1 Mid -0.23209674
## 20 XP_004925737.1 Mid 0.74125566
## 21 XP_004923167.1 Mid 0.13624042
## 22 ACU09495.1 Mid 0.55995448
## 23 AAF70499.1 Mid 0.45862819
## 24 NP_001040478.1 Mid 0.44721598
## 25 XP_004516876.1 Late 0.33752276
## 26 NP_001040146.1 Late 0.16227592
## 27 BAM19446.1 Late 0.18816003
## 28 NP_001040460.1 Late -0.09929125
## 29 XP_004926654.1 Late -0.41983541
## 30 NP_001166724.1 Late -0.74501597
## 31 Q962R1.1 Late -0.38402748
## 32 XP_004925737.1 Late 0.16639745
## 33 XP_004923167.1 Late 0.17285755
## 34 ACU09495.1 Late -0.36782900
## 35 AAF70499.1 Late 0.15149306
## 36 NP_001040478.1 Late 0.31630776
## Description.x
## 1 PREDICTED: albumin-2-like [Cicer arietinum]
## 2 proteasome zeta subunit [Bombyx mori]
## 3 isocitrate dehydrogenase partial [Papilio xuthus]
## 4 proteasome beta 3 subunit [Bombyx mori]
## 5 PREDICTED: calexcitin-2-like [Bombyx mori]
## 6 cuticular protein RR-1 motif 26 precursor [Bombyx mori]
## 7 RS18_SPOFRRecName: Full=40S ribosomal protein S18
## 8 PREDICTED: flavin reductase (NADPH)-like isoform X1 [Bombyx mori]
## 9 PREDICTED: lactoylglutathione lyase-like isoform X1 [Bombyx mori]
## 10 glutathione S-transferase 16 [Helicoverpa armigera]
## 11 AF255341_13-dehydroecdysone 3alpha-reductase [Spodoptera littoralis]
## 12 NADH dehydrogenase [ubiquinone] 1 beta subcomplex subunit 10 [Bombyx mori]
## 13 PREDICTED: albumin-2-like [Cicer arietinum]
## 14 proteasome zeta subunit [Bombyx mori]
## 15 isocitrate dehydrogenase partial [Papilio xuthus]
## 16 proteasome beta 3 subunit [Bombyx mori]
## 17 PREDICTED: calexcitin-2-like [Bombyx mori]
## 18 cuticular protein RR-1 motif 26 precursor [Bombyx mori]
## 19 RS18_SPOFRRecName: Full=40S ribosomal protein S18
## 20 PREDICTED: flavin reductase (NADPH)-like isoform X1 [Bombyx mori]
## 21 PREDICTED: lactoylglutathione lyase-like isoform X1 [Bombyx mori]
## 22 glutathione S-transferase 16 [Helicoverpa armigera]
## 23 AF255341_13-dehydroecdysone 3alpha-reductase [Spodoptera littoralis]
## 24 NADH dehydrogenase [ubiquinone] 1 beta subcomplex subunit 10 [Bombyx mori]
## 25 PREDICTED: albumin-2-like [Cicer arietinum]
## 26 proteasome zeta subunit [Bombyx mori]
## 27 isocitrate dehydrogenase partial [Papilio xuthus]
## 28 proteasome beta 3 subunit [Bombyx mori]
## 29 PREDICTED: calexcitin-2-like [Bombyx mori]
## 30 cuticular protein RR-1 motif 26 precursor [Bombyx mori]
## 31 RS18_SPOFRRecName: Full=40S ribosomal protein S18
## 32 PREDICTED: flavin reductase (NADPH)-like isoform X1 [Bombyx mori]
## 33 PREDICTED: lactoylglutathione lyase-like isoform X1 [Bombyx mori]
## 34 glutathione S-transferase 16 [Helicoverpa armigera]
## 35 AF255341_13-dehydroecdysone 3alpha-reductase [Spodoptera littoralis]
## 36 NADH dehydrogenase [ubiquinone] 1 beta subcomplex subunit 10 [Bombyx mori]
## Description.y
## 1 heat shock protein 70
## 2 translation elongation factor 2
## 3 heat shock protein
## 4 heat shock protein 70
## 5 eukaryotic translation initiation factor 3 subunit B
## 6 trypsin-like protease
## 7 trypsin-like protease
## 8 diverged serine protease
## 9 elongation factor 1 gamma
## 10 chymotrypsin-like protease
## 11 chaperonin
## 12 glutathione S-transferase 16
## 13 heat shock protein 70
## 14 translation elongation factor 2
## 15 heat shock protein
## 16 heat shock protein 70
## 17 eukaryotic translation initiation factor 3 subunit B
## 18 trypsin-like protease
## 19 trypsin-like protease
## 20 diverged serine protease
## 21 elongation factor 1 gamma
## 22 chymotrypsin-like protease
## 23 chaperonin
## 24 glutathione S-transferase 16
## 25 heat shock protein 70
## 26 translation elongation factor 2
## 27 heat shock protein
## 28 heat shock protein 70
## 29 eukaryotic translation initiation factor 3 subunit B
## 30 trypsin-like protease
## 31 trypsin-like protease
## 32 diverged serine protease
## 33 elongation factor 1 gamma
## 34 chymotrypsin-like protease
## 35 chaperonin
## 36 glutathione S-transferase 167. Plotando os resultados
ggplot(df2, aes(variable, Description.y , fill= value)) +
geom_tile()