Seiya Imoto

Structured biological evidence enables general-purpose language models to predict bacteriophage-host interactions

The paper introduces a structured-evidence framework for predicting bacteriophage-host interactions using a large language model, achieving high accuracy and enabling interpretable inference.

RiboPipe: efficient per-transcript codon-resolution ribo-seq coverage imputation for low-coverage transcripts

RiboPipe imputes codon-resolution Ribo-seq coverage for low-coverage transcripts using a unified framework that improves accuracy and efficiency.

Phylogenetic tree-aware positive-unlabeled deep metric learning for phage-host interaction identification

The paper introduces a phylogenetic tree-aware positive-unlabeled deep metric learning framework to improve phage-host interaction prediction by incorporating biological constraints and handling unlabeled data.

Causal assessment of gene regulatory network in single-cell transcriptomics data based on Bayesian networks

The paper introduces scstruc, an R package for learning and evaluating Bayesian networks from single-cell transcriptomics data to infer causal gene regulatory relationships.

Rethinking Representation Complexity in Drug-Target Prediction via Supervised Vector Quantization

This study evaluates complex features in drug-target interaction prediction and introduces a supervised vector quantization framework that improves performance and interpretability.

Weakly Supervised Vector Quantization for Whole Slide Image Classification

This paper introduces VQ-MIL, a weakly supervised vector quantization method for WSI classification, achieving state-of-the-art results on benchmark datasets.

PharaCon: A new framework for identifying bacteriophages via conditional representation learning

PharaCon uses a conditional BERT framework to improve phage identification in metagenomic data by incorporating label constraints during pre-training.

Simulating The Effect of the Radiotherapy on Cancer Stem Cell Evolution

This study simulates how radiotherapy affects cancer stem cell evolution, showing increased resistance, proliferation, and CSC proportion, and highlights the importance of CSC-targeted treatment.

Tissue-Specific Cell Type Annotation with Supervised Representation Learning using Split Vector Quantization and Its Comparisons with Single-cell Foundation Models

The paper introduces scVQC, a supervised representation learning method for cell-type annotation, and shows it outperforms unsupervised and pre-trained foundation models in tissue-specific annotation.

Enhanced spatially resolved transcriptomics analysis by matching between expression profiles and spatial topology

This paper introduces STForte, a method for spatially resolved transcriptomics analysis that matches expression profiles with spatial topology, improving downstream analysis and spatial enhancement.

Predicting cell types with supervised contrastive learning on cells and their types

This paper introduces SCLSC, a supervised contrastive learning method for cell type annotation in scRNA-seq data, achieving better accuracy and scalability than existing methods.

Microbial Gene Ontology informed deep neural network for microbe functionality discovery in human diseases

The paper introduces a deep neural network using Gene Ontology to discover microbiome functionality in human diseases, finding novel important genes and functions across four conditions.

Dysfunctional analysis of the pre-training model on nucleotide sequences and the evaluation of different k-mer embeddings

The paper analyzes how a pre-trained BERT model processes nucleotide sequences, identifies k-mer embeddings as key, and proposes an accelerated pre-training method.

Identification of bacteriophage genome sequences with representation learning

The paper introduces INHERIT, a deep learning model that combines database-based and alignment-free methods for phage identification, achieving an F1-score of 0.9932 on a benchmark dataset.

Impact of Salivary and Pancreatic Amylase Gene Copy Numbers on Diabetes, Obesity, and Functional Profiles of Microbiome in Northern Japanese Population

The paper investigates the association between amylase gene copy numbers and diabetes, obesity, and gut microbiome function in a northern Japanese population, finding a positive link between higher amylase copy numbers and these conditions.

On the application of BERT models for nanopore methylation detection

This paper explores using refined BERT models for nanopore methylation detection, achieving competitive performance and faster inference speed compared to biRNN models.

Enhancing breakpoint resolution with deep segmentation model: a general refinement method for read-depth based structural variant callers

RDBKE improves breakpoint resolution of read-depth SV callers using a deep segmentation model, increasing the number of SVs with more precise breakpoints on simulation and real data.

A multifunctional R package for identification of tumor-specific neoantigens

The paper introduces an R package for predicting tumor-specific neoantigens from various mutations and integrating additional biological information.

Quantifying Immune-Based Counterselection of Somatic Mutations

The paper quantifies immune-based counterselection of somatic mutations by analyzing their depletion in MHC class I-displayed peptides and shows that MHC alleles are incompletely dominant.

Nanopore base-calling from a perspective of instance segmentation

This paper introduces a base-calling method for nanopore sequencing by framing it as a one-dimensional segmentation task, achieving competitive accuracy compared to existing methods.

Capturing the Differences between Humoral Immunity in the Normal and Tumor Environments from Repertoire-Seq of B-Cell Receptors Using Supervised Machine Learning

This study uses supervised machine learning to classify BCR/Ig sequences from normal and tumor tissues, finding distinct sequence-level features between the two environments.

Immuno-genomic Pan-cancer Landscape Reveals Diverse Immune Escape Mechanisms and Immuno-Editing Histories

The paper analyzes immuno-genomic data across 31 cancer types to identify immune escape mechanisms and immuno-editing histories.

ALPHLARD: a Bayesian method for analyzing HLA genes from whole genome sequence data

ALPHLARD is a Bayesian method for HLA genotyping from WGS data, achieving high accuracy and detecting rare variants and somatic mutations.

Large-Scale Uniform Analysis of Cancer Whole Genomes in Multiple Computing Environments

The paper describes the PCAWG project's large-scale analysis of cancer whole genomes across multiple computing environments, producing validated consensus variants for downstream research.

Cancer evolution simulation identifies possible principles underlying intratumor heterogeneity

The paper uses a computational model to identify principles of intratumor heterogeneity in cancer evolution.