Association·arcadia

Balancing curation of AFDB reduces accessible protein universe size

Claim that intentional curation and balancing of the AFDB dataset—adjusting for taxonomic biases—greatly reduces the accessible size of the known protein universe.

Confidence
80%
active

Evidence Quote

“Data balancing greatly reduces the accessible protein universe. Curation of the AFDB would impact the size of the known protein universe.”

Relationship

Taxonomic completeness reduces Protein diversity

Arguments

Taxonomic completenesssubject
Protein diversityobject

Connections (2)

Taxonomic bias reasoning for AFDB and model outcomesInferenceChain
Petabase-scale sequence alignment increases viral discoveryAssociation

Evidence

“Evidence of large-scale clustering of predicted protein structures, showing approaches to cluster the known protein universe, by Barrio-Hernandez et al. (2023).”

Barrio-Hernandez I et al. (2023). Clustering predicted structures at the scale of the known protein universe doi:10.1038/s41586-023-06510-w ↗