Skip to content

Cardinal OPLS result is different from ropls result #75

Description

@weicao-PSN

Dear Cardinal,
I tried to run opls-da by Cardinal with test data, but the result seems strange. So I use ropls to run it. The result were different from Cardinal's. Is it a bug or did I configure some parameters incorrectly?

Here's my R script and package version:

library(Cardinal)
library(ropls)
set.seed(2020, kind="L'Ecuyer-CMRG")
mse2 <- simulateImage(preset=7, dim=c(32,32), sdnoise=0.3,
nrun=3, peakdiff=2, centroided=TRUE)
mse2$class <- makeFactor(A=mse2$circleA, B=mse2$circleB)
dat <- mse2[,!is.na(mse2$class)]

#PLS
bbb <- Cardinal::PLS(dat, y=dat$class, ncomp=2)
plot(bbb, type="scores", groups=dat$class, linewidth=2)

aaa<-ropls::opls(t(spectra(dat)),dat$class, orthoI = 0)
plot(aaa)

Image Image

#OPLS
bbb <- Cardinal::OPLS(dat, y=dat$class, ncomp=2)
plot(bbb, type="scores", groups=dat$class, linewidth=2)

aaa<-ropls::opls(t(spectra(dat)),dat$class, predI = 1, orthoI = NA)
plot(aaa)

Image Image

Rversion:
platform x86_64-w64-mingw32
arch x86_64
os mingw32
crt ucrt
system x86_64, mingw32
status
major 4
minor 4.1
year 2024
month 06
day 14
svn rev 86737
language R
version.string R version 4.4.1 (2024-06-14 ucrt)
nickname Race for Your Life

packageversion:

for(i in (.packages())){print(paste0(i,' ',packageVersion(i)))}
[1] "matter 2.6.3"
[1] "Matrix 1.7.0"
[1] "ropls 1.36.0"
[1] "Cardinal 3.6.5"
[1] "S4Vectors 0.42.0"
[1] "stats4 4.4.1"
[1] "BiocParallel 1.38.0"
[1] "BiocGenerics 0.48.1"
[1] "ProtGenerics 1.36.0"
[1] "stats 4.4.1"
[1] "graphics 4.4.1"
[1] "grDevices 4.4.1"
[1] "utils 4.4.1"
[1] "datasets 4.4.1"
[1] "methods 4.4.1"
[1] "base 4.4.1"

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions