library(gap)
#> Loading required package: gap.datasets
#> gap version 1.6
knitr::kable(p3,caption="An example pedigree")

library(DOT)
# one can see the diagram in RStudio
pedtodot_verbatim(p3,run=TRUE,toDOT=TRUE,return="verbatim")
#> Pedigree  10081 
#> running DOT::dot on 10081
library(DiagrammeR)
pedtodot_verbatim(p3)
#> Pedigree  10081
grViz(readr::read_file("10081.dot"))

# pedigree diagram
data(lukas, package="gap.datasets")
library(kinship2)
#> Loading required package: Matrix
#> Loading required package: quadprog
ped <- with(lukas,pedigree(id,father,mother,sex))
plot(ped,cex=0.4)

# unordered individuals
gk1 <- kin.morgan(lukas)
write.table(gk1$kin.matrix,"gap_1.txt",quote=FALSE)

library(kinship2)
kk1 <- kinship(lukas[,1],lukas[,2],lukas[,3])
write.table(kk1,"kinship_1.txt",quote=FALSE)

d <- gk1$kin.matrix-kk1
sum(abs(d))
#> [1] 2.443634

# order individuals so that parents precede their children
library(pedigree)
op <- orderPed(lukas)
olukas <- lukas[order(op),]
gk2 <- kin.morgan(olukas)

write.table(olukas,"olukas.csv",quote=FALSE)
write.table(gk2$kin.matrix,"gap_2.txt",quote=FALSE)

kk2 <- kinship(olukas[,1],olukas[,2],olukas[,3])
write.table(kk2,"kinship_2.txt",quote=FALSE)

z <- gk2$kin.matrix-kk2
sum(abs(z))
#> [1] 0

options(width=150)
library(gap)
models <- matrix(c(
         4.0, 0.01,
         4.0, 0.10,
         4.0, 0.50, 
         4.0, 0.80,
         2.0, 0.01,
         2.0, 0.10,
         2.0, 0.50,
         2.0, 0.80,
         1.5, 0.01,    
         1.5, 0.10,
         1.5, 0.50,
         1.5, 0.80), ncol=2, byrow=TRUE)
outfile <- "fbsize.txt"
cat("gamma","p","Y","N_asp","P_A","H1","N_tdt","H2","N_asp/tdt",
    "L_o","L_s\n",file=outfile,sep="\t")
for(i in 1:12) {
    g <- models[i,1]
    p <- models[i,2]
    z <- fbsize(g,p)
    cat(z$gamma,z$p,z$y,z$n1,z$pA,z$h1,z$n2,z$h2,z$n3,
        z$lambdao,z$lambdas,file=outfile,append=TRUE,sep="\t")
    cat("\n",file=outfile,append=TRUE)
}
table1 <- read.table(outfile,header=TRUE,sep="\t")
nc <- c(4,7,9)
table1[,nc] <- ceiling(table1[,nc])
dc <- c(3,5,6,8,10,11)
table1[,dc] <- round(table1[,dc],2)
unlink(outfile)
knitr::kable(table1,caption="Power/Sample size of family-based designs")

g <- 4.5
p <- 0.15
alz <- data.frame(fbsize(g,p))
knitr::kable(alz,caption="Power/Sample size of study on Alzheimer's disease")

library(gap)
kp <- c(0.01,0.05,0.10,0.2)
models <- matrix(c(
          4.0, 0.01,
          4.0, 0.10,
          4.0, 0.50, 
          4.0, 0.80,
          2.0, 0.01,
          2.0, 0.10,
          2.0, 0.50,
          2.0, 0.80,
          1.5, 0.01,    
          1.5, 0.10,
          1.5, 0.50,
          1.5, 0.80), ncol=2, byrow=TRUE)
outfile <- "pbsize.txt"
cat("gamma","p","p1","p5","p10","p20\n",sep="\t",file=outfile)
for(i in 1:dim(models)[1])
{
   g <- models[i,1]
   p <- models[i,2]
   n <- vector()
   for(k in kp) n <- c(n,ceiling(pbsize(k,g,p)))
   cat(models[i,1:2],n,sep="\t",file=outfile,append=TRUE)
   cat("\n",file=outfile,append=TRUE)
} 
table5 <- read.table(outfile,header=TRUE,sep="\t")
knitr::kable(table5,caption="Sample size of population-based design")

