Tailored machine learning models for functional RNA detection in genome-wide screens

The prediction of noncoding RNA and protein coding genetic loci has received
  considerable attention in comparative genomics aiming in particular
  at the identification of properties of nucleotide sequences that are
  informative of their biological role in the cell. We present here a
  software framework for the alignment-based training, evaluation and
  application of machine learning models with user-defined
  parameters. Instead of focusing on the one-size-fits-all approach of
  pervasive \is annotation pipelines, we offer a framework for the
  structured generation and evaluation of models based on arbitrary
  features and input data, focusing on stable and explainable results.
  Furthermore, we showcase the usage of our software package in a
  full-genome screen of Drosophila melanogaster and evaluate
  our results against the well-known but much less flexible program
  RNAz.