Email updates

Keep up to date with the latest news and content from BMC Genomics and BioMed Central.

Open Access Highly Accessed Research article

Prediction and classification of ncRNAs using structural information

Bharat Panwar, Amit Arora* and Gajendra PS Raghava*

Author Affiliations

Bioinformatics Centre, Institute of Microbial Technology (CSIR), Sector 39A, Chandigarh, India

For all author emails, please log on.

BMC Genomics 2014, 15:127  doi:10.1186/1471-2164-15-127

Published: 13 February 2014

Additional files

Additional file 1: Figure S1:

Average percent mono-nucleotide and di-nucleotide compositions of non-coding and coding-RNAs. Figure S2. Comparative average percent mono-nucleotides compositions (MNC) of different non-coding classes. Figure S3. Comparative average percent di-nucleotides compositions (DNC) of different non-coding RNA classes. Figure S4. Comparative average percent tri-nucleotides compositions (TNC) of different non-coding RNA classes for the 20% non-redundant dataset. Figure S5. Confusion matrix for 18 different classes of non-coding RNAs using RandomForest algorithm. Figure S6. Confusion matrix for 18 different classes of non-coding RNAs using MultilayerPerceptron algorithm. Figure S7. Confusion matrix for 18 different classes of non-coding RNAs using SMO (RBF kernel) algorithm. Table S1. SVM-based prediction performances (at all threshold levels) of mono-nucleotide composition (MNC) approach for the discrimination between non-coding and coding RNAs. Table S2. SVM-based prediction performances (at all threshold levels) of di-nucleotide composition (DNC) approach for the discrimination between non-coding and coding-RNAs. Table S3. SVM-based prediction performances (at all threshold levels) of tri-nucleotide composition (TNC) approach for the discrimination between non-coding and coding-RNAs. Table S4. SVM-based prediction performances (at all threshold levels) of tetra-nucleotide composition (TTNC) approach for the discrimination between non-coding and coding-RNAs. Table S5. SVM-based prediction performances (at all threshold levels) of penta-nucleotide composition (PNC) approach for the discrimination between non-coding and coding-RNAs. Table S6. SVM-based prediction performances (at all threshold levels) of Hybrid approach for the discrimination between non-coding and coding-RNAs. Table S7. Average length and prediction performance (sensitivity) of different ncRNA classes. Table S8. Performance of different gene-calling programs and RNAcon on the CONC dataset. Table S9. Comparison of Rfam-based covariance models with RNAcon using non-similar sequences between Rfam 9.0 and 11.0 release. Table S10. Description of the different graph properties and values of the graph properties of predicted RNA secondary structure of an example sequence (As shown in the Figure  5).

Format: DOCX Size: 3.8MB Download file

Open Data