Quartz 4

Home

❯

notes

❯

AlphaFold3 inference benefits more from phylogenetically diverse MSAs than deep redundant MSAs

AlphaFold3 inference benefits more from phylogenetically diverse MSAs than deep redundant MSAs

Created Jul 19, 2026Modified Jul 20, 2026

  • alphafold3

Summary

AlphaFold3 inference shows improved performance when using phylogenetically diverse MSAs versus deep alignments dominated by near-identical sequences (1).

See also

  • Diverse MSAs are better for training structure prediction neural networks than random MSAs
1.
Feldman J, Skolnick J. AlphaInterp: Mechanistic Interpretability of AlphaFold 3 Reveals How Evolutionary Information Shapes Protein Structure Prediction. openRxiv; 2026. Available from: https://doi.org/10.64898/2026.04.22.720175

Graph View

Backlinks

  • Query-conditioned outer product

Created with Quartz v4.5.2 © 2026

  • GitHub
  • Discord Community