Transferring Peptide-Target Interaction Patterns to Small Molecules by Joint Guidance for Diffusion and Flow Matching
Read the original on arXiv Machine Learning →The paper introduces PIFT, a framework that transfers peptide‑target interaction patterns to small molecules by jointly guiding masked discrete diffusion and continuous flow matching. PIFT maps peptide‑target and small‑molecule‑target interfaces into a shared, target‑conditioned interaction space, enabling peptide‑derived references to steer both building‑block logits and 3D coordinates toward peptide‑compatible molecules while maintaining a strong molecular prior. Experiments on diverse protein‑protein interaction targets demonstrate that this cross‑modal representation improves interface recovery, docking performance, and molecular properties.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.