Hideyuki Shimizu

Axolotl regeneration reveals a dormant cis-regulatory grammar conserved across vertebrate genomes

The paper identifies a conserved cis-regulatory grammar in axolotl limb regeneration and shows it is dormant in mammalian genomes, suggesting a potential for reactivating regenerative programs.

Integrating virtual cell modeling with patient-derived transcriptomics to uncover target signals in rheumatoid arthritis

The paper evaluates virtual cell models in rheumatoid arthritis by comparing empirical and virtual perturbations in patient-derived T cells, finding preserved target priorities with disease-specific shifts.

Dose-dependent modeling of combinatorial drug responses stratifies patient survival and reveals therapeutic vulnerabilities in precision oncology

XACT models dose-dependent drug responses using transcriptomic data to predict patient survival and identify therapeutic vulnerabilities in cancer.

Cell-type-resolved Metabolic Flux Inference Reveals Stromal Metabolic Reprogramming Across Human Cardiomyopathies

The paper develops a cell-type-resolved metabolic flux inference pipeline to analyze human cardiomyopathies, revealing stromal metabolic reprogramming and genotype-specific metabolic alterations.

Pan-Pharmacological Drug-Target Interaction Prediction with 3D-Informed Protein Encoding at Scale

OmniBind predicts drug-target interactions across multiple endpoints using structural protein encoding, outperforming existing methods and recovering known drug targets.

De novo design of therapeutic scFvs and multi-specific engagers from sequence alone

This paper introduces IASO, a sequence-centric framework for designing therapeutic scFvs and multi-specific engagers using only antigen sequence, demonstrating its ability to identify novel binders and overcome drug resistance.

Geometric-Evolutionary Deep Learning Decodes the Human GPCR-Metabolome Interactome and Enables Systematic De-Orphanization

G-LEAP uses deep learning to predict GPCR-ligand interactions, identifying endogenous ligands and orphan ligands with high accuracy.

A Functional Atlas of the Tardigrade Resistome Reveals a Diverse Molecular Toolkit for Extremotolerance

The paper develops AEGIS, an AI tool, to discover novel guardian proteins in tardigrades, revealing a diverse molecular toolkit for extremotolerance.

High-Resolution Mapping of the Human E3-Substrate Interactome using Ubicon Uncovers Network Architecture and Cancer Vulnerabilities

The paper introduces Ubicon, a deep learning framework for predicting human E3-substrate interactions, revealing network architecture and cancer-related vulnerabilities.

MetDeeCINE: Deciphering Metabolic Regulation through Deep Learning and Multi-Omics

MetDeeCINE predicts enzyme-metabolite relationships using multi-omics data and outperforms existing models in predicting concentration control coefficients in E. coli.

AMP-Atlas: Comprehensive Atlas of Antimicrobial Peptides to Combat Multidrug-resistant Bacteria

AMP-Atlas uses AI to predict antimicrobial peptides from sequences, outperforming existing methods and identifying new candidates in human bacteria.

BaCNet: Deep Learning Accelerates Novel Antibiotic Discovery Against Resistant Pathogens

BaCNet uses deep learning to predict antibiotic-target interactions and discover novel compounds against drug-resistant pathogens.