In [30]:
#libraries
library(GO.db)
library(topGO)
# library(org.Hs.eg.db)
library(org.Sc.sgd.db)
library(GOSemSim)
library(gridExtra)
Attaching package: ‘gridExtra’
The following object is masked from ‘package:Biobase’:
combine
The following object is masked from ‘package:BiocGenerics’:
combine
In [18]:
file <- "yeast_uetz"
ont <- "BP"
p <- 0.1
init <- 1
db <- org.Sc.sgd.db
mapping <- "org.Sc.sgd.db"
ID <- "ENSEMBL"
# db <- org.Hs.eg.db
# mapping <- "org.Hs.eg.db"
# ID <- "ENTREZ"
##load all community gene lists
setwd(sprintf("/home/david/Documents/ghsom/%s_communities_%s_%s", file, p, init))
#background gene list
backgroundFilename <- "all_genes.txt"
allGenes <- scan(backgroundFilename, character())
#load communities from file
g <- list()
numCom <- 0
filename <- sprintf("community_%s.txt", numCom)
while (file.exists(filename)) {
numCom <- numCom + 1
g[[numCom]] <- scan(filename, character())
filename <- sprintf("community_%s.txt", numCom)
}
#distances between neurons
shortest.path <- read.csv("shortest_path.csv", sep=",", header=FALSE)
In [19]:
numCom
51
In [26]:
names <- character()
for (i in 1:length(g)){
names <- c(names, sprintf("Com %s", i))
}
In [4]:
##SEMATIC SIMILARITY
#construct gosemsim object
scGO <- godata(mapping, ont=ont, keytype=ID)
print("DONE")
[1] "preparing gene to GO mapping data..."
[1] "preparing IC data..."
[1] "DONE"
In [64]:
allGeneNames <- scan(character(), file="../yeast_uetz_communities_0.5_1/all_genes.txt")
g <- sapply(g, function(i) allGeneNames[as.integer(i)])
allGenes <- allGeneNames[as.integer(allGenes)]
In [20]:
enrichedGOTerms <- function(genes, allGenes, cutoff, correction, ont, mapping, ID, algorithm){
interestingGenes <- factor(as.integer(allGenes %in% genes))
names(interestingGenes) <- allGenes
GOdata <- new("topGOdata", description=sprintf("topGO object"),
ontology = ont, allGenes = interestingGenes,
annotationFun = annFUN.org, mapping = mapping,
ID = ID, nodeSize = 10)
result <- runTest(GOdata, algorithm = algorithm, statistic = "fisher")
if (correction){
GOs <- score(result)[which(p.adjust(score(result), method="BH") <= cutoff)]
} else {
GOs <- score(result)[score(result) <= cutoff]
}
plot <- showSigOfNodes(GOdata, score(result), firstSigNodes = 10, useInfo ='all', swPlot = FALSE)
return(list(GOdata, GOs, plot))
}
In [21]:
enrichedGOs <- sapply(g, enrichedGOTerms, allGenes=allGenes,
cutoff=0.05, correction=FALSE, ont=ont, mapping=mapping, ID=ID, algorithm="weight01")
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 95 nontrivial nodes
parameters:
test statistic: fisher
Level 9: 1 nodes to be scored (0 eliminated genes)
Level 8: 2 nodes to be scored (0 eliminated genes)
Level 7: 3 nodes to be scored (12 eliminated genes)
Level 6: 7 nodes to be scored (21 eliminated genes)
Level 5: 21 nodes to be scored (45 eliminated genes)
Level 4: 27 nodes to be scored (139 eliminated genes)
Level 3: 22 nodes to be scored (197 eliminated genes)
Level 2: 11 nodes to be scored (216 eliminated genes)
Level 1: 1 nodes to be scored (230 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 198 nontrivial nodes
parameters:
test statistic: fisher
Level 13: 1 nodes to be scored (0 eliminated genes)
Level 12: 3 nodes to be scored (0 eliminated genes)
Level 11: 5 nodes to be scored (15 eliminated genes)
Level 10: 5 nodes to be scored (33 eliminated genes)
Level 9: 7 nodes to be scored (52 eliminated genes)
Level 8: 12 nodes to be scored (57 eliminated genes)
Level 7: 24 nodes to be scored (71 eliminated genes)
Level 6: 40 nodes to be scored (109 eliminated genes)
Level 5: 44 nodes to be scored (146 eliminated genes)
Level 4: 30 nodes to be scored (167 eliminated genes)
Level 3: 19 nodes to be scored (202 eliminated genes)
Level 2: 7 nodes to be scored (222 eliminated genes)
Level 1: 1 nodes to be scored (231 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 162 nontrivial nodes
parameters:
test statistic: fisher
Level 13: 1 nodes to be scored (0 eliminated genes)
Level 12: 3 nodes to be scored (0 eliminated genes)
Level 11: 4 nodes to be scored (15 eliminated genes)
Level 10: 4 nodes to be scored (33 eliminated genes)
Level 9: 5 nodes to be scored (44 eliminated genes)
Level 8: 8 nodes to be scored (44 eliminated genes)
Level 7: 18 nodes to be scored (54 eliminated genes)
Level 6: 28 nodes to be scored (77 eliminated genes)
Level 5: 31 nodes to be scored (136 eliminated genes)
Level 4: 31 nodes to be scored (169 eliminated genes)
Level 3: 20 nodes to be scored (186 eliminated genes)
Level 2: 8 nodes to be scored (219 eliminated genes)
Level 1: 1 nodes to be scored (228 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 227 nontrivial nodes
parameters:
test statistic: fisher
Level 12: 3 nodes to be scored (0 eliminated genes)
Level 11: 4 nodes to be scored (0 eliminated genes)
Level 10: 5 nodes to be scored (33 eliminated genes)
Level 9: 9 nodes to be scored (44 eliminated genes)
Level 8: 12 nodes to be scored (54 eliminated genes)
Level 7: 25 nodes to be scored (71 eliminated genes)
Level 6: 40 nodes to be scored (114 eliminated genes)
Level 5: 52 nodes to be scored (167 eliminated genes)
Level 4: 43 nodes to be scored (182 eliminated genes)
Level 3: 23 nodes to be scored (211 eliminated genes)
Level 2: 10 nodes to be scored (225 eliminated genes)
Level 1: 1 nodes to be scored (231 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 108 nontrivial nodes
parameters:
test statistic: fisher
Level 12: 1 nodes to be scored (0 eliminated genes)
Level 11: 3 nodes to be scored (0 eliminated genes)
Level 10: 3 nodes to be scored (24 eliminated genes)
Level 9: 4 nodes to be scored (52 eliminated genes)
Level 8: 6 nodes to be scored (57 eliminated genes)
Level 7: 4 nodes to be scored (65 eliminated genes)
Level 6: 13 nodes to be scored (78 eliminated genes)
Level 5: 29 nodes to be scored (107 eliminated genes)
Level 4: 21 nodes to be scored (133 eliminated genes)
Level 3: 15 nodes to be scored (183 eliminated genes)
Level 2: 8 nodes to be scored (217 eliminated genes)
Level 1: 1 nodes to be scored (227 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 106 nontrivial nodes
parameters:
test statistic: fisher
Level 9: 2 nodes to be scored (0 eliminated genes)
Level 8: 4 nodes to be scored (0 eliminated genes)
Level 7: 8 nodes to be scored (10 eliminated genes)
Level 6: 15 nodes to be scored (47 eliminated genes)
Level 5: 25 nodes to be scored (83 eliminated genes)
Level 4: 26 nodes to be scored (136 eliminated genes)
Level 3: 18 nodes to be scored (191 eliminated genes)
Level 2: 7 nodes to be scored (219 eliminated genes)
Level 1: 1 nodes to be scored (230 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 101 nontrivial nodes
parameters:
test statistic: fisher
Level 9: 1 nodes to be scored (0 eliminated genes)
Level 8: 3 nodes to be scored (0 eliminated genes)
Level 7: 8 nodes to be scored (13 eliminated genes)
Level 6: 16 nodes to be scored (50 eliminated genes)
Level 5: 26 nodes to be scored (102 eliminated genes)
Level 4: 24 nodes to be scored (150 eliminated genes)
Level 3: 15 nodes to be scored (195 eliminated genes)
Level 2: 7 nodes to be scored (224 eliminated genes)
Level 1: 1 nodes to be scored (230 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 131 nontrivial nodes
parameters:
test statistic: fisher
Level 13: 1 nodes to be scored (0 eliminated genes)
Level 12: 3 nodes to be scored (0 eliminated genes)
Level 11: 4 nodes to be scored (15 eliminated genes)
Level 10: 4 nodes to be scored (33 eliminated genes)
Level 9: 4 nodes to be scored (44 eliminated genes)
Level 8: 3 nodes to be scored (44 eliminated genes)
Level 7: 13 nodes to be scored (46 eliminated genes)
Level 6: 22 nodes to be scored (51 eliminated genes)
Level 5: 30 nodes to be scored (107 eliminated genes)
Level 4: 25 nodes to be scored (136 eliminated genes)
Level 3: 12 nodes to be scored (180 eliminated genes)
Level 2: 9 nodes to be scored (214 eliminated genes)
Level 1: 1 nodes to be scored (220 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 58 nontrivial nodes
parameters:
test statistic: fisher
Level 10: 1 nodes to be scored (0 eliminated genes)
Level 9: 3 nodes to be scored (0 eliminated genes)
Level 8: 3 nodes to be scored (11 eliminated genes)
Level 7: 7 nodes to be scored (18 eliminated genes)
Level 6: 7 nodes to be scored (28 eliminated genes)
Level 5: 12 nodes to be scored (39 eliminated genes)
Level 4: 12 nodes to be scored (70 eliminated genes)
Level 3: 7 nodes to be scored (132 eliminated genes)
Level 2: 5 nodes to be scored (188 eliminated genes)
Level 1: 1 nodes to be scored (215 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 137 nontrivial nodes
parameters:
test statistic: fisher
Level 13: 1 nodes to be scored (0 eliminated genes)
Level 12: 3 nodes to be scored (0 eliminated genes)
Level 11: 5 nodes to be scored (15 eliminated genes)
Level 10: 4 nodes to be scored (33 eliminated genes)
Level 9: 7 nodes to be scored (52 eliminated genes)
Level 8: 8 nodes to be scored (57 eliminated genes)
Level 7: 14 nodes to be scored (78 eliminated genes)
Level 6: 25 nodes to be scored (87 eliminated genes)
Level 5: 31 nodes to be scored (99 eliminated genes)
Level 4: 22 nodes to be scored (148 eliminated genes)
Level 3: 11 nodes to be scored (183 eliminated genes)
Level 2: 5 nodes to be scored (216 eliminated genes)
Level 1: 1 nodes to be scored (222 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 176 nontrivial nodes
parameters:
test statistic: fisher
Level 13: 1 nodes to be scored (0 eliminated genes)
Level 12: 3 nodes to be scored (0 eliminated genes)
Level 11: 5 nodes to be scored (15 eliminated genes)
Level 10: 5 nodes to be scored (33 eliminated genes)
Level 9: 7 nodes to be scored (52 eliminated genes)
Level 8: 8 nodes to be scored (57 eliminated genes)
Level 7: 17 nodes to be scored (68 eliminated genes)
Level 6: 28 nodes to be scored (87 eliminated genes)
Level 5: 38 nodes to be scored (111 eliminated genes)
Level 4: 33 nodes to be scored (168 eliminated genes)
Level 3: 20 nodes to be scored (194 eliminated genes)
Level 2: 10 nodes to be scored (212 eliminated genes)
Level 1: 1 nodes to be scored (225 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 14 nontrivial nodes
parameters:
test statistic: fisher
Level 6: 1 nodes to be scored (0 eliminated genes)
Level 5: 1 nodes to be scored (0 eliminated genes)
Level 4: 2 nodes to be scored (13 eliminated genes)
Level 3: 4 nodes to be scored (24 eliminated genes)
Level 2: 5 nodes to be scored (103 eliminated genes)
Level 1: 1 nodes to be scored (178 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 168 nontrivial nodes
parameters:
test statistic: fisher
Level 12: 1 nodes to be scored (0 eliminated genes)
Level 11: 2 nodes to be scored (0 eliminated genes)
Level 10: 3 nodes to be scored (16 eliminated genes)
Level 9: 4 nodes to be scored (44 eliminated genes)
Level 8: 11 nodes to be scored (44 eliminated genes)
Level 7: 17 nodes to be scored (52 eliminated genes)
Level 6: 31 nodes to be scored (100 eliminated genes)
Level 5: 40 nodes to be scored (139 eliminated genes)
Level 4: 29 nodes to be scored (175 eliminated genes)
Level 3: 20 nodes to be scored (204 eliminated genes)
Level 2: 9 nodes to be scored (223 eliminated genes)
Level 1: 1 nodes to be scored (230 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 176 nontrivial nodes
parameters:
test statistic: fisher
Level 13: 1 nodes to be scored (0 eliminated genes)
Level 12: 3 nodes to be scored (0 eliminated genes)
Level 11: 5 nodes to be scored (15 eliminated genes)
Level 10: 5 nodes to be scored (33 eliminated genes)
Level 9: 9 nodes to be scored (52 eliminated genes)
Level 8: 12 nodes to be scored (57 eliminated genes)
Level 7: 17 nodes to be scored (77 eliminated genes)
Level 6: 27 nodes to be scored (101 eliminated genes)
Level 5: 35 nodes to be scored (117 eliminated genes)
Level 4: 32 nodes to be scored (138 eliminated genes)
Level 3: 19 nodes to be scored (183 eliminated genes)
Level 2: 10 nodes to be scored (220 eliminated genes)
Level 1: 1 nodes to be scored (231 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 82 nontrivial nodes
parameters:
test statistic: fisher
Level 12: 1 nodes to be scored (0 eliminated genes)
Level 11: 2 nodes to be scored (0 eliminated genes)
Level 10: 2 nodes to be scored (24 eliminated genes)
Level 9: 2 nodes to be scored (44 eliminated genes)
Level 8: 4 nodes to be scored (44 eliminated genes)
Level 7: 5 nodes to be scored (44 eliminated genes)
Level 6: 14 nodes to be scored (69 eliminated genes)
Level 5: 20 nodes to be scored (113 eliminated genes)
Level 4: 15 nodes to be scored (151 eliminated genes)
Level 3: 11 nodes to be scored (166 eliminated genes)
Level 2: 5 nodes to be scored (206 eliminated genes)
Level 1: 1 nodes to be scored (216 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 54 nontrivial nodes
parameters:
test statistic: fisher
Level 7: 5 nodes to be scored (0 eliminated genes)
Level 6: 8 nodes to be scored (0 eliminated genes)
Level 5: 9 nodes to be scored (32 eliminated genes)
Level 4: 12 nodes to be scored (50 eliminated genes)
Level 3: 11 nodes to be scored (103 eliminated genes)
Level 2: 8 nodes to be scored (191 eliminated genes)
Level 1: 1 nodes to be scored (223 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 144 nontrivial nodes
parameters:
test statistic: fisher
Level 11: 1 nodes to be scored (0 eliminated genes)
Level 10: 1 nodes to be scored (0 eliminated genes)
Level 9: 5 nodes to be scored (12 eliminated genes)
Level 8: 9 nodes to be scored (17 eliminated genes)
Level 7: 11 nodes to be scored (44 eliminated genes)
Level 6: 16 nodes to be scored (82 eliminated genes)
Level 5: 38 nodes to be scored (134 eliminated genes)
Level 4: 35 nodes to be scored (175 eliminated genes)
Level 3: 19 nodes to be scored (208 eliminated genes)
Level 2: 8 nodes to be scored (227 eliminated genes)
Level 1: 1 nodes to be scored (230 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 68 nontrivial nodes
parameters:
test statistic: fisher
Level 9: 1 nodes to be scored (0 eliminated genes)
Level 8: 2 nodes to be scored (0 eliminated genes)
Level 7: 5 nodes to be scored (11 eliminated genes)
Level 6: 12 nodes to be scored (21 eliminated genes)
Level 5: 18 nodes to be scored (74 eliminated genes)
Level 4: 13 nodes to be scored (122 eliminated genes)
Level 3: 11 nodes to be scored (170 eliminated genes)
Level 2: 5 nodes to be scored (207 eliminated genes)
Level 1: 1 nodes to be scored (222 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 98 nontrivial nodes
parameters:
test statistic: fisher
Level 9: 1 nodes to be scored (0 eliminated genes)
Level 8: 1 nodes to be scored (0 eliminated genes)
Level 7: 7 nodes to be scored (12 eliminated genes)
Level 6: 17 nodes to be scored (18 eliminated genes)
Level 5: 23 nodes to be scored (82 eliminated genes)
Level 4: 22 nodes to be scored (152 eliminated genes)
Level 3: 17 nodes to be scored (198 eliminated genes)
Level 2: 9 nodes to be scored (221 eliminated genes)
Level 1: 1 nodes to be scored (229 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 56 nontrivial nodes
parameters:
test statistic: fisher
Level 10: 1 nodes to be scored (0 eliminated genes)
Level 9: 3 nodes to be scored (0 eliminated genes)
Level 8: 3 nodes to be scored (11 eliminated genes)
Level 7: 6 nodes to be scored (18 eliminated genes)
Level 6: 5 nodes to be scored (28 eliminated genes)
Level 5: 12 nodes to be scored (30 eliminated genes)
Level 4: 12 nodes to be scored (39 eliminated genes)
Level 3: 8 nodes to be scored (127 eliminated genes)
Level 2: 5 nodes to be scored (190 eliminated genes)
Level 1: 1 nodes to be scored (225 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 25 nontrivial nodes
parameters:
test statistic: fisher
Level 8: 1 nodes to be scored (0 eliminated genes)
Level 7: 1 nodes to be scored (0 eliminated genes)
Level 6: 2 nodes to be scored (10 eliminated genes)
Level 5: 2 nodes to be scored (16 eliminated genes)
Level 4: 8 nodes to be scored (17 eliminated genes)
Level 3: 7 nodes to be scored (51 eliminated genes)
Level 2: 3 nodes to be scored (94 eliminated genes)
Level 1: 1 nodes to be scored (208 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 143 nontrivial nodes
parameters:
test statistic: fisher
Level 12: 1 nodes to be scored (0 eliminated genes)
Level 11: 2 nodes to be scored (0 eliminated genes)
Level 10: 4 nodes to be scored (19 eliminated genes)
Level 9: 6 nodes to be scored (44 eliminated genes)
Level 8: 7 nodes to be scored (54 eliminated genes)
Level 7: 16 nodes to be scored (62 eliminated genes)
Level 6: 26 nodes to be scored (84 eliminated genes)
Level 5: 34 nodes to be scored (132 eliminated genes)
Level 4: 23 nodes to be scored (171 eliminated genes)
Level 3: 16 nodes to be scored (199 eliminated genes)
Level 2: 7 nodes to be scored (216 eliminated genes)
Level 1: 1 nodes to be scored (229 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 37 nontrivial nodes
parameters:
test statistic: fisher
Level 8: 1 nodes to be scored (0 eliminated genes)
Level 7: 1 nodes to be scored (0 eliminated genes)
Level 6: 4 nodes to be scored (13 eliminated genes)
Level 5: 8 nodes to be scored (13 eliminated genes)
Level 4: 8 nodes to be scored (92 eliminated genes)
Level 3: 9 nodes to be scored (140 eliminated genes)
Level 2: 5 nodes to be scored (201 eliminated genes)
Level 1: 1 nodes to be scored (220 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 69 nontrivial nodes
parameters:
test statistic: fisher
Level 12: 1 nodes to be scored (0 eliminated genes)
Level 11: 3 nodes to be scored (0 eliminated genes)
Level 10: 2 nodes to be scored (11 eliminated genes)
Level 9: 2 nodes to be scored (44 eliminated genes)
Level 8: 3 nodes to be scored (44 eliminated genes)
Level 7: 4 nodes to be scored (44 eliminated genes)
Level 6: 11 nodes to be scored (50 eliminated genes)
Level 5: 18 nodes to be scored (101 eliminated genes)
Level 4: 11 nodes to be scored (135 eliminated genes)
Level 3: 9 nodes to be scored (148 eliminated genes)
Level 2: 4 nodes to be scored (179 eliminated genes)
Level 1: 1 nodes to be scored (212 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 77 nontrivial nodes
parameters:
test statistic: fisher
Level 8: 2 nodes to be scored (0 eliminated genes)
Level 7: 5 nodes to be scored (0 eliminated genes)
Level 6: 10 nodes to be scored (35 eliminated genes)
Level 5: 16 nodes to be scored (61 eliminated genes)
Level 4: 17 nodes to be scored (117 eliminated genes)
Level 3: 18 nodes to be scored (188 eliminated genes)
Level 2: 8 nodes to be scored (212 eliminated genes)
Level 1: 1 nodes to be scored (231 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 141 nontrivial nodes
parameters:
test statistic: fisher
Level 13: 1 nodes to be scored (0 eliminated genes)
Level 12: 2 nodes to be scored (0 eliminated genes)
Level 11: 4 nodes to be scored (15 eliminated genes)
Level 10: 4 nodes to be scored (28 eliminated genes)
Level 9: 5 nodes to be scored (52 eliminated genes)
Level 8: 8 nodes to be scored (57 eliminated genes)
Level 7: 14 nodes to be scored (63 eliminated genes)
Level 6: 24 nodes to be scored (77 eliminated genes)
Level 5: 30 nodes to be scored (100 eliminated genes)
Level 4: 23 nodes to be scored (138 eliminated genes)
Level 3: 16 nodes to be scored (171 eliminated genes)
Level 2: 9 nodes to be scored (209 eliminated genes)
Level 1: 1 nodes to be scored (224 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 119 nontrivial nodes
parameters:
test statistic: fisher
Level 11: 1 nodes to be scored (0 eliminated genes)
Level 10: 1 nodes to be scored (0 eliminated genes)
Level 9: 2 nodes to be scored (12 eliminated genes)
Level 8: 6 nodes to be scored (17 eliminated genes)
Level 7: 6 nodes to be scored (32 eliminated genes)
Level 6: 17 nodes to be scored (92 eliminated genes)
Level 5: 31 nodes to be scored (113 eliminated genes)
Level 4: 26 nodes to be scored (157 eliminated genes)
Level 3: 18 nodes to be scored (198 eliminated genes)
Level 2: 10 nodes to be scored (215 eliminated genes)
Level 1: 1 nodes to be scored (229 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 90 nontrivial nodes
parameters:
test statistic: fisher
Level 12: 1 nodes to be scored (0 eliminated genes)
Level 11: 3 nodes to be scored (0 eliminated genes)
Level 10: 2 nodes to be scored (11 eliminated genes)
Level 9: 4 nodes to be scored (44 eliminated genes)
Level 8: 5 nodes to be scored (44 eliminated genes)
Level 7: 6 nodes to be scored (53 eliminated genes)
Level 6: 14 nodes to be scored (61 eliminated genes)
Level 5: 22 nodes to be scored (111 eliminated genes)
Level 4: 17 nodes to be scored (140 eliminated genes)
Level 3: 10 nodes to be scored (155 eliminated genes)
Level 2: 5 nodes to be scored (191 eliminated genes)
Level 1: 1 nodes to be scored (219 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 38 nontrivial nodes
parameters:
test statistic: fisher
Level 7: 2 nodes to be scored (0 eliminated genes)
Level 6: 7 nodes to be scored (0 eliminated genes)
Level 5: 10 nodes to be scored (32 eliminated genes)
Level 4: 10 nodes to be scored (77 eliminated genes)
Level 3: 4 nodes to be scored (117 eliminated genes)
Level 2: 4 nodes to be scored (160 eliminated genes)
Level 1: 1 nodes to be scored (198 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 131 nontrivial nodes
parameters:
test statistic: fisher
Level 13: 1 nodes to be scored (0 eliminated genes)
Level 12: 2 nodes to be scored (0 eliminated genes)
Level 11: 3 nodes to be scored (15 eliminated genes)
Level 10: 3 nodes to be scored (28 eliminated genes)
Level 9: 3 nodes to be scored (44 eliminated genes)
Level 8: 7 nodes to be scored (44 eliminated genes)
Level 7: 14 nodes to be scored (46 eliminated genes)
Level 6: 25 nodes to be scored (85 eliminated genes)
Level 5: 28 nodes to be scored (124 eliminated genes)
Level 4: 24 nodes to be scored (156 eliminated genes)
Level 3: 14 nodes to be scored (187 eliminated genes)
Level 2: 6 nodes to be scored (208 eliminated genes)
Level 1: 1 nodes to be scored (225 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 143 nontrivial nodes
parameters:
test statistic: fisher
Level 12: 1 nodes to be scored (0 eliminated genes)
Level 11: 3 nodes to be scored (0 eliminated genes)
Level 10: 4 nodes to be scored (19 eliminated genes)
Level 9: 8 nodes to be scored (52 eliminated genes)
Level 8: 8 nodes to be scored (57 eliminated genes)
Level 7: 15 nodes to be scored (78 eliminated genes)
Level 6: 25 nodes to be scored (93 eliminated genes)
Level 5: 32 nodes to be scored (116 eliminated genes)
Level 4: 23 nodes to be scored (150 eliminated genes)
Level 3: 16 nodes to be scored (181 eliminated genes)
Level 2: 7 nodes to be scored (211 eliminated genes)
Level 1: 1 nodes to be scored (230 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 65 nontrivial nodes
parameters:
test statistic: fisher
Level 10: 1 nodes to be scored (0 eliminated genes)
Level 9: 2 nodes to be scored (0 eliminated genes)
Level 8: 4 nodes to be scored (17 eliminated genes)
Level 7: 2 nodes to be scored (22 eliminated genes)
Level 6: 8 nodes to be scored (32 eliminated genes)
Level 5: 14 nodes to be scored (72 eliminated genes)
