mirror of
https://github.com/MillironX/beefblup.git
synced 2024-12-22 09:08:16 +00:00
Revamp fixed-effect algorithm
This commit is contained in:
parent
4b66ad8b1f
commit
d4bb72c458
2 changed files with 44 additions and 61 deletions
103
src/BeefBLUP.jl
103
src/BeefBLUP.jl
|
@ -71,9 +71,9 @@ function beefblup(path::String, savepath::String, h2::Float64)
|
||||||
A = additiverelationshipmatrix(data.id, data.dam, data.sire)
|
A = additiverelationshipmatrix(data.id, data.dam, data.sire)
|
||||||
|
|
||||||
# Extract all of the fixed effects
|
# Extract all of the fixed effects
|
||||||
fixedfx = select(data, Not([:id, :birthdate, :sire, :dam]))[:,1:end - 1]
|
fixedeffectdata = data[:,5:end-1]
|
||||||
|
|
||||||
(X, numgroups, normal, adjustedtraits) = fixedeffectmatrix(fixedfx)
|
(X, fixedeffects) = fixedeffectmatrix(fixedeffectdata)
|
||||||
|
|
||||||
# Extract the observed data
|
# Extract the observed data
|
||||||
Y = convert(Array{Float64}, data[:,end])
|
Y = convert(Array{Float64}, data[:,end])
|
||||||
|
@ -173,71 +173,42 @@ function beefblup(path::String, savepath::String, h2::Float64)
|
||||||
|
|
||||||
end
|
end
|
||||||
|
|
||||||
function fixedeffectmatrix(fixedeffects::AbstractDataFrame)
|
"""
|
||||||
# Find any columns that need to be deleted
|
fixedeffectmatrix(fixedeffectdata::DataFrame)
|
||||||
for i in 1:ncol(fixedeffects)
|
|
||||||
if length(unique(fixedeffects[:,i])) <= 1
|
Creates contemporary groupings and the fixed-effect incidence matrix based on the fixed
|
||||||
@warn string("column '", names(fixedeffects)[i], "' does not have any unique animals and will be removed from this analysis")
|
effects listed in `fixedeffectdata`.
|
||||||
DataFrames.select!(fixedeffects, Not(i))
|
|
||||||
|
Returns a tuple `(X::Matrix{Int}, fixedeffects::Array{FixedEffect})` in which `X` is the
|
||||||
|
actual matrix, and `fixedeffects` is the contemporary groupings.
|
||||||
|
"""
|
||||||
|
function fixedeffectmatrix(fixedeffectdata::DataFrame)
|
||||||
|
# Declare an empty return matrix
|
||||||
|
fixedeffects = FixedEffect[]
|
||||||
|
|
||||||
|
# Add each trait to the array
|
||||||
|
for i in 1:size(fixedeffectdata)[2]
|
||||||
|
name = names(fixedeffectdata)[i]
|
||||||
|
traits = eachcol(fixedeffectdata)[i]
|
||||||
|
|
||||||
|
if length(unique(traits)) > 1
|
||||||
|
push!(fixedeffects, FixedEffect(name, traits))
|
||||||
|
else
|
||||||
|
@warn string("column '", name, "' does not have any unique animals and will be dropped from analysis")
|
||||||
|
DataFrames.select!(fixedeffectdata, Not(pname))
|
||||||
end
|
end
|
||||||
end
|
end
|
||||||
|
|
||||||
# Determine how many contemporary groups there are
|
X = ones(Int64, (size(fixedeffectdata)[1], 1))
|
||||||
numtraits = ncol(fixedeffects)
|
|
||||||
numgroups = ones(1, numtraits)
|
|
||||||
for i in 1:numtraits
|
|
||||||
numgroups[i] = length(unique(fixedeffects[:,i]))
|
|
||||||
end
|
|
||||||
|
|
||||||
# If there are more groups than animals, then the analysis cannot continue
|
for i in 1:length(fixedeffects)
|
||||||
numanimals = length(fixedeffects[:,1])
|
trait = fixedeffects[i]
|
||||||
if sum(numgroups) >= numanimals
|
for phenotype in trait.alltraits
|
||||||
throw(ErrorException("there are more contemporary groups than animals"))
|
X = cat(X, Int64.(fixedeffectdata[:,i] .== phenotype), dims=2)
