How Do Co-folding Models Organize Structural Information?

Minha Park, Shinwoo Kim, Seokhyun Moon, Hyeongwoo Kim, Gyuho Jeon, Woo Youn Kim

Keywords: Co-folding, Pairformer, Biomolecular Structure, Induced fit

TL;DR: We reveal that Boltz-1 separates atomic detail, chain geometry, and molecular arrangement across distinct representation types, while diffusion resolves intra– and inter-molecular representational conflicts.

Abstract:

Co-folding models accurately predict biomolecular complexes, but how their internal representations support joint structure prediction remains unclear.
We analyze the Boltz-1 trunk by decomposing its pair representation into intra-chain and inter-chain blocks and applying ablation, layer-wise representation geometry, and activation patching.
Our results show that structural information is distributed across three streams: the single representation carries token-internal atomic detail, the intra-chain pair representation encodes chain-level geometry, and the inter-chain pair representation controls relative molecular arrangement.
Across the trunk depth, representations follow a Mix–Compress–Refine trajectory, while linear probes reveal that intra-chain distance content is largely supplied by MSA preconditioning and inter-chain distance content is constructed progressively across Pairformer layers at each recycle.
Apo–holo patching further shows that ligand-induced backbone changes are not fully resolved before diffusion; instead, the diffusion module reconciles partially inconsistent intra- and inter-chain constraints.
These findings provide a mechanistic view of how co-folding trunks organize structural information and suggest more partition-aware designs for future biomolecular structure prediction models.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 230