######################################################################
#                   Factorial analysis code
######################################################################
#
# Version 1 by Sohela Shah and Saunak Sen
# Date 11 September 2009
#
#######################################################################
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# any later version.
#
# This program is distributed in the hope that it will be useful, but
# WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
# General Public License for more details.
#
# A copy of the GNU General Public License is available at
# http://www.gnu.org/licenses/.
#######################################################################
# This code is meant to accompany the paper entitled Strain Background 
# Modifies Phenotypes in the Atp8b1-Deficient Mouse 
# by S. Shah, U.R. Sanford, J. Vargas, H. Xu, A. Groen, 
# C.C. Paulusma, L. Pawlikowska, S. Sen, R.P.J. Oude Elferink, 
# L.N. Bull
########################################################################
# Our objective is to analyze the pup weight (at toe clip and weaning) to 
# discover differences between strains (C57BL/6, 129S, and F1), genotype 
# (mutant or wild type), and sex. The initial (base) analysis focused on 
# these factors and their interaction. Two 129S sub-strains (129S1 and 129S4) 
# were used. These were combined into one group for both pure strains 
# and F1 mice.

# We entered data from two sheets saved as CSV files in MS Excel and 
# then combine them into a single table. The column names were consistent 
# across sheets, which was checked.


# input data files

wt <- read.delim("/Users/sohelashah/Documents/Cholestasis/Mouse data/Pup-record/WT weights norm.txt")
mut <- read.delim("/Users/sohelashah/Documents/Cholestasis/Mouse data/Pup-record/Mutant weights norm.txt")

# keep subset to rows with meaningful data, remove rows with no data

idx <- complete.cases(wt[,2])
wt <-wt[idx,]
idx <- complete.cases(mut[,2])
mut <-mut[idx,]
idx.c <- c(1:8)

#combine data files into one matrix

pupwt <- rbind(wt[,idx.c],mut[,idx.c])

# assign column names

names(pupwt)<-c("mouse","sex","strain","genotype","wt1","n.wt1","wt2","n.wt2")

# set strain, genotype, and sex as factors

pupwt$strain <- as.factor(as.character(pupwt$strain))
pupwt$sex <- as.factor(as.character(pupwt$sex))
pupwt$genotype <- as.factor(as.character(pupwt$genotype))

# combine the 2 S129 strains

pupwt$strain2 <- pupwt$strain
idx <- grep("S",as.character(pupwt$strain))
pupwt $strain2 <- as.character(pupwt$strain2)
pupwt$strain2[idx] <- "S129"
pupwt$strain2 <- as.factor(pupwt$strain2)

# combine the 2 F1 strains

pupwt$strainC <- pupwt$strain2
idx <- grep("F",as.character(pupwt$strain2))
pupwt$strainC <- as.character(pupwt$strainC)
pupwt$strainC[idx] <- "F1"
pupwt$strainC <- as.factor(pupwt$strainC)


contrasts(pupwt$strainC) <- contr.treatment(3)
pupwt$genotype <- relevel(pupwt$genotype,2)


# Generalized linear mode for stepwise regression

fitbic <- function(formula,data,...)
   {
     git <- glm(as.formula(formula),data=data,...)
     # hit <- step(git,k=log(nrow(git$qr$qr)),trace=0)
     hit <- step(git,k=log(length(git$residuals)),trace=0)
     # print(summary(hit)$call)
     # print(summary(hit)$coefficients,digits=3)
     print(summary(hit),sign=FALSE,digits=2)
     hit
   }
 
plotpheno <- function(x,y,z,xlab="",ylab="",fac=0,cex=0.7)
   {
     xylim <- range(c(x,fac+y),na.rm=T)
     plot(x,y,xlim=xylim,ylim=xylim-fac,xlab=xlab,ylab=ylab,type="n")
     # open circles
     points(x[z],y[z],pch=21,cex=cex)
     # solid circles
     points(x[!z],y[!z],pch=19,cex=cex)
     lines(xylim,xylim-fac)
   }
 form.a <- "strainC*genotype*sex"


pupwt$n.wt1<-as.numeric(pupwt$n.wt1)
pupwt$n.wt2<-as.numeric(pupwt$n.wt2)


form.start <- "log(n.wt1) ~"
form.end <- "log(n.wt2) ~"
idx.se <- complete.cases(pupwt$n.wt1,pupwt$n.wt2)
idx <- which(!is.na(log(pupwt$n.wt1))&!is.na(log(pupwt$n.wt2))&(pupwt$n.wt1!=0)&(pupwt$n.wt2!=0))
pupwt.comp<-pupwt[idx,]


# Fit toe clip weight data  using fitbit function 

hit0 <- fitbic( as.formula(paste(form.start,form.a)), data=pupwt.comp)

# Fit wean weight data  using fitbit function 

hit1 <- fitbic( as.formula(paste(form.end,form.a)), data=pupwt.comp)