Load data

corpus_md<-create_corpus_dataset(f_corp_meta,jarprepro)
dfu<-(read.csv(f_rousage,stringsAsFactors = FALSE))
dfu$AX<-apply(dfu[c("AX")],1,base64)
df<-unique(dfu)

df_sample<-read.csv(f_onts,stringsAsFactors = FALSE)
#df_ad_raw<-read_csvs_tdl(f_impactad)
nrow(df)
## [1] 870713
#nrow(df_ad_raw)

Preprocess RO usage dataset

df$O<-gsub("http://purl.obolibrary.org/obo/","", df$ONT)
df$O<-gsub(".owl$","", df$O)
df$O<-gsub(".obo$","", df$O)
df$O<-gsub("^ontoneo/","", df$O)
df$O<-gsub("http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus","NCITNCBO", df$O)
df$O<-gsub("http://www.ebi.ac.uk/swo/","", df$O)
df$O<-gsub("http://semanticscience.org/ontology/","", df$O)
df$O<-gsub("http://anobase.vectorbase.org/mirnao/","", df$O)
df$O<-gsub("agro-edit","agro", df$O)
df$O<-gsub("caro/caro","caro", df$O)
df$O<-gsub("^mfmo$","feed", df$O)
df$O<-gsub("^ico$","ico_merged", df$O)
df$O<-gsub("^ido$","ido-merged", df$O)
df$O<-gsub("^ncro$","ncro-all-in-one", df$O)
df$O<-gsub("^obcs$","obcs_merged_inferred", df$O)
df$O<-gsub("^obib$","obib_merged_inferred", df$O)
df$O<-gsub("^omiabis$","omiabis_merged", df$O)
df$O<-gsub("^opl$","opl_inferred", df$O)
df$O<-gsub("^pco_merged$","pco_merged_inferred", df$O)
df$O<-gsub("^bcgo$","bcgo_merged_inferred", df$O)
df$O<-gsub("^DINTO$","DINTO_1.2", df$O)
df$O<-gsub("^swo$","swo_merged", df$O)
df$O<-gsub("^ogg$","ogg-merged", df$O)
df$TEMP_ANN<-ifelse(df$TEMP_ANN==""&df$RO_REL=="depends on","Dom:X-Ran:X~Time:Same~Rig:Yes-Nec:No",df$TEMP_ANN)
df$TEMP_ANN_ALL<-paste(df$TEMP_ANN,df$TEMP_INF_ANN,sep="~")
df$CAT<-ifelse(grepl("Dom:C.*Ran:C",df$TEMP_ANN_ALL),"CC",ifelse(grepl("(Dom:C.*Ran:O)|(Dom:O.*Ran:C)",df$TEMP_ANN_ALL),"OC-CO",ifelse(grepl("Dom:O.*Ran:O",df$TEMP_ANN_ALL),"OO","OT")))
df$containsnecno<-grepl("Nec:No",df$TEMP_ANN_ALL)

kable(plyr::count(df$MATCH),row.names = FALSE)
x freq
exact 362326
smart 508387
# removing broken records (that are neither exact nor smart matches)
df_broken<-(df[!(df$MATCH %in% c("exact","smart")),])
df<-(df[(df$MATCH %in% c("exact","smart")),])



# Excluding exact matches
df_ex<-(df[(df$MATCH %in% c("exact")),])
df<-(df[(df$MATCH %in% c("smart")),])

o_smart<-unique(df$ONT)
o_exact<-unique(df_ex$ONT)
# ontologies with smart matches:
length(o_smart)
## [1] 98
# ontologies with exact matches:
length(o_exact)
## [1] 68
length(o_exact)/length(o_smart)
## [1] 0.6938776
length(unique(df_ex$AX))/length(unique(df$AX))
## [1] 0.7018598
print("Broken")
## [1] "Broken"
nrow(df_broken)
## [1] 0
print("Excluded Exact matches (redundant)")
## [1] "Excluded Exact matches (redundant)"
nrow(df_ex)
## [1] 362326
print("Remaining Smart matches")
## [1] "Remaining Smart matches"
nrow(df)
## [1] 508387
# Variable with number of all ontologies in dataset
ct_o<-length(unique(df$O))

Dataset characteristics

d0<-unique(df[c("O","ONT_TOTAL_AX","AX")])

## Percentage of axioms with temporal annotations across ontologies
ct_ov_o<-plyr::count(d0[c("O","ONT_TOTAL_AX")])
ct_ov_o$pc<-round((ct_ov_o$freq/ct_ov_o$ONT_TOTAL_AX)*100,2)
summary(ct_ov_o$pc)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   0.040   5.485  18.005  25.784  39.005  98.510
ct_ov_o<-ct_ov_o[order(-ct_ov_o$pc),]
kable(ct_ov_o,row.names = FALSE)
O ONT_TOTAL_AX freq pc
flopo 23504 23154 98.51
emap 21723 21196 97.57
wbls 1424 1334 93.68
xao 5887 4373 74.28
zfa 11750 8619 73.35
tgma 2733 1952 71.42
tads 948 663 69.94
oba 36448 24245 66.52
mmusdv 307 196 63.84
ddanat 347 221 63.69
hsapdv 698 442 63.32
zfs 148 92 62.16
fbdv 719 437 60.78
fbbt 33282 19997 60.08
spd 840 458 54.52
clo 117057 61416 52.47
ma 4104 1975 48.12
cl 7976 3784 47.44
olatdv 91 42 46.15
wbbt 15187 7002 46.11
uberon 53169 24218 45.55
pdumdv 42 19 45.24
fypo 33040 14080 42.62
ehdaa2 13369 5394 40.35
cvdo 580 229 39.48
bto 6884 2587 37.58
mp 22776 8516 37.39
po 3152 1053 33.41
opl_inferred 886 292 32.96
emapa 21772 6877 31.59
dpo 1265 393 31.07
exo 101 31 30.69
mro 3098 920 29.70
go 106492 31414 29.50
ceph 604 178 29.47
aeo 366 101 27.60
bspo 473 130 27.48
feed 353 97 27.48
hp 21326 5719 26.82
ovae 4701 1173 24.95
idomal 3468 846 24.39
so-xp 3096 747 24.13
obi 6316 1461 23.13
hao 10171 2274 22.36
caro 163 36 22.09
fao 116 25 21.55
cteno 999 202 20.22
bcgo_merged_inferred 4514 886 19.63
sibo 1106 205 18.54
to 6406 1119 17.47
obib_merged_inferred 1291 216 16.73
chebi 224955 36582 16.26
omiabis_merged 990 153 15.45
poro 1211 186 15.36
dideo 442 65 14.71
ido-merged 1064 150 14.10
fbcv 2836 399 14.07
stato 1876 264 14.07
agro 986 135 13.69
ontoneo 430 58 13.49
envo 9896 1238 12.51
ico_merged 705 86 12.20
cheminf 485 56 11.55
MicrO 5441 623 11.45
DINTO_1.2 173859 19400 11.16
bco 304 32 10.53
mirnao 764 79 10.34
oostt 175 18 10.29
omp 1998 203 10.16
rex 730 62 8.49
xco 607 49 8.07
obcs_merged_inferred 1438 99 6.88
ero 4893 322 6.58
NCITNCBO 281421 14411 5.12
iao 383 19 4.96
rxno 1328 58 4.37
pw 3253 136 4.18
swo_merged 7683 320 4.17
ms 2949 114 3.87
ogsf-merged 1056 36 3.41
fix 1684 51 3.03
chmo 3417 91 2.66
mi 1424 33 2.32
mod 3581 82 2.29
aero 1101 23 2.09
miro 4457 79 1.77
MFOEM 289 5 1.73
vario 405 4 0.99
pato 2384 15 0.63
mop 3809 20 0.53
cdao 421 2 0.48
genepio 3148 14 0.44
pco_merged_inferred 2600 11 0.42
mpath 941 3 0.32
cmo 3299 8 0.24
ncro-all-in-one 5471 7 0.13
rs 5922 7 0.12
ogg-merged 70116 28 0.04
## Distribution of ontologies
options(scipen=1000)
ov_o_size<-unique(d0[c("O","ONT_TOTAL_AX")])
summary(ov_o_size$ONT_TOTAL_AX)
##     Min.  1st Qu.   Median     Mean  3rd Qu.     Max. 
##     42.0    708.5   2191.0  14958.1   6217.5 281421.0
#ggplot(ov_o_size,aes(ONT_TOTAL_AX)) + geom_histogram(bins = 10) + scale_x_log10()
ct_cat<-plyr::count(df$CAT)
kable(ct_cat,row.names = FALSE)
x freq
CC 253334
OC-CO 29694
OO 35071
OT 190288
### The impact of smart matching (difference of top ten relation by coverage)
ds<-unique(df[c("O","AX","RO_REL","CAT")])
de<-unique(df_ex[c("O","AX","RO_REL","CAT")])
coverage_rel_wosmart<-compute_coverage_rel(de[c("O","RO_REL","CAT")],ct_o)
coverage_rel<-compute_coverage_rel(ds[c("O","RO_REL","CAT")],ct_o)
top10<-head(coverage_rel[order(-coverage_rel$coverage),],10)
top10e<-coverage_rel_wosmart[coverage_rel_wosmart$x %in% top10$x,]
top10e$source<-"exact"
top10$source<-"smart"
top<-merge(top10,top10e,all = TRUE)
top$CAT<-NULL
top$freq<-NULL
top<-reshape(top,direction = "wide",timevar = "source",idvar = "x")
names(top)<-c("Relation","Exact","Smart")
top$pdiff<-round(((top$Smart-top$Exact)/top$Exact)*100,2)
top<-top[order(-top$Smart),]
kable(top,row.names = FALSE)
Relation Exact Smart pdiff
part of 52.04 79.59 52.94
has part 40.82 48.98 19.99
inheres in 24.49 29.59 20.82
has participant 17.35 27.55 58.79
has role 16.33 26.53 62.46
realizes 21.43 24.49 14.28
located in 18.37 21.43 16.66
has quality 12.24 20.41 66.75
bearer of 15.31 19.39 26.65
develops from 16.33 19.39 18.74
print(xtable(top,digits=c(0,0,2,2,2)),include.rownames=FALSE,file="coverage_rel_exact_v_smart.tex")

## Histogram of smart matches over ontology size
#### y axis = number of ontologies, x axis: % of (axioms that use RO relations) / (total axioms)
ct_o_smart<-plyr::count(unique(ds[c("O","AX")])[c("O")])
ct_o_smart<-merge(ct_o_smart,ov_o_size,by="O")
ct_o_smart$rat<-ct_o_smart$freq/ct_o_smart$ONT_TOTAL_AX
p<-ggplot(ct_o_smart,aes(rat)) + geom_histogram() + xlab("% of axioms with smart matches") + ylab("Number of ontologies")
theme_tdl(p)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggsave("hist_matches_d_ontsize.jpg",width = 3,height = 4,units="in")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
#### y axis = number of ontologies, x axis: number of DIFFERENT ro relations used in ontology
ct_o_ro<-plyr::count(unique(ds[c("O","RO_REL")])[c("O")])
ct_o_ro$pc<-100*(ct_o_ro$freq/nr_ro_rel)

p<-ggplot(ct_o_ro,aes(freq)) + geom_histogram() + xlab("Nr. of RO relations used") + ylab("Number of ontologies")
theme_tdl(p)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggsave("hist_ro_rel_ont.jpg",width = 3,height = 4,units="in")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
### Check for duplicates
xx<-plyr::count(dfu[!(names(dfu) %in% c("AX"))])
yy<-xx[xx$freq>1,]

### Number of exact duplicate records in raw dataset
nrow(yy)
## [1] 4
head(yy)
##        ONT_TOTAL_AX       RO_REL      OBO_REL
## 93370        117057      part of      part_of
## 93371        117057      part of      part_of
## 189473       117057 derives from derives from
## 189474       117057 derives from derives from
##                                                                   TEMP_INF_ANN
## 93370                                                                         
## 93371                                                                         
## 189473 Time:Diff~Dom:C-Ran:IC~Ran:Changed~Dom:C-Ran:C~Dom:Changed~Dom:IC-Ran:C
## 189474 Time:Diff~Dom:C-Ran:IC~Ran:Changed~Dom:C-Ran:C~Dom:Changed~Dom:IC-Ran:C
##                                           ONT
## 93370  http://purl.obolibrary.org/obo/clo.owl
## 93371  http://purl.obolibrary.org/obo/clo.owl
## 189473 http://purl.obolibrary.org/obo/clo.owl
## 189474 http://purl.obolibrary.org/obo/clo.owl
##                                        RO_REL_IRI  RO_REL_HC OBO_REL_HC
## 93370  http://purl.obolibrary.org/obo/BFO_0000050 -978027865 -978027865
## 93371  http://purl.obolibrary.org/obo/BFO_0000050 -978027865 -978027865
## 189473  http://purl.obolibrary.org/obo/RO_0001000 1643394301 1643394301
## 189474  http://purl.obolibrary.org/obo/RO_0001000 1643394301 1643394301
##        MATCH      AX_HC                                OBO_REL_IRI
## 93370  exact 1812853289 http://purl.obolibrary.org/obo/BFO_0000050
## 93371  smart 1812853289 http://purl.obolibrary.org/obo/BFO_0000050
## 189473 exact 1812853289  http://purl.obolibrary.org/obo/RO_0001000
## 189474 smart 1812853289  http://purl.obolibrary.org/obo/RO_0001000
##                                             TEMP_ANN  X freq
## 93370  Dom:X-Ran:X~Time:Same~Rig:Yes-Nec:No~TI:AHFAT NA    2
## 93371  Dom:X-Ran:X~Time:Same~Rig:Yes-Nec:No~TI:AHFAT NA    2
## 189473   Dom:IC-Ran:IC~Time:Past~Dom:Birth~Ran:Death NA    2
## 189474   Dom:IC-Ran:IC~Time:Past~Dom:Birth~Ran:Death NA    2

