demo_dataset

This dataset contains the features of 20 lncRNA sequences and 20 protein-coding
sequences.

Long non-coding RNAs identification and analysis. Default models are trained with human, mouse and wheat datasets by employing SVM. Features are based on intrinsic composition of sequence, EIIP value (electron-ion interaction pseudopotential), and secondary structure. This package can also extract other classic features and build new classifiers. Reference: Han SY., Liang YC., Li Y., et al. (2018) <doi:10.1093/bib/bby065>.

Han Siyu

LncFinder

LncRNA Identification and Analysis Using Heterologous Features

Siyu HAN

Ying LI

Yanchun LIANG

demo_dataset function

A data frame with 40 rows and 20 variables:<dl>
 <dt>Label</dt>
<dd>the class of the sequences</dd> <dt>ORF.Max.Len</dt>
<dd>the length of the longest ORF</dd> <dt>ORF.Max.Cov</dt>
<dd>the coverage of the longest ORF</dd> <dt>Seq.lnc.Dist</dt>
<dd>Log-Distance.lncRNA</dd> <dt>Seq.pct.Dist</dt>
<dd>Log-Distance.protein-coding transcripts</dd> <dt>Seq.Dist.Ratio</dt>
<dd>Distance-Ratio.sequence</dd> <dt>Signal.Peak</dt>
<dd>Signal as 1/3 position</dd> <dt>SNR</dt>
<dd>Signal to noise ratio</dd> <dt>Signal.Min</dt>
<dd>the minimum value of the top 10% power spectrum</dd> <dt>Signal.Q1</dt>
<dd>the quantile Q1 of the top 10% power spectrum</dd> <dt>Signal.Q2</dt>
<dd>the quantile Q2 of the top 10% power spectrum</dd> <dt>Signal.Max</dt>
<dd>the maximum value of the top 10% power spectrum</dd> <dt>Dot_lnc.dist</dt>
<dd>Log-Distance.acguD.lncRNA</dd> <dt>Dot_pct.dist</dt>
<dd>Log-Distance.acguD.protein-coding transcripts</dd> <dt>Dot_Dist.Ratio</dt>
<dd>Distance-Ratio.acguD</dd> <dt>SS.lnc.dist</dt>
<dd>Log-Distance.acgu-ACGU.lncRNA</dd> <dt>SS.pct.dist</dt>
<dd>Log-Distance.acgu-ACGU.protein-coding transcripts</dd> <dt>SS.Dist.Ratio</dt>
<dd>Distance-Ratio.acgu-ACGU</dd> <dt>MFE</dt>
<dd>Minimum free energy</dd> <dt>UP.PCT</dt>
<dd>Percentage of Unpair-Pair</dd>
</dl>

Format

A demo of dataset — demo_dataset

A data frame with 40 rows and 20 variables:<dl>
 <dt>Label</dt>
<dd>the class of the sequences</dd>

 <dt>ORF.Max.Len</dt>
<dd>the length of the longest ORF</dd>

 <dt>ORF.Max.Cov</dt>
<dd>the coverage of the longest ORF</dd>

 <dt>Seq.lnc.Dist</dt>
<dd>Log-Distance.lncRNA</dd>

 <dt>Seq.pct.Dist</dt>
<dd>Log-Distance.protein-coding transcripts</dd>

 <dt>Seq.Dist.Ratio</dt>
<dd>Distance-Ratio.sequence</dd>

 <dt>Signal.Peak</dt>
<dd>Signal as 1/3 position</dd>

 <dt>SNR</dt>
<dd>Signal to noise ratio</dd>

 <dt>Signal.Min</dt>
<dd>the minimum value of the top 10% power spectrum</dd>

 <dt>Signal.Q1</dt>
<dd>the quantile Q1 of the top 10% power spectrum</dd>

 <dt>Signal.Q2</dt>
<dd>the quantile Q2 of the top 10% power spectrum</dd>

 <dt>Signal.Max</dt>
<dd>the maximum value of the top 10% power spectrum</dd>

 <dt>Dot_lnc.dist</dt>
<dd>Log-Distance.acguD.lncRNA</dd>

 <dt>Dot_pct.dist</dt>
<dd>Log-Distance.acguD.protein-coding transcripts</dd>

 <dt>Dot_Dist.Ratio</dt>
<dd>Distance-Ratio.acguD</dd>

 <dt>SS.lnc.dist</dt>
<dd>Log-Distance.acgu-ACGU.lncRNA</dd>

 <dt>SS.pct.dist</dt>
<dd>Log-Distance.acgu-ACGU.protein-coding transcripts</dd>

 <dt>SS.Dist.Ratio</dt>
<dd>Distance-Ratio.acgu-ACGU</dd>

 <dt>MFE</dt>
<dd>Minimum free energy</dd>

 <dt>UP.PCT</dt>
<dd>Percentage of Unpair-Pair</dd>


</dl>

demo_dataset: A demo of dataset

Description

Usage

Arguments

Format