Level 4: 15 nodes to be scored (140 eliminated genes)
Level 3: 12 nodes to be scored (155 eliminated genes)
Level 2: 6 nodes to be scored (176 eliminated genes)
Level 1: 1 nodes to be scored (221 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 102 nontrivial nodes
parameters:
test statistic: fisher
Level 13: 1 nodes to be scored (0 eliminated genes)
Level 12: 2 nodes to be scored (0 eliminated genes)
Level 11: 3 nodes to be scored (15 eliminated genes)
Level 10: 3 nodes to be scored (28 eliminated genes)
Level 9: 3 nodes to be scored (44 eliminated genes)
Level 8: 3 nodes to be scored (44 eliminated genes)
Level 7: 8 nodes to be scored (46 eliminated genes)
Level 6: 16 nodes to be scored (55 eliminated genes)
Level 5: 20 nodes to be scored (105 eliminated genes)
Level 4: 21 nodes to be scored (142 eliminated genes)
Level 3: 14 nodes to be scored (179 eliminated genes)
Level 2: 7 nodes to be scored (205 eliminated genes)
Level 1: 1 nodes to be scored (221 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 155 nontrivial nodes
parameters:
test statistic: fisher
Level 11: 1 nodes to be scored (0 eliminated genes)
Level 10: 3 nodes to be scored (0 eliminated genes)
Level 9: 5 nodes to be scored (44 eliminated genes)
Level 8: 7 nodes to be scored (54 eliminated genes)
Level 7: 15 nodes to be scored (63 eliminated genes)
Level 6: 28 nodes to be scored (87 eliminated genes)
Level 5: 39 nodes to be scored (147 eliminated genes)
Level 4: 29 nodes to be scored (180 eliminated genes)
Level 3: 19 nodes to be scored (206 eliminated genes)
Level 2: 8 nodes to be scored (217 eliminated genes)
Level 1: 1 nodes to be scored (230 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 91 nontrivial nodes
parameters:
test statistic: fisher
Level 12: 3 nodes to be scored (0 eliminated genes)
Level 11: 4 nodes to be scored (0 eliminated genes)
Level 10: 3 nodes to be scored (33 eliminated genes)
Level 9: 3 nodes to be scored (44 eliminated genes)
Level 8: 2 nodes to be scored (44 eliminated genes)
Level 7: 7 nodes to be scored (46 eliminated genes)
Level 6: 12 nodes to be scored (46 eliminated genes)
Level 5: 21 nodes to be scored (86 eliminated genes)
Level 4: 15 nodes to be scored (119 eliminated genes)
Level 3: 13 nodes to be scored (179 eliminated genes)
Level 2: 7 nodes to be scored (211 eliminated genes)
Level 1: 1 nodes to be scored (224 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 137 nontrivial nodes
parameters:
test statistic: fisher
Level 10: 1 nodes to be scored (0 eliminated genes)
Level 9: 2 nodes to be scored (0 eliminated genes)
Level 8: 7 nodes to be scored (17 eliminated genes)
Level 7: 19 nodes to be scored (23 eliminated genes)
Level 6: 33 nodes to be scored (77 eliminated genes)
Level 5: 32 nodes to be scored (135 eliminated genes)
Level 4: 21 nodes to be scored (147 eliminated genes)
Level 3: 14 nodes to be scored (177 eliminated genes)
Level 2: 7 nodes to be scored (204 eliminated genes)
Level 1: 1 nodes to be scored (221 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 38 nontrivial nodes
parameters:
test statistic: fisher
Level 7: 1 nodes to be scored (0 eliminated genes)
Level 6: 3 nodes to be scored (0 eliminated genes)
Level 5: 8 nodes to be scored (12 eliminated genes)
Level 4: 9 nodes to be scored (54 eliminated genes)
Level 3: 10 nodes to be scored (107 eliminated genes)
Level 2: 6 nodes to be scored (178 eliminated genes)
Level 1: 1 nodes to be scored (226 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 62 nontrivial nodes
parameters:
test statistic: fisher
Level 8: 2 nodes to be scored (0 eliminated genes)
Level 7: 4 nodes to be scored (0 eliminated genes)
Level 6: 8 nodes to be scored (35 eliminated genes)
Level 5: 17 nodes to be scored (63 eliminated genes)
Level 4: 12 nodes to be scored (106 eliminated genes)
Level 3: 12 nodes to be scored (189 eliminated genes)
Level 2: 6 nodes to be scored (209 eliminated genes)
Level 1: 1 nodes to be scored (225 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 178 nontrivial nodes
parameters:
test statistic: fisher
Level 13: 1 nodes to be scored (0 eliminated genes)
Level 12: 4 nodes to be scored (0 eliminated genes)
Level 11: 5 nodes to be scored (15 eliminated genes)
Level 10: 5 nodes to be scored (38 eliminated genes)
Level 9: 9 nodes to be scored (44 eliminated genes)
Level 8: 9 nodes to be scored (54 eliminated genes)
Level 7: 25 nodes to be scored (73 eliminated genes)
Level 6: 33 nodes to be scored (101 eliminated genes)
Level 5: 34 nodes to be scored (163 eliminated genes)
Level 4: 31 nodes to be scored (176 eliminated genes)
Level 3: 15 nodes to be scored (197 eliminated genes)
Level 2: 6 nodes to be scored (224 eliminated genes)
Level 1: 1 nodes to be scored (226 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 176 nontrivial nodes
parameters:
test statistic: fisher
Level 13: 1 nodes to be scored (0 eliminated genes)
Level 12: 3 nodes to be scored (0 eliminated genes)
Level 11: 4 nodes to be scored (15 eliminated genes)
Level 10: 4 nodes to be scored (33 eliminated genes)
Level 9: 5 nodes to be scored (44 eliminated genes)
Level 8: 8 nodes to be scored (44 eliminated genes)
Level 7: 18 nodes to be scored (54 eliminated genes)
Level 6: 32 nodes to be scored (84 eliminated genes)
Level 5: 44 nodes to be scored (128 eliminated genes)
Level 4: 28 nodes to be scored (175 eliminated genes)
Level 3: 19 nodes to be scored (199 eliminated genes)
Level 2: 9 nodes to be scored (222 eliminated genes)
Level 1: 1 nodes to be scored (228 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 147 nontrivial nodes
parameters:
test statistic: fisher
Level 13: 1 nodes to be scored (0 eliminated genes)
Level 12: 2 nodes to be scored (0 eliminated genes)
Level 11: 3 nodes to be scored (15 eliminated genes)
Level 10: 3 nodes to be scored (28 eliminated genes)
Level 9: 4 nodes to be scored (44 eliminated genes)
Level 8: 4 nodes to be scored (44 eliminated genes)
Level 7: 13 nodes to be scored (55 eliminated genes)
Level 6: 25 nodes to be scored (67 eliminated genes)
Level 5: 32 nodes to be scored (127 eliminated genes)
Level 4: 31 nodes to be scored (162 eliminated genes)
Level 3: 19 nodes to be scored (199 eliminated genes)
Level 2: 9 nodes to be scored (220 eliminated genes)
Level 1: 1 nodes to be scored (230 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 59 nontrivial nodes
parameters:
test statistic: fisher
Level 8: 1 nodes to be scored (0 eliminated genes)
Level 7: 4 nodes to be scored (0 eliminated genes)
Level 6: 6 nodes to be scored (20 eliminated genes)
Level 5: 13 nodes to be scored (39 eliminated genes)
Level 4: 13 nodes to be scored (81 eliminated genes)
Level 3: 13 nodes to be scored (117 eliminated genes)
Level 2: 8 nodes to be scored (171 eliminated genes)
Level 1: 1 nodes to be scored (209 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 71 nontrivial nodes
parameters:
test statistic: fisher
Level 12: 1 nodes to be scored (0 eliminated genes)
Level 11: 2 nodes to be scored (0 eliminated genes)
Level 10: 2 nodes to be scored (24 eliminated genes)
Level 9: 2 nodes to be scored (44 eliminated genes)
Level 8: 2 nodes to be scored (44 eliminated genes)
Level 7: 3 nodes to be scored (44 eliminated genes)
Level 6: 8 nodes to be scored (46 eliminated genes)
Level 5: 17 nodes to be scored (86 eliminated genes)
Level 4: 15 nodes to be scored (105 eliminated genes)
Level 3: 12 nodes to be scored (155 eliminated genes)
Level 2: 6 nodes to be scored (174 eliminated genes)
Level 1: 1 nodes to be scored (215 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 35 nontrivial nodes
parameters:
test statistic: fisher
Level 8: 1 nodes to be scored (0 eliminated genes)
Level 7: 3 nodes to be scored (0 eliminated genes)
Level 6: 4 nodes to be scored (20 eliminated genes)
Level 5: 8 nodes to be scored (31 eliminated genes)
Level 4: 9 nodes to be scored (66 eliminated genes)
Level 3: 6 nodes to be scored (89 eliminated genes)
Level 2: 3 nodes to be scored (143 eliminated genes)
Level 1: 1 nodes to be scored (153 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 1 nontrivial nodes
parameters:
test statistic: fisher
Nothing to do:
Nothing to do:
Level 1: 1 nodes to be scored (0 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 98 nontrivial nodes
parameters:
test statistic: fisher
Level 12: 2 nodes to be scored (0 eliminated genes)
Level 11: 3 nodes to be scored (0 eliminated genes)
Level 10: 2 nodes to be scored (30 eliminated genes)
Level 9: 2 nodes to be scored (44 eliminated genes)
Level 8: 3 nodes to be scored (44 eliminated genes)
Level 7: 4 nodes to be scored (44 eliminated genes)
Level 6: 15 nodes to be scored (58 eliminated genes)
Level 5: 22 nodes to be scored (96 eliminated genes)
Level 4: 18 nodes to be scored (142 eliminated genes)
Level 3: 16 nodes to be scored (173 eliminated genes)
Level 2: 10 nodes to be scored (197 eliminated genes)
Level 1: 1 nodes to be scored (222 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 85 nontrivial nodes
parameters:
test statistic: fisher
Level 12: 1 nodes to be scored (0 eliminated genes)
Level 11: 2 nodes to be scored (0 eliminated genes)
Level 10: 3 nodes to be scored (16 eliminated genes)
Level 9: 3 nodes to be scored (44 eliminated genes)
Level 8: 5 nodes to be scored (44 eliminated genes)
Level 7: 8 nodes to be scored (44 eliminated genes)
Level 6: 15 nodes to be scored (59 eliminated genes)
Level 5: 20 nodes to be scored (107 eliminated genes)
Level 4: 13 nodes to be scored (124 eliminated genes)
Level 3: 9 nodes to be scored (151 eliminated genes)
Level 2: 5 nodes to be scored (198 eliminated genes)
Level 1: 1 nodes to be scored (216 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 104 nontrivial nodes
parameters:
test statistic: fisher
Level 11: 1 nodes to be scored (0 eliminated genes)
Level 10: 2 nodes to be scored (0 eliminated genes)
Level 9: 2 nodes to be scored (44 eliminated genes)
Level 8: 4 nodes to be scored (44 eliminated genes)
Level 7: 11 nodes to be scored (44 eliminated genes)
Level 6: 22 nodes to be scored (69 eliminated genes)
Level 5: 27 nodes to be scored (122 eliminated genes)
Level 4: 17 nodes to be scored (154 eliminated genes)
Level 3: 11 nodes to be scored (185 eliminated genes)
Level 2: 6 nodes to be scored (203 eliminated genes)
Level 1: 1 nodes to be scored (216 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 107 nontrivial nodes
parameters:
test statistic: fisher
Level 9: 3 nodes to be scored (0 eliminated genes)
Level 8: 4 nodes to be scored (0 eliminated genes)
Level 7: 9 nodes to be scored (23 eliminated genes)
Level 6: 12 nodes to be scored (40 eliminated genes)
Level 5: 23 nodes to be scored (75 eliminated genes)
Level 4: 30 nodes to be scored (128 eliminated genes)
Level 3: 17 nodes to be scored (203 eliminated genes)
Level 2: 8 nodes to be scored (220 eliminated genes)
Level 1: 1 nodes to be scored (227 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 117 nontrivial nodes
parameters:
test statistic: fisher
Level 11: 1 nodes to be scored (0 eliminated genes)
Level 10: 2 nodes to be scored (0 eliminated genes)
Level 9: 3 nodes to be scored (44 eliminated genes)
Level 8: 6 nodes to be scored (44 eliminated genes)
Level 7: 9 nodes to be scored (52 eliminated genes)
Level 6: 21 nodes to be scored (64 eliminated genes)
Level 5: 27 nodes to be scored (133 eliminated genes)
Level 4: 23 nodes to be scored (148 eliminated genes)
Level 3: 16 nodes to be scored (166 eliminated genes)
Level 2: 8 nodes to be scored (207 eliminated genes)
Level 1: 1 nodes to be scored (223 eliminated genes)
Building most specific GOs .....