Example MIRNAO

unique(ct_ov_o[ct_ov_o$O=="mirnao",c("O","ONT_TOTAL_AX","freq","pc")])
##         O ONT_TOTAL_AX freq    pc
## 50 mirnao          764   79 10.34
ct_different_rorels <-plyr::count(ds[ds$O=="mirnao","RO_REL"])
nrow(ct_different_rorels)
## [1] 8
ct_different_rorels
##                 x freq
## 1     adjacent to    1
## 2    derives from   41
## 3        has part    1
## 4 has participant    1
## 5        has role    1
## 6         part of   30
## 7     preceded by    1
## 8       regulates    3
summary(ct_o_ro$freq)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.000   2.000   4.500   8.306  11.000  78.000
summary(ct_o_ro$pc)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   0.250   0.500   1.125   2.077   2.750  19.500
(ct_o_ro[ct_o_ro$freq>20,])
##                       O freq    pc
## 4  bcgo_merged_inferred   23  5.75
## 26                 envo   35  8.75
## 30                 fbbt   30  7.50
## 36                 fypo   21  5.25
## 63                  obi   25  6.25
## 70              ontoneo   21  5.25
## 73                 ovae   51 12.75
## 91               uberon   78 19.50

Coverage: Relation

coverage_rel<-compute_coverage_rel(df[c("O","RO_REL","CAT")],ct_o)
d_coverage_rel<-preparePlotRanksDf(coverage_rel,"x","coverage")

plotRanks(coverage_rel,"x","coverage",xlab="Relation",ylab="Coverage",ncol=1)
ggsave("coverage_rel.jpg",width = 3,height = 4,units="in")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
top10<-head(coverage_rel[order(-coverage_rel$coverage),],10)
top10relcov<-top10$x
all<-coverage_rel[order(coverage_rel$CAT,-coverage_rel$coverage),]
print(xtable(all,digits=c(0,0,2,2,2)),include.rownames=FALSE,file="coverage_rel.tex")
print(xtable(top10,digits=c(0,0,2,2,2)),include.rownames=FALSE,file="coverage_rel_top10.tex")

# Summary stats over ALL temporal features
summary(all$coverage)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.020   1.020   2.040   5.728   6.120  79.590
sd(all$coverage)
## [1] 9.375772
# Summary stats BY DOMAIN RANGE over ALL temporal features
ddply(all,~CAT,summarise,mean=mean(coverage),median=median(coverage),sd=sd(coverage), min=min(coverage),max=max(coverage))
##     CAT      mean median        sd  min   max
## 1    CC  4.413980   2.04  5.801800 1.02 29.59
## 2 OC-CO  6.844583   3.06  7.538174 1.02 27.55
## 3    OO  5.555000   3.06  5.482081 1.02 18.37
## 4    OT 26.734000   2.04 35.949403 1.02 79.59
kable(all,row.names = FALSE)
x freq coverage CAT
inheres in 29 29.59 CC
has role 26 26.53 CC
located in 21 21.43 CC
has quality 20 20.41 CC
bearer of 19 19.39 CC
develops from 19 19.39 CC
derives from 16 16.33 CC
adjacent to 15 15.31 CC
concretizes 15 15.31 CC
has function 10 10.20 CC
has member 10 10.20 CC
towards 10 10.20 CC
overlaps 9 9.18 CC
continuous with 8 8.16 CC
composed primarily of 7 7.14 CC
has component 7 7.14 CC
location of 7 7.14 CC
member of 7 7.14 CC
surrounded by 7 7.14 CC
function of 6 6.12 CC
is concretized as 6 6.12 CC
produces 6 6.12 CC
role of 6 6.12 CC
surrounds 6 6.12 CC
attached to 5 5.10 CC
inheres in part of 5 5.10 CC
connected to 4 4.08 CC
connects 4 4.08 CC
has developmental contribution from 4 4.08 CC
innervates 4 4.08 CC
produced by 4 4.08 CC
bounding layer of 3 3.06 CC
contains 3 3.06 CC
develops into 3 3.06 CC
directly develops from 3 3.06 CC
has potential to develop into 3 3.06 CC
innervated_by 3 3.06 CC
conduit for 2 2.04 CC
contributes to morphology of 2 2.04 CC
developmentally induced by 2 2.04 CC
developmentally replaces 2 2.04 CC
develops in 2 2.04 CC
has 2D boundary 2 2.04 CC
has habitat 2 2.04 CC
has modifier 2 2.04 CC
has plasma membrane part 2 2.04 CC
has potential to developmentally contribute to 2 2.04 CC
has skeleton 2 2.04 CC
has soma location 2 2.04 CC
has synaptic terminal in 2 2.04 CC
immediate transformation of 2 2.04 CC
interacts with 2 2.04 CC
luminal space of 2 2.04 CC
quality of 2 2.04 CC
skeleton of 2 2.04 CC
supplies 2 2.04 CC
synapsed by 2 2.04 CC
synapsed to 2 2.04 CC
transformation of 2 2.04 CC
tributary of 2 2.04 CC
attached to part of 1 1.02 CC
branching part of 1 1.02 CC
child nucleus of 1 1.02 CC
child nucleus of in hermaphrodite 1 1.02 CC
child nucleus of in male 1 1.02 CC
confers advantage in 1 1.02 CC
contained in 1 1.02 CC
determined by 1 1.02 CC
determined by part of 1 1.02 CC
develops from part of 1 1.02 CC
distributary of 1 1.02 CC
drains 1 1.02 CC
electrically_synapsed_to 1 1.02 CC
expresses 1 1.02 CC
fasciculates with 1 1.02 CC
gene product of 1 1.02 CC
has disposition 1 1.02 CC
has fused element 1 1.02 CC
has host 1 1.02 CC
has muscle antagonist 1 1.02 CC
has muscle insertion 1 1.02 CC
has muscle origin 1 1.02 CC
has postsynaptic terminal in 1 1.02 CC
has presynaptic terminal in 1 1.02 CC
has synaptic terminal of 1 1.02 CC
has vector 1 1.02 CC
in homology relationship with 1 1.02 CC
lumen of 1 1.02 CC
molecularly interacts with 1 1.02 CC
partially overlaps 1 1.02 CC
serially homologous to 1 1.02 CC
spatially disjoint from 1 1.02 CC
synapsed_via_type_Ib_bouton_to 1 1.02 CC
synapsed_via_type_II_bouton_to 1 1.02 CC
synapsed_via_type_III_bouton_to 1 1.02 CC
synapsed_via_type_Is_bouton_to 1 1.02 CC
transcribed from 1 1.02 CC
transcribed to 1 1.02 CC
has participant 27 27.55 OC-CO
realizes 24 24.49 OC-CO
realized in 17 17.35 OC-CO
participates in 15 15.31 OC-CO
occurs in 14 14.29 OC-CO
capable of 10 10.20 OC-CO
has output 8 8.16 OC-CO
output of 6 6.12 OC-CO
has input 5 5.10 OC-CO
existence starts during 4 4.08 OC-CO
existence starts during or after 4 4.08 OC-CO
capable of part of 3 3.06 OC-CO
existence ends during 3 3.06 OC-CO
existence ends during or before 3 3.06 OC-CO
existence starts and ends during 3 3.06 OC-CO
actively participates in 2 2.04 OC-CO
existence ends with 2 2.04 OC-CO
existence starts with 2 2.04 OC-CO
formed as result of 2 2.04 OC-CO
has active participant 2 2.04 OC-CO
results in formation of 2 2.04 OC-CO
contains process 1 1.02 OC-CO
functionally related to 1 1.02 OC-CO
has intermediate 1 1.02 OC-CO
preceded by 18 18.37 OO
immediately preceded by 15 15.31 OO
precedes 15 15.31 OO
regulates 10 10.20 OO
negatively regulates 6 6.12 OO
starts 6 6.12 OO
ends during 4 4.08 OO
positively regulates 4 4.08 OO
ends 3 3.06 OO
happens during 3 3.06 OO
obsolete preceded by 3 3.06 OO
ends with 2 2.04 OO
immediately precedes 2 2.04 OO
starts during 2 2.04 OO
starts with 2 2.04 OO
causally downstream of 1 1.02 OO
causally upstream of or within 1 1.02 OO
simultaneous with 1 1.02 OO
part of 78 79.59 OT
has part 48 48.98 OT
in taxon 2 2.04 OT
only in taxon 2 2.04 OT
depends on 1 1.02 OT
kable(top10,row.names = FALSE)
x freq coverage CAT
part of 78 79.59 OT
has part 48 48.98 OT
inheres in 29 29.59 CC
has participant 27 27.55 OC-CO
has role 26 26.53 CC
realizes 24 24.49 OC-CO
located in 21 21.43 CC
has quality 20 20.41 CC
bearer of 19 19.39 CC
develops from 19 19.39 CC

Coverage: Temporal Annotation

coverage_ann<-compute_coverage_ann(df[df$TEMP_ANN!="",c("O","TEMP_ANN","CAT")],ct_o)
coverage_ann$ann_id<-paste("A",1:nrow(coverage_ann),sep="")
plotRanks(coverage_ann,"ann_id","coverage",xlab="Annotation",ylab="Coverage")
ggsave("coverage_ann.jpg",width = 3,height = 2.5,units="in")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
top10<-head(coverage_ann[order(-coverage_ann$coverage),],10)
top10anncov<-top10$x
all<-coverage_ann[order(coverage_ann$CAT,-coverage_ann$coverage),]

