library(gprofiler2)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(ggplot2)
library(plotly)
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
library(ggplotify)
library(magrittr)
Kidney g:profiler analysis
k1 <- gost(query = c(
'Q64213' ,
'Q9CQC6' ,
'Q9CWK8' ,
'P70460' ,
'Q62448' ,
'P62806' ,
'Q61686' ,
'P27546' ,
'Q3U182' ,
'P05213' ,
'Q08093' ,
'Q61074' ,
'Q8K1B8' ,
'Q921M7' ,
'Q9CQC6' ,
'D0QMC3' ,
'Q8K352' ,
'P61028' ,
'Q61937' ,
'P60762' ,
'Q9JLQ0' ,
'P70315' ,
'Q99PM3' ,
'Q9ESZ8' ,
'Q8VEK3' ,
'Q921M7' ,
'P20444' ,
'P70460'
),
organism = 'mmusculus')
head(k1$result)
## query significant p_value term_size query_size intersection_size
## 1 query_1 TRUE 0.005366026 1390 21 9
## 2 query_1 TRUE 0.015838901 6090 21 16
## 3 query_1 TRUE 0.016084613 3798 21 13
## 4 query_1 TRUE 0.016457989 533 21 6
## 5 query_1 TRUE 0.023906342 6270 21 16
## 6 query_1 TRUE 0.034987264 354 21 5
## precision recall term_id source
## 1 0.4285714 0.006474820 GO:0007010 GO:BP
## 2 0.7619048 0.002627258 GO:0016043 GO:BP
## 3 0.6190476 0.003422854 GO:0006996 GO:BP
## 4 0.2857143 0.011257036 GO:0051493 GO:BP
## 5 0.7619048 0.002551834 GO:0071840 GO:BP
## 6 0.2380952 0.014124294 GO:0010639 GO:BP
## term_name effective_domain_size
## 1 cytoskeleton organization 21118
## 2 cellular component organization 21118
## 3 organelle organization 21118
## 4 regulation of cytoskeleton organization 21118
## 5 cellular component organization or biogenesis 21118
## 6 negative regulation of organelle organization 21118
## source_order parents
## 1 2946 GO:0006996
## 2 5665 GO:0071840
## 3 2933 GO:0016043
## 4 15932 GO:0007010, GO:0033043
## 5 19815 GO:0009987
## 6 4797 GO:0006996, GO:0033043, GO:0051129
p <- gostplot(k1, capped = FALSE, interactive = 1)
p
l1 <- gost(query = c(
'Q9CZ69' ,
'Q9QZ73' ,
'Q9CWK8' ,
'Q8CGC7' ,
'Q99K48' ,
'O54931' ,
'Q99KJ8' ,
'P63038' ,
'Q9JLQ0' ,
'O08585' ,
'A3KGB4' ,
'P05213' ,
'P61028' ,
'Q9DAW9' ,
'P70158' ,
'P98078' ,
'Q64213' ,
'Q99K30' ,
'Q9JMB0' ,
'Q9QUH0' ,
'Q9WVB0' ,
'Q9Z2C8' ,
'Q3UMF0' ,
'Q61937' ,
'Q62415' ,
'Q64152' ,
'Q8K310' ,
'Q6AW69' ,
'Q91Y97' ,
'P98078' ,
'Q8N7N5' ,
'P17225' ,
'P63038' ,
'Q6IRU5' ,
'Q8CAY6' ,
'Q8BSY0' ,
'P16546'
),
organism = 'mmusculus')
head(l1$result)
## query significant p_value term_size query_size intersection_size
## 1 query_1 TRUE 2.278106e-03 2897 29 15
## 2 query_1 TRUE 1.142951e-02 2416 29 13
## 3 query_1 TRUE 1.347587e-02 2452 29 13
## 4 query_1 TRUE 3.968715e-02 1535 29 10
## 5 query_1 TRUE 2.493956e-06 3849 28 19
## 6 query_1 TRUE 1.158446e-03 11093 28 26
## precision recall term_id source term_name
## 1 0.5172414 0.005177770 GO:0033036 GO:BP macromolecule localization
## 2 0.4482759 0.005380795 GO:0071702 GO:BP organic substance transport
## 3 0.4482759 0.005301794 GO:0008104 GO:BP protein localization
## 4 0.3448276 0.006514658 GO:0015031 GO:BP protein transport
## 5 0.6785714 0.004936347 GO:0005829 GO:CC cytosol
## 6 0.9285714 0.002343820 GO:0005737 GO:CC cytoplasm
## effective_domain_size source_order parents
## 1 21118 9231 GO:0051179
## 2 21118 19737 GO:0006810
## 3 21118 3542 GO:0033036
## 4 21118 5363 GO:0045184, GO:0071702, GO:0071705
## 5 21016 470 GO:0005737, GO:0110165
## 6 21016 385 GO:0005622, GO:0110165
p <- gostplot(l1, capped = FALSE, interactive = 1)
p
COFRADIC data from spleen in g:profiler
s1 <- gost(query = c(
'Q64213' ,
'Q9CQC6' ,
'Q9CWK8' ,
'Q9CXF0' ,
'Q62448' ,
'Q9DBP5' ,
'Q9CY58' ,
'P60762' ,
'O08585' ,
'Q8VDJ3' ,
'O35490' ,
'O55022' ,
'P05213' ,
'P17225' ,
'P30115' ,
'Q4VAA2' ,
'Q6IRU5' ,
'Q99KJ8' ,
'Q9D8Y0' ,
'Q9QXD6' ,
'P08113' ,
'Q8R0Y6' ,
'P22907' ,
'Q9DBG7' ,
'Q3U182'
),
organism = 'mmusculus')
head(s1$result)
## query significant p_value term_size query_size intersection_size
## 1 query_1 TRUE 0.001309112 3849 18 12
## 2 query_1 TRUE 0.026077633 11093 18 17
## precision recall term_id source term_name effective_domain_size
## 1 0.6666667 0.003117693 GO:0005829 GO:CC cytosol 21016
## 2 0.9444444 0.001532498 GO:0005737 GO:CC cytoplasm 21016
## source_order parents
## 1 470 GO:0005737, GO:0110165
## 2 385 GO:0005622, GO:0110165
p <- gostplot(s1, capped = FALSE, interactive = 1)
p