42 citations · 86 across the 9 of their papers we have counts for
10 papers
ProtoGTX: Prototype-Aligned Graph Transformer for Explainable Whole-Slide Image Analysis
Iori Azuma, Hiroyuki Kusuhara, Tadahaya Mizuno
Deep learning has achieved strong performance in computational pathology, but explaining whole-slide image (WSI) predictions remains challenging. Existing explanation methods often…
From Syntax to Semantics: Unveiling the Emergence of Chirality in SMILES Translation Models
Zehao Li, Yasuhiro Yoshikai, Shumpei Nemoto +2
Understanding how chemical language models (CLMs) learn chemical meaning from molecular string representations, rather than only surface-level string patterns, is an important ques…
Exploring Multi-Objective Trade-offs in Reference Compound Selection for Validation Studies of Toxicity Assays
Yohei Ohto, Tadahaya Mizuno, Yasuhiro Yoshikai +2
In chemical safety assessment, validation studies rely on reference compound lists to evaluate the applicability of alternative methods prior to regulatory acceptance. These lists…
Notation-level confounding: When inconsistent molecular notations mislead chemical language models
Yosuke Kikuchi, Yasuhiro Yoshikai, Shumpei Nemoto +4
Chemical language models (CLMs) are increasingly used for molecular design and property prediction. Because these models learn from textual encodings of molecules, differences in h…
A novel molecule generative model of VAE combined with Transformer for unseen structure generation
Yasuhiro Yoshikai, Tadahaya Mizuno, Shumpei Nemoto +1
Recently, molecule generation using deep learning has been actively investigated in drug discovery. In this field, Transformer and VAE are widely used as powerful models, but they…
Difficulty in chirality recognition for Transformer architectures learning chemical structures from string
Yasuhiro Yoshikai, Tadahaya Mizuno, Shumpei Nemoto +1
Recent years have seen rapid development of descriptor generation based on representation learning of extremely diverse molecules, especially those that apply natural language proc…
Investigation of chemical structure recognition by encoder-decoder models in learning progress
Shumpei Nemoto, Tadahaya Mizuno, Hiroyuki Kusuhara
Descriptor generation methods using latent representations of encoderdecoder (ED) models with SMILES as input are useful because of the continuity of descriptor and restorabilit…
NRBdMF: A recommendation algorithm for predicting drug effects considering directionality
Iori Azuma, Tadahaya Mizuno, Hiroyuki Kusuhara
Predicting the novel effects of drugs based on information about approved drugs can be regarded as a recommendation system. Matrix factorization is one of the most used recommendat…
Investigation of a Data Split Strategy Involving the Time Axis in Adverse Event Prediction Using Machine Learning
Katsuhisa Morita, Tadahaya Mizuno, Hiroyuki Kusuhara
Adverse events are a serious issue in drug development and many prediction methods using machine learning have been developed. The random split cross-validation is the de facto sta…
Extraction of diverse gene groups with individual relationship from gene co-expression networks
Iori Azuma, Tadahaya Mizuno, Hiroyuki Kusuhara
Motivation: Modules in gene coexpression networks (GCN) can be regarded as gene groups with individual relationships. No studies have optimized module detection methods to extract…