Help for package ggrisk

Title:

Risk Score Plot for Cox Regression

Version:

1.3

Description:

The risk plot may be one of the most commonly used figures in tumor genetic data analysis. We can conclude the following two points: Comparing the prediction results of the model with the real survival situation to see whether the survival rate of the high-risk group is lower than that of the low-level group, and whether the survival time of the high-risk group is shorter than that of the low-risk group. The other is to compare the heat map and scatter plot to see the correlation between the predictors and the outcome.

License:

GPL-2

Encoding:

UTF-8

LazyData:

true

RoxygenNote:

7.1.1

Depends:

R (≥ 2.10)

Imports:

ggplot2, survival, egg, do, set, cutoff, grid, rms, nomogramFormula, reshape2

URL:

https://github.com/yikeshu0611/ggrisk

BugReports:

https://github.com/yikeshu0611/ggrisk/issues

NeedsCompilation:

Packaged:

2021-08-07 14:40:20 UTC; asus

Author:

Jing Zhang [aut, cre], Zhi Jin [aut]

Maintainer:

Jing Zhang <zj391120@163.com>

Repository:

CRAN

Date/Publication:

2021-08-09 07:40:06 UTC

ICGC Liver Data from Japan

Description

This data is a liver cancer data from Japan Data released in ICGC database (Link). It cantains time, event and four genes.

Usage

data(LIRI)

Format

An object of class data.frame with 232 rows and 6 columns.

Examples

data(LIRI)

Risk Score Plot for Cox Regression

Description

Risk Score Plot for Cox Regression

Usage

ggrisk(
  fit,
  heatmap.genes = NULL,
  new.data = NULL,
  code.0 = "Alive",
  code.1 = "Dead",
  code.highrisk = "High",
  code.lowrisk = "Low",
  cutoff.show = TRUE,
  cutoff.value = "median",
  cutoff.x = NULL,
  cutoff.y = NULL,
  cutoff.label = NULL,
  title.A.ylab = "Risk Score",
  title.B.ylab = "Survival Time",
  title.A.legend = "Risk Group",
  title.B.legend = "Status",
  title.C.legend = "Expression",
  size.ABC = 1.5,
  size.ylab.title = 14,
  size.Atext = 11,
  size.Btext = 11,
  size.Ctext = 11,
  size.yticks = 0.5,
  size.yline = 0.5,
  size.points = 2,
  size.dashline = 1,
  size.cutoff = 5,
  size.legendtitle = 13,
  size.legendtext = 12,
  color.A = c(low = "blue", high = "red"),
  color.B = c(code.0 = "blue", code.1 = "red"),
  color.C = c(low = "blue", median = "white", high = "red"),
  vjust.A.ylab = 1,
  vjust.B.ylab = 2,
  family = "sans",
  expand.x = 3,
  relative_heights = c(0.1, 0.1, 0.01, 0.15)
)

Arguments

fit

cox regression results of coxph() from 'survival' package or cph() from 'rms' package

heatmap.genes

(optional) numeric variables. Name for genes

new.data

new data for validation

code.0

string. Code for event 0. Default is 'Alive'

code.1

string. Code for event 1. Default is 'Dead'

code.highrisk

string. Code for highrisk in risk score. Default is 'High'

code.lowrisk

string. Code for lowrisk in risk score. Default is 'Low'

cutoff.show

logical, whether to show text for cutoff in figure A. Default is TRUE

cutoff.value

string, which can be 'median', 'roc' or 'cutoff'. Even you can define it by yourself

cutoff.x

numeric (optional), ordination x for cutoff text

cutoff.y

numeric (optional), ordination y for cutoff text

cutoff.label

(should be) string. Define cutoff label by yourself

title.A.ylab

string, y-lab title for figure A. Default is 'Risk Score'

title.B.ylab

string, y-lab title for figure B. Default is 'Survival Time'

title.A.legend

string, legend title for figure A. Default is 'Risk Group'

title.B.legend

string, legend title for figure B. Default is 'Status'

title.C.legend

string, legend title for figure C. Default is 'Expression'

