| Title: | Classification of RNA Sequences using Complex Network and Information Theory |
| Version: | 0.99.6 |
| Description: | It makes the creation of networks from sequences of RNA, with this is done the abstraction of characteristics of these networks with a methodology of maximum entropy for the purpose of making a classification between the classes of the sequences. There are two data present in the 'BASiNET' package, "mRNA", and "ncRNA" with 10 sequences. These sequences were taken from the data set used in the article (LI, Aimin; ZHANG, Junying; ZHOU, Zhongyin, 2014) <doi:10.1186/1471-2105-15-311>, these sequences are used to run examples. |
| License: | GPL-3 |
| Encoding: | UTF-8 |
| Depends: | R (≥ 4.1.0) |
| Imports: | igraph, Biostrings, randomForest |
| biocViews: | Software, BiologicalQuestion, GenePrediction, FunctionalPrediction, Network, Classification |
| RoxygenNote: | 7.2.0 |
| Suggests: | knitr, rmarkdown |
| VignetteBuilder: | knitr |
| NeedsCompilation: | no |
| Packaged: | 2023-08-16 16:33:45 UTC; matheus |
| Author: | Murilo Montanini Breve
 [aut],
Matheus Henrique Pimenta-Zanon
[aut],
Fabricio Martins Lopes
[aut, cre] |
| Maintainer: | Fabricio Martins Lopes <fabricio@utfpr.edu.br> |
| Repository: | CRAN |
| Date/Publication: | 2023-08-16 18:24:35 UTC |
Performs the classification methodology using complex network and entropy theories
Description
Given three or two distinct data sets, one of mRNA, one of lncRNA and one of sncRNA. The classification of the data is done from the structure of the networks formed by the sequences, that is filtered by an entropy methodology. After this is done, the classification starts.
Usage
classify(
mRNA,
lncRNA,
sncRNA = NULL,
trainingResult,
save_dataframe = NULL,
save_model = NULL,
predict_with_model = NULL
)
Arguments
mRNA |
Directory where the file .FASTA lies with the mRNA sequences |
lncRNA |
Directory where the file .FASTA lies with the lncRNA sequences |
sncRNA |
Directory where the file .FASTA lies with the sncRNA sequences (optional) |
trainingResult |
The result of the training, (three or two matrices) |
save_dataframe |
save when set, this parameter saves a .csv file with the features in the current directory. No file is created by default. |
save_model |
save when set, this parameter saves a .rds file with the model in the current directory. No file is created by default. |
predict_with_model |
predict the input sequences with the previously generated model. |
Value
Results
Author(s)
Murilo Montanini Breve
Examples
library(BASiNETEntropy)
arqSeqMRNA <- system.file("extdata", "mRNA.fasta",package = "BASiNETEntropy")
arqSeqLNCRNA <- system.file("extdata", "ncRNA.fasta", package = "BASiNETEntropy")
load(system.file("extdata", "trainingResult.RData", package = "BASiNETEntropy"))
r_classify <- classify(mRNA=arqSeqMRNA, lncRNA=arqSeqLNCRNA, trainingResult = trainingResult)
Creates an untargeted graph from a biological sequence
Description
A function that from a biological sequence generates a graph not addressed having as words vertices, this being able to have its size parameter set by the' word 'parameter. The connections between words depend of the' step 'parameter that indicates the next connection to be formed
Usage
createedges(sequence, word = 3, step = 1)
Arguments
sequence |
It is a vector that represents the sequence |
word |
This integer parameter decides the size of the word that will be formed |
step |
It is the integer parameter that decides the step that will be taken to make a new connection |
Value
Returns the array used to creates the edge list
Author(s)
Murilo Montanini Breve
Creates a feature matrix using complex network topological measures
Description
A function that from the complex network topological measures create the feature matrix.
Usage
creatingDataframe(measures, tamM, tamLNC, tamSNC)
Arguments
measures |
The complex network topological measures |
tamM |
mRNA sequence size |
tamLNC |
lncRNA sequence size |
tamSNC |
snRNA sequence size |
Value
Returns the feature matrix in scale 0-1
Author(s)
Murilo Montanini Breve
Creates an entropy curve
Description
A function that from the entropy measures and threshold creates an entropy curve.
Usage
curveofentropy(H, threshold)
Arguments
H |
The 'training' return for the entropy measures |
threshold |
The 'training' return for the threshold |
Value
Returns a entropy curve
Author(s)
Murilo Montanini Breve
Calculates the entropy
Description
A function that calculates the entropy
Usage
entropy(x)
Arguments
x |
The probabilities P0 and P1 |
Value
Returns the entropy
Author(s)
Murilo Montanini Breve
Filters the edges
Description
A function that filters the edges after the maximum entropy is obtained
Usage
filtering(edgestoselect, edgestofilter)
Arguments
edgestoselect |
The selected edges |
edgestofilter |
The edges used to filter |
Value
Returns the filtered edges
Author(s)
Murilo Montanini Breve
Compares the matrices
Description
A function that compares the matrices 'trainingResult' and the adjacency matrix to produce a filtered adjacency matrix.
Usage
matrixmultiplication(data, histodata)
Arguments
data |
Adjacency matrix |
histodata |
'trainingResult' data |
Value
Returns the filtered adjacency matrix
Author(s)
Murilo Montanini Breve
Calculates the maximum entropy
Description
A function that calculates the maximum entropy
Usage
maxentropy(histogram)
Arguments
histogram |
The histogram (used in 'training' function) |
Value
Returns the maximum entropy
Author(s)
Murilo Montanini Breve
Rescales the results between values from 0 to 1
Description
Given the results the data is rescaled for values between 0 and 1, so that the length of the sequences does not influence the results. The rescaling of the sequences are made separately
Usage
preprocessing(datah, tamM, tamLNC, tamSNC)
Arguments
datah |
Array with results numerics |
tamM |
Integer number of mRNA sequences |
tamLNC |
Integer number of lncRNA sequences |
tamSNC |
Integer number of sncRNA sequences |
Value
Returns the array with the rescaled values
Author(s)
Murilo Montanini Breve
Selects the edges of the adjacency matrix
Description
A function that selects the edges of the adjacency matrix
Usage
selectingEdges(MAX, data)
Arguments
MAX |
The maximum entropy |
data |
The adjacency matrix |
Value
Returns the selected edges of the adjacency matrix
Author(s)
Murilo Montanini Breve
Trains the algorithm to select the edges that maximize the entropy
Description
A function that trains the algorithm to select the edges that maximize the entropy
Usage
training(mRNA, lncRNA, sncRNA = NULL)
Arguments
mRNA |
Directory where the file .FASTA lies with the mRNA sequences |
lncRNA |
Directory where the file .FASTA lies with the lncRNA sequences |
sncRNA |
Directory where the file .FASTA lies with the sncRNA sequences (optional) |
Value
Returns the edge lists and the 'curveofentropy' function inputs
Author(s)
Murilo Montanini Breve