( 571 GO terms found. )
Build GO DAG topology ..........
( 1846 GO terms and 4079 relations. )
Annotating nodes ...............
( 250 genes annotated to the GO terms. )
-- Weight01 Algorithm --
the algorithm is scoring 93 nontrivial nodes
parameters:
test statistic: fisher
Level 13: 1 nodes to be scored (0 eliminated genes)
Level 12: 4 nodes to be scored (0 eliminated genes)
Level 11: 5 nodes to be scored (15 eliminated genes)
Level 10: 4 nodes to be scored (38 eliminated genes)
Level 9: 4 nodes to be scored (44 eliminated genes)
Level 8: 3 nodes to be scored (44 eliminated genes)
Level 7: 11 nodes to be scored (46 eliminated genes)
Level 6: 16 nodes to be scored (51 eliminated genes)
Level 5: 19 nodes to be scored (86 eliminated genes)
Level 4: 13 nodes to be scored (119 eliminated genes)
Level 3: 8 nodes to be scored (158 eliminated genes)
Level 2: 4 nodes to be scored (180 eliminated genes)
Level 1: 1 nodes to be scored (212 eliminated genes)
In [10]:
lengths(enrichedGOs)
- 1
- 20
- 2
- 1
- 5
- 2
- 1
- 7
- 2
- 1
- 8
- 2
- 1
- 13
- 2
- 1
- 3
- 2
In [11]:
p.values <- enrichedGOs[2,]
In [22]:
mgeneSim(genes = g[[1]], semData = scGO, measure = "Wang", combine = "BMA")
|======================================================================| 100%
YER179W YIL105C YMR068W YDR326C YNL047C YPL059W YOR353C YER179W 1.000 0.298 0.252 0.067 0.298 0.284 0.228 YIL105C 0.298 1.000 0.711 0.617 1.000 0.300 0.421 YMR068W 0.252 0.711 1.000 0.083 0.711 0.255 0.490 YDR326C 0.067 0.617 0.083 1.000 0.617 0.059 0.121 YNL047C 0.298 1.000 0.711 0.617 1.000 0.300 0.421 YPL059W 0.284 0.300 0.255 0.059 0.300 1.000 0.227 YOR353C 0.228 0.421 0.490 0.121 0.421 0.227 1.000
In [36]:
clusterSims <- sapply(g, function(i)
mean(mgeneSim(genes = i, semData = scGO, measure = "Wang", combine = "BMA", verbose = FALSE)))
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
|======================================================================| 100%
In [38]:
mean(clusterSims)
0.574264669390298
In [23]:
mclusterSim <- mclusterSim(clusters = g, semData = scGO, measure = "Wang", combine = "BMA")
In [35]:
rownames(mclusterSim) <- names
colnames(mclusterSim) <- names
grid.table(mclusterSim[1:8, 1:8])
In [34]:
rownames(shortest.path) <- names
colnames(shortest.path) <- names
grid.table(shortest.path[1:8, 1:8])
In [ ]:
library(gri)
In [11]:
pathways <- read.table("../biochemical_pathways.tab", sep="\t")
cols <- c("pathway_name", "enzyme_name", "E.C._reaction_number", "gene_name", "reference")
colnames(pathways) <- cols
toGene <- function(ORFIdentifiers){
genes <- character()
for (identifier in ORFIdentifiers){
gene <- character()
try(
gene <- as.character(org.Sc.sgdGENENAME[identifier])
)
genes <- c(genes, gene)
}
return(genes)
}
toPath <- function(ORFIdentifiers){
paths <- character()
for (identifier in ORFIdentifiers){
path <- character()
try(
path <- as.character(org.Sc.sgdPATH[identifier])
)
paths <- c(paths, path)
}
return(paths)
}
get_pathways <- function(ORFIdentifiers, pathways) {
genes <- toGene(ORFIdentifiers)
return(subset(pathways, gene_name %in% genes)$pathway_name)
}
get_pathway_genes <- function(ORFIdentifiers, pathways) {
genes <- toGene(ORFIdentifiers)
return(subset(pathways, gene_name %in% genes)$gene_name)
}
In [12]:
pathway_list <- sapply(g, get_pathways, pathways)
pathway_genes <- sapply(g, get_pathway_genes, pathways)
In [15]:
enrichedGOsPathway <- sapply(pathway_genes[lengths(pathway_genes) > 0], enrichedGOTerms, allGenes=allGenes,
cutoff=0.05, correction=FALSE, ont=ont, mapping=mapping, ID=ID)
Error in .local(.Object, ...): allGenes must be a factor with 2 levels
Traceback:
1. sapply(pathway_genes[lengths(pathway_genes) > 0], enrichedGOTerms,
. allGenes = allGenes, cutoff = 0.05, correction = FALSE, ont = ont,
. mapping = mapping, ID = ID)
2. sapply(pathway_genes[lengths(pathway_genes) > 0], enrichedGOTerms,
. allGenes = allGenes, cutoff = 0.05, correction = FALSE, ont = ont,
. mapping = mapping, ID = ID)
3. lapply(X = X, FUN = FUN, ...)
4. FUN(X[[i]], ...)
5. new("topGOdata", description = sprintf("topGO object"), ontology = ont,
. allGenes = interestingGenes, annotationFun = annFUN.org,
. mapping = mapping, ID = ID, nodeSize = 10) # at line 5-8 of file <text>
6. initialize(value, ...)
7. initialize(value, ...)
8. .local(.Object, ...)
9. stop("allGenes must be a factor with 2 levels")
In [ ]:
range <- 1:length(enrichedGOsPathway)
simsPathway <- sapply(range, function(i) sapply(range, function(j)
mgoSim(names(enrichedGOsPathway[[i]]),
names(enrichedGOsPathway[[j]]),
semData=scGO, measure="Wang", combine="BMA")))
In [ ]:
head(simsPathway)
In [ ]:
head(shortest.path)
In [ ]:
geneSimilarities <- sapply(allGenes, function(i)
sapply(allGenes, function(j)
geneSim(i, j, semData=scGO, measure = "Wang", combine="BMA")))
In [ ]:
geneSimilarities
In [6]:
cutOff <- 0.05
filename <- sprintf("%s-%s-%s-%s.rda", file, p, cutOff, ont)
if (file.exists(filename)){
print(sprintf("loading: %s", filename))
load(filename)
print("loaded")
} else {
print("creating topGO objects")
geneLists <- vector("list", numCom)
GOdataObjects <- vector("list", numCom)
resultFishers <- vector("list", numCom)
results <- vector("list", numCom)
gos <- vector("list", numCom)
#perform enrichment analyses
for (c in 1:numCom){
#factor of interesting genes
geneList <- factor(as.integer(allGenes %in% g[[c]]))
names(geneList) <- allGenes
geneLists[[c]] <- geneList
#construct topGO object
GOdata <- new("topGOdata", description=sprintf("topGO object for community %s", c),
ontology = ont, allGenes = geneList,
annotationFun = annFUN.org, mapping = mapping,
ID = ID, nodeSize = 10)
GOdataObjects[[c]] <- GOdata
#fishers exact test classic
resultFisher <- runTest(GOdata, algorithm = "classic", statistic = "fisher")
resultFishers[[c]] <- resultFisher
#tabulate results
allRes <- GenTable(GOdata, classicFisher = resultFisher,
orderBy = "classicFisher")
results[[c]] <- allRes
#go terms < cut off Benjamini-Hochberg multiple hypothesis corrected pval
gos[[c]] <- score(resultFisher)[which(p.adjust(score(resultFisher), method="BH") <= cutOff)]
print(sprintf("community %s complete", c))
}
print(sprintf("Saving data: %s", filename))
save(geneLists, GOdataObjects, resultFishers, results, gos, file=filename)
print("saved")
}
[1] "creating topGO objects"
Building most specific GOs .....
( 1689 GO terms found. )
Build GO DAG topology ..........
( 3643 GO terms and 8240 relations. )
Annotating nodes ...............
( 1558 genes annotated to the GO terms. )
-- Classic Algorithm --
the algorithm is scoring 355 nontrivial nodes
parameters:
test statistic: fisher
[1] "community 1 complete"
Building most specific GOs .....
( 1689 GO terms found. )
Build GO DAG topology ..........
( 3643 GO terms and 8240 relations. )
Annotating nodes ...............
( 1558 genes annotated to the GO terms. )
-- Classic Algorithm --
the algorithm is scoring 581 nontrivial nodes
parameters:
test statistic: fisher
[1] "community 2 complete"
Building most specific GOs .....
( 1689 GO terms found. )
Build GO DAG topology ..........
( 3643 GO terms and 8240 relations. )
Annotating nodes ...............
( 1558 genes annotated to the GO terms. )
-- Classic Algorithm --
the algorithm is scoring 835 nontrivial nodes
parameters:
test statistic: fisher
[1] "community 3 complete"
Building most specific GOs .....
( 1689 GO terms found. )
Build GO DAG topology ..........
( 3643 GO terms and 8240 relations. )
Annotating nodes ...............
( 1558 genes annotated to the GO terms. )
-- Classic Algorithm --
the algorithm is scoring 681 nontrivial nodes
parameters:
test statistic: fisher
[1] "community 4 complete"
Building most specific GOs .....