# Summary stats over ALL temporal features
summary(all$coverage)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.020   2.040   4.080   9.168  14.290  85.710
sd(all$coverage)
## [1] 12.71982
# Summary stats BY DOMAIN RANGE over ALL temporal features
ddply(all,~CAT,summarise,mean=mean(coverage),median=median(coverage),sd=sd(coverage), min=min(coverage),max=max(coverage))
##     CAT      mean median        sd  min   max
## 1    CC  8.832187   4.08  9.949514 1.02 34.69
## 2 OC-CO  8.216316   4.08  8.089142 1.02 27.55
## 3    OO  6.777857   3.57  6.387612 1.02 21.43
## 4    OT 29.930000   3.06 48.317664 1.02 85.71
kable(all,row.names = FALSE)
x freq coverage CAT ann_id
Dom:IC-Ran:ICTime:SameRig:Yes-Nec:No~TI:AHFAT 34 34.69 CC A32
Dom:IC-Ran:SDCTime:SameRig:Yes-Nec:No 34 34.69 CC A38
Dom:SDC-Ran:ICTime:SameRig:Yes-Nec:No~TI:AHFAT 29 29.59 CC A63
Dom:C-Ran:CTime:SameRig:Yes-Nec:No~TI:AHFAT 19 19.39 CC A2
Dom:IC-Ran:ICTime:PastIdentity:Same-Nec:No~Dom:Birth-Nec:No 19 19.39 CC A26
Dom:IC-Ran:SDCTime:SameRig:Yes-Nec:No~TI:AHFAT 19 19.39 CC A39
Dom:IC-Ran:ICTime:PastDom:Birth~Ran:Death 17 17.35 CC A23
Dom:SDC-Ran:GDCTime:SameRig:Yes-Nec:No 15 15.31 CC A61
Dom:IC-Ran:ICTime:SameRig:Yes-Nec:No 14 14.29 CC A31
Dom:SDC-Ran:C~Time:Same 10 10.20 CC A60
Dom:SDC-Ran:ICTime:SameRig:Yes-Nec:No 9 9.18 CC A62
Dom:GDC-Ran:SDCTime:SameRig:Yes-Nec:No 6 6.12 CC A14
Dom:IC-Ran:ICTime:FutureRan:Birth 6 6.12 CC A20
Dom:IC-Ran:IC~Time:Same 5 5.10 CC A29
Dom:IC-Ran:ICTime:SameRig:Yes~TI:AHFAT 5 5.10 CC A33
Dom:IC-Ran:IC~Time:Past 4 4.08 CC A21
Dom:IC-Ran:ICTime:PastDom:Birth 4 4.08 CC A22
Dom:IC-Ran:ICTime:SameRig:Yes 4 4.08 CC A30
Dom:IC-Ran:ICTime:FutureIdentity:Same-Nec:No~Dom:Birth-Nec:No 3 3.06 CC A18
Dom:IC-Ran:ICTime:FutureIdentity:Same-Nec:No~Ran:Birth-Nec:No 3 3.06 CC A19
Dom:IC-Ran:CTime:SameRig:Yes-Nec:No~TI:AHFAT 2 2.04 CC A17
Dom:IC-Ran:ICTime:PastDom:Changed 2 2.04 CC A24
Dom:IC-Ran:ICTime:PastDom:ChangedRan:ChangedDom:Birth-Nec:No~Ran:Death-Nec:No 2 2.04 CC A25
Dom:IC-Ran:ICTime:PastIdentity:Same~Dom:Changed 2 2.04 CC A27
Dom:IC-Ran:ICTime:PastImmediateIdentity:Same~Dom:Changed 2 2.04 CC A28
Dom:SDC-Ran:SDCTime:SameRig:Yes-Nec:No 2 2.04 CC A65
Dom:C-Ran:C~Time:Same 1 1.02 CC A1
Dom:C-Ran:ICTime:SameRig:Yes-Nec:No~TI:AHFAT 1 1.02 CC A3
Dom:GDC-Ran:GDCTime:FutureRan:Birth 1 1.02 CC A12
Dom:GDC-Ran:GDCTime:PastDom:Birth 1 1.02 CC A13
Dom:IC-Ran:CTime:PastDom:Birth 1 1.02 CC A15
Dom:IC-Ran:C~Time:Same 1 1.02 CC A16
Dom:P-Ran:CTime:SameRig:Yes-Nec:No 27 27.55 OC-CO A57
Dom:P-Ran:SDCTime:SameRig:Yes-Nec:No 24 24.49 OC-CO A59
Dom:SDC-Ran:PTime:SameRig:Yes-Nec:No 17 17.35 OC-CO A64
Dom:C-Ran:PTime:SameRig:Yes-Nec:No 16 16.33 OC-CO A11
Dom:O-Ran:ICTime:SameRig:Yes 14 14.29 OC-CO A40
Dom:IC-Ran:P~Time:Future 10 10.20 OC-CO A35
Dom:P-Ran:CTime:SameRan:Birth 9 9.18 OC-CO A54
Dom:C-Ran:P~Time:Same 6 6.12 OC-CO A9
Dom:P-Ran:CTime:SameRan:Changed 5 5.10 OC-CO A55
Dom:C-Ran:OTime:Same/PastDom:Birth 4 4.08 OC-CO A5
Dom:C-Ran:OTime:SameDom:Birth 4 4.08 OC-CO A6
Dom:C-Ran:OTime:Same/FutureDom:Death 3 3.06 OC-CO A4
Dom:C-Ran:OTime:SameRig:YesDom:BirthDom:Death 3 3.06 OC-CO A7
Dom:C-Ran:OTime:SameRig:Yes~Dom:Death 3 3.06 OC-CO A8
Dom:IC-Ran:P~Time:Same 3 3.06 OC-CO A36
Dom:C-Ran:PTime:SameDom:Birth 2 2.04 OC-CO A10
Dom:IC-Ran:OTime:SameRig:Yes-Nec:No 1 1.02 OC-CO A34
Dom:IC-Ran:PTime:SameRig:Yes 1 1.02 OC-CO A37
Dom:P-Ran:CTime:SameRig:Yes 1 1.02 OC-CO A56
Dom:O-Ran:O~Time:BeforeInverse 21 21.43 OO A43
Dom:O-Ran:O~Time:Before 15 15.31 OO A41
Dom:O-Ran:O~Time:MeetsInverse 15 15.31 OO A51
Dom:P-Ran:P~Time:Before/During 10 10.20 OO A58
Dom:O-Ran:O~Time:Before/During 7 7.14 OO A42
Dom:O-Ran:O~Time:Starts 6 6.12 OO A52
Dom:O-Ran:O~Time:During/Overlaps 4 4.08 OO A45
Dom:O-Ran:O~Time:During 3 3.06 OO A44
Dom:O-Ran:O~Time:Finishes 3 3.06 OO A47
Dom:O-Ran:O~Time:During/OverlapsInverse 2 2.04 OO A46
Dom:O-Ran:O~Time:FinishesInverse 2 2.04 OO A48
Dom:O-Ran:O~Time:Meets 2 2.04 OO A50
Dom:O-Ran:O~Time:StartsInverse 2 2.04 OO A53
Dom:O-Ran:O~Time:IsEqualTo 1 1.02 OO A49
Dom:X-Ran:XTime:SameRig:Yes-Nec:No~TI:AHFAT 84 85.71 OT A68
Dom:X-Ran:IC~Time:Same 3 3.06 OT A66
Dom:X-Ran:XTime:SameRig:Yes-Nec:No 1 1.02 OT A67
kable(top10,row.names = FALSE)
x freq coverage CAT ann_id
Dom:X-Ran:XTime:SameRig:Yes-Nec:No~TI:AHFAT 84 85.71 OT A68
Dom:IC-Ran:ICTime:SameRig:Yes-Nec:No~TI:AHFAT 34 34.69 CC A32
Dom:IC-Ran:SDCTime:SameRig:Yes-Nec:No 34 34.69 CC A38
Dom:SDC-Ran:ICTime:SameRig:Yes-Nec:No~TI:AHFAT 29 29.59 CC A63
Dom:P-Ran:CTime:SameRig:Yes-Nec:No 27 27.55 OC-CO A57
Dom:P-Ran:SDCTime:SameRig:Yes-Nec:No 24 24.49 OC-CO A59
Dom:O-Ran:O~Time:BeforeInverse 21 21.43 OO A43
Dom:C-Ran:CTime:SameRig:Yes-Nec:No~TI:AHFAT 19 19.39 CC A2
Dom:IC-Ran:ICTime:PastIdentity:Same-Nec:No~Dom:Birth-Nec:No 19 19.39 CC A26
Dom:IC-Ran:SDCTime:SameRig:Yes-Nec:No~TI:AHFAT 19 19.39 CC A39
coverage_ann_xt<-coverage_ann
coverage_ann_xt$x<-NULL
print(xtable(all[,c("ann_id","freq","coverage","CAT")],digits=c(0,0,2,2,2)),include.rownames=FALSE,file="coverage_ann.tex")
print(xtable(top10[,c("ann_id","freq","coverage","CAT")],digits=c(0,0,2,2,2)),include.rownames=FALSE,file="coverage_ann_top10.tex")

Coverage: Temporal Attributes

coverage_feat<-compute_coverage_feat(df[c("O","TEMP_ANN_ALL","CAT")],ct_o)
## Warning in "\"\"": attributes are not identical across measure variables;
## they will be dropped
plotRanks(coverage_feat,"x","coverage",xlab="Temporal Feature",ylab="Coverage",ncol = 1)
ggsave("coverage_feat.jpg",width = 3,height = 4,units="in")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
top10<-head(coverage_feat[order(-coverage_feat$coverage),],10)
top10attcov<-top10$x
all<-coverage_feat[order(coverage_feat$CAT,-coverage_feat$coverage),]

# Summary stats over ALL temporal features
summary(all$coverage)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    1.02    5.10   15.31   23.45   36.73   85.71
sd(all$coverage)
## [1] 23.22989
# Summary stats BY DOMAIN RANGE over ALL temporal features
ddply(all,~CAT,summarise,mean=mean(coverage),median=median(coverage),sd=sd(coverage), min=min(coverage),max=max(coverage))
##     CAT     mean median       sd  min   max
## 1    CC 25.31258  19.39 21.22622 1.02 69.39
## 2 OC-CO 18.90095  13.27 14.03151 3.06 46.94
## 3    OO 11.54375   5.10 13.33598 1.02 41.84
## 4    OT 69.18000  85.71 36.96220 3.06 85.71
kable(all,row.names = FALSE)
x freq coverage CAT
CC-Dom:C-Ran:C 68 69.39 CC
CC-Dom:IC-Ran:C 62 63.27 CC
CC-Time:Same 60 61.22 CC
CC-Rig:Yes-Nec:No 59 60.20 CC
CC-TI:AHFAT 53 54.08 CC
CC-Dom:C-Ran:IC 46 46.94 CC
CC-Dom:IC-Ran:IC 46 46.94 CC
CC-Dom:IC-Ran:SDC 38 38.78 CC
CC-Time:Diff 37 37.76 CC
CC-Time:Past 36 36.73 CC
CC-Dom:SDC-Ran:C 34 34.69 CC
CC-Dom:SDC-Ran:IC 30 30.61 CC
CC-Dom:Birth 22 22.45 CC
CC-Dom:Changed 22 22.45 CC
CC-Ran:Changed 22 22.45 CC
CC-Dom:Birth-Nec:No 19 19.39 CC
CC-Dom:Changed-Nec:No 19 19.39 CC
CC-Identity:Same-Nec:No 19 19.39 CC
CC-Ran:Death 17 17.35 CC
CC-Dom:SDC-Ran:GDC 15 15.31 CC
CC-Time:Future 9 9.18 CC
CC-Ran:Birth 7 7.14 CC
CC-Dom:GDC-Ran:SDC 6 6.12 CC
CC-Rig:Yes 6 6.12 CC
CC-Ran:Changed-Nec:No 5 5.10 CC
CC-Ran:Birth-Nec:No 3 3.06 CC
CC-Dom:SDC-Ran:SDC 2 2.04 CC
CC-Identity:Same 2 2.04 CC
CC-Ran:Death-Nec:No 2 2.04 CC
CC-Time:PastImmediate 2 2.04 CC
CC-Dom:GDC-Ran:GDC 1 1.02 CC
OC-CO-Time:Same 46 46.94 OC-CO
OC-CO-Dom:O-Ran:C 42 42.86 OC-CO
OC-CO-Dom:P-Ran:C 37 37.76 OC-CO
OC-CO-Rig:Yes-Nec:No 36 36.73 OC-CO
OC-CO-Dom:C-Ran:O 34 34.69 OC-CO
OC-CO-Dom:C-Ran:P 33 33.67 OC-CO
OC-CO-Dom:P-Ran:SDC 24 24.49 OC-CO
OC-CO-Rig:Yes 18 18.37 OC-CO
OC-CO-Dom:SDC-Ran:P 17 17.35 OC-CO
OC-CO-Dom:O-Ran:IC 14 14.29 OC-CO
OC-CO-Time:Diff 13 13.27 OC-CO
OC-CO-Dom:IC-Ran:O 11 11.22 OC-CO
OC-CO-Dom:IC-Ran:P 11 11.22 OC-CO
OC-CO-Time:Future 10 10.20 OC-CO
OC-CO-Ran:Birth 9 9.18 OC-CO
OC-CO-Ran:Changed 9 9.18 OC-CO
OC-CO-Dom:Birth 7 7.14 OC-CO
OC-CO-Dom:Changed 7 7.14 OC-CO
OC-CO-Dom:Death 4 4.08 OC-CO
OC-CO-Time:Same/Past 4 4.08 OC-CO
OC-CO-Time:Same/Future 3 3.06 OC-CO
OO-Dom:O-Ran:O 41 41.84 OO
OO-Time:All 41 41.84 OO
OO-Time:BeforeInverse 21 21.43 OO
OO-Time:Before 15 15.31 OO
OO-Time:MeetsInverse 15 15.31 OO
OO-Time:Before/During 13 13.27 OO
OO-Dom:P-Ran:P 10 10.20 OO
OO-Time:Starts 6 6.12 OO
OO-Time:During/Overlaps 4 4.08 OO
OO-Time:During 3 3.06 OO
OO-Time:Finishes 3 3.06 OO
OO-Time:During/OverlapsInverse 2 2.04 OO
OO-Time:FinishesInverse 2 2.04 OO
OO-Time:Meets 2 2.04 OO
OO-Time:StartsInverse 2 2.04 OO
OO-Time:IsEqualTo 1 1.02 OO
OT-Dom:X-Ran:X 84 85.71 OT
OT-Rig:Yes-Nec:No 84 85.71 OT
OT-TI:AHFAT 84 85.71 OT
OT-Time:Same 84 85.71 OT
OT-Dom:X-Ran:IC 3 3.06 OT
kable(top10,row.names = FALSE)
x freq coverage CAT
OT-Dom:X-Ran:X 84 85.71 OT
OT-Rig:Yes-Nec:No 84 85.71 OT
OT-TI:AHFAT 84 85.71 OT
OT-Time:Same 84 85.71 OT
CC-Dom:C-Ran:C 68 69.39 CC
CC-Dom:IC-Ran:C 62 63.27 CC
CC-Time:Same 60 61.22 CC
CC-Rig:Yes-Nec:No 59 60.20 CC
CC-TI:AHFAT 53 54.08 CC
CC-Dom:C-Ran:IC 46 46.94 CC
print(xtable(all,digits=c(0,0,2,2,2)),include.rownames=FALSE,file="coverage_att.tex")
print(xtable(top10,digits=c(0,0,2,2,2)),include.rownames=FALSE,file="coverage_att_top10.tex")

Impact: Relations

impact_rel<-compute_impact_rel(df[c("O","CAT","ONT_TOTAL_AX","RO_REL")])
plotRanks(impact_rel,"RO_REL","impact",xlab="Relation",ylab="Impact (Basic)",ncol=1)
ggsave("impact_rel.jpg",width = 3,height = 4,units="in")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
top10<-head(impact_rel[order(-impact_rel$impact),],10)
top10relim<-top10$RO_REL
all<-impact_rel[order(impact_rel$CAT,-impact_rel$impact),]

