what data and files are needed for train step

[ds-gene104]

I ran funannotate for genome annotation and accomplished the first two steps, clean and mask, now I have the masked file and need to download the SRA datasets through prefetch and fasterq-dump... apart from this what else data do I need and how could I download those files in my EC2...

could you share any picture that how the downloaded datasets could look after being got them through 'prefetch' command

also if there is any other method to do so then please mention that as well

thank you