( 1689 GO terms found. )
Build GO DAG topology ..........
( 3643 GO terms and 8240 relations. )
Annotating nodes ...............
( 1558 genes annotated to the GO terms. )
-- Classic Algorithm --
the algorithm is scoring 586 nontrivial nodes
parameters:
test statistic: fisher
[1] "community 5 complete"
Building most specific GOs .....
( 1689 GO terms found. )
Build GO DAG topology ..........
( 3643 GO terms and 8240 relations. )
Annotating nodes ...............
( 1558 genes annotated to the GO terms. )
-- Classic Algorithm --
the algorithm is scoring 644 nontrivial nodes
parameters:
test statistic: fisher
[1] "community 6 complete"
Building most specific GOs .....
( 1689 GO terms found. )
Build GO DAG topology ..........
( 3643 GO terms and 8240 relations. )
Annotating nodes ...............
( 1558 genes annotated to the GO terms. )
-- Classic Algorithm --
the algorithm is scoring 877 nontrivial nodes
parameters:
test statistic: fisher
[1] "community 7 complete"
Building most specific GOs .....
( 1689 GO terms found. )
Build GO DAG topology ..........
( 3643 GO terms and 8240 relations. )
Annotating nodes ...............
( 1558 genes annotated to the GO terms. )
-- Classic Algorithm --
the algorithm is scoring 706 nontrivial nodes
parameters:
test statistic: fisher
[1] "community 8 complete"
Building most specific GOs .....
( 1689 GO terms found. )
Build GO DAG topology ..........
( 3643 GO terms and 8240 relations. )
Annotating nodes ...............
( 1558 genes annotated to the GO terms. )
-- Classic Algorithm --
the algorithm is scoring 831 nontrivial nodes
parameters:
test statistic: fisher
[1] "community 9 complete"
Building most specific GOs .....
( 1689 GO terms found. )
Build GO DAG topology ..........
( 3643 GO terms and 8240 relations. )
Annotating nodes ...............
( 1558 genes annotated to the GO terms. )
-- Classic Algorithm --
the algorithm is scoring 408 nontrivial nodes
parameters:
test statistic: fisher
[1] "community 10 complete"
Building most specific GOs .....
( 1689 GO terms found. )
Build GO DAG topology ..........
( 3643 GO terms and 8240 relations. )
Annotating nodes ...............
( 1558 genes annotated to the GO terms. )
-- Classic Algorithm --
the algorithm is scoring 516 nontrivial nodes
parameters:
test statistic: fisher
[1] "community 11 complete"
Building most specific GOs .....
( 1689 GO terms found. )
Build GO DAG topology ..........
( 3643 GO terms and 8240 relations. )
Annotating nodes ...............
( 1558 genes annotated to the GO terms. )
-- Classic Algorithm --
the algorithm is scoring 567 nontrivial nodes
parameters:
test statistic: fisher
[1] "community 12 complete"
Building most specific GOs .....
( 1689 GO terms found. )
Build GO DAG topology ..........
( 3643 GO terms and 8240 relations. )
Annotating nodes ...............
( 1558 genes annotated to the GO terms. )
-- Classic Algorithm --
the algorithm is scoring 706 nontrivial nodes
parameters:
test statistic: fisher
[1] "community 13 complete"
Building most specific GOs .....
( 1689 GO terms found. )
Build GO DAG topology ..........
( 3643 GO terms and 8240 relations. )
Annotating nodes ...............
( 1558 genes annotated to the GO terms. )
-- Classic Algorithm --
the algorithm is scoring 531 nontrivial nodes
parameters:
test statistic: fisher
[1] "community 14 complete"
Building most specific GOs .....
( 1689 GO terms found. )
Build GO DAG topology ..........
( 3643 GO terms and 8240 relations. )
Annotating nodes ...............
( 1558 genes annotated to the GO terms. )
-- Classic Algorithm --
the algorithm is scoring 473 nontrivial nodes
parameters:
test statistic: fisher
[1] "community 15 complete"
Building most specific GOs .....
( 1689 GO terms found. )
Build GO DAG topology ..........
( 3643 GO terms and 8240 relations. )
Annotating nodes ...............
( 1558 genes annotated to the GO terms. )
-- Classic Algorithm --
the algorithm is scoring 612 nontrivial nodes
parameters:
test statistic: fisher
[1] "community 16 complete"
Building most specific GOs .....
( 1689 GO terms found. )
Build GO DAG topology ..........
( 3643 GO terms and 8240 relations. )
Annotating nodes ...............
( 1558 genes annotated to the GO terms. )
-- Classic Algorithm --
the algorithm is scoring 577 nontrivial nodes
parameters:
test statistic: fisher
[1] "community 17 complete"
Building most specific GOs .....
( 1689 GO terms found. )
Build GO DAG topology ..........
( 3643 GO terms and 8240 relations. )
Annotating nodes ...............
( 1558 genes annotated to the GO terms. )
-- Classic Algorithm --
the algorithm is scoring 501 nontrivial nodes
parameters:
test statistic: fisher
[1] "community 18 complete"
Building most specific GOs .....
( 1689 GO terms found. )
Build GO DAG topology ..........
( 3643 GO terms and 8240 relations. )
Annotating nodes ...............
( 1558 genes annotated to the GO terms. )
-- Classic Algorithm --
the algorithm is scoring 463 nontrivial nodes
parameters:
test statistic: fisher
[1] "community 19 complete"
Building most specific GOs .....
( 1689 GO terms found. )
Build GO DAG topology ..........
( 3643 GO terms and 8240 relations. )
Annotating nodes ...............
( 1558 genes annotated to the GO terms. )
-- Classic Algorithm --
the algorithm is scoring 602 nontrivial nodes
parameters:
test statistic: fisher
[1] "community 20 complete"
[1] "Saving data: yeast_union-0.7-0.05-BP.rda"
[1] "saved"
In [7]:
print_accession_number <- function(terms, file){
for (s in strsplit(names(terms), ":")){
write(s[2], file=file, append=TRUE)
}
}
In [8]:
###write accession number to file
for (i in 1:length(gos)){
accessionFile <- sprintf("accession_numbers-%s-%s-%s", cutOff, ont, i)
print_accession_number(gos[[i]], file=accessionFile)
}
In [10]:
wangAllGeneSim <- mgeneSim(allGenes, semData=scGO, measure="Wang", combine="BMA", verbose=TRUE)
|======================================================================| 100%
In [11]:
clusters <- hclust(as.dist(-log(wangAllGeneSim)))
clusterCut <- cutree(clusters, numCom)
In [12]:
plot(clusters)
In [13]:
assignedCommunities <- numeric(length(allGenes))
names(assignedCommunities) <- allGenes
for (i in 1:numCom){
for (geneName in g[[i]]){
assignedCommunities[geneName] <- i
}
}
In [14]:
library(NMI)
In [15]:
assignedCommunities <- assignedCommunities[names(assignedCommunities) %in% names(clusterCut)]
In [16]:
assignedCommunitiesDF <- data.frame(assignedCommunities)
assignedCommunitiesDF <- cbind(Row.Names = rownames(assignedCommunitiesDF), assignedCommunitiesDF)
In [17]:
clusterCutDF <- data.frame(clusterCut)
clusterCutDF <- cbind(Row.Names = rownames(clusterCutDF), clusterCutDF)
In [18]:
NMI(assignedCommunitiesDF, clusterCutDF)
$value = 0.0711074542082947
In [98]:
most_representative_term_weighted <- function(namedTerms){
counts <- numeric(length(namedTerms))
names(counts) <- names(namedTerms)
for (term in names(namedTerms)) {
ancestors <- as.list(GOBPANCESTOR[term])
for (ancestor in ancestors[[term]]) {
if (ancestor %in% names(counts)) {
counts[ancestor] <- counts[ancestor] + 1
}
}
}
# return (sort(counts / sum(counts), decreasing=TRUE))
return (sort(counts / max(counts), decreasing=TRUE))
}
In [33]:
most_representative_term_ancestor <- function(namedTerms){
counts <- numeric(length(namedTerms))
names(counts) <- names(namedTerms)
for (term in names(namedTerms)) {
ancestors <- as.list(GOBPANCESTOR[term])
for (ancestor in ancestors[[term]]) {
if (ancestor %in% names(counts)) {
counts[ancestor] <- counts[ancestor] + 1
}
}
}
# return (sort(counts / sum(counts), decreasing=TRUE))
return (names(sort(counts / sum(counts), decreasing=TRUE)[1]))
}
In [34]:
representativeTermsAncestor <- sapply(Filter(length, gos), most_representative_term_ancestor)
In [35]:
select(GO.db, keys=representativeTermsAncestor, columns=c("TERM", "DEFINITION"))
'select()' returned many:1 mapping between keys and columns
GOID TERM DEFINITION GO:0006644 phospholipid metabolic process The chemical reactions and pathways involving phospholipids, any lipid containing phosphoric acid as a mono- or diester. GO:0007049 cell cycle The progression of biochemical and morphological phases and events that occur in a cell during successive cell replication or nuclear replication events. Canonically, the cell cycle comprises the replication and segregation of genetic material followed by the division of the cell, but in endocycles or syncytial cells nuclear replication or nuclear division may not be followed by cell division. GO:0044699 single-organism process A biological process that involves only one organism. GO:0044710 single-organism metabolic process A metabolic process - chemical reactions and pathways, including anabolism and catabolism, by which living organisms transform chemical substances - which involves a single organism. GO:0051128 regulation of cellular component organization Any process that modulates the frequency, rate or extent of a process involved in the formation, arrangement of constituent parts, or disassembly of cell structures, including the plasma membrane and any external encapsulating structures such as the cell wall and cell envelope. GO:0034641 cellular nitrogen compound metabolic process The chemical reactions and pathways involving various organic and inorganic nitrogenous compounds, as carried out by individual cells. GO:0006725 cellular aromatic compound metabolic process The chemical reactions and pathways involving aromatic compounds, any organic compound characterized by one or more planar rings, each of which contains conjugated double bonds and delocalized pi electrons, as carried out by individual cells. GO:0044710 single-organism metabolic process A metabolic process - chemical reactions and pathways, including anabolism and catabolism, by which living organisms transform chemical substances - which involves a single organism. GO:0044238 primary metabolic process The chemical reactions and pathways involving those compounds which are formed as a part of the normal anabolic and catabolic processes. These processes take place in most, if not all, cells of the organism. GO:0044699 single-organism process A biological process that involves only one organism. GO:0005975 carbohydrate metabolic process The chemical reactions and pathways involving carbohydrates, any of a group of organic compounds based of the general formula Cx(H2O)y. Includes the formation of carbohydrate derivatives by the addition of a carbohydrate residue to another molecule. GO:0044710 single-organism metabolic process A metabolic process - chemical reactions and pathways, including anabolism and catabolism, by which living organisms transform chemical substances - which involves a single organism. GO:0030029 actin filament-based process Any cellular process that depends upon or alters the actin cytoskeleton, that part of the cytoskeleton comprising actin filaments and their associated proteins. GO:0051726 regulation of cell cycle Any process that modulates the rate or extent of progression through the cell cycle. GO:0016070 RNA metabolic process The cellular chemical reactions and pathways involving RNA, ribonucleic acid, one of the two main type of nucleic acid, consisting of a long, unbranched macromolecule formed from ribonucleotides joined in 3',5'-phosphodiester linkage. GO:0044085 cellular component biogenesis A process that results in the biosynthesis of constituent macromolecules, assembly, and arrangement of constituent parts of a cellular component. Includes biosynthesis of constituent macromolecules, and those macromolecular modifications that are involved in synthesis or assembly of the cellular component. GO:0044763 single-organism cellular process Any process that is carried out at the cellular level, occurring within a single organism. GO:0048518 positive regulation of biological process Any process that activates or increases the frequency, rate or extent of a biological process. Biological processes are regulated by many means; examples include the control of gene expression, protein modification or interaction with a protein or substrate molecule. GO:0016070 RNA metabolic process The cellular chemical reactions and pathways involving RNA, ribonucleic acid, one of the two main type of nucleic acid, consisting of a long, unbranched macromolecule formed from ribonucleotides joined in 3',5'-phosphodiester linkage. GO:0051716 cellular response to stimulus Any process that results in a change in state or activity of a cell (in terms of movement, secretion, enzyme production, gene expression, etc.) as a result of a stimulus. The process begins with detection of the stimulus by a cell and ends with a change in state or activity or the cell. GO:0009893 positive regulation of metabolic process Any process that activates or increases the frequency, rate or extent of the chemical reactions and pathways within a cell or an organism. GO:0009056 catabolic process The chemical reactions and pathways resulting in the breakdown of substances, including the breakdown of carbon compounds with the liberation of energy for use by the cell or organism. GO:0042221 response to chemical Any process that results in a change in state or activity of a cell or an organism (in terms of movement, secretion, enzyme production, gene expression, etc.) as a result