# Summary stats over ALL temporal features
summary(all$impact)
##      Min.   1st Qu.    Median      Mean   3rd Qu.      Max. 
##  0.000000  0.002347  0.014796  0.225384  0.115408 11.518980
sd(all$impact)
## [1] 1.027628
# Summary stats BY DOMAIN RANGE over ALL temporal features
ddply(all,~CAT,summarise,mean=mean(impact),median=median(impact),sd=sd(impact), min=min(impact),max=max(impact))
##     CAT      mean      median        sd          min       max
## 1    CC 0.1060933 0.007959184 0.3140803 0.0000000000  2.066224
## 2 OC-CO 0.1267007 0.027295918 0.1550766 0.0001020408  0.560102
## 3    OO 0.2440986 0.065459184 0.5318933 0.0000000000  2.239592
## 4    OT 2.9697755 0.276224490 4.9457643 0.0047959184 11.518980
kable(all,row.names = FALSE)
RO_REL impact CAT
inheres in 2.0662245 CC
has quality 1.5213265 CC
bearer of 1.3021429 CC
develops from 0.9943878 CC
has modifier 0.6513265 CC
derives from 0.5711224 CC
has role 0.5301020 CC
overlaps 0.3409184 CC
has component 0.2064286 CC
attached to 0.1939796 CC
concretizes 0.1577551 CC
has function 0.1474490 CC
towards 0.1320408 CC
has member 0.1308163 CC
has plasma membrane part 0.1286735 CC
child nucleus of 0.1255102 CC
inheres in part of 0.1227551 CC
located in 0.1154082 CC
composed primarily of 0.0916327 CC
innervated_by 0.0760204 CC
directly develops from 0.0478571 CC
adjacent to 0.0475510 CC
continuous with 0.0446939 CC
has postsynaptic terminal in 0.0381633 CC
gene product of 0.0372449 CC
has presynaptic terminal in 0.0353061 CC
child nucleus of in male 0.0347959 CC
has disposition 0.0278571 CC
has synaptic terminal in 0.0259184 CC
child nucleus of in hermaphrodite 0.0255102 CC
interacts with 0.0225510 CC
is concretized as 0.0220408 CC
surrounds 0.0218367 CC
role of 0.0206122 CC
has soma location 0.0201020 CC
connected to 0.0200000 CC
fasciculates with 0.0181633 CC
has potential to develop into 0.0172449 CC
expresses 0.0169388 CC
contributes to morphology of 0.0166327 CC
has developmental contribution from 0.0161224 CC
produces 0.0159184 CC
connects 0.0147959 CC
synapsed by 0.0116327 CC
quality of 0.0100000 CC
member of 0.0098980 CC
location of 0.0095918 CC
synapsed to 0.0095918 CC
has host 0.0080612 CC
surrounded by 0.0078571 CC
innervates 0.0074490 CC
has skeleton 0.0071429 CC
skeleton of 0.0069388 CC
immediate transformation of 0.0068367 CC
spatially disjoint from 0.0058163 CC
in homology relationship with 0.0051020 CC
develops into 0.0050000 CC
function of 0.0048980 CC
has muscle insertion 0.0047959 CC
has vector 0.0045918 CC
transcribed to 0.0045918 CC
branching part of 0.0044898 CC
has muscle origin 0.0044898 CC
has potential to developmentally contribute to 0.0036735 CC
produced by 0.0036735 CC
luminal space of 0.0034694 CC
synapsed_via_type_Ib_bouton_to 0.0033673 CC
bounding layer of 0.0031633 CC
develops in 0.0028571 CC
contains 0.0026531 CC
supplies 0.0026531 CC
tributary of 0.0020408 CC
determined by 0.0019388 CC
molecularly interacts with 0.0017347 CC
conduit for 0.0016327 CC
drains 0.0014286 CC
has synaptic terminal of 0.0014286 CC
developmentally induced by 0.0013265 CC
transformation of 0.0011224 CC
has fused element 0.0010204 CC
has muscle antagonist 0.0009184 CC
determined by part of 0.0006122 CC
developmentally replaces 0.0006122 CC
electrically_synapsed_to 0.0006122 CC
transcribed from 0.0006122 CC
has habitat 0.0005102 CC
distributary of 0.0002041 CC
has 2D boundary 0.0002041 CC
synapsed_via_type_II_bouton_to 0.0002041 CC
synapsed_via_type_Is_bouton_to 0.0002041 CC
attached to part of 0.0001020 CC
confers advantage in 0.0001020 CC
develops from part of 0.0001020 CC
partially overlaps 0.0001020 CC
serially homologous to 0.0001020 CC
synapsed_via_type_III_bouton_to 0.0001020 CC
contained in 0.0000000 CC
lumen of 0.0000000 CC
has participant 0.5601020 OC-CO
realized in 0.3850000 OC-CO
participates in 0.2664286 OC-CO
existence ends during 0.2630612 OC-CO
existence starts during or after 0.2605102 OC-CO
existence starts during 0.2604082 OC-CO
existence ends during or before 0.2587755 OC-CO
realizes 0.2330612 OC-CO
occurs in 0.2279592 OC-CO
capable of 0.1451020 OC-CO
has output 0.0626531 OC-CO
has input 0.0291837 OC-CO
output of 0.0254082 OC-CO
existence starts and ends during 0.0218367 OC-CO
formed as result of 0.0171429 OC-CO
has active participant 0.0054082 OC-CO
capable of part of 0.0051020 OC-CO
actively participates in 0.0042857 OC-CO
results in formation of 0.0036735 OC-CO
has intermediate 0.0023469 OC-CO
existence ends with 0.0012245 OC-CO
existence starts with 0.0012245 OC-CO
contains process 0.0008163 OC-CO
functionally related to 0.0001020 OC-CO
immediately preceded by 2.2395918 OO
preceded by 0.5603061 OO
ends during 0.4964286 OO
starts during 0.4964286 OO
regulates 0.1565306 OO
happens during 0.1162245 OO
negatively regulates 0.0829592 OO
precedes 0.0717347 OO
positively regulates 0.0710204 OO
obsolete preceded by 0.0598980 OO
immediately precedes 0.0233673 OO
causally downstream of 0.0115306 OO
starts 0.0068367 OO
ends 0.0003061 OO
ends with 0.0002041 OO
simultaneous with 0.0002041 OO
starts with 0.0002041 OO
causally upstream of or within 0.0000000 OO
part of 11.5189796 OT
has part 3.0292857 OT
in taxon 0.2762245 OT
only in taxon 0.0195918 OT
depends on 0.0047959 OT
kable(top10,row.names = FALSE)
RO_REL impact CAT
part of 11.5189796 OT
has part 3.0292857 OT
immediately preceded by 2.2395918 OO
inheres in 2.0662245 CC
has quality 1.5213265 CC
bearer of 1.3021429 CC
develops from 0.9943878 CC
has modifier 0.6513265 CC
derives from 0.5711224 CC
preceded by 0.5603061 OO
print(xtable(all,digits=c(3)),include.rownames=FALSE,file="impact_rel.tex")
print(xtable(top10,digits=c(2)),include.rownames=FALSE,file="impact_rel_top10.tex")

Impact: Annotations

impact_anno<-compute_impact_anno(df[c("O","CAT","ONT_TOTAL_AX","TEMP_ANN")])
impact_anno<-merge(impact_anno,unique(coverage_ann[,c("x","ann_id")]),by.x = "TEMP_ANN",by.y = "x")
plotRanks(impact_anno,"ann_id","impact",xlab="Annotation",ylab="Impact (Basic)")
ggsave("impact_anno.jpg",width = 3,height = 2.5,units="in")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
top10<-head(impact_anno[order(-impact_anno$impact),],10)
top10annim<-top10$TEMP_ANN
all<-impact_anno[order(impact_anno$CAT,-impact_anno$impact),]

# Summary stats over ALL temporal features
summary(all$impact)
##      Min.   1st Qu.    Median      Mean   3rd Qu.      Max. 
##  0.000102  0.005077  0.036480  0.480609  0.277041 14.548673
sd(all$impact)
## [1] 1.801924
# Summary stats BY DOMAIN RANGE over ALL temporal features
ddply(all,~CAT,summarise,mean=mean(impact),median=median(impact),sd=sd(impact), min=min(impact),max=max(impact))
##     CAT      mean     median        sd          min        max
## 1    CC 0.3249235 0.02397959 0.6010122 0.0002040816  2.2267347
## 2 OC-CO 0.1600430 0.14510204 0.1601661 0.0001020408  0.5654082
## 3    OO 0.3138484 0.09397959 0.5946116 0.0002040816  2.2395918
## 4    OT 4.9497279 0.29571429 8.3142032 0.0047959184 14.5486735
kable(all,row.names = FALSE)
TEMP_ANN impact CAT ann_id
Dom:IC-Ran:SDCTime:SameRig:Yes-Nec:No 2.2267347 CC A38
Dom:SDC-Ran:ICTime:SameRig:Yes-Nec:No~TI:AHFAT 2.1889796 CC A63
Dom:IC-Ran:SDCTime:SameRig:Yes-Nec:No~TI:AHFAT 1.3021429 CC A39
Dom:IC-Ran:ICTime:PastIdentity:Same-Nec:No~Dom:Birth-Nec:No 1.0425510 CC A26
Dom:IC-Ran:ICTime:SameRig:Yes-Nec:No~TI:AHFAT 0.8132653 CC A32
Dom:IC-Ran:ICTime:PastDom:Birth~Ran:Death 0.7569388 CC A23
Dom:SDC-Ran:SDCTime:SameRig:Yes-Nec:No 0.6513265 CC A65
Dom:C-Ran:CTime:SameRig:Yes-Nec:No~TI:AHFAT 0.4816327 CC A2
Dom:IC-Ran:ICTime:SameRig:Yes-Nec:No 0.3142857 CC A31
Dom:SDC-Ran:GDCTime:SameRig:Yes-Nec:No 0.1577551 CC A61
Dom:SDC-Ran:C~Time:Same 0.1320408 CC A60
Dom:IC-Ran:ICTime:SameRig:Yes 0.0780612 CC A30
Dom:IC-Ran:CTime:PastDom:Birth 0.0372449 CC A15
Dom:SDC-Ran:ICTime:SameRig:Yes-Nec:No 0.0357143 CC A62
Dom:IC-Ran:IC~Time:Same 0.0260204 CC A29
Dom:IC-Ran:CTime:SameRig:Yes-Nec:No~TI:AHFAT 0.0259184 CC A17
Dom:GDC-Ran:SDCTime:SameRig:Yes-Nec:No 0.0220408 CC A14
Dom:IC-Ran:ICTime:FutureIdentity:Same-Nec:No~Dom:Birth-Nec:No 0.0172449 CC A18
Dom:IC-Ran:C~Time:Same 0.0169388 CC A16
Dom:IC-Ran:IC~Time:Past 0.0161224 CC A21
Dom:IC-Ran:ICTime:FutureRan:Birth 0.0159184 CC A20
Dom:IC-Ran:ICTime:SameRig:Yes~TI:AHFAT 0.0132653 CC A33
Dom:IC-Ran:ICTime:PastImmediateIdentity:Same~Dom:Changed 0.0068367 CC A28
Dom:IC-Ran:ICTime:FutureIdentity:Same-Nec:No~Ran:Birth-Nec:No 0.0050000 CC A19
Dom:GDC-Ran:GDCTime:FutureRan:Birth 0.0045918 CC A12
Dom:IC-Ran:ICTime:PastDom:Birth 0.0036735 CC A22
Dom:C-Ran:ICTime:SameRig:Yes-Nec:No~TI:AHFAT 0.0014286 CC A3
Dom:IC-Ran:ICTime:PastDom:Changed 0.0013265 CC A24
Dom:IC-Ran:ICTime:PastIdentity:Same~Dom:Changed 0.0011224 CC A27
Dom:GDC-Ran:GDCTime:PastDom:Birth 0.0006122 CC A13
Dom:IC-Ran:ICTime:PastDom:ChangedRan:ChangedDom:Birth-Nec:No~Ran:Death-Nec:No 0.0006122 CC A25
Dom:C-Ran:C~Time:Same 0.0002041 CC A1
Dom:P-Ran:CTime:SameRig:Yes-Nec:No 0.5654082 OC-CO A57
Dom:SDC-Ran:PTime:SameRig:Yes-Nec:No 0.3850000 OC-CO A64
Dom:C-Ran:PTime:SameRig:Yes-Nec:No 0.2708163 OC-CO A11
Dom:C-Ran:OTime:SameRig:Yes~Dom:Death 0.2642857 OC-CO A8
Dom:C-Ran:OTime:SameDom:Birth 0.2616327 OC-CO A6
Dom:C-Ran:OTime:Same/PastDom:Birth 0.2605102 OC-CO A5
Dom:C-Ran:OTime:Same/FutureDom:Death 0.2587755 OC-CO A4
Dom:P-Ran:SDCTime:SameRig:Yes-Nec:No 0.2330612 OC-CO A59
Dom:O-Ran:ICTime:SameRig:Yes 0.2279592 OC-CO A40
Dom:IC-Ran:P~Time:Future 0.1451020 OC-CO A35
Dom:P-Ran:CTime:SameRan:Birth 0.0663265 OC-CO A54
Dom:P-Ran:CTime:SameRan:Changed 0.0291837 OC-CO A55
Dom:C-Ran:P~Time:Same 0.0254082 OC-CO A9
Dom:C-Ran:OTime:SameRig:YesDom:BirthDom:Death 0.0218367 OC-CO A7
Dom:C-Ran:PTime:SameDom:Birth 0.0171429 OC-CO A10
Dom:IC-Ran:P~Time:Same 0.0051020 OC-CO A36
Dom:P-Ran:CTime:SameRig:Yes 0.0023469 OC-CO A56
Dom:IC-Ran:PTime:SameRig:Yes 0.0008163 OC-CO A37
Dom:IC-Ran:OTime:SameRig:Yes-Nec:No 0.0001020 OC-CO A34
Dom:O-Ran:O~Time:MeetsInverse 2.2395918 OO A51
Dom:O-Ran:O~Time:BeforeInverse 0.6318367 OO A43
Dom:O-Ran:O~Time:During/Overlaps 0.4964286 OO A45
Dom:O-Ran:O~Time:During/OverlapsInverse 0.4964286 OO A46
Dom:P-Ran:P~Time:Before/During 0.1565306 OO A58
Dom:O-Ran:O~Time:Before/During 0.1539796 OO A42
Dom:O-Ran:O~Time:During 0.1162245 OO A44
Dom:O-Ran:O~Time:Before 0.0717347 OO A41
Dom:O-Ran:O~Time:Meets 0.0233673 OO A50
Dom:O-Ran:O~Time:Starts 0.0068367 OO A52
Dom:O-Ran:O~Time:Finishes 0.0003061 OO A47
Dom:O-Ran:O~Time:FinishesInverse 0.0002041 OO A48
Dom:O-Ran:O~Time:IsEqualTo 0.0002041 OO A49
Dom:O-Ran:O~Time:StartsInverse 0.0002041 OO A53
Dom:X-Ran:XTime:SameRig:Yes-Nec:No~TI:AHFAT 14.5486735 OT A68
Dom:X-Ran:IC~Time:Same 0.2957143 OT A66
Dom:X-Ran:XTime:SameRig:Yes-Nec:No 0.0047959 OT A67
kable(top10,row.names = FALSE)
TEMP_ANN impact CAT ann_id
Dom:X-Ran:XTime:SameRig:Yes-Nec:No~TI:AHFAT 14.5486735 OT A68
Dom:O-Ran:O~Time:MeetsInverse 2.2395918 OO A51
Dom:IC-Ran:SDCTime:SameRig:Yes-Nec:No 2.2267347 CC A38
Dom:SDC-Ran:ICTime:SameRig:Yes-Nec:No~TI:AHFAT 2.1889796 CC A63
Dom:IC-Ran:SDCTime:SameRig:Yes-Nec:No~TI:AHFAT 1.3021429 CC A39
Dom:IC-Ran:ICTime:PastIdentity:Same-Nec:No~Dom:Birth-Nec:No 1.0425510 CC A26
Dom:IC-Ran:ICTime:SameRig:Yes-Nec:No~TI:AHFAT 0.8132653 CC A32
Dom:IC-Ran:ICTime:PastDom:Birth~Ran:Death 0.7569388 CC A23
Dom:SDC-Ran:SDCTime:SameRig:Yes-Nec:No 0.6513265 CC A65
Dom:O-Ran:O~Time:BeforeInverse 0.6318367 OO A43
impact_anno_x<-merge(impact_anno,unique(coverage_ann[,c("x","ann_id")]),by.x = "TEMP_ANN",by.y = "x")
print(xtable(all[,c("ann_id","impact","CAT")],digits=c(3)),include.rownames=FALSE,file="impact_ann.tex")
print(xtable(top10[,c("ann_id","impact","CAT")],digits=c(2)),include.rownames=FALSE,file="impact_ann_top10.tex")

