evo-design / evo

Biological foundation modeling from molecular to genome scale
Apache License 2.0
874 stars 99 forks source link

Prompt for virus and plasmid generation #37

Closed apcamargo closed 2 weeks ago

apcamargo commented 4 months ago

The example notebook show the utilization of a Greengenes-style lineage as a prompt for generation. However, it does not address the process of prompting for non-chromosomal sequences. For viruses, was the ICTV taxonomy from IMG/VR used during training? Additionally, concerning plasmids, if their host lineage was utilized, how can I direct Evo to generate a plasmid?

brianhie commented 2 weeks ago

For viruses, was the ICTV taxonomy from IMG/VR used during training?

This is correct!

Additionally, concerning plasmids, if their host lineage was utilized, how can I direct Evo to generate a plasmid?

During the finetuning phase, there was no species level prompt prepended to the plasmids.