of a chemical stimulus. GO:0051179 localization Any process in which a cell, a substance, or a cellular entity, such as a protein complex or organelle, is transported, tethered to or otherwise maintained in a specific location. In the case of substances, localization may also be achieved via selective degradation. GO:0061024 membrane organization A process which results in the assembly, arrangement of constituent parts, or disassembly of a membrane. A membrane is a double layer of lipid molecules that encloses all cells, and, in eukaryotes, many organelles; may be a single or double lipid bilayer; also includes associated proteins. GO:0050789 regulation of biological process Any process that modulates the frequency, rate or extent of a biological process. Biological processes are regulated by many means; examples include the control of gene expression, protein modification or interaction with a protein or substrate molecule. GO:0006629 lipid metabolic process The chemical reactions and pathways involving lipids, compounds soluble in an organic solvent but not, or sparingly, in an aqueous solvent. Includes fatty acids; neutral fats, other fatty-acid esters, and soaps; long-chain (fatty) alcohols and waxes; sphingoids and other long-chain bases; glycolipids, phospholipids and sphingolipids; and carotenes, polyprenols, sterols, terpenes and other isoprenoids. GO:0065007 biological regulation Any process that modulates a measurable attribute of any biological process, quality or function. GO:0018130 heterocycle biosynthetic process The chemical reactions and pathways resulting in the formation of heterocyclic compounds, those with a cyclic molecular structure and at least two different atoms in the ring (or rings). GO:0008152 metabolic process The chemical reactions and pathways, including anabolism and catabolism, by which living organisms transform chemical substances. Metabolic processes typically transform small molecules, but also include macromolecular processes such as DNA repair and replication, and protein synthesis and degradation. GO:0007031 peroxisome organization A process that is carried out at the cellular level which results in the assembly, arrangement of constituent parts, or disassembly of a peroxisome. A peroxisome is a small, membrane-bounded organelle that uses dioxygen (O2) to oxidize organic molecules. GO:0065007 biological regulation Any process that modulates a measurable attribute of any biological process, quality or function. GO:0051179 localization Any process in which a cell, a substance, or a cellular entity, such as a protein complex or organelle, is transported, tethered to or otherwise maintained in a specific location. In the case of substances, localization may also be achieved via selective degradation. GO:0071840 cellular component organization or biogenesis A process that results in the biosynthesis of constituent macromolecules, assembly, arrangement of constituent parts, or disassembly of a cellular component. GO:0071840 cellular component organization or biogenesis A process that results in the biosynthesis of constituent macromolecules, assembly, arrangement of constituent parts, or disassembly of a cellular component. GO:0008152 metabolic process The chemical reactions and pathways, including anabolism and catabolism, by which living organisms transform chemical substances. Metabolic processes typically transform small molecules, but also include macromolecular processes such as DNA repair and replication, and protein synthesis and degradation. GO:0008152 metabolic process The chemical reactions and pathways, including anabolism and catabolism, by which living organisms transform chemical substances. Metabolic processes typically transform small molecules, but also include macromolecular processes such as DNA repair and replication, and protein synthesis and degradation. GO:0050789 regulation of biological process Any process that modulates the frequency, rate or extent of a biological process. Biological processes are regulated by many means; examples include the control of gene expression, protein modification or interaction with a protein or substrate molecule. GO:0043603 cellular amide metabolic process The chemical reactions and pathways involving an amide, any derivative of an oxoacid in which an acidic hydroxy group has been replaced by an amino or substituted amino group, as carried out by individual cells. GO:0009132 nucleoside diphosphate metabolic process The chemical reactions and pathways involving a nucleoside diphosphate, a compound consisting of a nucleobase linked to a deoxyribose or ribose sugar esterified with diphosphate on the sugar. GO:0009058 biosynthetic process The chemical reactions and pathways resulting in the formation of substances; typically the energy-requiring part of metabolism in which simpler substances are transformed into more complex ones. GO:0051179 localization Any process in which a cell, a substance, or a cellular entity, such as a protein complex or organelle, is transported, tethered to or otherwise maintained in a specific location. In the case of substances, localization may also be achieved via selective degradation. GO:0048519 negative regulation of biological process Any process that stops, prevents, or reduces the frequency, rate or extent of a biological process. Biological processes are regulated by many means; examples include the control of gene expression, protein modification or interaction with a protein or substrate molecule. GO:1901360 organic cyclic compound metabolic process The chemical reactions and pathways involving organic cyclic compound. GO:0022402 cell cycle process The cellular process that ensures successive accurate and complete genome replication and chromosome segregation. GO:0007163 establishment or maintenance of cell polarity Any cellular process that results in the specification, formation or maintenance of anisotropic intracellular organization or cell growth patterns. GO:0043170 macromolecule metabolic process The chemical reactions and pathways involving macromolecules, any molecule of high relative molecular mass, the structure of which essentially comprises the multiple repetition of units derived, actually or conceptually, from molecules of low relative molecular mass. GO:0009056 catabolic process The chemical reactions and pathways resulting in the breakdown of substances, including the breakdown of carbon compounds with the liberation of energy for use by the cell or organism. GO:0043170 macromolecule metabolic process The chemical reactions and pathways involving macromolecules, any molecule of high relative molecular mass, the structure of which essentially comprises the multiple repetition of units derived, actually or conceptually, from molecules of low relative molecular mass. GO:0051716 cellular response to stimulus Any process that results in a change in state or activity of a cell (in terms of movement, secretion, enzyme production, gene expression, etc.) as a result of a stimulus. The process begins with detection of the stimulus by a cell and ends with a change in state or activity or the cell. GO:0016043 cellular component organization A process that results in the assembly, arrangement of constituent parts, or disassembly of a cellular component. GO:0009058 biosynthetic process The chemical reactions and pathways resulting in the formation of substances; typically the energy-requiring part of metabolism in which simpler substances are transformed into more complex ones.
In [36]:
simsGOAncestor <- mgoSim(representativeTermsAncestor, representativeTermsAncestor, semData=scGO, measure="Wang", combine=NULL)
In [37]:
head(simsGOAncestor)
GO:0006644 GO:0007049 GO:0044699 GO:0044710 GO:0051128 GO:0034641 GO:0006725 GO:0044238 GO:0005975 GO:0030029 ⋯ GO:0071840 GO:0043603 GO:0009132 GO:0009058 GO:0048519 GO:1901360 GO:0022402 GO:0007163 GO:0043170 GO:0016043 GO:0006644 1.000 0.354 0.239 0.405 0.130 0.334 0.354 0.323 0.362 0.354 ⋯ 0.106 0.294 0.618 0.197 0.087 0.281 0.339 0.354 0.281 0.184 GO:0007049 0.354 1.000 0.547 0.379 0.245 0.289 0.321 0.191 0.139 0.722 ⋯ 0.243 0.256 0.291 0.191 0.180 0.156 0.872 0.722 0.156 0.379 GO:0044699 0.239 0.547 1.000 0.643 0.178 0.212 0.243 0.340 0.236 0.547 ⋯ 0.444 0.192 0.198 0.340 0.304 0.276 0.493 0.547 0.276 0.286 GO:0044710 0.405 0.379 0.643 1.000 0.129 0.340 0.379 0.507 0.371 0.379 ⋯ 0.286 0.305 0.336 0.507 0.210 0.419 0.349 0.379 0.419 0.198 GO:0051128 0.130 0.245 0.178 0.129 1.000 0.225 0.245 0.142 0.107 0.245 ⋯ 0.400 0.198 0.107 0.142 0.447 0.117 0.229 0.245 0.117 0.651 GO:0034641 0.334 0.289 0.212 0.340 0.225 1.000 0.649 0.379 0.283 0.289 ⋯ 0.212 0.888 0.433 0.379 0.161 0.314 0.268 0.289 0.314 0.340
In [38]:
head(shortest.path)
V1 V2 V3 V4 V5 V6 V7 V8 V9 V10 ⋯ V43 V44 V45 V46 V47 V48 V49 V50 V51 V52 0 1 1 1 1 2 2 1 2 2 ⋯ 5 3 5 2 4 3 3 3 3 3 1 0 1 1 1 1 2 2 1 2 ⋯ 5 3 5 2 4 3 3 3 2 2 1 1 0 2 2 2 3 2 2 3 ⋯ 6 2 6 3 5 4 2 2 3 3 1 1 2 0 2 2 3 2 2 3 ⋯ 6 4 6 3 5 4 4 4 3 3 1 1 2 2 0 1 1 1 1 1 ⋯ 4 4 4 1 3 2 4 4 2 2 2 1 2 2 1 0 1 2 2 2 ⋯ 5 4 5 2 4 3 4 4 1 1
In [15]:
information_content <- function(term){
return (goSim(term, term, semData=scGO, measure="Resnik"))
}
most_representative_term_ic <- function(namedTerms){
ics <- sapply(names(namedTerms), information_content)
names(ics) <- names(namedTerms)
return(names(sort(ics, decreasing=TRUE)[1]))
}
In [16]:
representativeTermsIC <- sapply(Filter(length, gos), most_representative_term_ic)
In [17]:
select(GO.db, keys=representativeTermsIC, columns=c("TERM", "DEFINITION"))
'select()' returned 1:1 mapping between keys and columns
GOID TERM DEFINITION GO:0090114 COPII-coated vesicle budding The evagination of an endoplasmic reticulum membrane, resulting in formation of a COPII-coated vesicle. GO:0031146 SCF-dependent proteasomal ubiquitin-dependent protein catabolic process The chemical reactions and pathways resulting in the breakdown of a protein or peptide by hydrolysis of its peptide bonds, initiated by the covalent attachment of ubiquitin, with ubiquitin-protein ligation catalyzed by an SCF (Skp1/Cul1/F-box protein) complex, and mediated by the proteasome. GO:0009132 nucleoside diphosphate metabolic process The chemical reactions and pathways involving a nucleoside diphosphate, a compound consisting of a nucleobase linked to a deoxyribose or ribose sugar esterified with diphosphate on the sugar. GO:0044038 cell wall macromolecule biosynthetic process The chemical reactions and pathways resulting in the formation of a macromolecule destined to form part of a cell wall. GO:0043467 regulation of generation of precursor metabolites and energy Any process that modulates the frequency, rate or extent of the chemical reactions and pathways resulting in the formation of precursor metabolites, substances from which energy is derived, and the processes involved in the liberation of energy from these substances. GO:0008033 tRNA processing The process in which a pre-tRNA molecule is converted to a mature tRNA, ready for addition of an aminoacyl group. GO:0031113 regulation of microtubule polymerization Any process that modulates the frequency, rate or extent of microtubule polymerization. GO:0051123 RNA polymerase II transcriptional preinitiation complex assembly The aggregation, arrangement and bonding together of proteins on an RNA polymerase II promoter DNA to form the transcriptional preinitiation complex (PIC), the formation of which is a prerequisite for transcription by RNA polymerase. GO:0006896 Golgi to vacuole transport The directed movement of substances from the Golgi to the vacuole. GO:0016973 poly(A)+ mRNA export from nucleus The directed movement of poly(A)+ mRNA out of the nucleus into the cytoplasm. GO:0006576 cellular biogenic amine metabolic process The chemical reactions and pathways occurring at the level of individual cells involving any of a group of naturally occurring, biologically active amines, such as norepinephrine, histamine, and serotonin, many of which act as neurotransmitters. GO:0002181 cytoplasmic translation The chemical reactions and pathways resulting in the formation of a protein in the cytoplasm. This is a ribosome-mediated process in which the information in messenger RNA (mRNA) is used to specify the sequence of amino acids in the protein. GO:0040001 establishment of mitotic spindle localization The cell cycle process in which the directed movement of the mitotic spindle to a specific location in the cell occurs. GO:0016558 protein import into peroxisome matrix The import of proteins into the peroxisomal matrix. A peroxisome targeting signal (PTS) binds to a soluble receptor protein in the cytosol, and the resulting complex then binds to a receptor protein in the peroxisome membrane and is imported. The cargo protein is then released into the peroxisome matrix. GO:0006999 nuclear pore organization A process that is carried out at the cellular level which results in the assembly, arrangement of constituent parts, or disassembly of the nuclear pore. GO:0007096 regulation of exit from mitosis Any process involved in the progression from anaphase/telophase to G1 that is associated with a conversion from high to low mitotic CDK activity. GO:1904669 ATP export The directed movement of ATP out of a cell or organelle.
