Hugging Face Trending Papers
RiboBridge: protein-conditioned de novo RNA binder structure design
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Machine Learning
Oct 23
RiboBridge: protein-conditioned de novo RNA binder structure design
RiboBridge is a new structure-first framework for designing RNA molecules that bind to target proteins without assuming a predefined binding site. It separates RNA conformational generation from protein–RNA assembly by first proposing candidate binding interfaces on the protein surface, generating canonical RNA conformations in a pretrained RNA latent space (RiboSphere), and then predicting interaction constraints to bridge the RNA and protein coordinate frames. The predicted interaction geometry is converted into a geometrically consistent protein-relative pose via rigid placement, and RiboBridge outperforms existing methods on a benchmark of 124 protein–RNA complexes, achieving higher fNAT and DockQ scores and lower RMSDs.
arXiv AI
Oct 9
La-Ribo: RNA Co-Design via Geometry-Latent Flow Matching
La‑Ribo is a generative framework that jointly designs RNA nucleotide sequences and their three‑dimensional structures using geometry‑latent flow matching. It preserves a sparse phosphate‑sugar‑base scaffold while encoding nucleotide identity and local conformation in residue‑wise latent variables, which a shared flow network generates before an RNA‑specific decoder reconstructs all heavy atoms. The authors also built a large, quality‑controlled corpus of 168,561 RNA structures—combining experimental data with predictions from three folding models—to expand supervision, and demonstrate that La‑Ribo outperforms baselines in designability and co‑designability across sampling budgets and refolding models, while also enabling scaffold‑conditioned inverse folding without extra training.
arXiv Machine Learning
Aug 6
RiboSphere: Learning Unified and Efficient Representations of RNA Structures
arXiv:2603. 19636v2 Announce Type: replace Abstract: Accurate RNA structure modeling remains difficult because RNA backbones are highly flexible, non-canonical interactions are prevalent, and experimentally determined 3D structures are comparatively scarce.
arXiv AI
Oct 23
REFLEX: RNA Ensemble Generation via Flexibility-Calibrated Stochastic Bridge
REFLEX is a sequence‑conditioned generator that produces RNA backbone‑frame ensembles using a heteroscedastic stochastic bridge on SE(3). It calibrates residue‑wise bridge widths with experimental B‑factors, allowing each observed conformer to be accessed through local perturbation neighborhoods while maintaining sharpness in constrained regions. In inference, REFLEX requires only the input sequence and, on a multi‑conformer RNA benchmark, achieves the best precision‑recall trade‑off for ensemble coverage across evaluation thresholds, with ablation studies showing improved target‑frame recovery under stronger perturbations.
arXiv Machine Learning
Oct 5
RNADyn: A Benchmark for Generating and Understanding RNA Dynamics
RNADynBench is a new standardized benchmark for RNA molecular dynamics, comprising 2,585 high‑quality 100‑nanosecond all‑atom trajectories with carefully controlled data splits. RNADynNet is a unified model that simultaneously generates RNA trajectories and extracts dynamics fingerprints from a single conformer, leveraging coordinate denoising, alignment, and physical grounding. The model achieves strong agreement with MD data, achieving RMSF correlations of 0.875 and 0.766 on test sets, including a high‑flexibility challenge set.
arXiv AI
2d ago
Predicting protein structures at any folding stage from sequence
arXiv:2611.04287v2 Announce Type: replace-cross Abstract: Protein structure prediction has largely focused on native conformations, leaving the continuum of unfolded states, folding intermediates, an...