Takuji Yamada

Benchmarking long-context genome language models on biosynthetic gene clusters

This study benchmarks long-context genome language models on biosynthetic gene clusters, showing layer selection impacts performance and revealing how models encode biological information.

DeepRES: Deep learning enables reaction-based comprehensive enzyme screening

DeepRES identifies candidate proteins for orphan enzymes and discovers novel biosynthetic gene clusters using deep learning.

DeepES: Deep learning-based enzyme screening to identify orphan enzyme genes

DeepES identifies orphan enzyme genes using deep learning, focusing on biosynthetic gene clusters and reaction classes, and identifies candidates in metagenome-assembled genomes.

Automated Harmonization and Large-Scale Integration of Heterogeneous Biomedical Sample Metadata Using Large Language Models

This paper introduces a framework using large language models to automate metadata harmonization and integration across biomedical studies, achieving higher recovery rates than traditional methods.

Enteropathway: the metabolic pathway database for the human gut microbiota

Enteropathway is a comprehensive metabolic pathway database for the human gut microbiota, integrating curated data from literature to provide visualization and analysis tools for studying microbiota-host interactions.

Discovering and exploring the hidden diversity of human gut viruses using highly enriched virome samples

The paper presents a method to discover new human gut viruses using enriched virome samples and reports over 162,000 novel viral sequences.