Repository Mirror for your Cloud Server and Webhosting

LazyLoad:

yes

LazyData:

yes

Version:

2024.7-30

Title:

Forward Stepwise Deep Autoencoder-Based Monotone NLDR

Maintainer:

Youyi Fong <youyifong@gmail.com>

Depends:

R (≥ 3.5.0)

Suggests:

R.rsp, RUnit

Imports:

kyotil, reticulate (≥ 1.10)

VignetteBuilder:

R.rsp

Description:

FS-DAM performs feature extraction through latent variables identification. Implementation is based on autoencoders with monotonicity and orthogonality constraints.

License:

GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]

NeedsCompilation:

Packaged:

2024-07-31 14:57:27 UTC; Youyi

Author:

Youyi Fong [cre], Jun Xu [aut]

Repository:

CRAN

Date/Publication:

2024-07-31 15:30:02 UTC

Select Biomarkers from the HVTN 505 Correlates Analysis

Description

See reference.

Usage

data("cc.505")

Format

A data frame with 189 observations on the following 27 variables.

ptid: a character vector
trt: a numeric vector
case: a numeric vector
control: a numeric vector
perprot: a numeric vector
last_uninfec_immun_vst: a numeric vector
racefull: a numeric vector
racefulltxt: a character vector
bmi: a numeric vector
bmicat: a numeric vector
bmicattxt: a character vector
earliest_pos_vst: a numeric vector
level: a character vector
matchlevel: a character vector
samplingfraction: a numeric vector
vst9subcohort: a numeric vector
HIVwk28preunbl: a numeric vector
age: a numeric vector
racecc: a character vector
bhvrisk: a numeric vector
BMI: a numeric vector
stratuminds_vaccs: a numeric vector
stratuminds: a numeric vector
cd4.env.poly: a numeric vector
cd8.env.poly: a numeric vector
mfounders: a numeric vector
wei: a numeric vector

References

Fong, Y, Xu, J. Multi-Stage Simultaneous Deep Autoencoder-based Monotone (MSS-DAM) Nonlinear Dimensionality Reduction Methods, Journal of Computational and Graphical Statistics, in press.

FS-DAM NLDR

Description

Forward stepwise deep autoencoder-based monotone nonlinear dimension reduction.

Usage

fsdam(dat, opt_numCode = ncol(dat), opt_seed = 1, opt_model = "n", opt_gpu = 0, 
opt_k = 100, opt_nEpochs = 10000, 
opt_constr = c("newpenalization", "constrained", "none"),
 opt_tuneParam = 10, opt_penfun = "mean", opt_ortho = 1, opt_earlystop = "no", 
 verbose = FALSE)

## S3 method for class 'fsdam'
 plot(x, which=c("mse", "history", "decoder.func", "scatterplot"),
 k=NULL, dim.1=NULL, dim.2=NULL, col.predict=2, ...)

Arguments

dat

data frame.

opt_numCode

number of components to extract

opt_seed

seed for torch

opt_model

n for newpenalization

opt_gpu

zero-based index of gpu to be used among all gpus. If negative, then no gpu is used

opt_k

number of nodes in the coding/decoding layers

opt_nEpochs

number of epochs for training

opt_constr

constraint string

opt_tuneParam

tuning parameter for monotonicity penalty

opt_penfun

penalize sum or mean

opt_ortho

tuning parameter for orthogonality penalty

opt_earlystop

whether to stop early

verbose

verbose

x

fsdam object

which

which

k

the component to plot

dim.1

index of the first variable

dim.2

index of the second variable

col.predict

color of the predicted curve when which = scatterplot

...

plotting arguments

Details

If the torch python package is not available, this function will stop.

To make sure the right python installation is used, run reticulate::use_python("/app/easybuild/software/Python/3.7.4-foss-2016b/bin/python") in R before running this function for the first time.

It is recommended that dat is scaled before calling fsdam.

References

Fong, Y, Xu, J. Multi-Stage Simultaneous Deep Autoencoder-based Monotone (MSS-DAM) Nonlinear Dimensionality Reduction Methods, Journal of Computational and Graphical Statistics, in press.

Examples


## Not run: 
    
fit=fsdam(hvtn505tier1[1:100,-1], opt_numCode=2, verbose=TRUE)
fit
plot(fit,which="mse")
plot(fit,which="history")


## End(Not run)

HVTN 505 Immune Correlates Tier 1 Dataset

Description

Contains eight immune response variables from the vaccine arm of the HVTN 505 trial.

Usage

data("hvtn505tier1")

Format

A data frame with 150 observations on the following 9 variables.

ptid: a character vector
CD8_ANYVRCENV_PolyfunctionalityScore_score: a numeric vector
IgGw28_env_mdw: a numeric vector
IgGw28_V1V2_mdw: a numeric vector
IgGw28_gp41_mdw: a numeric vector
ADCP1: a numeric vector
R2aConSgp140CFI: a numeric vector
IgAw28_env_mdw: a numeric vector
IgG3w28_env_mdw: a numeric vector

References

Fong, Y, Xu, J. Multi-Stage Simultaneous Deep Autoencoder-based Monotone (MSS-DAM) Nonlinear Dimensionality Reduction Methods, Journal of Computational and Graphical Statistics, in press.

Janes, H.E., Cohen, K.W., Frahm, N., De Rosa, S.C., Sanchez, B., Hural, J. et al (2017), Higher T-cell responses induced by DNA/rAd5 HIV-1 preventive vaccine are associated with lower HIV-1 infection risk in an efficacy trial, The Journal of infectious diseases, 215, 1376-1385.

Fong, Y., Shen, X., Ashley, V.C., Deal, A., Seaton, K.E., Yu, C. et al (2018), Vaccine-induced antibody responses modify the association between T-cell immune responses and HIV-1 infection risk in HVTN 505, The Journal of Infectious Diseases, 217, 1280–1288.

Neidich, S.D., Fong, Y., Shen, X., Ashley, V.C., Deal, A., Seaton, K.E. et al (2019), Antibody Fc-effector Functions and IgG3 Associates with Decreased HIV-1 Acquisition Risk, The Journal of Infectious Diseases, 129, 4838-4849.