Yo Akiyama

yoakiyama.bsky.social

21 July 2026 21:27

Bonus: this project actually started with the goal of understanding how structure prediction models extract structural information from MSAs, but I may have lost the plot… Please check out @sokrypton.org's X thread (and Methods S1 of the manuscript) to learn more x.com/sokrypton/st... (10/10)

Yo Akiyama

yoakiyama.bsky.social

21 July 2026 21:27

We're excited to see how the community will continue to use MSA Pairformer as a tool to study and engineer biology. Please reach out if there's anything we can help out with! Credit to Olivia Tang for this cool illustration of our project👩‍🎨 (9/10)

Yo Akiyama

yoakiyama.bsky.social

21 July 2026 21:27

Excited to share our now published paper @cp-cell.bsky.social highlighting advances in modeling the evolution of protein-protein interactions with MSA Pairformer. Big thanks to Zhidian Zhang, Olivia Tang, @eunbelivable.bsky.social @milot.bsky.social @martinsteinegger.bsky.social and @sokrypton.org!

Umberto Lupo

umbislupo.bsky.social

15 January 2026 13:55

It turns out that masking template AAs in "AF2Rank-Unmasked" may not be the optimal choice for ab-ag complexes. This is a much trickier modality for AFM—it is systematically less capable & confident there than on many PPIs seen in protein design papers. So, we restore the template AAs! [7/n]

Kresten Lindorff-Larsen

lindorfflarsen.bsky.social

23 December 2025 22:36

I agree, which is why I initially asked whether you think the EBM represents an (internal) energy or a free energy. Your figures are suggestive of it modelling free energy landscapes including for substantially non-native structures. I am curious how far away from the ground state this breaks down