Kengo Sato

LinearKnot approximates CParty's hierarchical pseudoknot analysis with linear time complexity, achieving comparable accuracy for RNA structure prediction and ensemble calculations.

LinearRaccess computes RNA accessibility for long windows in linear time without base-pair span limits, achieving high accuracy and efficiency.

This paper introduces RNA-MDLM, a model for generating and inpainting non-coding RNA sequences, showing it produces sequences with natural composition and folding statistics.

PKProbDesign optimizes thermodynamic folding probability for pseudoknotted RNA targets, achieving high pseudo-joint folding probability on most tested targets.

UTR-Diffusion is a diffusion model for designing 5-prime UTR and UTR-CDS junctions that optimizes translation efficiency, RNA stability, and codon adaptation while preserving sequence constraints.

The paper introduces Mountain Centroid, a method for representing RNA structural ensembles as single secondary structures, showing improved performance over existing methods in certain metrics.

RNArefine improves RNA structure prediction by refining atomic details and stereochemistry using AI and physics-based methods.

This paper evaluates blind predictions of dynamic water and ion ensembles around RNA using cryo-EM densities from CASP16, finding that molecular dynamics approaches perform best.

The paper identifies pathway redistribution across cellular states using a framework combining co-expression data and deep learning, revealing shared signaling modules and context-dependent regulatory networks in RNA-binding proteins.

The paper introduces a neural network method for RNA secondary structure prediction that directly infers base-pairing probabilities, improving accuracy for structures with pseudoknots.

This paper introduces a max-margin model to predict residue-base contacts in protein-RNA interactions using only sequence and predicted structural information, achieving results comparable to methods using 3D structures.

This paper introduces MXfold2, a deep learning method for RNA secondary structure prediction that integrates thermodynamic parameters, achieving higher accuracy and robustness than previous methods.

This paper introduces an RNA secondary structure prediction algorithm that combines thermodynamic modeling with a structured support vector machine to improve accuracy and reduce overfitting.