@article{Videm_Rose_Costa-Block_effic_clust-2014,
author = {Videm, Pavankumar and Rose, Dominic and Costa, Fabrizio and 
          Backofen, Rolf},
title = {{BlockClust}: efficient clustering and classification of 
         non-coding {RNAs} from short read {RNA}-seq profiles},
journal = {Bioinformatics},
year = {2014},
doi = {10.1093/bioinformatics/btu270},
volume = {30},
user = {kousik},
pmid = {24931994},
pages = {i274-i282},
number = {12},
issn = {1367-4803},
abstract = {SUMMARY: Non-coding RNAs (ncRNAs) play a vital role in many 
            cellular processes such as RNA splicing, translation, gene 
            regulation. However the vast majority of ncRNAs still have 
            no functional annotation. One prominent approach for 
            putative function assignment is clustering of transcripts 
            according to sequence and secondary structure. However 
            sequence information is changed by post-transcriptional 
            modifications, and secondary structure is only a proxy for 
            the true 3D conformation of the RNA polymer. A different 
            type of information that does not suffer from these issues 
            and that can be used for the detection of RNA classes, is 
            the pattern of processing and its traces in small RNA-seq 
            reads data. Here we introduce BlockClust, an efficient 
            approach to detect transcripts with similar processing 
            patterns. We propose a novel way to encode expression 
            profiles in compact discrete structures, which can then be 
            processed using fast graph-kernel techniques. We perform 
            both unsupervised clustering and develop family specific 
            discriminative models; finally we show how the proposed 
            approach is scalable, accurate and robust across different 
            organisms, tissues and cell lines. Availability: The whole 
            BlockClust galaxy workflow including all tool dependencies 
            is available at 
            http://toolshed.g2.bx.psu.edu/view/rnateam/blockclust_workflow. 
            CONTACT: backofen@informatik.uni-freiburg.de; 
            costa@informatik.uni-freiburg.de Supplementary information: 
            Supplementary data are available at Bioinformatics online.}
}