size.ABC

numeric, size for ABC. Default is 1.5

size.ylab.title

numeric, size for y-axis label title. Default is 14

size.Atext

numeric, size for y-axis text in figure A. Default is 11

size.Btext

numeric, size for y-axis text in figure B. Default is 11

size.Ctext

numeric, size for y-axis text in figure C. Default is 11

size.yticks

numeric, size for y-axis ticks. Default is 0.5

size.yline

numeric, size for y-axis line. Default is 0.5

size.points

numeric, size for scatter points. Default is 2

size.dashline

numeric, size for dashline. Default is 1

size.cutoff

numeric, size for cutoff text. Default is 5

size.legendtitle

numeric, size for legend title. Default is 13

size.legendtext

numeric, size for legend text. Default is 12

color.A

color for figure A. Default is low = 'blue', high = 'red'

color.B

color for figure B. Default is code.0 = 'blue', code.1 = 'red'

color.C

color for figure C. Default is low = 'blue', median = 'white', high = 'red'

vjust.A.ylab

numeric, vertical just for y-label in figure A. Default is 1

vjust.B.ylab

numeric, vertical just for y-label in figure B. Default is 2

family

family, default is sans

expand.x

numeric, expand for x-axis

relative_heights

numeric, relative heights for figure A, B, colored side bar and heatmap. Default is 0.1 0.1 0.01 and 0.15

Value

A risk score picture

Examples

library(rms)
library(ggrisk)
fit <- cph(Surv(time,status)~ANLN+CENPA+GPR182+BCO2,LIRI)
ggrisk(fit,
       cutoff.value='median',
       cutoff.x = 145,
       cutoff.y = -0.8)


#more detailed example
#plot
ggrisk(fit)

#heatmap.genes
ggrisk(fit,
       heatmap.genes=c('GPR182','CENPA','BCO2'))

#cutoff
ggrisk(fit,
       cutoff.value='median') #default
ggrisk(fit,
       cutoff.value='roc')
ggrisk(fit,
       cutoff.value='cutoff')
ggrisk(fit,
       cutoff.value=-1)
ggrisk(fit,
       cutoff.value='median',
       cutoff.x = 145,
       cutoff.y = -0.8)
ggrisk(fit,
       cutoff.value='median',
       cutoff.x = 145,
       cutoff.y = -0.8,
       cutoff.label='This is cutoff')

#code for 0 and 1
ggrisk(fit,
       cutoff.value='median',
       cutoff.x = 145,
       cutoff.y = -0.8,
       code.0 = 'Still Alive',
       code.1 = 'Already Dead')

#code for high and low risk group
ggrisk(fit,
       cutoff.value='median',
       cutoff.x = 145,
       cutoff.y = -0.8,
       code.0 = 'Still Alive',
       code.1 = 'Already Dead',
       code.highrisk = 'High Risk',
       code.lowrisk = 'Low Risk')
#title
ggrisk(fit,
       cutoff.value='median',
       cutoff.x = 145,
       cutoff.y = -0.8,
       code.0 = 'Still Alive',
       code.1 = 'Already Dead',
       code.highrisk = 'High Risk',
       code.lowrisk = 'Low Risk',
       title.A.ylab='Risk Score',
       title.B.ylab='Survival Time(year)',
       title.A.legend='Risk Group',
       title.B.legend='Status',
       title.C.legend='Expression')
#size
ggrisk(fit,
       cutoff.value='median',
       cutoff.x = 145,
       cutoff.y = -0.8,
       code.0 = 'Still Alive',
       code.1 = 'Already Dead',
       code.highrisk = 'High Risk',
       code.lowrisk = 'Low Risk',
       title.A.ylab='Risk Score',
       title.B.ylab='Survival Time(year)',
       title.A.legend='Risk Group',
       title.B.legend='Status',
       title.C.legend='Expression',
       size.ABC=1.5,
       size.ylab.title=14,
       size.Atext=11,
       size.Btext=11,
       size.Ctext=11,
       size.yticks=0.5,
       size.yline=0.5,
       size.points=2,
       size.dashline=1,
       size.cutoff=5,
       size.legendtitle=13,
       size.legendtext=12)
#color
ggrisk(fit,
       cutoff.value='median',
       cutoff.x = 145,
       cutoff.y = -0.8,
       code.0 = 'Still Alive',
       code.1 = 'Already Dead',
       code.highrisk = 'High Risk',
       code.lowrisk = 'Low Risk',
       title.A.ylab='Risk Score',
       title.B.ylab='Survival Time(year)',
       title.A.legend='Risk Group',
       title.B.legend='Status',
       title.C.legend='Expression',
       size.ABC=1.5,
       size.ylab.title=14,
       size.Atext=11,
       size.Btext=11,
       size.Ctext=11,
       size.yticks=0.5,
       size.yline=0.5,
       size.points=2,
       size.dashline=1,
       size.cutoff=5,
       size.legendtitle=13,
       size.legendtext=12,
       color.A=c(low='blue',high='red'),
       color.B=c(code.0='blue',code.1='red'),
       color.C=c(low='blue',median='white',high='red'))