library(gap)
# ARIC study
outfile <- "aric.txt"
n <- 15792
pD <- 0.03
p1 <- 0.25
alpha <- 0.05
theta <- c(1.35,1.40,1.45)
beta <- 0.2
s_nb <- c(1463,722,468)
cat("n","pD","p1","hr","q","power","ssize\n",file=outfile,sep="\t")
for(i in 1:3)
{
  q <- s_nb[i]/n
  power <- ccsize(n,q,pD,p1,log(theta[i]),alpha,beta,TRUE)
  ssize <- ccsize(n,q,pD,p1,log(theta[i]),alpha,beta,FALSE)
  cat(n,"\t",pD,"\t",p1,"\t",theta[i],"\t",q,"\t",
      signif(power,3),"\t",ssize,"\n",
      file=outfile,append=TRUE)
}
read.table(outfile,header=TRUE,sep="\t")
#>       n   pD   p1   hr          q power ssize
#> 1 15792 0.03 0.25 1.35 0.09264184   0.8  1463
#> 2 15792 0.03 0.25 1.40 0.04571935   0.8   722
#> 3 15792 0.03 0.25 1.45 0.02963526   0.8   468
unlink(outfile)
# EPIC study
outfile <- "epic.txt"
n <- 25000
alpha <- 0.00000005
beta <- 0.2
s_pD <- c(0.3,0.2,0.1,0.05)
s_p1 <- seq(0.1,0.5,by=0.1)
s_hr <- seq(1.1,1.4,by=0.1)
cat("n","pD","p1","hr","alpha","ssize\n",file=outfile,sep="\t")
# direct calculation
for(pD in s_pD)
{
   for(p1 in s_p1)
   {
      for(hr in s_hr)
      {
         ssize <- ccsize(n,q,pD,p1,log(hr),alpha,beta,FALSE)
         if (ssize>0) cat(n,"\t",pD,"\t",p1,"\t",hr,"\t",alpha,"\t",
                          ssize,"\n",
                          file=outfile,append=TRUE)
      }
   }
}
knitr::kable(read.table(outfile,header=TRUE,sep="\t"),caption="Sample size of case-cohort designs")

unlink(outfile)

library(gap)
u_obs <- runif(1000)
r <- qqunif(u_obs,pch=21,bg="blue",bty="n")
u_exp <- r$y
hits <- u_exp >= 2.30103
points(r$x[hits],u_exp[hits],pch=21,bg="green")
legend("topleft",sprintf("GC.lambda=%.4f",gc.lambda(u_obs)))

ord <- with(w4,order(chr,pos))
w4 <- w4[ord,]
oldpar <- par()
par(cex=0.6)
colors <- c(rep(c("blue","red"),15),"red")
mhtplot(w4,control=mht.control(colors=colors,gap=1000),pch=19,srt=0)
axis(2,cex.axis=2)
suggestiveline <- -log10(3.60036E-05)
genomewideline <- -log10(1.8E-06)
abline(h=suggestiveline, col="blue")
abline(h=genomewideline, col="green")
abline(h=0)

data <- with(mhtdata,cbind(chr,pos,p))
glist <- c("IRS1","SPRY2","FTO","GRIK3","SNED1","HTR1A","MARCH3","WISP3",
           "PPP1R3B","RP1L1","FDFT1","SLC39A14","GFRA1","MC4R")
hdata <- subset(mhtdata,gene%in%glist)[c("chr","pos","p","gene")]
color <- rep(c("lightgray","gray"),11)
glen <- length(glist)
hcolor <- rep("red",glen)  
par(las=2, xpd=TRUE, cex.axis=1.8, cex=0.4)
ops <- mht.control(colors=color,yline=1.5,xline=3)
hops <- hmht.control(data=hdata,colors=hcolor)
mhtplot(data,ops,hops,pch=19)
axis(2,pos=2,at=1:16,cex.axis=0.5)

circos.mhtplot(mhtdata, glist)
#> Note: 11 points are out of plotting region in sector 'chr16', track '3'.

require(gap.datasets)
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
testdat <- mhtdata[c("chr","pos","p","gene","start","end")] %>%
           rename(log10p=p) %>%
           mutate(chr=paste0("chr",chr),log10p=-log10(log10p))
dat <- mutate(testdat,start=pos,end=pos) %>%
       select(chr,start,end,log10p)
labs <- subset(testdat,gene %in% glist) %>%
        group_by(gene,chr,start,end) %>%
        summarize() %>%
        mutate(cols="blue") %>%
        select(chr,start,end,gene,cols)
#> `summarise()` has grouped output by 'gene', 'chr', 'start'. You can override using the `.groups` argument.
labs[2,"cols"] <- "red"
ticks <- 0:2*5
circos.mhtplot2(dat,labs,ticks=ticks,ymax=max(ticks))
#> Note: 43 points are out of plotting region in sector 'chr16', track '5'.

