Sign inGet started
Paper · arXiv

ConforNets: Latents-Based Conformational Control in OpenFold3

Models from the AlphaFold (AF) family reliably predict one dominant conformation for most well-ordered proteins but struggle to capture biologically relevant alternate states. Several efforts have focused on eliciting greater conformational variability through ad hoc inference-time perturbations of AF models or their inputs. Despite their progress, these approaches remain inefficient and fail to consistently recover major conformational modes. Here, we investigate both the optimal location and manner-of-operation for perturbing latent representations in the AF3 architecture. We distill our findings in ConforNets: channel-wise affine transforms of the pre-Pairformer pair latents. Unlike pr...

AuthorsMinji Lee, Colin Kalicki, Minkyu Jeon et al.
Primary categoryq-bio.BM
Published20 April 2026
Last updated at source20 April 2026
q-bio.BMcs.LG
Embed this entry
<iframe src="https://silytics.si/embed/item/9e07b19f-f634-4a33-8c5b-3296b61e790c" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.