Mao, A.; Ji, H. J.; Haas, B.; Salzberg, S.; Sommer, M. J.

The transcriptome encompasses all RNA transcripts in eukaryotic cells, orchestrating gene expression and regulating cellular function, development, and adaptation. Identifying open reading frames (ORFs) in transcripts is a critical step in transcriptome analysis. We introduce TD2, a new tool for ab initio annotation of protein-coding ORFs in transcripts. We find TD2 to be sensitive and precise when compared to other state-of-the-art tools in reference transcripts and transcriptome assemblies from a diverse array of eukaryotes. TD2 is available at https://github.com/Markusjsommer/TD2. The project is open-source, developed in Python with PyTorch, and is freely available to all academic, government, and commercial users under the MIT license.