Impact: Attributes

impact_feat<-compute_impact_feat(df[c("O","CAT","ONT_TOTAL_AX","TEMP_ANN_ALL")])
## Warning in "\"\"": attributes are not identical across measure variables;
## they will be dropped
plotRanks(impact_feat,"TEMP_FEAT","impact",xlab="Temporal Feature",ylab="Impact (Basic)",ncol = 1)
ggsave("impact_feat.jpg",width = 3,height = 4,units="in")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
top10<-head(impact_feat[order(-impact_feat$impact),],10)
top10attim<-top10$TEMP_FEAT
all<-impact_feat[order(impact_feat$CAT,-impact_feat$impact),]

# Summary stats over ALL temporal features
summary(all$impact)
##      Min.   1st Qu.    Median      Mean   3rd Qu.      Max. 
##  0.000204  0.095510  0.560918  2.068777  1.916020 14.849286
sd(all$impact)
## [1] 3.692601
# Summary stats BY DOMAIN RANGE over ALL temporal features
ddply(all,~CAT,summarise,mean=mean(impact),median=median(impact),sd=sd(impact), min=min(impact),max=max(impact))
##     CAT       mean     median        sd          min       max
## 1    CC  2.0942363  0.8082653 2.8314447 0.0006122449 10.397653
## 2 OC-CO  0.6648299  0.5172449 0.6285685 0.0663265306  2.375918
## 3    OO  0.8335842  0.1363776 1.4952231 0.0002040816  4.393469
## 4    OT 11.7601224 14.5534694 6.4100931 0.2957142857 14.849286
kable(all,row.names = FALSE)
TEMP_FEAT impact CAT
CC-Dom:C-Ran:C 10.3976531 CC
CC-Time:Same 8.4880612 CC
CC-Rig:Yes-Nec:No 8.2214286 CC
CC-Dom:IC-Ran:C 6.7211224 CC
CC-TI:AHFAT 4.8268367 CC
CC-Dom:IC-Ran:SDC 3.5289796 CC
CC-Dom:SDC-Ran:C 3.1658163 CC
CC-Dom:C-Ran:IC 3.1136735 CC
CC-Dom:IC-Ran:IC 3.1123469 CC
CC-Dom:SDC-Ran:IC 2.2246939 CC
CC-Time:Diff 1.9096939 CC
CC-Time:Past 1.8668367 CC
CC-Identity:Same-Nec:No 1.0647959 CC
CC-Dom:Birth-Nec:No 1.0603061 CC
CC-Dom:Changed-Nec:No 1.0603061 CC
CC-Dom:Changed 0.8082653 CC
CC-Dom:Birth 0.7984694 CC
CC-Ran:Changed 0.7780612 CC
CC-Ran:Death 0.7569388 CC
CC-Dom:SDC-Ran:SDC 0.6513265 CC
CC-Dom:SDC-Ran:GDC 0.1577551 CC
CC-Rig:Yes 0.0913265 CC
CC-Time:Future 0.0427551 CC
CC-Dom:GDC-Ran:SDC 0.0220408 CC
CC-Ran:Birth 0.0205102 CC
CC-Identity:Same 0.0079592 CC
CC-Time:PastImmediate 0.0068367 CC
CC-Ran:Changed-Nec:No 0.0056122 CC
CC-Dom:GDC-Ran:GDC 0.0053061 CC
CC-Ran:Birth-Nec:No 0.0050000 CC
CC-Ran:Death-Nec:No 0.0006122 CC
OC-CO-Time:Same 2.3759184 OC-CO
OC-CO-Dom:C-Ran:O 1.9160204 OC-CO
OC-CO-Rig:Yes-Nec:No 1.4540816 OC-CO
OC-CO-Dom:O-Ran:C 1.1243878 OC-CO
OC-CO-Dom:Changed 1.0838776 OC-CO
OC-CO-Dom:P-Ran:C 0.8963265 OC-CO
OC-CO-Dom:C-Ran:P 0.8491837 OC-CO
OC-CO-Time:Diff 0.6643878 OC-CO
OC-CO-Dom:Birth 0.5609184 OC-CO
OC-CO-Dom:Death 0.5447959 OC-CO
OC-CO-Rig:Yes 0.5172449 OC-CO
OC-CO-Dom:SDC-Ran:P 0.3850000 OC-CO
OC-CO-Time:Same/Past 0.2605102 OC-CO
OC-CO-Time:Same/Future 0.2587755 OC-CO
OC-CO-Dom:P-Ran:SDC 0.2330612 OC-CO
OC-CO-Dom:O-Ran:IC 0.2279592 OC-CO
OC-CO-Dom:IC-Ran:O 0.1510204 OC-CO
OC-CO-Dom:IC-Ran:P 0.1510204 OC-CO
OC-CO-Time:Future 0.1451020 OC-CO
OC-CO-Ran:Changed 0.0955102 OC-CO
OC-CO-Ran:Birth 0.0663265 OC-CO
OO-Dom:O-Ran:O 4.3934694 OO
OO-Time:All 4.3934694 OO
OO-Time:MeetsInverse 2.2395918 OO
OO-Time:BeforeInverse 0.6318367 OO
OO-Time:During/Overlaps 0.4964286 OO
OO-Time:During/OverlapsInverse 0.4964286 OO
OO-Time:Before/During 0.3105102 OO
OO-Dom:P-Ran:P 0.1565306 OO
OO-Time:During 0.1162245 OO
OO-Time:Before 0.0717347 OO
OO-Time:Meets 0.0233673 OO
OO-Time:Starts 0.0068367 OO
OO-Time:Finishes 0.0003061 OO
OO-Time:FinishesInverse 0.0002041 OO
OO-Time:IsEqualTo 0.0002041 OO
OO-Time:StartsInverse 0.0002041 OO
OT-Time:Same 14.8492857 OT
OT-Dom:X-Ran:X 14.5534694 OT
OT-Rig:Yes-Nec:No 14.5534694 OT
OT-TI:AHFAT 14.5486735 OT
OT-Dom:X-Ran:IC 0.2957143 OT
kable(top10,row.names = FALSE)
TEMP_FEAT impact CAT
OT-Time:Same 14.849286 OT
OT-Dom:X-Ran:X 14.553469 OT
OT-Rig:Yes-Nec:No 14.553469 OT
OT-TI:AHFAT 14.548673 OT
CC-Dom:C-Ran:C 10.397653 CC
CC-Time:Same 8.488061 CC
CC-Rig:Yes-Nec:No 8.221429 CC
CC-Dom:IC-Ran:C 6.721122 CC
CC-TI:AHFAT 4.826837 CC
OO-Dom:O-Ran:O 4.393469 OO
#write.csv(impact_feat,file="impact_feat.csv")
#print(xtable(impact_feat[order(impact_feat$CAT,-impact_feat$impact),],digits=c(0,0,2,2)),include.rownames=FALSE)

print(xtable(all[,],digits=c(3)),include.rownames=FALSE,file="impact_att.tex")
print(xtable(top10[,],digits=c(2)),include.rownames=FALSE,file="impact_att_top10.tex")

Correlation: Coverage and Impact

plotCovImRel(coverage_rel,impact_rel,"RO_REL",top10relcov,top10relim)
## Warning in "\"\"": Transformation introduced infinite values in continuous
## x-axis

ggsave("cor_rel_imp_cov.jpg",width = 3,height = 4,units="in")
## Warning in "\"\"": Transformation introduced infinite values in continuous
## x-axis
plotCovImRel(coverage_ann,impact_anno,"TEMP_ANN",top10anncov,top10annim)

ggsave("cor_ann_imp_cov.jpg",width = 3,height = 4,units="in")

plotCovImRel(coverage_feat,impact_feat,"TEMP_FEAT",top10attcov,top10attim)

ggsave("cor_feat_imp_cov.jpg",width = 3,height = 4,units="in")

rel<-merge(coverage_rel[,c("x","coverage","CAT")],impact_rel[,c("RO_REL","impact","CAT")],by.x=c("x","CAT"),by.y=c("RO_REL","CAT"))
ann<-merge(coverage_ann[,c("ann_id","coverage","CAT")],impact_anno[,c("ann_id","impact","CAT")],by=c("ann_id","CAT"))
att<-merge(coverage_feat[,c("x","coverage","CAT")],impact_feat[,c("TEMP_FEAT","impact","CAT")],by.x=c("x","CAT"),by.y=c("TEMP_FEAT","CAT"))

# Actual correlations of impact and coverage for temporal features
cor(rel$coverage,rel$impact,method="pearson")
## [1] 0.8307543
cor(ann$coverage,ann$impact,method="pearson")
## [1] 0.8428761
cor(att$coverage,att$impact,method="pearson")
## [1] 0.9068331
cordf <- function(xx) {
return(data.frame(COR = cor(xx$coverage, xx$impact,method="pearson")))
}

asis_output("Correlations by group")

Correlations by group

ddply(rel, .(CAT), cordf)
##     CAT       COR
## 1    CC 0.7639252
## 2 OC-CO 0.7629174
## 3    OO 0.5516688
## 4    OT 0.9404088
ddply(ann, .(CAT), cordf)
##     CAT       COR
## 1    CC 0.8484335
## 2 OC-CO 0.7248845
## 3    OO 0.5129402
## 4    OT 0.9999935
ddply(att, .(CAT), cordf)
##     CAT       COR
## 1    CC 0.9207927
## 2 OC-CO 0.7612683
## 3    OO 0.9087527
## 4    OT 0.9997981

