@article{SharanFoerstnerEulalioetal.2017,
  author    = {Sharan, Malvika and F{\"o}rstner, Konrad U. and Eulalio, Ana and Vogel, J{\"o}rg},
  title     = {APRICOT: an integrated computational pipeline for the sequence-based identification and characterization of RNA-binding proteins},
  series = {Nucleic Acids Research},
  volume    = {45},
  journal   = {Nucleic Acids Research},
  number    = {11},
  doi       = {10.1093/nar/gkx137},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-157963},
  pages     = {e96},
  year      = {2017},
  abstract  = {RNA-binding proteins (RBPs) have been established as core components of several post-transcriptional gene regulation mechanisms. Experimental techniques such as cross-linking and co-immunoprecipitation have enabled the identification of RBPs, RNA-binding domains (RBDs) and their regulatory roles in the eukaryotic species such as human and yeast in large-scale. In contrast, our knowledge of the number and potential diversity of RBPs in bacteria is poorer due to the technical challenges associated with the existing global screening approaches. We introduce APRICOT, a computational pipeline for the sequence-based identification and characterization of proteins using RBDs known from experimental studies. The pipeline identifies functional motifs in protein sequences using position-specific scoring matrices and Hidden Markov Models of the functional domains and statistically scores them based on a series of sequence-based features. Subsequently, APRICOT identifies putative RBPs and characterizes them by several biological properties. Here we demonstrate the application and adaptability of the pipeline on large-scale protein sets, including the bacterial proteome of Escherichia coli. APRICOT showed better performance on various datasets compared to other existing tools for the sequence-based prediction of RBPs by achieving an average sensitivity and specificity of 0.90 and 0.91 respectively. The command-line tool and its documentation are available at https://pypi.python.org/pypi/bio-apricot.},
  language  = {en}
}