Author
Sho Tsukiyama
Kyushu Institute of TechnologyORCID 0000-0002-7871-0868Unclaimed ORCID profile · follow to get notified of new preprints
Biology Disciplines
Click to filter author papersSignature Assays, Organisms & Methods
Click to filter · or open tagActivity by Year
2021-2026 · peak 2/yrCo-Author Collaboration Network
10 top collaborators · 21 mutual co-author links5 papers
Recent·Most cited
- NeurosciencebioRxivPreprint
Mora-ERP-based RNN-Transformer for decoding single-trial EEGs during silent Japanese speeches
Toshimasa Yamazaki, Saori Kudo, Sei‐ichiro Kamata…·Shunsuke Aoki
This paper develops an RNN-Transformer model to decode single-trial EEGs during silent Japanese speeches with low error rates.
DOI 10.1101/2024.11.18.624218 - BioinformaticsPLoS ONEPeer-reviewed
ICAN: interpretable cross-attention network for identifying drug and target protein interactions
Hiroyuki Kurata, Sho Tsukiyama
The paper introduces ICAN, an attention-based method for predicting drug-target interactions using SMILES and amino acid sequences, achieving high performance and interpretability.
19 citations - BioinformaticsComputational and Structural Biotechnology JournalPeer-reviewed
Cross-attention PHV: Prediction of human and virus protein-protein interactions using cross-attention-based neural networks
Sho Tsukiyama, Hiroyuki Kurata
The paper introduces cross-attention PHV, a computational predictor for human-virus protein-protein interactions, which outperforms existing models and accurately predicts interactions for unknown viruses.
- BioinformaticsBriefings in BioinformaticsPeer-reviewed
LSTM-PHV: Prediction of human-virus protein-protein interactions by LSTM with word2vec
Sho Tsukiyama, Md Mehedi Hasan, Satoshi Fujii, Hiroyuki Kurata
The paper introduces LSTM-PHV, a sequence-based model predicting human-virus protein-protein interactions using LSTM and word2vec, achieving high accuracy on imbalanced data.