Vilya-1 Improves Macrocycle Conformation Prediction
DaveJuergens · x · 2026-07-18
Vilya-1 is an all-atom diffusion-based foundation model designed for macrocycle conformation prediction and design. It aims to solve a core bottleneck in drug discovery: stably sampling biologically relevant, low-energy conformations across diverse synthesizable chemical spaces, moving beyond standard peptides.
The authors report that across 66 cyclic peptide X-ray structures, Vilya-1 achieved an 89.2% success rate in generating near-native ring conformations (ring RMSD < 1 Å), significantly outperforming Prime-MCS, RDKit ETKDGv3, Boltz-2/RF3, and several deep learning conformational generators.
The model also generalizes across various macrocycle types and topologies, including:
- Disulfide-linked cyclic peptides
- Sidechain-to-sidechain cyclization
- Tail-to-sidechain cyclization
- Non-peptidic macrocycles, such as macrolides/polyketides
The post also mentions FK506 among the example molecules.
More from Research
- Diamandis: AI Cancer Navigator and $100 Genome Sequencing Close the Care Gap — PeterDiamandis · 2026-10-27
- EMNLP Oral: training-free Nexus Sampling cuts KV-cache memory 10x; OpenResearcher tops BrowseComp-Plus at 54.8% — yuz9yuz · 2026-10-27
- ICML 2026 position paper: LLM 'thinking traces' are a harmful anthropomorphism — rao2z · 2026-10-27
- Forking gap follows a power law in context frequency; masking rare n-grams shrinks it — ZimingLiu11 · 2026-10-27
- How forking happens: n-gram tables split logits into non-interacting subspaces — ZimingLiu11 · 2026-10-27
- The best LoRA explainer video yet: rank constraints meet intrinsic dimension — sophiamyang · 2026-10-27