Requirements analysis pre-processing

## Warning in "\"\"": attributes are not identical across measure variables;
## they will be dropped

Annotation: Importance

ANNO importance impact n_impact coverage n_coverage
A68 1.0000000 14.5486735 1.0000000 85.71 1.0000000
A38 0.2753079 2.2267347 0.1530482 34.69 0.3975676
A63 0.2439005 2.1889796 0.1504531 29.59 0.3373480
A32 0.2267303 0.8132653 0.0558930 34.69 0.3975676
A57 0.1760583 0.5654082 0.0388565 27.55 0.3132601
A51 0.1613325 2.2395918 0.1539319 15.31 0.1687330
A39 0.1532024 1.3021429 0.0894961 19.39 0.2169087
A59 0.1465704 0.2330612 0.0160125 24.49 0.2771284
A26 0.1442809 1.0425510 0.0716530 19.39 0.2169087
A43 0.1422095 0.6318367 0.0434225 21.43 0.2409966
A2 0.1250034 0.4816327 0.0330981 19.39 0.2169087
A23 0.1224211 0.7569388 0.0520214 17.35 0.1928209
A64 0.1096385 0.3850000 0.0264561 17.35 0.1928209
A11 0.0996923 0.2708163 0.0186076 16.33 0.1807770
A61 0.0897847 0.1577551 0.0108363 15.31 0.1687330
A31 0.0891423 0.3142857 0.0215955 14.29 0.1566891
A41 0.0868284 0.0717347 0.0049237 15.31 0.1687330
A40 0.0861755 0.2279592 0.0156618 14.29 0.1566891
A58 0.0595737 0.1565306 0.0107522 10.20 0.1083953
A35 0.0591810 0.1451020 0.0099666 10.20 0.1083953
A60 0.0587321 0.1320408 0.0090688 10.20 0.1083953
A54 0.0504517 0.0663265 0.0045520 9.18 0.0963514
A62 0.0493996 0.0357143 0.0024478 9.18 0.0963514
A42 0.0414202 0.1539796 0.0105768 7.14 0.0722635
A45 0.0351235 0.4964286 0.0341151 4.08 0.0361318
A9 0.0309795 0.0254082 0.0017394 6.12 0.0602196
A14 0.0308638 0.0220408 0.0015080 6.12 0.0602196
A20 0.0306534 0.0159184 0.0010871 6.12 0.0602196
A52 0.0303413 0.0068367 0.0004629 6.12 0.0602196
A65 0.0284030 0.6513265 0.0447621 2.04 0.0120439
A6 0.0270541 0.2616327 0.0179764 4.08 0.0361318
A5 0.0270155 0.2605102 0.0178992 4.08 0.0361318
A55 0.0250873 0.0291837 0.0019989 5.10 0.0481757
A29 0.0249786 0.0260204 0.0017815 5.10 0.0481757
A33 0.0245402 0.0132653 0.0009048 5.10 0.0481757
A46 0.0230795 0.4964286 0.0341151 2.04 0.0120439
A66 0.0222034 0.2957143 0.0203190 3.06 0.0240878
A8 0.0211233 0.2642857 0.0181587 3.06 0.0240878
A4 0.0209339 0.2587755 0.0177800 3.06 0.0240878
A30 0.0207452 0.0780612 0.0053585 4.08 0.0361318
A21 0.0186165 0.0161224 0.0011012 4.08 0.0361318
A22 0.0181886 0.0036735 0.0002455 4.08 0.0361318
A44 0.0160348 0.1162245 0.0079817 3.06 0.0240878
A7 0.0127909 0.0218367 0.0014939 3.06 0.0240878
A18 0.0126331 0.0172449 0.0011783 3.06 0.0240878
A36 0.0122158 0.0051020 0.0003437 3.06 0.0240878
A19 0.0122123 0.0050000 0.0003367 3.06 0.0240878
A47 0.0120509 0.0003061 0.0000140 3.06 0.0240878
A17 0.0069092 0.0259184 0.0017745 2.04 0.0120439
A50 0.0068215 0.0233673 0.0015991 2.04 0.0120439
A10 0.0066076 0.0171429 0.0011713 2.04 0.0120439
A28 0.0062534 0.0068367 0.0004629 2.04 0.0120439
A24 0.0060640 0.0013265 0.0000842 2.04 0.0120439
A27 0.0060570 0.0011224 0.0000701 2.04 0.0120439
A25 0.0060395 0.0006122 0.0000351 2.04 0.0120439
A48 0.0060255 0.0002041 0.0000070 2.04 0.0120439
A53 0.0060255 0.0002041 0.0000070 2.04 0.0120439
A15 0.0012765 0.0372449 0.0025530 1.02 0.0000000
A16 0.0005786 0.0169388 0.0011573 1.02 0.0000000
A67 0.0001613 0.0047959 0.0003226 1.02 0.0000000
A12 0.0001543 0.0045918 0.0003086 1.02 0.0000000
A56 0.0000772 0.0023469 0.0001543 1.02 0.0000000
A3 0.0000456 0.0014286 0.0000912 1.02 0.0000000
A37 0.0000245 0.0008163 0.0000491 1.02 0.0000000
A13 0.0000175 0.0006122 0.0000351 1.02 0.0000000
A1 0.0000035 0.0002041 0.0000070 1.02 0.0000000
A49 0.0000035 0.0002041 0.0000070 1.02 0.0000000
A34 0.0000000 0.0001020 0.0000000 1.02 0.0000000

Requirements Analysis

asis_output("## Requirments Overview")

Requirments Overview

languages$ID<-as.numeric(gsub("R","",languages$LID))
languages<-languages[order(languages$ID),]
kable(languages,row.names = FALSE)
LID L ID
R1 A1, A2, A9, A10, A11, A20, A23, A29, A30, A31, A32, A35, A38, A40, A43, A47, A54, A55, A57, A58, A60, A63, A68 1
R2 A2, A63 2
R3 A2, A26, A30, A31, A32, A33, A68 3
R4 A2, A4, A5, A6, A8, A21, A26, A32, A45, A46, A68 4
R5 A2 5
R6 A2, A9, A23, A32, A38, A40, A41, A42, A43, A44, A45, A54, A58, A60, A63, A68 6
R7 A2, A14, A32, A38, A39, A43, A51, A52, A57, A59, A61, A62, A63, A64, A68 7
R8 A2, A11, A23, A32, A38, A39, A57, A59, A63, A64, A68 8
R9 A2, A3, A16, A17, A26, A30, A31, A32, A33, A35, A36, A40, A58, A63, A68 9
R10 A2, A4, A5, A6, A7, A8, A9, A11, A18, A20, A21, A22, A24, A25, A26, A27, A28, A29, A30, A31, A32, A33, A34, A35, A36, A37, A38, A41, A42, A43, A47, A48, A49, A51, A52, A53, A58, A66, A68 10
R11 A2, A38, A41, A43, A50, A51, A58, A60, A63, A68 11
R12 A2, A12, A13, A23, A32, A38, A68 12
R13 A2, A11, A14, A23, A32, A38, A39, A52, A57, A59, A61, A62, A63, A64, A68 13
R14 A2, A11, A38, A39, A57, A59, A61, A63, A68 14
R15 A2, A5, A7, A21, A26, A31, A32, A33, A36, A51, A68 15
R16 A2, A32, A51, A63 16
R17 A2, A41, A43, A50, A51, A58, A60, A63, A68 17
R18 A2, A11, A14, A23, A31, A32, A38, A39, A40, A43, A51, A52, A57, A59, A61, A62, A63, A64, A68 18
R19 A2, A4, A5, A6, A7, A8, A18, A20, A21, A22, A24, A25, A26, A27, A28, A29, A31, A32, A38, A40, A41, A43, A47, A48, A51, A52, A53, A57, A59, A61, A64, A68 19
R20 A6, A22, A35, A40, A42, A60, A63, A65, A68 20
R21 A9, A38, A41, A54, A55, A57, A68 21
R22 A9, A14, A38, A39, A40, A54, A55, A59, A61, A63, A64, A68 22
R23 A9, A23, A32, A38, A39, A54, A55, A57, A59, A61, A63, A64, A68 23
R24 A10, A26, A29, A31, A32, A35, A38, A39, A40, A57, A59, A62, A64, A68 24
R25 A11, A38, A39, A41, A43, A44, A59, A68 25
R26 A11, A20, A32, A35, A38, A40, A42, A54, A59, A63, A64, A68 26
R27 A11, A14, A18, A19, A23, A26, A32, A35, A38, A39, A51, A57, A59, A61, A62, A63, A64, A68 27
R28 A11, A26, A32, A41, A43, A57, A68 28
R29 A11, A17, A19, A20, A26, A32, A33, A35, A39, A68 29
R30 A11, A39, A43, A57, A59, A61, A62, A63, A64, A68 30
R31 A11, A31, A32, A38, A57, A68 31
R32 A11, A38, A39, A42, A43, A57, A59, A61, A63, A64, A68 32
R33 A11, A31, A38, A40, A41, A43, A52, A57, A59, A60, A61, A62, A63, A67, A68 33
R34 A11, A23, A41, A57 34
R35 A14, A23, A32, A38, A39, A41, A43, A57, A59, A61, A62, A63, A64, A68 35
R36 A15, A66, A68 36
R37 A19, A26, A43, A45, A46, A68 37
R38 A20, A22, A26, A32, A35, A54, A68 38
R39 A23, A32, A38, A43, A57, A58, A68 39
R40 A23, A32, A41, A43, A68 40
R41 A23, A32, A38, A39, A41, A57, A59, A61, A62, A63, A64, A68 41
R42 A23, A32 42
R43 A23, A26, A68 43
R44 A23, A32, A38, A59, A61, A63, A64, A68 44
R45 A23, A38, A39, A57, A59, A63, A68 45
R46 A26, A68 46
R47 A26, A29, A31, A32, A35, A66, A68 47
R48 A26, A31, A32, A68 48
R49 A31, A68 49
R50 A32, A39, A68 50
R51 A32, A68 51
R52 A32, A38, A41, A59 52
R53 A32, A58, A68 53
R54 A38, A41, A57 54
R55 A38, A42, A58, A60, A63, A68 55
R56 A38, A57, A63, A64 56
R57 A38, A59 57
R58 A38, A68 58
R59 A38, A39, A60, A68 59
R60 A38, A40, A43, A60, A63, A65, A68 60
R61 A39, A57, A61, A68 61
R62 A40, A63, A68 62
R63 A40, A59, A64 63
R64 A40, A42, A44, A45, A58, A68 64
R65 A43, A51, A68 65
R66 A43 66
R67 A51, A68 67
R68 A51 68
R69 A54 69
R70 A54, A55, A57, A68 70
R71 A56, A57, A59, A68 71
R72 A57, A59 72
R73 A60, A68 73
R74 A63, A68 74
R75 A68 75
#print(xtable(languages,digits=c(0,0,2)),include.rownames=FALSE)
print(xtable(languages[c("LID","L")],digits=c(0,0,2)),include.rownames=FALSE,file="languages.tex")

asis_output("## Annotations Overview")

