COME

COME is a software tool that identifies and characterizes novel long non-coding RNAs (lncRNAs) from RNA sequencing data. It utilizes a decompose-compose method to integrate multiple sequence-derived and experiment-based features, which enhances its accuracy and robustness compared to other well-known tools. COME not only predicts lncRNA transcripts but also provides various lines of supporting evidence for each predicted lncRNA, a feature not offered by other tools.

One key finding from using COME is that a subgroup of lncRNAs, classified by their conserved local RNA secondary structure, was highly enriched in a well-validated database (lncRNAdb). Furthermore, the conserved structural domains on lncRNAs were found to have a better chance of interacting with RNA binding proteins based on recent eCLIP-seq data in humans, suggesting their potential regulatory roles.