Colabfoldv Database

This repository is intended to replicate only the `colabfold_search` functionality of the local ColabFold MSA generation pipeline, with an added protein database of `129944764` proteins tailored for viruses, especially phages. Please see `dataset_curation` for more details on how it was constructed.

For the full Colabfold functionality and up-to-date changes (and frankly anything outside of the use case presented below), please go to the [ColabFold repository](https://github.com/sokrypton/ColabFold).