Annotations Overview

kable(annotations,row.names = FALSE)
ann_id TEMP_ANN TEMP_INF_ANN
A1 Dom:C-Ran:C~Time:Same
A2 Dom:C-Ran:CTime:SameRig:Yes-Nec:No~TI:AHFAT
A3 Dom:C-Ran:ICTime:SameRig:Yes-Nec:No~TI:AHFAT Dom:C-Ran:C
A4 Dom:C-Ran:OTime:Same/FutureDom:Death Time:Diff~Dom:Changed
A5 Dom:C-Ran:OTime:Same/PastDom:Birth Time:Diff~Dom:Changed
A6 Dom:C-Ran:OTime:SameDom:Birth Dom:Changed
A7 Dom:C-Ran:OTime:SameRig:YesDom:BirthDom:Death Dom:Changed
A8 Dom:C-Ran:OTime:SameRig:Yes~Dom:Death Dom:Changed
A9 Dom:C-Ran:P~Time:Same Dom:C-Ran:O
A10 Dom:C-Ran:PTime:SameDom:Birth Dom:C-Ran:O~Dom:Changed
A11 Dom:C-Ran:PTime:SameRig:Yes-Nec:No Dom:C-Ran:O
A12 Dom:GDC-Ran:GDCTime:FutureRan:Birth Time:DiffRan:ChangedDom:C-Ran:C
A13 Dom:GDC-Ran:GDCTime:PastDom:Birth Time:DiffDom:C-Ran:CDom:Changed
A14 Dom:GDC-Ran:SDCTime:SameRig:Yes-Nec:No Dom:C-Ran:C
A15 Dom:IC-Ran:CTime:PastDom:Birth Time:DiffDom:ChangedDom:C-Ran:C
A16 Dom:IC-Ran:C~Time:Same Dom:C-Ran:C
A17 Dom:IC-Ran:CTime:SameRig:Yes-Nec:No~TI:AHFAT Dom:C-Ran:C
A18 Dom:IC-Ran:ICTime:FutureIdentity:Same-Nec:No~Dom:Birth-Nec:No Time:DiffDom:Changed-Nec:NoDom:C-Ran:ICDom:C-Ran:CDom:IC-Ran:C
A19 Dom:IC-Ran:ICTime:FutureIdentity:Same-Nec:No~Ran:Birth-Nec:No Time:DiffRan:Changed-Nec:NoDom:C-Ran:ICDom:C-Ran:CDom:IC-Ran:C
A20 Dom:IC-Ran:ICTime:FutureRan:Birth Time:DiffDom:C-Ran:ICRan:ChangedDom:C-Ran:CDom:IC-Ran:C
A21 Dom:IC-Ran:IC~Time:Past Time:DiffDom:C-Ran:ICDom:C-Ran:C~Dom:IC-Ran:C
A22 Dom:IC-Ran:ICTime:PastDom:Birth Time:DiffDom:C-Ran:ICDom:C-Ran:CDom:ChangedDom:IC-Ran:C
A23 Dom:IC-Ran:ICTime:PastDom:Birth~Ran:Death Time:DiffDom:C-Ran:ICRan:ChangedDom:C-Ran:CDom:Changed~Dom:IC-Ran:C
A24 Dom:IC-Ran:ICTime:PastDom:Changed Time:DiffDom:C-Ran:ICDom:C-Ran:C~Dom:IC-Ran:C
A25 Dom:IC-Ran:ICTime:PastDom:ChangedRan:ChangedDom:Birth-Nec:No~Ran:Death-Nec:No Time:DiffRan:Changed-Nec:NoDom:Changed-Nec:NoDom:C-Ran:ICDom:C-Ran:C~Dom:IC-Ran:C
A26 Dom:IC-Ran:ICTime:PastIdentity:Same-Nec:No~Dom:Birth-Nec:No Time:DiffDom:Changed-Nec:NoDom:C-Ran:ICDom:C-Ran:CDom:IC-Ran:C
A27 Dom:IC-Ran:ICTime:PastIdentity:Same~Dom:Changed Time:DiffDom:C-Ran:ICDom:C-Ran:C~Dom:IC-Ran:C
A28 Dom:IC-Ran:ICTime:PastImmediateIdentity:Same~Dom:Changed Time:DiffTime:PastDom:C-Ran:ICDom:C-Ran:CDom:IC-Ran:C
A29 Dom:IC-Ran:IC~Time:Same Dom:C-Ran:ICDom:C-Ran:CDom:IC-Ran:C
A30 Dom:IC-Ran:ICTime:SameRig:Yes Dom:C-Ran:ICDom:C-Ran:CDom:IC-Ran:C
A31 Dom:IC-Ran:ICTime:SameRig:Yes-Nec:No Dom:C-Ran:ICDom:C-Ran:CDom:IC-Ran:C
A32 Dom:IC-Ran:ICTime:SameRig:Yes-Nec:No~TI:AHFAT Dom:C-Ran:ICDom:C-Ran:CDom:IC-Ran:C
A33 Dom:IC-Ran:ICTime:SameRig:Yes~TI:AHFAT Dom:C-Ran:ICDom:C-Ran:CDom:IC-Ran:C
A34 Dom:IC-Ran:OTime:SameRig:Yes-Nec:No Dom:C-Ran:O
A35 Dom:IC-Ran:P~Time:Future Time:DiffDom:C-Ran:PDom:C-Ran:O~Dom:IC-Ran:O
A36 Dom:IC-Ran:P~Time:Same Dom:C-Ran:PDom:C-Ran:ODom:IC-Ran:O
A37 Dom:IC-Ran:PTime:SameRig:Yes Dom:C-Ran:PDom:C-Ran:ODom:IC-Ran:O
A38 Dom:IC-Ran:SDCTime:SameRig:Yes-Nec:No Dom:C-Ran:C~Dom:IC-Ran:C
A39 Dom:IC-Ran:SDCTime:SameRig:Yes-Nec:No~TI:AHFAT Dom:C-Ran:C~Dom:IC-Ran:C
A40 Dom:O-Ran:ICTime:SameRig:Yes Dom:O-Ran:C
A41 Dom:O-Ran:O~Time:Before Time:All
A42 Dom:O-Ran:O~Time:Before/During Time:All
A43 Dom:O-Ran:O~Time:BeforeInverse Time:All
A44 Dom:O-Ran:O~Time:During Time:All
A45 Dom:O-Ran:O~Time:During/Overlaps Time:All
A46 Dom:O-Ran:O~Time:During/OverlapsInverse Time:All
A47 Dom:O-Ran:O~Time:Finishes Time:All
A48 Dom:O-Ran:O~Time:FinishesInverse Time:All
A49 Dom:O-Ran:O~Time:IsEqualTo Time:All
A50 Dom:O-Ran:O~Time:Meets Time:All
A51 Dom:O-Ran:O~Time:MeetsInverse Time:All
A52 Dom:O-Ran:O~Time:Starts Time:All
A53 Dom:O-Ran:O~Time:StartsInverse Time:All
A54 Dom:P-Ran:CTime:SameRan:Birth Dom:O-Ran:C~Ran:Changed
A55 Dom:P-Ran:CTime:SameRan:Changed Dom:O-Ran:C
A56 Dom:P-Ran:CTime:SameRig:Yes Dom:O-Ran:C
A57 Dom:P-Ran:CTime:SameRig:Yes-Nec:No Dom:O-Ran:C
A58 Dom:P-Ran:P~Time:Before/During Dom:O-Ran:O~Time:All
A59 Dom:P-Ran:SDCTime:SameRig:Yes-Nec:No Dom:O-Ran:C~Dom:P-Ran:C
A60 Dom:SDC-Ran:C~Time:Same Dom:C-Ran:C
A61 Dom:SDC-Ran:GDCTime:SameRig:Yes-Nec:No Dom:SDC-Ran:C~Dom:C-Ran:C
A62 Dom:SDC-Ran:ICTime:SameRig:Yes-Nec:No Dom:SDC-Ran:C~Dom:C-Ran:C
A63 Dom:SDC-Ran:ICTime:SameRig:Yes-Nec:No~TI:AHFAT Dom:SDC-Ran:C~Dom:C-Ran:C
A64 Dom:SDC-Ran:PTime:SameRig:Yes-Nec:No Dom:C-Ran:P~Dom:C-Ran:O
A65 Dom:SDC-Ran:SDCTime:SameRig:Yes-Nec:No Dom:SDC-Ran:C~Dom:C-Ran:C
A66 Dom:X-Ran:IC~Time:Same
A67 Dom:X-Ran:XTime:SameRig:Yes-Nec:No
A68 Dom:X-Ran:XTime:SameRig:Yes-Nec:No~TI:AHFAT
l<-annotations
l$TEMP_ANN<-gsub("~"," ",l$TEMP_ANN)
l$TEMP_INF_ANN<-gsub("~"," ",l$TEMP_INF_ANN)
print(xtable(l,digits=c(0,0,0,0)),include.rownames=FALSE,file="annotations.tex")

asis_output("## Requirements Importance Overview")

Requirements Importance Overview

kable(ct_need_suff,row.names = FALSE)
LID CTN PCN CTR PCR L
R1 1 0.010204 34 0.346939 A1, A2, A9, A10, A11, A20, A23, A29, A30, A31, A32, A35, A38, A40, A43, A47, A54, A55, A57, A58, A60, A63, A68
R10 1 0.010204 39 0.397959 A2, A4, A5, A6, A7, A8, A9, A11, A18, A20, A21, A22, A24, A25, A26, A27, A28, A29, A30, A31, A32, A33, A34, A35, A36, A37, A38, A41, A42, A43, A47, A48, A49, A51, A52, A53, A58, A66, A68
R11 1 0.010204 31 0.316327 A2, A38, A41, A43, A50, A51, A58, A60, A63, A68
R12 1 0.010204 22 0.224490 A2, A12, A13, A23, A32, A38, A68
R13 2 0.020408 33 0.336735 A2, A11, A14, A23, A32, A38, A39, A52, A57, A59, A61, A62, A63, A64, A68
R14 3 0.030612 25 0.255102 A2, A11, A38, A39, A57, A59, A61, A63, A68
R15 2 0.020408 31 0.316327 A2, A5, A7, A21, A26, A31, A32, A33, A36, A51, A68
R16 3 0.030612 4 0.040816 A2, A32, A51, A63
R17 2 0.020408 29 0.295918 A2, A41, A43, A50, A51, A58, A60, A63, A68
R18 1 0.010204 49 0.500000 A2, A11, A14, A23, A31, A32, A38, A39, A40, A43, A51, A52, A57, A59, A61, A62, A63, A64, A68
R19 1 0.010204 40 0.408163 A2, A4, A5, A6, A7, A8, A18, A20, A21, A22, A24, A25, A26, A27, A28, A29, A31, A32, A38, A40, A41, A43, A47, A48, A51, A52, A53, A57, A59, A61, A64, A68
R2 12 0.122449 2 0.020408 A2, A63
R20 1 0.010204 21 0.214286 A6, A22, A35, A40, A42, A60, A63, A65, A68
R21 1 0.010204 22 0.224490 A9, A38, A41, A54, A55, A57, A68
R22 1 0.010204 24 0.244898 A9, A14, A38, A39, A40, A54, A55, A59, A61, A63, A64, A68
R23 1 0.010204 31 0.316327 A9, A23, A32, A38, A39, A54, A55, A57, A59, A61, A63, A64, A68
R24 1 0.010204 31 0.316327 A10, A26, A29, A31, A32, A35, A38, A39, A40, A57, A59, A62, A64, A68
R25 1 0.010204 21 0.214286 A11, A38, A39, A41, A43, A44, A59, A68
R26 1 0.010204 25 0.255102 A11, A20, A32, A35, A38, A40, A42, A54, A59, A63, A64, A68
R27 1 0.010204 38 0.387755 A11, A14, A18, A19, A23, A26, A32, A35, A38, A39, A51, A57, A59, A61, A62, A63, A64, A68
R28 1 0.010204 24 0.244898 A11, A26, A32, A41, A43, A57, A68
R29 1 0.010204 24 0.244898 A11, A17, A19, A20, A26, A32, A33, A35, A39, A68
R3 3 0.030612 27 0.275510 A2, A26, A30, A31, A32, A33, A68
R30 2 0.020408 22 0.224490 A11, A39, A43, A57, A59, A61, A62, A63, A64, A68
R31 3 0.030612 22 0.224490 A11, A31, A32, A38, A57, A68
R32 1 0.010204 25 0.255102 A11, A38, A39, A42, A43, A57, A59, A61, A63, A64, A68
R33 1 0.010204 28 0.285714 A11, A31, A38, A40, A41, A43, A52, A57, A59, A60, A61, A62, A63, A67, A68
R34 1 0.010204 1 0.010204 A11, A23, A41, A57
R35 1 0.010204 34 0.346939 A14, A23, A32, A38, A39, A41, A43, A57, A59, A61, A62, A63, A64, A68
R36 1 0.010204 18 0.183673 A15, A66, A68
R37 1 0.010204 23 0.234694 A19, A26, A43, A45, A46, A68
R38 1 0.010204 24 0.244898 A20, A22, A26, A32, A35, A54, A68
R39 2 0.020408 23 0.234694 A23, A32, A38, A43, A57, A58, A68
R4 1 0.010204 24 0.244898 A2, A4, A5, A6, A8, A21, A26, A32, A45, A46, A68
R40 3 0.030612 21 0.214286 A23, A32, A41, A43, A68
R41 2 0.020408 31 0.316327 A23, A32, A38, A39, A41, A57, A59, A61, A62, A63, A64, A68
R42 14 0.142857 1 0.010204 A23, A32
R43 2 0.020408 22 0.224490 A23, A26, A68
R44 7 0.071429 23 0.234694 A23, A32, A38, A59, A61, A63, A64, A68
R45 8 0.081633 22 0.224490 A23, A38, A39, A57, A59, A63, A68
R46 19 0.193878 21 0.214286 A26, A68
R47 2 0.020408 26 0.265306 A26, A29, A31, A32, A35, A66, A68
R48 8 0.081633 25 0.255102 A26, A31, A32, A68
R49 14 0.142857 19 0.193878 A31, A68
R5 19 0.193878 1 0.010204 A2
R50 11 0.112245 19 0.193878 A32, A39, A68
R51 31 0.316327 18 0.183673 A32, A68
R52 4 0.040816 2 0.020408 A32, A38, A41, A59
R53 6 0.061224 19 0.193878 A32, A58, A68
R54 6 0.061224 1 0.010204 A38, A41, A57
R55 2 0.020408 21 0.214286 A38, A42, A58, A60, A63, A68
R56 10 0.102041 1 0.010204 A38, A57, A63, A64
R57 20 0.204082 1 0.010204 A38, A59
R58 30 0.306122 18 0.183673 A38, A68
R59 1 0.010204 20 0.204082 A38, A39, A60, A68
R6 1 0.010204 32 0.326531 A2, A9, A23, A32, A38, A40, A41, A42, A43, A44, A45, A54, A58, A60, A63, A68
R60 1 0.010204 23 0.234694 A38, A40, A43, A60, A63, A65, A68
R61 11 0.112245 18 0.183673 A39, A57, A61, A68
R62 10 0.102041 19 0.193878 A40, A63, A68
R63 6 0.061224 1 0.010204 A40, A59, A64
R64 2 0.020408 18 0.183673 A40, A42, A44, A45, A58, A68
R65 8 0.081633 24 0.244898 A43, A51, A68
R66 21 0.214286 1 0.010204 A43
R67 13 0.132653 21 0.214286 A51, A68
R68 15 0.153061 1 0.010204 A51
R69 9 0.091837 1 0.010204 A54
R7 2 0.020408 36 0.367347 A2, A14, A32, A38, A39, A43, A51, A52, A57, A59, A61, A62, A63, A64, A68
R70 4 0.040816 19 0.193878 A54, A55, A57, A68
R71 1 0.010204 19 0.193878 A56, A57, A59, A68
R72 17 0.173469 1 0.010204 A57, A59
R73 10 0.102041 18 0.183673 A60, A68
R74 26 0.265306 18 0.183673 A63, A68
R75 84 0.857143 17 0.173469 A68
R8 3 0.030612 29 0.295918 A2, A11, A23, A32, A38, A39, A57, A59, A63, A64, A68
R9 1 0.010204 32 0.326531 A2, A3, A16, A17, A26, A30, A31, A32, A33, A35, A36, A40, A58, A63, A68
asis_output("## Requirments Coverage (Sufficiency)")

Requirments Coverage (Sufficiency)