In [18]:
simsGOIC <- mgoSim(representativeTermsIC, representativeTermsIC, semData=scGO, measure="Wang", combine=NULL)
In [19]:
head(simsGOIC)
GO:0090114 GO:0031146 GO:0009132 GO:0044038 GO:0043467 GO:0008033 GO:0031113 GO:0051123 GO:0006896 GO:0016973 GO:0006576 GO:0002181 GO:0040001 GO:0016558 GO:0006999 GO:0007096 GO:1904669 GO:0090114 1.000 0.045 0.126 0.083 0.070 0.050 0.187 0.086 0.551 0.392 0.068 0.048 0.428 0.496 0.197 0.193 0.214 GO:0031146 0.045 1.000 0.186 0.241 0.161 0.226 0.037 0.154 0.024 0.092 0.196 0.296 0.040 0.032 0.072 0.035 0.020 GO:0009132 0.126 0.186 1.000 0.193 0.192 0.404 0.102 0.294 0.065 0.112 0.350 0.247 0.119 0.097 0.089 0.106 0.056 GO:0044038 0.083 0.241 0.193 1.000 0.205 0.270 0.106 0.399 0.029 0.114 0.250 0.462 0.080 0.064 0.141 0.071 0.025 GO:0043467 0.070 0.161 0.192 0.205 1.000 0.185 0.181 0.126 0.039 0.063 0.274 0.162 0.068 0.053 0.128 0.176 0.033 GO:0008033 0.050 0.226 0.404 0.270 0.185 1.000 0.042 0.383 0.026 0.130 0.328 0.328 0.046 0.037 0.083 0.040 0.021
In [20]:
head(shortest.path)
V1 V2 V3 V4 V5 V6 V7 V8 V9 V10 V11 V12 V13 V14 V15 V16 V17 V18 V19 V20 0 1 1 1 1 1 2 1 2 2 2 2 3 3 2 3 2 3 3 4 1 0 1 1 2 2 1 1 1 1 1 1 2 2 1 2 1 2 2 3 1 1 0 2 2 1 1 2 2 2 2 2 3 3 2 2 2 3 3 4 1 1 2 0 1 2 2 2 2 2 2 2 3 3 2 3 2 3 3 4 1 2 2 1 0 2 3 2 3 3 3 3 4 4 3 4 3 4 4 5 1 2 1 2 2 0 2 2 3 3 3 3 4 4 3 3 3 4 4 5
In [148]:
wangClusterSim <- mclusterSim(g, semData=scGO, measure="Wang", combine="BMA")
In [149]:
head(wangClusterSim)
1.000 0.527 0.544 0.491 0.534 0.491 0.513 0.495 0.448 0.505 0.375 0.632 0.531 0.527 1.000 0.610 0.568 0.520 0.534 0.523 0.507 0.548 0.540 0.455 0.584 0.494 0.544 0.610 1.000 0.625 0.523 0.608 0.651 0.606 0.634 0.602 0.358 0.604 0.391 0.491 0.568 0.625 1.000 0.514 0.558 0.609 0.552 0.623 0.592 0.416 0.521 0.383 0.534 0.520 0.523 0.514 1.000 0.496 0.514 0.522 0.464 0.585 0.409 0.554 0.453 0.491 0.534 0.608 0.558 0.496 1.000 0.557 0.540 0.539 0.549 0.354 0.591 0.453
In [150]:
head(shortest.path)
V1 V2 V3 V4 V5 V6 V7 V8 V9 V10 V11 V12 V13 0 1 1 1 2 2 1 1 2 2 1 1 1 1 0 1 2 1 1 2 2 3 1 2 2 2 1 1 0 1 1 2 2 2 3 2 2 2 2 1 2 1 0 2 3 1 2 2 3 2 2 2 2 1 1 2 0 1 3 3 4 2 3 3 3 2 1 2 3 1 0 3 3 4 1 3 3 3
In [156]:
goSims <- matrix(numeric(), nrow=numCom, ncol=numCom)
for (i in 1:numCom){
for (j in 1:numCom){
goSims[i, j] = mgoSim(names(gos[[i]]), names(gos[[j]]), measure="Wang", semData=scGO, combine="BMA")
}
}
In [157]:
head(goSims)
1.000 0.164 0.093 0.140 0.602 0.145 0.221 0.338 0.134 0.276 NA 0.525 0.626 0.164 1.000 0.633 0.475 0.171 0.348 0.363 0.322 0.672 0.234 NA 0.362 0.082 0.093 0.633 1.000 0.343 0.085 0.286 0.411 0.201 0.563 0.200 NA 0.246 0.073 0.140 0.475 0.343 1.000 0.132 0.321 0.236 0.226 1.000 0.276 NA 0.331 0.094 0.602 0.171 0.085 0.132 1.000 0.182 0.298 0.511 0.134 0.234 NA 0.447 0.537 0.145 0.348 0.286 0.321 0.182 1.000 0.285 0.278 0.385 0.286 NA 0.368 0.137
In [18]:
wangGoSims <- sapply(names(enrichedGOs),
function(i) sapply(names(enrichedGOs),
function(j) mgoSim(i, j, semData=scGO, measure="Wang", combine="BMA")))
In [19]:
wangGoSims
In [22]:
mgeneSim(allGeneNames[as.integer(g[[1]])], semData=scGO, measure="Wang", combine="BMA")
|======================================================================| 100%
YML028W YGL122C YPL214C YHL006C YKL130C YCR011C YBL007C YJR091C YGL145W YBR133C YDR214W YGR268C YLR291C YOR138C YEL023C YFR002W YML028W 1.000 0.218 0.330 0.389 0.193 0.385 0.183 0.150 0.121 0.324 0.547 0.477 0.146 0.157 0.477 0.152 YGL122C 0.218 1.000 0.270 0.318 0.119 0.340 0.085 0.332 0.451 0.351 0.098 0.185 0.295 0.223 0.185 0.326 YPL214C 0.330 0.270 1.000 0.338 0.188 0.171 0.131 0.212 0.053 0.319 0.106 0.069 0.396 0.123 0.069 0.080 YHL006C 0.389 0.318 0.338 1.000 0.208 0.234 0.264 0.263 0.078 0.310 0.235 0.105 0.230 0.249 0.105 0.196 YKL130C 0.193 0.119 0.188 0.208 1.000 0.245 0.176 0.298 0.203 0.152 0.142 0.243 0.118 0.091 0.243 0.156 YCR011C 0.385 0.340 0.171 0.234 0.245 1.000 0.391 0.242 0.512 0.373 0.284 0.196 0.161 0.112 0.196 0.350 YBL007C 0.183 0.085 0.131 0.264 0.176 0.391 1.000 0.149 0.453 0.167 0.158 0.283 0.079 0.062 0.283 0.328 YJR091C 0.150 0.332 0.212 0.263 0.298 0.242 0.149 1.000 0.344 0.210 0.118 0.200 0.115 0.140 0.200 0.221 YGL145W 0.121 0.451 0.053 0.078 0.203 0.512 0.453 0.344 1.000 0.117 0.095 0.158 0.045 0.035 0.158 0.451 YBR133C 0.324 0.351 0.319 0.310 0.152 0.373 0.167 0.210 0.117 1.000 0.192 0.217 0.294 0.330 0.217 0.132 YDR214W 0.547 0.098 0.106 0.235 0.142 0.284 0.158 0.118 0.095 0.192 1.000 0.477 0.099 0.144 0.477 0.145 YGR268C 0.477 0.185 0.069 0.105 0.243 0.196 0.283 0.200 0.158 0.217 0.477 1.000 0.077 0.144 1.000 0.203 YLR291C 0.146 0.295 0.396 0.230 0.118 0.161 0.079 0.115 0.045 0.294 0.099 0.077 1.000 0.268 0.077 0.064 YOR138C 0.157 0.223 0.123 0.249 0.091 0.112 0.062 0.140 0.035 0.330 0.144 0.144 0.268 1.000 0.144 0.070 YEL023C 0.477 0.185 0.069 0.105 0.243 0.196 0.283 0.200 0.158 0.217 0.477 1.000 0.077 0.144 1.000 0.203 YFR002W 0.152 0.326 0.080 0.196 0.156 0.350 0.328 0.221 0.451 0.132 0.145 0.203 0.064 0.070 0.203 1.000
In [21]:
mgoSim(names(enrichedGOs[[1]]), names(enrichedGOs[[2]]), semData=scGO, measure="Wang", combine="BMA")
0.106
In [15]:
head(shortest.path)
V1 V2 V3 V4 V5 V6 0 1 1 1 1 1 1 0 1 2 2 2 1 1 0 1 1 1 1 2 1 0 2 2 1 2 1 2 0 2 1 2 1 2 2 0
In [116]:
distances <- numeric(length = (numCom * (numCom - 1)) / 2)
semSims <- numeric(length = (numCom * (numCom - 1)) / 2)
completed <- 0
for (c1 in 1:length(enrichedGOsPathway)) {
for (c2 in c1:length(enrichedGOsPathway)) {
if (c1 == c2) next
completed <- completed + 1
semSims[completed] <- simsPathway[c1, c2]
distances[completed] <- shortest.path[c1, c2]
print(sprintf("Completed: %s", completed))
}
}
[1] "Completed: 1"
[1] "Completed: 2"
[1] "Completed: 3"
[1] "Completed: 4"
[1] "Completed: 5"
[1] "Completed: 6"
[1] "Completed: 7"
[1] "Completed: 8"
[1] "Completed: 9"
[1] "Completed: 10"
[1] "Completed: 11"
[1] "Completed: 12"
[1] "Completed: 13"
[1] "Completed: 14"
[1] "Completed: 15"
[1] "Completed: 16"
[1] "Completed: 17"
[1] "Completed: 18"
[1] "Completed: 19"
[1] "Completed: 20"
[1] "Completed: 21"
[1] "Completed: 22"
[1] "Completed: 23"
[1] "Completed: 24"
[1] "Completed: 25"
[1] "Completed: 26"
[1] "Completed: 27"
[1] "Completed: 28"
[1] "Completed: 29"
[1] "Completed: 30"
[1] "Completed: 31"
[1] "Completed: 32"
[1] "Completed: 33"
[1] "Completed: 34"
[1] "Completed: 35"
[1] "Completed: 36"
[1] "Completed: 37"
[1] "Completed: 38"
[1] "Completed: 39"
[1] "Completed: 40"
[1] "Completed: 41"
[1] "Completed: 42"
[1] "Completed: 43"
[1] "Completed: 44"
[1] "Completed: 45"
[1] "Completed: 46"
[1] "Completed: 47"
[1] "Completed: 48"
[1] "Completed: 49"
[1] "Completed: 50"
[1] "Completed: 51"
[1] "Completed: 52"
[1] "Completed: 53"
[1] "Completed: 54"
[1] "Completed: 55"
[1] "Completed: 56"
[1] "Completed: 57"
[1] "Completed: 58"
[1] "Completed: 59"
[1] "Completed: 60"
[1] "Completed: 61"
[1] "Completed: 62"
[1] "Completed: 63"
[1] "Completed: 64"
[1] "Completed: 65"
[1] "Completed: 66"
[1] "Completed: 67"
[1] "Completed: 68"
[1] "Completed: 69"
[1] "Completed: 70"
[1] "Completed: 71"
[1] "Completed: 72"
[1] "Completed: 73"
[1] "Completed: 74"
[1] "Completed: 75"
[1] "Completed: 76"
[1] "Completed: 77"
[1] "Completed: 78"
[1] "Completed: 79"
[1] "Completed: 80"
[1] "Completed: 81"
[1] "Completed: 82"
[1] "Completed: 83"
[1] "Completed: 84"
[1] "Completed: 85"
[1] "Completed: 86"
[1] "Completed: 87"
[1] "Completed: 88"
[1] "Completed: 89"
[1] "Completed: 90"
[1] "Completed: 91"
[1] "Completed: 92"
[1] "Completed: 93"
[1] "Completed: 94"
[1] "Completed: 95"
[1] "Completed: 96"
[1] "Completed: 97"
[1] "Completed: 98"
[1] "Completed: 99"
[1] "Completed: 100"
[1] "Completed: 101"
[1] "Completed: 102"
[1] "Completed: 103"
[1] "Completed: 104"
[1] "Completed: 105"
[1] "Completed: 106"
[1] "Completed: 107"
[1] "Completed: 108"
[1] "Completed: 109"
[1] "Completed: 110"
[1] "Completed: 111"
[1] "Completed: 112"
[1] "Completed: 113"
[1] "Completed: 114"
