Hiroyuki Kurata

GDA-Pred improves prediction of IL-6 and IL-13 inducing peptides by using generative AI to augment small datasets, enhancing classifier performance through data expansion.

Meta-PseU is a meta-classifier that improves RNA pseudouridine site prediction using long sequences, outperforming existing methods across species.

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

The paper compares kinetic models of E. coli ammonium transport and assimilation to determine the mechanism of energy coupling and growth robustness under varying conditions.

The paper introduces ICAN, an attention-based method for predicting drug-target interactions using SMILES and amino acid sequences, achieving high performance and interpretability.

The paper introduces cross-attention PHV, a computational predictor for human-virus protein-protein interactions, which outperforms existing models and accurately predicts interactions for unknown viruses.

This study compares synchronization in activator- and repressor-based coupled gene oscillators, showing that repressor-based models achieve robust in-phase synchronization while activator-based models require coupling delays for anti-phase synchronization.

The paper introduces LSTM-PHV, a sequence-based model predicting human-virus protein-protein interactions using LSTM and word2vec, achieving high accuracy on imbalanced data.

The paper develops a comprehensive virtual metabolic human model to analyze diabetes mechanisms and design therapies, identifying glycerol kinase inhibitors as potential treatments.

RCGAToolbox provides real-coded genetic algorithms for parameter estimation in kinetic models, offering two algorithms and a user-friendly interface.

This study shows that negative autoregulation enhances memory function in a mutual repression network by reducing stochastic fluctuations and increasing steady-state stability.