arXiv AI
Joint Discrete and SE(3) Diffusion for Protein Interface Design
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
1d ago
Transferring Peptide-Target Interaction Patterns to Small Molecules by Joint Guidance for Diffusion and Flow Matching
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.
arXiv Machine Learning
Aug 17
READ: A Retrieval-Alignment Diffusion Framework for Structure-based Drug Design
arXiv:2506. 14488v2 Announce Type: replace-cross Abstract: Structure-based drug design (SBDD) models are central to modern pharmaceutical research, enabling the rational exploration of protein-ligand interactions at atomic resolution.
arXiv Machine Learning
Jun 24
Sesame: Structure-Aware Molecular Generation via Spatial Density-Map Conditioning
arXiv:2606. 23856v1 Announce Type: new Abstract: Generative molecular models for drug design are a promising direction with much active research.
arXiv Machine Learning
Sep 10
FuseDiff: Symmetry-Preserving Joint Diffusion for Dual-Target Structure-Based Drug Design
FuseDiff is an end‑to‑end diffusion model designed for dual‑target structure‑based drug design, jointly generating a ligand graph and two pocket‑specific binding poses conditioned on both target pockets. It employs a message‑passing backbone with Dual‑target Local Context Fusion (DLCF) to fuse ligand atom contexts from both pockets, preserving symmetry while enabling expressive joint modeling. The model enforces topological consistency across the two poses and allows target‑specific geometric adaptation, achieving state‑of‑the‑art docking performance and enabling systematic assessment of dual‑target pose quality before docking‑based pose search.
arXiv Machine Learning
Oct 8
PIT-GCL: Protein Interaction using Topological Graph Contrastive Learning
arXiv:2610.04850v2 Announce Type: replace Abstract: Protein binding prediction is central to target identification, therapeutic binder design, and large scale screening, yet remains challenging becau...
arXiv Machine Learning
Sep 22
SPID: Distilled Protein Backbone Generation
arXiv:2510.03095v4 Announce Type: replace Abstract: Diffusion- and flow-based generative models have recently demonstrated strong performance in protein backbone generation tasks, offering unpreceden...