[1] "Completed: 115"
[1] "Completed: 116"
[1] "Completed: 117"
[1] "Completed: 118"
[1] "Completed: 119"
[1] "Completed: 120"
[1] "Completed: 121"
[1] "Completed: 122"
[1] "Completed: 123"
[1] "Completed: 124"
[1] "Completed: 125"
[1] "Completed: 126"
[1] "Completed: 127"
[1] "Completed: 128"
[1] "Completed: 129"
[1] "Completed: 130"
[1] "Completed: 131"
[1] "Completed: 132"
[1] "Completed: 133"
[1] "Completed: 134"
[1] "Completed: 135"
[1] "Completed: 136"
[1] "Completed: 137"
[1] "Completed: 138"
[1] "Completed: 139"
[1] "Completed: 140"
[1] "Completed: 141"
[1] "Completed: 142"
[1] "Completed: 143"
[1] "Completed: 144"
[1] "Completed: 145"
[1] "Completed: 146"
[1] "Completed: 147"
[1] "Completed: 148"
[1] "Completed: 149"
[1] "Completed: 150"
[1] "Completed: 151"
[1] "Completed: 152"
[1] "Completed: 153"
[1] "Completed: 154"
[1] "Completed: 155"
[1] "Completed: 156"
[1] "Completed: 157"
[1] "Completed: 158"
[1] "Completed: 159"
[1] "Completed: 160"
[1] "Completed: 161"
[1] "Completed: 162"
[1] "Completed: 163"
[1] "Completed: 164"
[1] "Completed: 165"
[1] "Completed: 166"
[1] "Completed: 167"
[1] "Completed: 168"
[1] "Completed: 169"
[1] "Completed: 170"
[1] "Completed: 171"
[1] "Completed: 172"
[1] "Completed: 173"
[1] "Completed: 174"
[1] "Completed: 175"
[1] "Completed: 176"
[1] "Completed: 177"
[1] "Completed: 178"
[1] "Completed: 179"
[1] "Completed: 180"
[1] "Completed: 181"
[1] "Completed: 182"
[1] "Completed: 183"
[1] "Completed: 184"
[1] "Completed: 185"
[1] "Completed: 186"
[1] "Completed: 187"
[1] "Completed: 188"
[1] "Completed: 189"
[1] "Completed: 190"
[1] "Completed: 191"
[1] "Completed: 192"
[1] "Completed: 193"
[1] "Completed: 194"
[1] "Completed: 195"
[1] "Completed: 196"
[1] "Completed: 197"
[1] "Completed: 198"
[1] "Completed: 199"
[1] "Completed: 200"
[1] "Completed: 201"
[1] "Completed: 202"
[1] "Completed: 203"
[1] "Completed: 204"
[1] "Completed: 205"
[1] "Completed: 206"
[1] "Completed: 207"
[1] "Completed: 208"
[1] "Completed: 209"
[1] "Completed: 210"
[1] "Completed: 211"
[1] "Completed: 212"
[1] "Completed: 213"
[1] "Completed: 214"
[1] "Completed: 215"
[1] "Completed: 216"
[1] "Completed: 217"
[1] "Completed: 218"
[1] "Completed: 219"
[1] "Completed: 220"
[1] "Completed: 221"
[1] "Completed: 222"
[1] "Completed: 223"
[1] "Completed: 224"
[1] "Completed: 225"
[1] "Completed: 226"
[1] "Completed: 227"
[1] "Completed: 228"
[1] "Completed: 229"
[1] "Completed: 230"
[1] "Completed: 231"
[1] "Completed: 232"
[1] "Completed: 233"
[1] "Completed: 234"
[1] "Completed: 235"
[1] "Completed: 236"
[1] "Completed: 237"
[1] "Completed: 238"
[1] "Completed: 239"
[1] "Completed: 240"
[1] "Completed: 241"
[1] "Completed: 242"
[1] "Completed: 243"
[1] "Completed: 244"
[1] "Completed: 245"
[1] "Completed: 246"
[1] "Completed: 247"
[1] "Completed: 248"
[1] "Completed: 249"
[1] "Completed: 250"
[1] "Completed: 251"
[1] "Completed: 252"
[1] "Completed: 253"
In [117]:
plot(distances, semSims, xlab="Distance on Map", ylab="Shared Paths")
In [102]:
cor(distances, semSims, method="spearman")
-0.05678168738453
In [42]:
library(GOSim)
setOntology(ont, loadIC=FALSE)
setEvidenceLevel(evidences="all",organism=org.Sc.sgdORGANISM, gomap=org.Sc.sgdGO)
e <- GOenrichment(g[[46]], allGenes)
-> retrieving GO information for all available genes for organism 'Saccharomyces cerevisiae' in GO database
-> filtering GO terms according to evidence levels 'all'
Building most specific GOs .....
( 1690 GO terms found. )
Build GO DAG topology ..........
( 3645 GO terms and 8243 relations. )
Annotating nodes ...............
( 1567 genes annotated to the GO terms. )
-- Elim Algorithm --
the algorithm is scoring 172 nontrivial nodes
parameters:
test statistic: fisher
cutOff: 0.01
Level 14: 1 nodes to be scored (0 eliminated genes)
Level 13: 3 nodes to be scored (0 eliminated genes)
Level 12: 7 nodes to be scored (0 eliminated genes)
Level 11: 9 nodes to be scored (0 eliminated genes)
Level 10: 8 nodes to be scored (1 eliminated genes)
Level 9: 17 nodes to be scored (3 eliminated genes)
Level 8: 14 nodes to be scored (8 eliminated genes)
Level 7: 20 nodes to be scored (8 eliminated genes)
Level 6: 25 nodes to be scored (8 eliminated genes)
Level 5: 28 nodes to be scored (8 eliminated genes)
Level 4: 20 nodes to be scored (28 eliminated genes)
Level 3: 12 nodes to be scored (28 eliminated genes)
Level 2: 7 nodes to be scored (28 eliminated genes)
Level 1: 1 nodes to be scored (28 eliminated genes)
In [49]:
e
- $GOTerms
go_id Term Definition 15591 GO:0018343 protein farnesylation The covalent attachment of a farnesyl group to a protein. 15594 GO:0018344 protein geranylgeranylation The covalent attachment of a geranylgeranyl group to a protein. 16626 GO:0006874 cellular calcium ion homeostasis Any process involved in the maintenance of an internal steady state of calcium ions at the level of a cell. 17047 GO:0030010 establishment of cell polarity The specification and formation of anisotropic intracellular organization or cell growth patterns. 48636 GO:0042127 regulation of cell proliferation Any process that modulates the frequency, rate or extent of cell proliferation. 79331 GO:0070884 regulation of calcineurin-NFAT signaling cascade Any process that modulates the frequency, rate or extent of the calcineurin-NFAT signaling cascade.
- $p.values
- GO:0006874
- 0.00891715384596614
- GO:0042127
- 0.00446713465220172
- GO:0070884
- 0.00446713465220172
- GO:0018343
- 1.71154584375543e-05
- GO:0018344
- 0.000170063041559058
- GO:0030010
- 0.00345128149568176
- $genes
- $`GO:0006874`
- 'YBR187W'
- 'YGL155W'
- $`GO:0042127`
- 'YDL090C'
- $`GO:0070884`
- 'YKL159C'
- $`GO:0018343`
- 'YDL090C'
- 'YKL019W'
- $`GO:0018344`
- 'YGL155W'
- 'YJL031C'
- 'YKL019W'
- 'YOR370C'
- 'YPR176C'
- $`GO:0030010`
- 'YCR063W'
- 'YER093C'
- 'YER118C'
- 'YER149C'
- 'YFL039C'
- 'YGL054C'
- 'YGL155W'
- 'YGR014W'
- 'YGR058W'
- 'YGR262C'
- 'YHR115C'
- 'YHR129C'
- 'YIL144W'
- 'YLL049W'
- 'YLR319C'
- 'YMR294W'
- 'YNL116W'
- 'YOR127W'
- 'YOR301W'
- 'YPL161C'
- 'YPL174C'
In [88]:
goTerms <- e$GOTerms
p.values <- e$p.values
In [89]:
p.values.df <- data.frame(p.values)
p.values.df["go_id"] <- names(p.values)
p.values.df
p.values go_id GO:0006874 8.917154e-03 GO:0006874 GO:0042127 4.467135e-03 GO:0042127 GO:0070884 4.467135e-03 GO:0070884 GO:0018343 1.711546e-05 GO:0018343 GO:0018344 1.700630e-04 GO:0018344 GO:0030010 3.451281e-03 GO:0030010
In [90]:
goTerms <- merge(goTerms, p.values.df, by="go_id")
In [93]:
colnames(goTerms) <- c("GO_ID", "TERM", "DEFINITION", "P_VALUE")
head(goTerms)
GO_ID TERM DEFINITION P_VALUE GO:0006874 cellular calcium ion homeostasis Any process involved in the maintenance of an internal steady state of calcium ions at the level of a cell. 8.917154e-03 GO:0018343 protein farnesylation The covalent attachment of a farnesyl group to a protein. 1.711546e-05 GO:0018344 protein geranylgeranylation The covalent attachment of a geranylgeranyl group to a protein. 1.700630e-04 GO:0030010 establishment of cell polarity The specification and formation of anisotropic intracellular organization or cell growth patterns. 3.451281e-03 GO:0042127 regulation of cell proliferation Any process that modulates the frequency, rate or extent of cell proliferation. 4.467135e-03 GO:0070884 regulation of calcineurin-NFAT signaling cascade Any process that modulates the frequency, rate or extent of the calcineurin-NFAT signaling cascade. 4.467135e-03
In [94]:
library(gridExtra)
grid.table(goTerms[,c("GO_ID", "TERM", "P_VALUE")])
In [46]:
g[[46]]
- 'YKL019W'
- 'YGL155W'
- 'YKL159C'
- 'YCR063W'
- 'YBR247C'
- 'YDL090C'
- 'YOL135C'
In [103]:
l <- as.list(org.Sc.sgdGO[["YKL019W"]])
In [116]:
gos <- sapply(l, function(i) i[["GOID"]])
In [122]:
t <- select(GO.db, keys=gos, columns=c("GOID","TERM","ONTOLOGY"))
'select()' returned many:1 mapping between keys and columns
In [123]:
grid.table(t)
In [ ]:
Content source: DavidMcDonald1993/ghsom
Similar notebooks: