Intro Run Help Download Related Links About


LncFinder
From CRAN From GitHub (Dev)

LncFinder has been included in CRAN (Comprehensive R Archive Network). This package can be installed simply by entering command install.packages("LncFinder") in R, and an appropriate version with all dependencies will be installed automatically.

If users try to identify transcripts with secondary structure information, software RNAfold from ViennaRNA Package is required.

Additional models for other species can be downloaded from GitHub.

Examples

Identify Sequences
result_1 <- LncFinder::lnc_finder(yourFile, SS.features = FALSE, format = "DNA", frequencies.file = "human", svm.model = "human")

result_2 <- LncFinder::lnc_finder(Sequences, SS.features = TRUE, format = "SS", frequencies.file = "mouse", svm.model = "mouse")

Build New Model
myFile <- LncFinder::make_frequencies(cds.seq, mRNA.seq, lncRNA.seq, SS.features = TRUE, cds.format = "DNA", lnc.format = "SS")

myModel <- LncFinder::build_model(mRNA.seq, lncRNA.seq = SS.Seq, frequencies.file = myFile, SS.features = TRUE, lncRNA.format = "SS", mRNA.format = "SS", parallel.cores = -1, folds.num = 10)

Compute/Import Secondary Structure Information
SS_Seq_1 <- LncFinder::run_RNAfold(Seq, RNAfold.path = "RNAfold", parallel.cores = 2)

SS_Seq_2 <- LncFinder::read_SS(oneFile.loc = yourFile, separateFile = FALSE, withMFE = TRUE)

Perform SVM Parameter Tuning
tuneSVM <- LncFinder::svm_tune(dataset = Dataset, positive.class = "NonCoding", folds.num = 5, seed = 1, gamma.range = (2^seq(-5, -1, 0)), cost.range = (2^seq(0, 5, 1)), return.model = TRUE, parallel.cores = -1)

Please refer to our manual (pdf) for detailed information.

Dataset Database Composition
Human (Homo sapiens) A GENCODE1 12,190 lncRNA; 12,190 mRNA
Human (Homo sapiens) B GENCODE1 8,000 lncRNA; 8,000 mRNA (Training set)
2,500 lncRNA; 2,500 mRNA (Test set)
Mouse (Mus musculus) GENCODE1,2 4,200 lncRNA; 4,200 mRNA (Training set)
1,800 lncRNA; 1,800 mRNA (Test set)
Wheat (Triticum aestivum) Ensembl 4,000 lncRNA; 4,000 mRNA (Training set)
2,000 lncRNA; 2,000 mRNA (Test set)
Zebrafish (Danio rerio) Ensembl 4,000 lncRNA; 4,000 mRNA
Chicken (Gallus gallus) Ensembl 8,000 lncRNA; 8,000 mRNA
Caenorhabditis elegans Ensembl 1,645 lncRNA; 1,645 mRNA
1 Sequences are obtained from LncRNA-ID's datasets which are collected from GENCODE.
2 Several lncRNA sequences are selected from LncRNA-ID's dataset "M2" which is obtained from experimental verified dataset.
Download Datasets