#{r mhttest, fig.cap="Manhattanly plot", fig.height=8, fig.width=8, plotly=TRUE}
library(manhattanly)
mhttest <- manhattanly(mhtdata, chr = "chr", bp = "pos",
                       snp = "rsn", annotation1 = "gene", suggestiveline = TRUE,
                       annotation2 = "rsn", p = "p")
mhttest
htmlwidgets::saveWidget(mhttest,"mhttest.html")

mhtdata <- within(mhtdata,{pr=p})
miamiplot(mhtdata,chr="chr",bp="pos",p="p",pr="pr",snp="rsn")

# An alternative implementation
gwas <- select(mhtdata,chr,pos,p) %>%
        mutate(z=qnorm(p/2))
chrmaxpos <- miamiplot2(gwas,gwas,name1="Batch 2",name2="Batch 1",z1="z",z2="z")
#> Warning in max(c(dat1$pos[dat1$chr == i], dat2$pos[dat2$chr == i]), na.rm = TRUE): no non-missing arguments to max; returning -Inf
labelManhattan(chr=c(2,16),pos=c(226814165,52373776),name=c("AnonymousGene","FTO"),gwas,gwasZLab="z",chrmaxpos=chrmaxpos)

par(oma=c(0,0,0,0), mar=c(5,6.5,1,1))
mhtplot.trunc(filter(IL.12B,log10P>=2), chr="Chromosome", bp="Position", z="Z",
   snp="MarkerName",
   suggestiveline=FALSE, genomewideline=-log10(5e-10),
   cex.mtext=1.2, cex.text=1.2,
   annotatelog10P=-log10(5e-10), annotateTop = FALSE,
   highlight=with(genes,gene),
   mtext.line=3, y.brk1=115, y.brk2=300, trunc.yaxis=TRUE, delta=0.01,
   cex.axis=1.5, cex=0.8, font=3, font.axis=1.5,
   y.ax.space=20,
   col = c("blue4", "skyblue")
)

asplot(CDKNlocus, CDKNmap, CDKNgenes, best.pval=5.4e-8, sf=c(3,6))
#> - CDKN2A 
#> - CDKN2B
title("CDKN2A/CDKN2B Region")

cnvplot(gap.datasets::cnv)

library(gap)
rs12075 <- data.frame(id=c("CCL2","CCL7","CCL8","CCL11","CCL13","CXCL6","Monocytes"),
                      b=c(0.1694,-0.0899,-0.0973,0.0749,0.189,0.0816,0.0338387),
                      se=c(0.0113,0.013,0.0116,0.0114,0.0114,0.0115,0.00713386))
ESplot(rs12075)

data(OPG,package="gap.datasets")
meta::settings.meta(method.tau="DL")
METAL_forestplot(OPGtbl,OPGall,OPGrsid,width=6.75,height=5,digits.TE=2,digits.se=2,
                 col.diamond="black",col.inside="black",col.square="black")
#> Joining with `by = join_by(MarkerName)`
#> Joining with `by = join_by(MarkerName)`

METAL_forestplot(OPGtbl,OPGall,OPGrsid,package="metafor",method="FE",xlab="Effect",
                 showweights=TRUE)
#> Joining with `by = join_by(MarkerName)`
#> Joining with `by = join_by(MarkerName)`

# log(p) for a standard normal deviate z based on log()
logp <- function(z) log(2)+pnorm(-abs(z), lower.tail=TRUE, log.p=TRUE)

# log10(p) for a standard normal deviate z based on log()
log10p <- function(z) log(2, base=10)+pnorm(-abs(z), lower.tail=TRUE, log.p=TRUE)/log(10)

