New preprint from our group! We propose SHAPES, a set of metrics to quantify the distributional coverage of generative models of protein structures with embeddings at different structural hierarchies and quantify undersampling / extrapolation behaviors. - ThreadSky

About ThreadSky

possuhuanglab.bsky.social • 42 days ago

New preprint from our group! We propose SHAPES, a set of metrics to quantify the distributional coverage of generative models of protein structures with embeddings at different structural hierarchies and quantify undersampling / extrapolation behaviors.

Comments

possuhuanglab.bsky.social•42 days ago

Inspired by the FPD metric in EvoDiff for protein sequence distributions, we compute Fréchet distance using protein structure embeddings, also subsetted to designable and non-designable samples (FPD-D and FPD-ND).

possuhuanglab.bsky.social•42 days ago

One consequence of unbiased sampling of protein structure space is a higher likelihood of finding TERtiary Motifs (TERMs) which involve complex loops, with implications for functional protein design (see Figure 5 legend for group labels).

possuhuanglab.bsky.social•42 days ago

Our supplement has many additional figures of the rasterized protein structure space, stratified by designable and not designable and spatially organized by ESM3 and ProtDomainSegmentor embeddings.

possuhuanglab.bsky.social•42 days ago

Preprint: https://www.biorxiv.org/content/10.1101/2025.01.09.632260v1
Code: https://github.com/ProteinDesignLab/protein_shapes
Dataset: https://zenodo.org/records/14583581

Posting Rules

Be respectful to others
No spam or self-promotion
Stay on topic
Follow Bluesky's terms of service

Comments

Posting Rules

Reply