Protein language models (PLMs) have transformed our ability to learn from evolutionary sequence space, but protein engineering ultimately asks a different question: not what evolution selected, but what we should build next. Zero-shot likelihoods therefore provide useful, but not universal, measures of fitness and can...
Maurice Brenner, Julius Schlensok, A. Plaikner et al.· bioRxiv· 0 citations
ContrasTED uses CATH-supervised center-contrastive learning to project structure-aware embeddings into a domain-level metric space for nearest-centroid superfamily assignment, which separates superfamilies while retaining structural information below 20% sequence identity.
David Miller, Nicola Bordin, Janusan Jeyananthan et al.· bioRxiv· 0 citations
It is found that reverse folding algorithms are unable to energetically minimize evolutionary conserved frustration at specific residues, even when detrimental to overall structural stability, and it is proposed that these frustration hotspots act as architectural spandrels, inherent physical constraints of the fold th...
Miriam Poley-Gil, Miguel Fernández-Martín, Alin Banka et al.· bioRxiv· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