2*pnorm(-1.96,lower.tail=TRUE)

log10(2)+log10(pnorm(-abs(z),lower.tail=TRUE))

z <- 20000
-log10p(z)

require(Rmpfr)
2*pnorm(mpfr(-abs(z),100),lower.tail=TRUE,log.p=FALSE)
mpfr(log(2),100) + pnorm(mpfr(-abs(z),100),lower.tail=TRUE,log.p=TRUE)

as.numeric(-log10(2*pnorm(mpfr(-abs(z),100),lower.tail=TRUE)))

pvalue <- function (z, decimals = 2)
{
    lp <- -log10p(z)
    exponent <- ceiling(lp)
    base <- 10^-(lp - exponent)
    paste0(round(base, decimals), "e", -exponent)
}

log10pvalue <- function(p=NULL,base=NULL,exponent=NULL)
{
  if(!is.null(p))
  {
    p <- format(p,scientific=TRUE)
    p2 <- strsplit(p,"e")
    base <- as.numeric(lapply(p2,"[",1))
    exponent <- as.numeric(lapply(p2,"[",2))
  } else if(is.null(base) | is.null(exponent)) stop("base and exponent should both be specified")
  log10(base)+exponent
}

require(gap)
zlist <- c(5,10,30,40,50,100,500,1000,2000,3000,5000)
zp <- sapply(zlist,function(z) {c(z,pvalue(z),logp(z),log10p(z))})
rownames(zp) <- c("z","P","log(P)","log10(P)")
knitr::kable(t(zp),caption="z, P, log(P) and log10(P)")

get_b_se(0.6396966,23991,4.7245)
#>               b          se
#> [1,] 0.04490488 0.009504684

get_sdy(0.6396966,23991,0.04490488,0.009504684)
#> [1] 1

# zcat METAL/4E.BP1-1.tbl.gz | \
# awk 'NR==1 || ($1==4 && $2 >= 187158034 - 1e6 && $2 < 187158034 + 1e6)' >  4E.BP1.z
tbl <- within(read.delim("4E.BP1.z"),{logp <- logp(Effect/StdErr)})
z <- cs(tbl)
l <- cs(tbl,log_p="logp")

mr_names <- names(mrdat)
LIF.R <- cbind(mrdat[grepl("SNP|LIF.R",mr_names)],trait="LIF.R"); names(LIF.R) <- c("SNP","b","se","trait")
FEV1 <- cbind(mrdat[grepl("SNP|FEV1",mr_names)],trait="FEV1"); names(FEV1) <- c("SNP","b","se","trait")
CAD <- cbind(mrdat[grepl("SNP|CAD",mr_names)],trait="CAD"); names(CAD) <- c("SNP","b","se","trait")
mrdat2 <- within(rbind(LIF.R,FEV1,CAD),{y=b})
library(ggplot2)
p <- ggplot2::ggplot(mrdat2,aes(y = SNP, x = y))+
     ggplot2::theme_bw()+
     ggplot2::geom_point()+
     ggplot2::facet_wrap(~ trait, ncol=3, scales="free_x")+
     ggplot2::geom_segment(aes(x = b-1.96*se, xend = b+1.96*se, yend = SNP))+
     ggplot2::geom_vline(lty=2, ggplot2::aes(xintercept=0), colour = 'red')+
     ggplot2::xlab("Effect size")+
     ggplot2::ylab("")
p
#> Warning: Removed 1 row containing missing values or values outside the scale range (`geom_point()`).
#> Warning: Removed 1 row containing missing values or values outside the scale range (`geom_segment()`).

mr_forestplot(tnfb, colgap.forest.left="0.05cm", fontsize=14, leftlabs=c("Outcome","b","SE"),
              common=FALSE, random=FALSE, print.I2=FALSE, print.pval.Q=FALSE, print.tau2=FALSE,
              spacing=1.6,digits.TE=2,digits.se=2,xlab="Effect size",type.study="square",col.inside="black",col.square="black")

mr_forestplot(tnfb, colgap.forest.left="0.05cm", fontsize=14,
              leftcols="studlab", leftlabs="Outcome", plotwidth="3inch", sm="OR", rightlabs="ci",
              sortvar=tnfb[["Effect"]],
              common=FALSE, random=FALSE, print.I2=FALSE, print.pval.Q=FALSE, print.tau2=FALSE,
              backtransf=TRUE, spacing=1.6,type.study="square",col.inside="black",col.square="black")

