EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Transcriptome Transformer: improving patient survival prediction via multitask learning of transcriptomic and clinical features

Bonil Koo iD, Inyoung Sung iD, Sangseon Lee iD, Sun Kim iD

Briefings in Bioinformatics · 01.11.2025 · 26 (6)

DOI: 10.1093/bib/bbaf628 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 25.11.2025. Verfasst von Bonil Koo und 3 weiteren Autor:innen. Beteiligte Einrichtung: Interdisciplinary Program in Bioinformatics, Seoul National University, 1, Gwanak-ro, 08826 Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Transcriptome, Gene Expression Profiling, Machine Learning, Neoplasms. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, Korea Health Technology R&D Project through the Korea Health Industry Development Institute, Ministry of Health and Welfare, Republic of Korea.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate survival prediction is essential in healthcare as it guides treatment strategies and improves patient outcomes. While clinical features provide valuable prognostic information, they often fail to represent the molecular complexity of diseases. Transcriptomic data, which reflects gene expression patterns of tumors, present a complementary perspective to address this limitation. We introduce Transcriptome Transformer (TxT), a multitask learning framework that uses a transcriptome-centric approach to improve patient survival prediction. TxT employs a Transformer-based architecture with multihead attention mechanisms to effectively capture complex dependencies among genes, enabling dynamic modeling of gene–gene interactions while using shared information across multiple clinical prediction tasks. By jointly analyzing transcriptomic data and incorporating clinical features, TxT offers a more complete representation of patient biology. In experiments across both single-task and multitask datasets, TxT outperformed existing methods in survival prediction and related clinical tasks. Additionally, TxT offers biological insights through attention-derived gene interaction networks, identifying immune-related pathways in longer-surviving Luminal A patients and coagulation and epithelial–mesenchymal transition pathways in shorter-surviving counterparts. Differential attention analysis further revealed that integrating clinical features enhances the model’s ability to prioritize genes involved in biologically meaningful pathways that are known to influence tumor progression and distant recurrence. The source code of TxT is available at https://github.com/BonilKoo/TxT.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TranscriptomeGene Expression ProfilingMachine LearningNeoplasmsComputational BiologyHumansPrognosisGene Regulatory NetworksSurvival Analysis

Stichwörter der Autor:innen

gene expressionmultitask learningsurvival predictiontranscriptometransformer

Autor:innen und Institutionen

  • Interdisciplinary Program in Bioinformatics, Seoul National University, 1, Gwanak-ro, 08826 Seoul, Republic of Korea.
  • AIGENDRUG Co., Ltd., 1793, Nambusunhwan-ro, 08758 Seoul, Republic of Korea.
  • BK21 FOUR Intelligence Computing, Seoul National University, 1, Gwanak-ro, 08826 Seoul, Republic of Korea.
  • Department of Artificial Intelligence, Inha University, 100 Inha-ro, 22180 Incheon, Republic of Korea.
  • Department of Computer Science and Engineering, Seoul National University, 1, Gwanak-ro, 08826 Seoul, Republic of Korea.
  • Interdisciplinary Program in Artificial Intelligence, Seoul National University, 1, Gwanak-ro, 08826 Seoul, Republic of Korea.

ORCID-Profile: Bonil Koo, Inyoung Sung, Sangseon Lee, Sun Kim

Förderung

  • National Research Foundation of Korea
  • Korea Health Technology R&D Project through the Korea Health Industry Development Institute
  • Ministry of Health and Welfare, Republic of Korea
  • Institute of Information & Communications Technology Planning & Evaluation
  • Artificial Intelligence Graduate School Program

Zitieren

APA

Koo, B., Sung, I., Lee, S., & Kim, S. (2025). Transcriptome Transformer: improving patient survival prediction via multitask learning of transcriptomic and clinical features. Briefings in Bioinformatics, 26(6). https://doi.org/10.1093/bib/bbaf628

Vancouver

Koo B, Sung I, Lee S, Kim S. Transcriptome Transformer: improving patient survival prediction via multitask learning of transcriptomic and clinical features. Briefings in Bioinformatics. 2025;26(6). doi:10.1093/bib/bbaf628

BibTeX
@article{Koo2025,
  author = {Koo, Bonil and Sung, Inyoung and Lee, Sangseon and Kim, Sun},
  title = {Transcriptome Transformer: improving patient survival prediction via multitask learning of transcriptomic and clinical features},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  volume = {26},
  number = {6},
  doi = {10.1093/bib/bbaf628}
}
Kostenlos starten →