|
||||||
end
|
|
||||||
|
|
||||||
# Define a "normal" animal as one of the last in the groups, provided that
|
|
||||||
# all traits do not have null values
|
|
||||||
numtraits = ncol(fixedeffects)
|
|
||||||
numanimals = length(fixedeffects[:,1])
|
|
||||||
normal = Array{String}(undef, 1, numtraits)
|
|
||||||
for i in 1:numtraits
|
|
||||||
for j in numanimals:-1:1
|
|
||||||
if !ismissing(fixedeffects[j,i])
|
|
||||||
normal[i] = string(fixedeffects[j,i])
|
|
||||||
break
|
|
||||||
end
|
|
||||||
end
|
end
|
||||||
end
|
end
|
||||||
|
|
||||||
# Form the fixed-effect matrix
|
return X, fixedeffects
|
||||||
X = zeros(Int8, numanimals, floor(Int, sum(numgroups)) - length(numgroups) + 1)
|
|
||||||
X[:,1] = ones(Int8, 1, numanimals)
|
|
||||||
|
|
||||||
# Create an external counter that will increment through both loops
|
|
||||||
counter = 2
|
|
||||||
|
|
||||||
# Store the traits in a string array
|
|
||||||
adjustedtraits =
|
|
||||||
Array{String}(undef,floor(Int, sum(numgroups)) - length(numgroups))
|
|
||||||
# Iterate through each group
|
|
||||||
for i in 1:length(normal)
|
|
||||||
# Find the traits that are present in this trait
|
|
||||||
localdata = string.(fixedeffects[:,i])
|
|
||||||
traits = unique(localdata)
|
|
||||||
# Remove the normal version from the analysis
|
|
||||||
effecttraits = traits[findall(x -> x != normal[i], traits)]
|
|
||||||
# Iterate inside of the group
|
|
||||||
for j in 1:(length(effecttraits))
|
|
||||||
matchedindex = findall(x -> x == effecttraits[j], localdata)
|
|
||||||
X[matchedindex, counter] .= 1
|
|
||||||
# Add this trait to the string
|
|
||||||
adjustedtraits[counter - 1] = traits[j]
|
|
||||||
# Increment the big counter
|
|
||||||
counter = counter + 1
|
|
||||||
end
|
|
||||||
end
|
|
||||||
|
|
||||||
return X, numgroups, normal, adjustedtraits
|
|
||||||
end
|
end
|
||||||
|
|
||||||
"""
|
"""
|
||||||
|
@ -314,5 +285,17 @@ function renamecolstospec!(df::DataFrame)
|
||||||
return df
|
return df
|
||||||
end
|
end
|
||||||
|
|
||||||
|
struct FixedEffect
|
||||||
|
name::String
|
||||||
|
basetrait::Any
|
||||||
|
alltraits::AbstractArray{Any}
|
||||||
|
end
|
||||||
|
|
||||||
|
function FixedEffect(name::String, incidences)
|
||||||
|
basetrait = last(unique(incidences))
|
||||||
|
types = unique(incidences)[1:end-1]
|
||||||
|
return FixedEffect(name, basetrait, types)
|
||||||
|
end
|
||||||
|
|
||||||
|
|
||||||
end
|
end
|
||||||
|
|
|
@ -4,7 +4,7 @@ using Test
|
||||||
|
|
||||||
@testset "BeefBLUP.jl" begin
|
@testset "BeefBLUP.jl" begin
|
||||||
# Write your tests here.
|
# Write your tests here.
|
||||||
correctX = [1 1 0 0; 1 1 0 1; 1 0 1 0; 1 0 1 1; 1 0 1 0; 1 0 1 1; 1 0 0 0]
|
correctX = [1 1 0 1; 1 1 0 0; 1 0 1 1; 1 0 1 0; 1 0 1 1; 1 0 1 0; 1 0 0 1]
|
||||||
fixedfx = DataFrame(year = [1990, 1990, 1991, 1991, 1991, 1991, 1992], sex = ["male", "female", "male", "female", "male", "female", "male"])
|
fixedfx = DataFrame(year = [1990, 1990, 1991, 1991, 1991, 1991, 1992], sex = ["male", "female", "male", "female", "male", "female", "male"])
|
||||||
@test BeefBLUP.fixedeffectmatrix(fixedfx)[1] == correctX
|
@test BeefBLUP.fixedeffectmatrix(fixedfx)[1] == correctX
|
||||||
correctA = [1 0 1/2 1/2 1/2 0 0;
|
correctA = [1 0 1/2 1/2 1/2 0 0;
|
||||||
|
|
Loading…
Reference in a new issue