Author

Tomoko Ohta

ORCID 0000-0002-9418-8352Unclaimed ORCID profile · follow to get notified of new preprints

Biology Disciplines

Click to filter author papers

Signature Assays, Organisms & Methods

Click to filter · or open tag

Research Focus:database / resource· 3 Research Focus:benchmarking· 2 Approach:statistical model· 2 Approach:deep learning· 1 Assay:protein sequence· 1 Approach:transformer / foundation model· 1

Frequent Co-Authors

Katerina C. NastouiD· 3 shared Lars Juhl JenseniD· 3 shared Sampo PyysaloiD· 3 shared Farrokh MehryaryiD· 2 shared Jouni LuomaiD· 2 shared Evangelos PafilisiD· 1 shared Harttu Toivonen· 1 shared

Activity by Year

2023-2024 · peak 2/yr

Co-Author Collaboration Network

7 top collaborators · 19 mutual co-author links

Click any collaborator node to inspect or filter shared papers

Focal author (center)Selected co-authorORCID co-authorUnlinked name

Curved chords = mutual co-authorship

3 shared papersBioinformatics

Katerina C. NastouORCID

Mutual co-authors in cluster

Author profile →

3 papers

Recent·Most cited

STRING-ing together protein complexes: corpus and methods for extracting physical protein interactions from the biomedical literature

Farrokh Mehryary, Katerina C. Nastou, Tomoko Ohta, Lars Juhl Jensen, Sampo Pyysalo

The paper introduces a manually annotated corpus and a relation extraction model to identify physical protein interactions from biomedical literature, integrating results into the STRING database.

Bioinformatics · Sep 1, 2024Peer-reviewedBioinformatics

RegulaTome: a corpus of typed, directed, and signed relations between biomedical entities in the scientific literature

Katerina C. Nastou, Farrokh Mehryary, Tomoko Ohta, Jouni Luoma, Sampo Pyysalo, Lars Juhl Jensen

RegulaTome provides a comprehensive corpus of biomedical relations, enabling improved relation extraction with a Transformer model achieving 66.6% F1-score.

Database · Jan 1, 2024Peer-reviewedBioinformatics

S1000: A better taxonomic name corpus for biomedical information extraction

Jouni Luoma, Katerina C. Nastou, Tomoko Ohta, Harttu Toivonen, Evangelos Pafilis, Lars Juhl Jensen, Sampo Pyysalo

The paper introduces S1000, a new corpus for species name recognition in biomedical text, achieving high accuracy with both deep learning and dictionary-based methods.

Bioinformatics · Jun 1, 2023Peer-reviewedBioinformatics