Ten simple rules for optimal and careful use of generative AI in science
PLOS Computational Biology · 28.10.2025 · 21 (10) · e1013588
DOI: 10.1371/journal.pcbi.1013588 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 28.10.2025. Verfasst von Mohamed Helmy und 5 weiteren Autor:innen. Beteiligte Einrichtung: Vaccine and Infectious Diseases Organization (VIDO), University of Saskatchewan, Saskatchewan, Canada. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Vaccine and Infectious Disease Organization (VIDO), University of Saskatchewan.
Abstract (Originalsprache)
Modern AI technologies leverage natural language processing (NLP), a subfield of AI dedicated to understanding, interpreting, and generating human language for developing large language models (LLMs), which have significantly advanced the capabilities of AI systems. These models can perform complex language tasks such as text generation, summarization, translation, and sentiment analysis, with unprecedented accuracy. The two main kinds of pre-training LLMs are the BERT-like models (e.g., BioBERT, proteinBERT, and PubMedBERT used primarily for language understanding; and the GPT-like models (e.g., BioGPT and ChatGPT-4o) used primarily for language generation
Autor:innen und Institutionen
- Vaccine and Infectious Diseases Organization (VIDO), University of Saskatchewan, Saskatchewan, Canada.
- Vaccinology and Immunotherapeutics Program, School of Public Health, University of Saskatchewan, Saskatchewan, Canada.
- Department of Computer Science, University of Saskatchewan, Saskatchewan, Canada.
- Department of Computer Science, Idaho State University, Boise, Idaho, United States of America.
- Bioinformatics Institute (BII), Agency for Science, Technology and Research (A*STAR), Singapore, Republic of Singapore.
- Chemistry Department, Wesleyan University, Middletown, Connecticut, United States of America.
ORCID-Profile: Mohamed Helmy, Diogo Pellagrina
Förderung
- Vaccine and Infectious Disease Organization (VIDO), University of Saskatchewan
Zitieren
APA
Helmy, M., Jin, L., Alhossary, A., Mansour, T., Pellagrina, D., & Selvarajoo, K. (2025). Ten simple rules for optimal and careful use of generative AI in science. PLOS Computational Biology, 21(10), e1013588. https://doi.org/10.1371/journal.pcbi.1013588
Vancouver
Helmy M, Jin L, Alhossary A, Mansour T, Pellagrina D, Selvarajoo K. Ten simple rules for optimal and careful use of generative AI in science. PLOS Computational Biology. 2025;21(10):e1013588. doi:10.1371/journal.pcbi.1013588
BibTeX
@article{Helmy2025,
author = {Helmy, Mohamed and Jin, Lingling and Alhossary, Amr and Mansour, Tamer and Pellagrina, Diogo and Selvarajoo, Kumar},
title = {Ten simple rules for optimal and careful use of generative AI in science},
journal = {PLOS Computational Biology},
year = {2025},
volume = {21},
number = {10},
pages = {e1013588},
doi = {10.1371/journal.pcbi.1013588}
}
EUVIMED