README.md

In EnMCB: Predicting Disease Progression Based on Methylation Correlated Blocks using Ensemble Models

EnMCB

Package: EnMCB

Type: Package

Title: Predicting Disease Progression Based on Methylation Correlated Blocks using Ensemble Models

Version: 0.2.0

Author: Xin Yu

Maintainer: Xin Yu [e-mail] [e-mail]

Description: This package is designed to help you to create the methylation correlated blocks using methylation profiles. A stacked ensemble of machine learning models, which combined the Cox regression, support vector regression and elastic-net regression model, can be constructed using this package. You also can choose one of them to build DNA methylation signatures associated with disease progression.

License: GPL-3

Citation: Xin Yu et al. 2019 Predicting disease progression in lung adenocarcinoma patients based on methylation correlated blocks using ensemble machine learning classifiers (under review)

Note: This package is still under developing. Some of the functions may change.

Followings are brief insturctions for using this package:

You can install and test our package by downloading source package.

First, you need a methylation data set, currently only most common platform 'Illumina Infinium Human Methylation 450K' is supported.

You can use your own datasets:

eset_met<-some_methylation_datamatrix

or use our demo data.

data(demo_set)

Then, you can automatically run following:

library(SummarizedExperiment)

res<-IdentifyMCB(assays(demo_set)[[1]])

You can extract the MCB information,

MCB<-res$MCBinformation

and select some of MCBs for further modeling.

MCB<-MCB[MCB[,"CpGs_num"]>2,]

In order to build models, one may run following:

# sample the dataset into training set and testing set
trainingset<-colnames(demo_set) %in% sample(colnames(demo_set),0.6*length(colnames(demo_set)))

testingset<-!trainingset

#build the models

models<-metricMCB(MCB,
                    training_set=methylation_dataset[,training_set],
                    Surv=survival_data)

#select the best
onemodel<-models$best_cox_model

Then, you can predict the risk by the model you build:

predict(onemodel,methylation_dataset[,testing_set])

In order to build ensemble model, one may run following:

# You can choose one of MCBs:
select_single_one=1

em<-ensemble_model(MCB[select_single_one,],
                    training_set=methylation_dataset[,training_set],
                    Surv=survival_data)

Note that this function only can be used for single MCB only, otherwise the precessing time could be very long.

Then, you can predict the risk by the model you build:

ensemble_prediction(ensemble_model = em,
                    predition_data = methylation_dataset[,testing_set])

For detailed information, you can find at our references.

EnMCB documentation built on Dec. 22, 2020, 2 a.m.