For genome annotation

[starskyzheng]

Dear Team,

I express my gratitude for your excellent work.

I am currently working on annotating the rice genome transcriptome. I noticed that Nucleotide Transformer can predict exon and CDS regions from genome sequences. I was wondering if there is a method to generate GFF3 files containing gene, mRNA, exon and CDS annotations?

Thank you very much for your attention.

Kind Regards, Zeyu Zheng

[xiekunwhy]

Also want to know if SegmentNT can use for gene structure annotation, and how if it can.

[JavierMenRev]

Hi @starskyzheng and @xiekunwhy , We have not yet implemented that feature into SegmentNT, but in theory, it should be possible to come up with a way to leverage the probabilities and annotate your genome of interest. We will keep that in mind for future releases of the model.