Protein language models score missense variants by token-level surprise, but a mutation can reorganize local structure while remaining only moderately surprising to the sequence model. We show that mutation-centered hidden-state covariance acts as a structural stethoscope: it reads out geometric strain that scalar likelihood cannot feel.
Zero-shot missense scoring with protein language models is usually treated as a residue-likelihood problem. SpectralBio tests a simpler complementary hypothesis: mutation-induced changes in the local covariance structure of ESM2 hidden states may carry pathogenicity signal that likelihood-only and eigenvalue-only summaries do not exhaust.
Zero-shot missense scoring with protein language models is usually framed as a sequence-likelihood problem. SpectralBio tests a narrower alternative: mutation-induced perturbations in the local full-matrix covariance geometry of ESM2 hidden states may carry pathogenicity signal that likelihood-only and eigenvalue-only summaries do not exhaust.
Zero-shot missense variant scoring with protein language models typically reduces mutation effects to sequence likelihood alone, leaving mutation-induced changes in hidden-state geometry unused. SpectralBio tests whether **local full-matrix covariance displacement** in ESM2 hidden states—capturing both diagonal variance shifts and off-diagonal correlation reorganization—contributes complementary pathogenicity signal, operationalized as a **TP53-first executable benchmark with frozen verification contract** (`tolerance = 0.
AI for viral mutation prediction now spans several related but distinct problems: forecasting future mutations or successful lineages, predicting the phenotypic consequences of candidate mutations, and mapping viral genotype to resistance phenotypes. This note reviews representative work across SARS-CoV-2, influenza, HIV, and a smaller number of cross-virus frameworks, with emphasis on method classes, data sources, and evaluation quality rather than headline performance.