mr_forestplot(tnfb,colgap.forest.left="0.05cm", fontsize=14,
              leftcols=c("studlab"), leftlabs=c("Outcome"),
              plotwidth="3inch", sm="OR", sortvar=tnfb[["Effect"]],
              rightcols=c("effect","ci","pval"), rightlabs=c("OR","95%CI","P"),
              digits=3, digits.pval=2, scientific.pval=TRUE,
              common=FALSE, random=FALSE, print.I2=FALSE, print.pval.Q=FALSE, print.tau2=FALSE,
              addrow=TRUE, backtransf=TRUE, spacing=1.6,type.study="square",col.inside="black",col.square="black")

require(gap)
s <- chr_pos_a1_a2(1,c(123,321),letters[1:2],letters[2:1])
s
#> [1] "chr1:123_A_B" "chr1:321_A_B"
inv_chr_pos_a1_a2(s)
#>               chr pos a1 a2
#> chr1:123_A_B chr1 123  A  B
#> chr1:321_A_B chr1 321  A  B
inv_chr_pos_a1_a2("chr1:123-A_B",seps=c(":","-","_"))
#>               chr pos a1 a2
#> chr1:123-A_B chr1 123  A  B

example(ci2ms)
#> 
#> ci2ms> # rs3784099 and breast cancer recurrence/mortality
#> ci2ms> ms <- ci2ms("1.28-1.72")
#> 
#> ci2ms> print(ms)
#> $m
#> [1] 0.3945922
#> 
#> $s
#> [1] 0.07537491
#> 
#> $direction
#> [1] "+"
#> 
#> 
#> ci2ms> # Vector input
#> ci2ms> ci2 <- c("1.28-1.72","1.25-1.64")
#> 
#> ci2ms> ms2 <- ci2ms(ci2)
#> 
#> ci2ms> print(ms2)
#> $m
#> [1] 0.3945922 0.3589199
#> 
#> $s
#> [1] 0.07537491 0.06927492
#> 
#> $direction
#> [1] "+" "+"

gc.lambda <- function(x, logscale=FALSE, z=FALSE) {
  v <- x[!is.na(x)]
  n <- length(v)
  if (z) {
     obs <- v^2
     exp <- qchisq(log(1:n/n),1,lower.tail=FALSE,log.p=TRUE)
  } else {
    if (!logscale)
    {
      obs <- qchisq(v,1,lower.tail=FALSE)
      exp <- qchisq(1:n/n,1,lower.tail=FALSE)
    } else {
      obs <- qchisq(-log(10)*v,1,lower.tail=FALSE,log.p=TRUE)
      exp <- qchisq(log(1:n/n),1,lower.tail=FALSE,log.p=TRUE)
    }
  }

  lambda <- median(obs)/median(exp)
  return(lambda)
}

# A simplified version is as follows,
# obs <- median(chisq)
# exp <- qchisq(0.5, 1) # 0.4549364
# lambda <- obs/exp
# see also estlambda from GenABEL and qq.chisq from snpStats

# A related function

lambda1000 <- function(lambda, ncases, ncontrols)
  1 + (lambda - 1) * (1 / ncases + 1 / ncontrols)/( 1 / 1000 + 1 / 1000)

invnormal <- function(x) qnorm((rank(x,na.last="keep")-0.5)/sum(!is.na(x)))

set.seed(12345)
Ni <- rpois(50, lambda = 4); table(factor(Ni, 0:max(Ni)))
#> 
#>  0  1  2  3  4  5  6  7  8  9 
#>  2  4  6 11  8 10  4  2  2  1
y <- invnormal(Ni)
sd(y)
#> [1] 0.9755074
mean(y)
#> [1] 0.002650512
Ni <- 1:50
y <- invnormal(Ni)
mean(y)
#> [1] -1.810184e-17
sd(y)
#> [1] 0.9973999

alleles <- c("a","c","G","t")
revStrand(alleles)
#> [1] "t" "g" "C" "a"

d <- data.frame(ID_1=1,ID_2=1,missing=0,PC1=1,PC2=2,D1=1,P1=10)
snptest_sample(d,C=paste0("PC",1:2),D=paste0("D",1:1),P=paste0("P",1:1))