UMA-Inverse: Ligand-Conditioned Protein Inverse Folding with a Distogram-Supervised Dense Pair Encoder

Abstract

Designing protein sequences that bind specific ligands benefits from an inverse-folding model conditioned on full ligand geometry. We present UMA-Inverse, which replaces the sparse graph backbone of LigandMPNN with a dense pair-representation encoder: a six-block PairMixer (triangle multiplication, no triangle self-attention or sequence track) refines all residue-residue and residue-ligand atom pairs, supervised by an auxiliary distogram objective, and an autoregressive decoder attends over ligand atoms through a learned, position-specific readout of the pair tensor. The model is compact ($\sim$3.3 M parameters). On the LigandMPNN test splits it reaches 56.1%/55.1%/35.3% interface recovery (small-molecule/metal/nucleotide). It trails LigandMPNN, but by less than the published numbers suggest: re-run under our identical protocol, LigandMPNN scores 59.8/64.4/53.3 (vs. published 63.3/77.5/50.5). In a pocket-fixed setting the redesigns are confidently folded and ligand-binding-competent under Boltz-2 cofolding, again modestly behind LigandMPNN. Its distinctive property is representational: the dense encoder propagates ligand identity to residues far beyond the interface, where LigandMPNN's signal decays. We offer UMA-Inverse as a compact baseline for ligand-conditioned inverse folding that trails LigandMPNN in accuracy, together with a characterization of how a dense all-pairs encoder distributes ligand information.