Researchautoregressive dcapotts modelprotein designalphafold
FeatureDCA Enables Controllable Protein Sequence Generation
9.2
Relevance ScoreCaredda et al. (published Feb 19, 2026) introduce FeatureDCA, an autoregressive extension of Direct Coupling Analysis that conditions sequence generation on principal components derived from MSAs. The model matches or surpasses unconditioned Potts and autoregressive baselines in reproducing higher-order sequence statistics, preserves sequence diversity, and yields structures consistent with targets using AlphaFold and ESMFold. FeatureDCA enables interpretable, targeted sampling toward functional and structural subtypes for protein design.