#vjust
ggrisk(fit,
       cutoff.value='median',
       cutoff.x = 145,
       cutoff.y = -0.8,
       code.0 = 'Still Alive',
       code.1 = 'Already Dead',
       code.highrisk = 'High Risk',
       code.lowrisk = 'Low Risk',
       title.A.ylab='Risk Score',
       title.B.ylab='Survival Time(year)',
       title.A.legend='Risk Group',
       title.B.legend='Status',
       title.C.legend='Expression',
       size.ABC=1.5,
       size.ylab.title=14,
       size.Atext=11,
       size.Btext=11,
       size.Ctext=11,
       size.yticks=0.5,
       size.yline=0.5,
       size.points=2,
       size.dashline=1,
       size.cutoff=5,
       size.legendtitle=13,
       size.legendtext=12,
       color.A=c(low='blue',high='red'),
       color.B=c(code.0='blue',code.1='red'),
       color.C=c(low='blue',median='white',high='red'),
       vjust.A.ylab=1,
       vjust.B.ylab=2)

#family, expand, relative height
ggrisk(fit,
       cutoff.value='median',
       cutoff.x = 145,
       cutoff.y = -0.8,
       code.0 = 'Still Alive',
       code.1 = 'Already Dead',
       code.highrisk = 'High Risk',
       code.lowrisk = 'Low Risk',
       title.A.ylab='Risk Score',
       title.B.ylab='Survival Time(year)',
       title.A.legend='Risk Group',
       title.B.legend='Status',
       title.C.legend='Expression',
       size.ABC=1.5,
       size.ylab.title=14,
       size.Atext=11,
       size.Btext=11,
       size.Ctext=11,
       size.yticks=0.5,
       size.yline=0.5,
       size.points=2,
       size.dashline=1,
       size.cutoff=5,
       size.legendtitle=13,
       size.legendtext=12,
       color.A=c(low='blue',high='red'),
       color.B=c(code.0='blue',code.1='red'),
       color.C=c(low='blue',median='white',high='red'),
       vjust.A.ylab=1,
       vjust.B.ylab=2,
       family='sans',
       expand.x=3,
       relative_heights=c(0.1,0.1,0.01,0.15))

Two Scatter Plot Plot for Cox Regression

Description

Two Scatter Plot Plot for Cox Regression

Usage

two_scatter(
  fit,
  new.data = NULL,
  code.0 = "Alive",
  code.1 = "Dead",
  code.highrisk = "High",
  code.lowrisk = "Low",
  cutoff.show = TRUE,
  cutoff.value = "median",
  cutoff.x,
  cutoff.y,
  cutoff.label,
  title.A.ylab = "Risk Score",
  title.B.ylab = "Survival Time",
  title.xlab = "Rank",
  title.A.legend = "Risk Group",
  title.B.legend = "Status",
  size.AB = 1.5,
  size.ylab.title = 14,
  size.xlab.title = 14,
  size.Atext = 11,
  size.Btext = 11,
  size.xtext = 11,
  size.xyticks = 0.5,
  size.xyline = 0.5,
  size.points = 2,
  size.dashline = 1,
  size.cutoff = 5,
  size.legendtitle = 13,
  size.legendtext = 12,
  color.A = c(low = "blue", high = "red"),
  color.B = c(code.0 = "blue", code.1 = "red"),
  vjust.A.ylab = 1,
  vjust.B.ylab = 2,
  family = "sans",
  expand.x = 3
)

