Name Mode Size
R 040000
data 040000
inst 040000
man 040000
tests 040000
vignettes 040000
.Rbuildignore 100755 0 kb
.gitignore 100755 0 kb
DESCRIPTION 100644 1 kb
NAMESPACE 100755 3 kb
NEWS 100755 1 kb
README.Rmd 100755 3 kb
## Introduction [![Build Status](]( [![Downloads](]( [![InBioc](]( <br> MLSeq is an R/BIOCONDUCTOR package, which provides over 90 algorithms including support vector machines (SVM),random forest (RF), classification and regression trees (CART), Poisson and Negative Binomial Linear Discriminant Analysis (PLDA, NBLDA) and voom-based classifiers (voomDLDA, voomNSC, etc.) for the classification of sequencing data. MLSeq requires a count table as an input which contains the number of reads mapped to each transcript for each sample. This kind of count data can be obtained from RNA-Seq experiments, also from other sequencing experiments such as DNA or ChIP-sequencing. MLSeq includes both normalization (e.g deseq median ratio, trimmed mean of M values) and transformation (variance stabiliation transformation, regularized logarithmic transformation, etc.) techniques which can be performed through classification process. Although the main purpose of MLSeq is to classify samples using a count matrix from RNA-Sequencing data, some of the classifiers which are called sparse classifiers such as PLDA and voomNSC can be used to detect significant features. To install the MLSeq package in R: ```{r, eval = FALSE, message=FALSE, warning=FALSE} if (!requireNamespace("BiocManager", quietly=TRUE)) install.packages("BiocManager") BiocManager::install("MLSeq") ``` If you use MLSeq package in your research, please cite it as below: > Gokmen Zararsiz, Dincer Goksuluk, Selcuk Korkmaz, Vahap Eldem, Izzet Parug Duru, Ahmet Ozturk and Ahmet Ergun Karaagaoglu (2018). MLSeq: Machine Learning Interface for RNA-Seq Data. R package version 2.1.0. To get BibTeX entry for LaTeX users, type the following: ```{r, eval = FALSE} citation("MLSeq") ``` <br> Please contact us, if you have any questions or suggestions: <br> <br> ## News: #### Major changes in version 2.x.y * Functions are reconstructed using S4 systems and new classes such as `MLSeq`, `MLSeqMetaData` and `MLSeqModelInfo`. * New classifiers from [caret]( package are now available for MLSeq. These functions can be used for transformed continuous data using one of transformation techniques which are provided by MLSeq's classification algorithms. * A complete list of available classifiers can be viewed using `availableMethods()` and `printAvailableMethods()`. * New setter and getter functions are included. * Predictions are now evaluated usin generic function `predict(...)`. The older function `predictClassify(...)` can also be used for predictions. * For more details see package manuals.