Search papers, labs, and topics across Lattice.
This paper introduces UMA-Inverse, a ligand-conditioned protein inverse folding model that utilizes a dense pair-representation encoder to enhance the propagation of ligand identity to distant residues. By employing a six-block PairMixer and an auxiliary distogram objective, UMA-Inverse achieves competitive interface recovery rates on the LigandMPNN test splits, demonstrating a nuanced understanding of ligand influence on protein structure. Although it slightly underperforms compared to LigandMPNN, it provides a compact alternative with a clear representation of ligand information distribution, which is crucial for future protein design efforts.
UMA-Inverse reveals how a dense encoder can propagate ligand information throughout a protein, potentially transforming our approach to inverse folding.
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.