Arguments

fit

cox regression results of coxph() from 'survival' package or cph() from 'rms' package

new.data

new data for validation

code.0

string. Code for event 0. Default is 'Alive'

code.1

string. Code for event 1. Default is 'Dead'

code.highrisk

string. Code for highrisk in risk score. Default is 'High'

code.lowrisk

string. Code for lowrisk in risk score. Default is 'Low'

cutoff.show

logical, whether to show text for cutoff in figure A. Default is TRUE

cutoff.value

string, which can be 'median', 'roc' or 'cutoff'. Even you can define it by yourself

cutoff.x

numeric (optional), ordination x for cutoff text

cutoff.y

numeric (optional), ordination y for cutoff text

cutoff.label

(should be) string. Define cutoff label by yourself

title.A.ylab

string, y-lab title for figure A. Default is 'Riskscore'

title.B.ylab

string, y-lab title for figure B. Default is 'Survival Time'

title.xlab

string, x-lab title for figure B. Default is 'Rank'

title.A.legend

string, legend title for figure A. Default is 'Risk Group'

title.B.legend

string, legend title for figure B. Default is 'Status'

size.AB

numeric, size for ABC. Default is 1.5

size.ylab.title

numeric, size for y-axis label title. Default is 14

size.xlab.title

numeric, size for x-axis lab title. Default is 11

size.Atext

numeric, size for y-axis text in figure A. Default is 11

size.Btext

numeric, size for y-axis text in figure B. Default is 11

size.xtext

numeric, size for x-axis text. Default is 11

size.xyticks

numeric, size for y-axis ticks. Default is 0.5

size.xyline

numeric, size for y-axis line. Default is 0.5

size.points

numeric, size for scatter points. Default is 2

size.dashline

numeric, size for dashline. Default is 1

size.cutoff

numeric, size for cutoff text. Default is 5

size.legendtitle

numeric, size for legend title. Default is 13

size.legendtext

numeric, size for legend text. Default is 12

color.A

color for figure A. Default is low = 'blue', high = 'red'

color.B

color for figure B. Default is code.0 = 'blue', code.1 = 'red'

vjust.A.ylab

numeric, vertical just for y-label in figure A. Default is 1

vjust.B.ylab

numeric, vertical just for y-label in figure B. Default is 2

family

family, default is sans

expand.x

numeric, expand for x-axis

Value

A riskscore picture

Examples

library(rms)
fit <- cph(Surv(time,status)~ANLN+CENPA+GPR182+BCO2,LIRI)
two_scatter(fit,
            cutoff.value = 'median',
            cutoff.x = 142,
            cutoff.y = -0.5)

