Yasubumi Sakakibara

RIFT-VAE: grammar-conditioned pretraining and latent-space optimization for RNA inverse folding

RIFT-VAE improves RNA inverse folding by combining grammar-conditioned pretraining with latent-space optimization, achieving high structural recovery on benchmark datasets.

Genomic resources of Ascidiella aspersa and comparative analysis across tunicates reveal class-level features and evolutionary diversification

The paper constructs genomic resources for Ascidiella aspersa and 35 other tunicate species, revealing class-level genomic features and evolutionary patterns through comparative analysis.

Transcriptomic dynamics of petal development in the one-day flower species, Japanese morning glory (Ipomoea nil)

The paper analyzes transcriptomic changes in Japanese morning glory petals over time, identifying gene expression patterns related to development, nutrient transport, and circadian rhythms.

Generative AI-driven artificial DNA design for enhancing inter-species gene activation and enzymatic degradation of PET

OrthologTransformer improves gene conversion between species by learning evolutionary differences, outperforming codon optimization in PETase expression.

Quantum algorithm for position weight matrix matching

This paper introduces two quantum algorithms for position weight matrix matching, achieving speedups over classical methods in certain scenarios.

Direct inference of base-pairing probabilities with neural networks improves RNA secondary structure prediction with pseudoknots

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

Informative RNA-base embedding for functional RNA structural alignment and clustering by deep representation learning

This paper develops an informative RNA-base embedding using deep learning to improve RNA structural alignment and clustering, achieving better accuracy than existing methods.

A max-margin model for predicting residue-base contacts in protein-RNA interactions

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.

Chromosomal-scale De novo Genome Assemblies of Cynomolgus Macaque and Common Marmoset

This study presents de novo chromosome-scale genome assemblies for cynomolgus macaque and common marmoset using long-read and Hi-C data, achieving high contiguity and accuracy.

Deep learning integration of molecular and interactome data for protein-compound interaction prediction

The paper develops a deep learning framework that integrates molecular and interactome data to predict protein-compound interactions, showing improved performance over existing methods.

RNA secondary structure prediction using deep learning with thermodynamic integration

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.

Hamster PIWI proteins bind to piRNAs with stage-specific size variations during oocyte maturation

This study investigates piRNA size variations and PIWI protein dynamics during hamster oocyte maturation, revealing stage-specific piRNA binding and transcriptional regulation in ovarian piRNA clusters.

Genomic style: yet another deep-learning approach to characterize bacterial genome sequences

This paper introduces a new sequence feature called genomic style for bacterial DNA sequence classification, showing it outperforms k-mer frequency in metagenome binning.

A max-margin training of RNA secondary structure prediction integrated with the thermodynamic model

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.