library(clusterProfiler)
library(org.Dm.eg.db)
library(dplyr)
library(ggplot2)

plotTheme = theme(
    axis.title = element_text(family = "Arial", face = "bold", size = 16),
    legend.title = element_text(family = "Arial", face = "bold", size = 16), 
    text = element_text(family = "Arial",size = 14))

clusterProfiler v4.6.2  For help: https://yulab-smu.top/biomedical-knowledge-mining-book/

If you use clusterProfiler in published research, please cite:
T Wu, E Hu, S Xu, M Chen, P Guo, Z Dai, T Feng, L Zhou, W Tang, L Zhan, X Fu, S Liu, X Bo, and G Yu. clusterProfiler 4.0: A universal enrichment tool for interpreting omics data. The Innovation. 2021, 2(3):100141


Attaching package: ‘clusterProfiler’


The following object is masked from ‘package:stats’:

    filter


Loading required package: AnnotationDbi

Loading required package: stats4

Loading required package: BiocGenerics


Attaching package: ‘BiocGenerics’


The following objects are masked from ‘package:stats’:

    IQR, mad, sd, var, xtabs


The following objects are masked from ‘package:base’:

    anyDuplicated, aperm, append, as.data.frame, basename, cbind,
    colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,
    get, grep, grepl, intersect, is.unsorted, lapply, Map, mapply,
    match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,
    Position, rank, rbind, Reduce, rownames, sapply, setdiff, sort,
    table, tapply, union, unique, unsplit, which.max, which.min


Loading required package: Biobase

Welcome to Bioconductor

    Vignettes contain introductory material; view with
    'browseVignettes()'. To cite Bioconductor, see
    'citation("Biobase")', and for packages 'citation("pkgname")'.


Loading required package: IRanges

Loading required package: S4Vectors


Attaching package: ‘S4Vectors’


The following object is masked from ‘package:clusterProfiler’:

    rename


The following objects are masked from ‘package:base’:

    expand.grid, I, unname



Attaching package: ‘IRanges’


The following object is masked from ‘package:clusterProfiler’:

    slice



Attaching package: ‘AnnotationDbi’


The following object is masked from ‘package:clusterProfiler’:

    select





Attaching package: ‘dplyr’


The following object is masked from ‘package:AnnotationDbi’:

    select


The following objects are masked from ‘package:IRanges’:

    collapse, desc, intersect, setdiff, slice, union


The following objects are masked from ‘package:S4Vectors’:

    first, intersect, rename, setdiff, setequal, union


The following object is masked from ‘package:Biobase’:

    combine


The following objects are masked from ‘package:BiocGenerics’:

    combine, intersect, setdiff, union


The following objects are masked from ‘package:stats’:

    filter, lag


The following objects are masked from ‘package:base’:

    intersect, setdiff, setequal, union

anaGO = function(geneids,prefix){
    res = enrichGO(geneids,OrgDb = 'org.Dm.eg.db',keyType = 'ENTREZID',ont = 'ALL',readable = TRUE,maxGSSize = 300)
    if(!is.null(res)){
        write.csv(res@result,file = paste0('data/',prefix,'_GO.csv'))
        resTable = res@result[order(res@result$p.adjust),]
        resTable = resTable %>% group_by(ONTOLOGY) %>% top_n(-p.adjust,n = 10)
        p = ggplot(data = resTable,
                   aes(
                       x = reorder(Description,-p.adjust),
                       y = -log10(p.adjust),
                       fill = ONTOLOGY,
                       label = reorder(Count,-p.adjust)
                    )
            )+
            geom_bar(stat = 'identity')+
            geom_text(stat = 'identity',hjust = 1.2)+
            coord_flip()+
            facet_grid(ONTOLOGY~.,scales = 'free',space = 'free')+
            labs(x = '',fill = '')+
            theme_classic()+
            scale_fill_manual(
                breaks = c('BP','CC','MF'),
                labels = c('BP','CC','MF'),
                values = c('#ffc64b','#66CC33','#33ccff')
            )+
            theme(strip.text = element_blank(),
                  axis.line.y = element_blank(),
                  axis.ticks.y = element_blank(),
                  axis.title.x = element_text(size = 14),
                  text = element_text(size = 12),
                  axis.text = element_text(size = 12))+plotTheme
        ggsave(filename = paste0('pics/',prefix,'_GO.png'),plot = p,dpi = 300,width = 10,height = 8,bg = 'white')
        p
    }else{
        print(paste0('No GO terms enriched in ',prefix,'!!!!'))
    }
}

agingDEG = read.csv('data/aging_DEG.csv',header = TRUE,row.names = 1)
agingDEG

down = agingDEG$names[agingDEG$status=='down']
geneTmp = bitr(down,fromType = 'SYMBOL',toType = 'ENTREZID',OrgDb = 'org.Dm.eg.db',drop = FALSE)
numTmp = sum(is.na(geneTmp[,2]))
print(paste0(numTmp,' genes failed to map.'))
geneTmp[is.na(geneTmp[,2]),]

'select()' returned 1:1 mapping between keys and columns

Warning message in bitr(down, fromType = "SYMBOL", toType = "ENTREZID", OrgDb = "org.Dm.eg.db", :
“1.55% of input gene IDs are fail to map...”