# Percentage of ontologies that can are fully covered by the requirement set
ct_rep<-ct_o_repr[c("LID","value","pc")]
ct_rep$pc<-ct_rep$pc*100
#print(xtable(ct_rep[order(-ct_rep$pc),],digits=c(0,0,2,2)),include.rownames=FALSE)
kable(ct_rep[order(-ct_rep$pc),],row.names = FALSE)
LID value pc
R18 49 50.0000
R19 40 40.8163
R10 39 39.7959
R27 38 38.7755
R7 36 36.7347
R1 34 34.6939
R35 34 34.6939
R13 33 33.6735
R6 32 32.6531
R9 32 32.6531
R11 31 31.6327
R15 31 31.6327
R23 31 31.6327
R24 31 31.6327
R41 31 31.6327
R8 29 29.5918
R17 29 29.5918
R33 28 28.5714
R3 27 27.5510
R47 26 26.5306
R14 25 25.5102
R26 25 25.5102
R32 25 25.5102
R48 25 25.5102
R4 24 24.4898
R22 24 24.4898
R28 24 24.4898
R29 24 24.4898
R38 24 24.4898
R65 24 24.4898
R37 23 23.4694
R39 23 23.4694
R44 23 23.4694
R60 23 23.4694
R12 22 22.4490
R21 22 22.4490
R30 22 22.4490
R31 22 22.4490
R43 22 22.4490
R45 22 22.4490
R20 21 21.4286
R25 21 21.4286
R40 21 21.4286
R46 21 21.4286
R55 21 21.4286
R67 21 21.4286
R59 20 20.4082
R49 19 19.3878
R50 19 19.3878
R53 19 19.3878
R62 19 19.3878
R70 19 19.3878
R71 19 19.3878
R36 18 18.3673
R51 18 18.3673
R58 18 18.3673
R61 18 18.3673
R64 18 18.3673
R73 18 18.3673
R74 18 18.3673
R75 17 17.3469
R16 4 4.0816
R2 2 2.0408
R52 2 2.0408
R5 1 1.0204
R34 1 1.0204
R42 1 1.0204
R54 1 1.0204
R56 1 1.0204
R57 1 1.0204
R63 1 1.0204
R66 1 1.0204
R68 1 1.0204
R69 1 1.0204
R72 1 1.0204
print(xtable(ct_rep[order(-ct_rep$pc),],digits=c(0,0,2,2)),include.rownames=FALSE,file="language_sufficient.tex")

asis_output("## Requirments Necessity")

Requirments Necessity

# Percentage of ontologies that need the requirements to be handled

ct_need<-ct_o_need[c("LID","value","pc")]
ct_need$pc<-ct_need$pc*100
#print(xtable(ct_need[order(-ct_need$pc),],digits=c(0,0,2,2)),include.rownames=FALSE)kable(ct_need_suff,row.names = FALSE)
kable(ct_need[order(-ct_need$pc),],row.names = FALSE)
LID value pc
R75 84 85.7143
R51 31 31.6327
R58 30 30.6122
R74 26 26.5306
R66 21 21.4286
R57 20 20.4082
R5 19 19.3878
R46 19 19.3878
R72 17 17.3469
R68 15 15.3061
R42 14 14.2857
R49 14 14.2857
R67 13 13.2653
R2 12 12.2449
R50 11 11.2245
R61 11 11.2245
R56 10 10.2041
R62 10 10.2041
R73 10 10.2041
R69 9 9.1837
R45 8 8.1633
R48 8 8.1633
R65 8 8.1633
R44 7 7.1429
R53 6 6.1224
R54 6 6.1224
R63 6 6.1224
R52 4 4.0816
R70 4 4.0816
R3 3 3.0612
R8 3 3.0612
R14 3 3.0612
R16 3 3.0612
R31 3 3.0612
R40 3 3.0612
R7 2 2.0408
R13 2 2.0408
R15 2 2.0408
R17 2 2.0408
R30 2 2.0408
R39 2 2.0408
R41 2 2.0408
R43 2 2.0408
R47 2 2.0408
R55 2 2.0408
R64 2 2.0408
R1 1 1.0204
R4 1 1.0204
R6 1 1.0204
R9 1 1.0204
R10 1 1.0204
R11 1 1.0204
R12 1 1.0204
R18 1 1.0204
R19 1 1.0204
R20 1 1.0204
R21 1 1.0204
R22 1 1.0204
R23 1 1.0204
R24 1 1.0204
R25 1 1.0204
R26 1 1.0204
R27 1 1.0204
R28 1 1.0204
R29 1 1.0204
R32 1 1.0204
R33 1 1.0204
R34 1 1.0204
R35 1 1.0204
R36 1 1.0204
R37 1 1.0204
R38 1 1.0204
R59 1 1.0204
R60 1 1.0204
R71 1 1.0204
print(xtable(ct_need[order(-ct_need$pc),],digits=c(0,0,2,2)),include.rownames=FALSE,file="language_necessary.tex")


asis_output("## Requirements Analysis: Final table")

Requirements Analysis: Final table

# Percentage of ontologies that need the requirements to be handled
kable(loverview[c("LID","CTN","PCN","CTR","PCR","IMPANN","Importance")],row.names = FALSE)
LID CTN PCN CTR PCR IMPANN Importance
R75 84 0.857143 17 0.173469 1.0000000 0.7777776
R58 30 0.306122 18 0.183673 0.6376539 0.4406549
R51 31 0.316327 18 0.183673 0.6133651 0.4361448
R74 26 0.265306 18 0.183673 0.6219503 0.4190780
R46 19 0.193878 21 0.214286 0.5721404 0.3943142
R18 1 0.010204 49 0.500000 0.1767250 0.3776608
R67 13 0.132653 21 0.214286 0.5806662 0.3732106
R49 14 0.142857 19 0.193878 0.5445712 0.3506669
R65 8 0.081633 24 0.244898 0.4345140 0.3226577
R73 10 0.102041 18 0.183673 0.5293660 0.3223200
R50 11 0.112245 19 0.193878 0.4599776 0.3089227
R48 8 0.081633 25 0.255102 0.3650384 0.3052131
R27 1 0.010204 38 0.387755 0.1729561 0.2999488
R62 10 0.102041 19 0.193878 0.4433587 0.2990727
R7 2 0.020408 36 0.367347 0.1973562 0.2986416
R19 1 0.010204 40 0.408163 0.0984971 0.2876992
R35 1 0.010204 34 0.346939 0.2037797 0.2829917
R43 2 0.020408 22 0.224490 0.4222340 0.2803615
R53 6 0.061224 19 0.193878 0.4287680 0.2778862
R13 2 0.020408 33 0.336735 0.1919276 0.2759028
R41 2 0.020408 31 0.316327 0.2233202 0.2730342
R10 1 0.010204 39 0.397959 0.0747246 0.2724096
R8 3 0.030612 29 0.295918 0.2435023 0.2702456
R11 1 0.010204 31 0.316327 0.2159710 0.2664382
R61 11 0.112245 18 0.183673 0.3547614 0.2650421
R45 8 0.081633 22 0.224490 0.3024944 0.2624242
R23 1 0.010204 31 0.316327 0.2038564 0.2621855
R1 1 0.010204 34 0.346939 0.1289429 0.2567207
R44 7 0.071429 23 0.234694 0.2767942 0.2563307
R6 1 0.010204 32 0.326531 0.1625558 0.2546315
R24 1 0.010204 31 0.316327 0.1819481 0.2544947
R17 2 0.020408 29 0.295918 0.2093780 0.2542504
R15 2 0.020408 31 0.316327 0.1674244 0.2534123
R3 3 0.030612 27 0.275510 0.2329203 0.2526420
R14 3 0.030612 25 0.255102 0.2566133 0.2470706
R9 1 0.010204 32 0.326531 0.1399348 0.2466906
R31 3 0.030612 22 0.224490 0.3111552 0.2453840
R59 1 0.010204 20 0.204082 0.3718106 0.2447559
R40 3 0.030612 21 0.214286 0.3156379 0.2400132
R39 2 0.020408 23 0.234694 0.2860430 0.2394969
R47 2 0.020408 26 0.265306 0.2237881 0.2384758
R28 1 0.010204 24 0.244898 0.2679714 0.2360813
R33 1 0.010204 28 0.285714 0.1716203 0.2300353
R70 4 0.040816 19 0.193878 0.3128993 0.2291791
R32 1 0.010204 25 0.255102 0.2252532 0.2280297
R60 1 0.010204 23 0.234694 0.2621041 0.2270772
R55 2 0.020408 21 0.214286 0.2798224 0.2234244
R71 1 0.010204 19 0.193878 0.3306765 0.2233716
R36 1 0.010204 18 0.183673 0.3411600 0.2201067
R38 1 0.010204 24 0.244898 0.2184980 0.2187139
R26 1 0.010204 25 0.255102 0.1974768 0.2182790
R12 1 0.010204 22 0.224490 0.2499478 0.2158654
R37 1 0.010204 23 0.234694 0.2261509 0.2144561
R21 1 0.010204 22 0.224490 0.2349590 0.2106037
R30 2 0.020408 22 0.224490 0.2210456 0.2097355
R22 1 0.010204 24 0.244898 0.1868302 0.2075971
R25 1 0.010204 21 0.214286 0.2399807 0.2054222
R29 1 0.010204 24 0.244898 0.1757402 0.2037041
R4 1 0.010204 24 0.244898 0.1517237 0.1952732
R20 1 0.010204 21 0.214286 0.1736728 0.1821452
R64 2 0.020408 18 0.183673 0.2063879 0.1768118
R57 20 0.204082 1 0.010204 0.2109392 0.1326436
R66 21 0.214286 1 0.010204 0.1422095 0.1125325
R72 17 0.173469 1 0.010204 0.1613144 0.1031746
R5 19 0.193878 1 0.010204 0.1250034 0.0984603
R2 12 0.122449 2 0.020408 0.1844520 0.0981611
R42 14 0.142857 1 0.010204 0.1745757 0.0957818
R68 15 0.153061 1 0.010204 0.1613325 0.0951489
R56 10 0.102041 1 0.010204 0.2012263 0.0890732
R16 3 0.030612 4 0.040816 0.1892417 0.0775866
R52 4 0.040816 2 0.020408 0.1838592 0.0658244
R54 6 0.061224 1 0.010204 0.1793982 0.0653461
R63 6 0.061224 1 0.010204 0.1141281 0.0424334
R69 9 0.091837 1 0.010204 0.0504517 0.0321286
R34 1 0.010204 1 0.010204 0.1212500 0.0248533
print(xtable(loverview[c("LID","CTN","PCN","CTR","PCR","IMPANN","Importance")],digits=c(2)),include.rownames=FALSE,file="languages_overview_revised.tex")

print(xtable(head(loverview[c("LID","CTN","PCN","CTR","PCR","IMPANN","Importance")],20),digits=c(2)),include.rownames=FALSE,file="languages_top10.tex")
#write.csv(loverview,file="languages_overview_revised.csv")

Prepare Examples for Developmental ontologies

Prepare Pareto Frontier Plot Plot.ly and partial order

sky1 <- psel(loverview[c("LID","PCN","PCR","IMPANN")], high(PCN) * high(PCR) * high(IMPANN)) 
sky1$pareto<-"Pareto"
tt<-merge(loverview,sky1[c("LID","pareto")],by="LID",all.x = TRUE)
tt$PCN<-round(tt$PCN*100,2)
tt$PCR<-round(tt$PCR*100,2)
tt$pareto<-as.factor(ifelse(is.na(tt$pareto),"Other","Pareto"))

## Prepare just for developmental ontologies:
pref <- tt[tt$PCN>0&tt$LID %in% LIDSOFDEVELOP,c("LID","PCN","PCR","IMPANN")] 
pref<-rbind(pref,data.frame(LID="R0",PCN=max(pref$PCN)+0.01,PCR=max(pref$PCR)+0.01,IMPANN=max(pref$IMPANN)+0.01))
row.names(pref)<-pref$LID
paret <- high(PCN) * high(PCR) * high(IMPANN) 
btg <- get_btg(pref, paret) 
labels <- paste0(pref$LID)
g<-btg$graph

## requirements on pareto line:
kable(tt[tt$pareto=="Pareto",c("LID","Importance")],row.names = FALSE)
LID Importance
R7 0.2986416
R8 0.2702456
R18 0.3776608
R35 0.2829917
R41 0.2730342
R46 0.3943142
R48 0.3052131
R51 0.4361448
R58 0.4406549
R65 0.3226577
R67 0.3732106
R75 0.7777776

Analysis: Preferential plot (Developmental ontologies)

fine = 1000 # this will adjust the resolving power.
palettex = colorRampPalette(c('red','green'))
graphCol = palettex(fine)[as.numeric(cut(pref$PCR,breaks = fine))]
V(g)$color<-graphCol

pdf('developmental_preference_chart.pdf')
plot.igraph(g, layout = layout_as_tree(g, circular = FALSE),
     edge.arrow.size=0.5, 
     vertex.label.cex=1, 
     vertex.label.font=2,
     vertex.label.family="serif",
     vertex.size=pref$PCN/3, 
     edge.width=3,
     vertex.color=V(g)$color,
     vertex.label=gsub(" ","\n",pref$LID),
     vertex.label.degree = pi/2    
     )
dev.off()
## quartz_off_screen 
##                 2
#At first we use Graphviz. If the Rgraphviz package (from Bioconductor) is available, the dot layouter is used to plot the graph resulting in the left figure.
#plot_btg(df, pref, labels)
#If Rgraphviz is not available or we explicitly do not use it via
#plot_btg(df, pref, labels, use_dot = FALSE)