#more detailed example
library(ggrisk)
#plot
two_scatter(fit)
#regulate cutoff
##hidden cutoff
two_scatter(fit,
            cutoff.show = FALSE)
two_scatter(fit,
            cutoff.value = 'median')
two_scatter(fit,
            cutoff.value = 'roc')
two_scatter(fit,
            cutoff.value = 'cutoff')
two_scatter(fit,
            cutoff.value = -1)
two_scatter(fit,
            cutoff.value = 'median',
            cutoff.x = 142,
            cutoff.y = -0.5)
#code for 0 and 1
two_scatter(fit,
            cutoff.value = 'median',
            cutoff.x = 142,
            cutoff.y = -0.5,
            code.0 = 'Still Alive',
            code.1 = 'Dead')
#code for high and low risk group
two_scatter(fit,
            cutoff.value = 'median',
            cutoff.x = 142,
            cutoff.y = -0.5,
            code.0 = 'Still Alive',
            code.1 = 'Dead',
            code.highrisk = 'High Group',
            code.lowrisk = 'Low Group')
#title for legend, x and y lab
two_scatter(fit,
            cutoff.value = 'median',
            cutoff.x = 142,
            cutoff.y = -0.5,
            code.0 = 'Still Alive',
            code.1 = 'Dead',
            code.highrisk = 'High Group',
            code.lowrisk = 'Low Group',
            title.A.legend = 'Riskscore',
            title.B.legend = 'Event Status',
            title.A.ylab = 'Riskscore',
            title.B.ylab = 'Survival Time(year)',
            title.xlab = 'This is rank')
#vertical just for y-axis lab
two_scatter(fit,
            cutoff.value = 'median',
            cutoff.x = 142,
            cutoff.y = -0.5,
            code.0 = 'Still Alive',
            code.1 = 'Dead',
            code.highrisk = 'High Group',
            code.lowrisk = 'Low Group',
            title.A.legend = 'Riskscore',
            title.B.legend = 'Event Status',
            title.A.ylab = 'Riskscore',
            title.B.ylab = 'Survival Time(year)',
            title.xlab = 'This is rank',
            vjust.A.ylab = 1,
            vjust.B.ylab = 3)
#size
two_scatter(fit,
            cutoff.value = 'median',
            cutoff.x = 142,
            cutoff.y = -0.5,
            code.0 = 'Still Alive',
            code.1 = 'Dead',
            code.highrisk = 'High Group',
            code.lowrisk = 'Low Group',
            title.A.legend = 'Riskscore',
            title.B.legend = 'Event Status',
            title.A.ylab = 'Riskscore',
            title.B.ylab = 'Survival Time(year)',
            title.xlab = 'This is rank',
            vjust.A.ylab = 1,
            vjust.B.ylab = 3,
            size.AB = 2,
            size.ylab.title = 14,
            size.xlab.title = 14,
            size.Atext = 12,
            size.Btext = 12,
            size.xtext = 12,
            size.xyticks = 0.5,
            size.xyline = 0.5,
            size.dashline = 1.5,
            size.points = 1,
            size.cutoff = 5,
            size.legendtitle = 14,
            size.legendtext = 13)
#color
two_scatter(fit,
            cutoff.value = 'median',
            cutoff.x = 142,
            cutoff.y = -0.5,
            code.0 = 'Still Alive',
            code.1 = 'Dead',
            code.highrisk = 'High Group',
            code.lowrisk = 'Low Group',
            title.A.legend = 'Riskscore',
            title.B.legend = 'Event Status',
            title.A.ylab = 'Riskscore',
            title.B.ylab = 'Survival Time(year)',
            title.xlab = 'This is rank',
            vjust.A.ylab = 1,
            vjust.B.ylab = 3,
            size.AB = 2,
            size.ylab.title = 14,
            size.xlab.title = 14,
            size.Atext = 12,
            size.Btext = 12,
            size.xtext = 12,
            size.xyticks = 0.5,
            size.xyline = 0.5,
            size.dashline = 1.5,
            size.points = 1,
            size.cutoff = 5,
            size.legendtitle = 14,
            size.legendtext = 13,
            color.A = c(low='green',high='red'),
            color.B = c(code.0='green',code.1='red'))
#famli and expand
two_scatter(fit,
            cutoff.value = 'median',
            cutoff.x = 142,
            cutoff.y = -0.5,
            code.0 = 'Still Alive',
            code.1 = 'Dead',
            code.highrisk = 'High Group',
            code.lowrisk = 'Low Group',
            title.A.legend = 'Riskscore',
            title.B.legend = 'Event Status',
            title.A.ylab = 'Riskscore',
            title.B.ylab = 'Survival Time(year)',
            title.xlab = 'This is rank',
            vjust.A.ylab = 1,
            vjust.B.ylab = 3,
            size.AB = 2,
            size.ylab.title = 14,
            size.xlab.title = 14,
            size.Atext = 12,
            size.Btext = 12,
            size.xtext = 12,
            size.xyticks = 0.5,
            size.xyline = 0.5,
            size.dashline = 1.5,
            size.points = 1,
            size.cutoff = 5,
            size.legendtitle = 14,
            size.legendtext = 13,
            color.A = c(low='green',high='red'),
            color.B = c(code.0='green',code.1='red'),
            family = 'sans', # sans for Arail, serif for Times New Roman
            expand.x=10)