Whole transcriptome sequencing (RNA-seq) has become a standard for cataloguing and monitoring RNA populations. One of the main bottlenecks, however, is to correctly identify the different classes of RNAs among the plethora of reconstructed transcripts, particularly those that will be translated (mRNAs) from the class of long non-coding RNAs (lncRNAs). Here, we present FEELnc (FlExible Extraction of LncRNAs), an alignment-free program that accurately annotates lncRNAs based on a Random Forest model trained with general features such as multi k-mer frequencies and relaxed open reading frames. Benchmarking versus five state-of-the-art tools shows that FEELnc achieves similar or better classification performance on GENCODE and NONCODE data sets. The program also provides specific modules that enable the user to fine-tune classification accuracy, to formalize the annotation of lncRNA classes and to identify lncRNAs even in the absence of a training set of non-coding RNAs. We used FEELnc on a real data set comprising 20 canine RNA-seq samples produced by the European LUPA consortium to substantially expand the canine genome annotation to include 10 374 novel lncRNAs and 58 640 mRNA transcripts. FEELnc moves beyond conventional coding potential classifiers by providing a standardized and complete solution for annotating lncRNAs and is freely available at https://github.com/tderrien/FEELnc.

Spontaneously occurring melanomas are frequent in dogs. They appear at the same localizations as in humans, i.e. skin, mucosal sites, nail matrix and eyes. They display variable behaviors: tumors at oral localizations are more frequent and aggressive than at other anatomical sites. Interestingly, dog melanomas are associated with strong breed predispositions and overrepresentation of black-coated dogs. Epidemiological analysis of 2350 affected dogs showed that poodles are at high risk of developing oral melanoma, while schnauzers or Beauce shepherds mostly developped cutaneous melanoma. Clinical and histopathological analyses were performed on a cohort of 153 cases with a 4-yr follow-up. Histopathological characterization showed that most canine tumors are intradermal and homologous to human rare morphological melanomas types - 'nevocytoid type' and 'animal type'-. Tumor cDNA sequencing data, obtained from 95 dogs for six genes, relevant to human melanoma classification, detected somatic mutations in oral melanoma, in NRAS and PTEN genes, at human hotspot sites, but not in BRAF. Altogether, these findings support the relevance of the dog model for comparative oncology of melanomas, especially for the elucidation of non-UV induced pathways.