[1] "19 genes failed to map."

anaGO(na.omit(geneTmp[,2]),prefix = 'aging_down')

roxRNAiDEG = read.csv('data/roxRNAi_DEG.csv',header = TRUE,row.names = 1)
roxRNAiDEG

up = roxRNAiDEG$names[roxRNAiDEG$status=='up']
geneTmp = bitr(up,fromType = 'SYMBOL',toType = 'ENTREZID',OrgDb = 'org.Dm.eg.db',drop = FALSE)
numTmp = sum(is.na(geneTmp[,2]))
print(paste0(numTmp,' genes failed to map.'))
geneTmp[is.na(geneTmp[,2]),]

'select()' returned 1:1 mapping between keys and columns

Warning message in bitr(up, fromType = "SYMBOL", toType = "ENTREZID", OrgDb = "org.Dm.eg.db", :
“1.26% of input gene IDs are fail to map...”


[1] "63 genes failed to map."

anaGO(na.omit(geneTmp[,2]),prefix = 'roxRNAi_up')

inter = intersect(down,up)
geneTmp = bitr(inter,fromType = 'SYMBOL',toType = 'ENTREZID',OrgDb = 'org.Dm.eg.db',drop = FALSE)
numTmp = sum(is.na(geneTmp[,2]))
print(paste0(numTmp,' genes failed to map.'))
geneTmp[is.na(geneTmp[,2]),]

'select()' returned 1:1 mapping between keys and columns

Warning message in bitr(inter, fromType = "SYMBOL", toType = "ENTREZID", OrgDb = "org.Dm.eg.db", :
“1.25% of input gene IDs are fail to map...”


[1] "13 genes failed to map."

anaGO(na.omit(geneTmp[,2]),prefix = 'intersection')

write(inter,file = 'inter.txt')

sessionInfo()

R version 4.2.2 (2022-10-31)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: CentOS Linux 7 (Core)

Matrix products: default
BLAS:   /usr/local/lib64/R/lib/libRblas.so
LAPACK: /usr/local/lib64/R/lib/libRlapack.so

locale:
 [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
 [3] LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8    
 [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    stats     graphics  grDevices utils     datasets  methods  
[8] base     

other attached packages:
 [1] jsonlite_1.8.7        formatR_1.14          ggplot2_3.4.1        
 [4] dplyr_1.1.1           org.Dm.eg.db_3.16.0   AnnotationDbi_1.60.2 
 [7] IRanges_2.32.0        S4Vectors_0.36.2      Biobase_2.58.0       
[10] BiocGenerics_0.44.0   clusterProfiler_4.6.2

loaded via a namespace (and not attached):
  [1] fgsea_1.24.0           colorspace_2.1-0       ggtree_3.6.2          
  [4] gson_0.1.0             IRdisplay_1.1          qvalue_2.30.0         
  [7] XVector_0.38.0         base64enc_0.1-3        aplot_0.1.10          
 [10] farver_2.1.1           graphlayouts_0.8.4     ggrepel_0.9.3         
 [13] bit64_4.0.5            fansi_1.0.4            scatterpie_0.1.8      
 [16] codetools_0.2-18       splines_4.2.2          cachem_1.0.8          
 [19] GOSemSim_2.24.0        polyclip_1.10-4        IRkernel_1.3.2.9000   
 [22] Cairo_1.6-0            GO.db_3.16.0           png_0.1-8             
 [25] ggforce_0.4.1          compiler_4.2.2         httr_1.4.6            
 [28] Matrix_1.5-4           fastmap_1.1.1          lazyeval_0.2.2        
 [31] cli_3.6.1              tweenr_2.0.2           htmltools_0.5.5       
 [34] tools_4.2.2            igraph_1.5.0           gtable_0.3.3          
 [37] glue_1.6.2             GenomeInfoDbData_1.2.9 reshape2_1.4.4        
 [40] fastmatch_1.1-3        Rcpp_1.0.11            enrichplot_1.18.3     
 [43] vctrs_0.6.0            Biostrings_2.66.0      ape_5.7-1             
 [46] nlme_3.1-160           ggraph_2.1.0           stringr_1.5.0         
 [49] lifecycle_1.0.3        DOSE_3.24.2            zlibbioc_1.44.0       
 [52] MASS_7.3-58.1          scales_1.2.1           tidygraph_1.2.3       
 [55] ragg_1.2.4             parallel_4.2.2         RColorBrewer_1.1-3    
 [58] memoise_2.0.1          gridExtra_2.3          downloader_0.4        
 [61] ggfun_0.0.9            HDO.db_0.99.1          yulab.utils_0.0.6     
 [64] stringi_1.7.12         RSQLite_2.3.0          tidytree_0.4.2        
 [67] BiocParallel_1.32.6    repr_1.1.6             GenomeInfoDb_1.34.9   
 [70] rlang_1.1.1            pkgconfig_2.0.3        systemfonts_1.0.4     
 [73] bitops_1.0-7           evaluate_0.21          lattice_0.20-45       
 [76] purrr_1.0.1            treeio_1.22.0          patchwork_1.1.2       
 [79] labeling_0.4.2         cowplot_1.1.1          shadowtext_0.1.2      
 [82] bit_4.0.5              tidyselect_1.2.0       plyr_1.8.8            
 [85] magrittr_2.0.3         R6_2.5.1               generics_0.1.3        
 [88] pbdZMQ_0.3-9           DBI_1.1.3              pillar_1.9.0          
 [91] withr_2.5.0            KEGGREST_1.38.0        RCurl_1.98-1.12       
 [94] tibble_3.2.1           crayon_1.5.2           uuid_1.1-0            
 [97] utf8_1.2.3             viridis_0.6.2          grid_4.2.2            
[100] data.table_1.14.8      blob_1.2.4             digest_0.6.33         
[103] tidyr_1.3.0            gridGraphics_0.5-1     textshaping_0.3.6     
[106] munsell_0.5.0          viridisLite_0.4.2      ggplotify_0.1.0