EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI-Driven Data Extraction and AGREE-Based Greenness Evaluation of Analytical Methods for Natural Products: Insights from Selected Studies

Paweł Świt iD, Fabian Hammerle iD, Markus Ganzera iD

Analytical Chemistry · 11.08.2026 · 98 (31) · 22595-22608

DOI: 10.1021/acs.analchem.6c02529 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Analytical Chemistry, online erschienen am 29.07.2026. Verfasst von Paweł Świt und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Chemistry, Faculty of Science and Technology, University of Silesia in Katowice, Szkolna 9, Katowice40-006, Poland. Hauptthemen laut MEDLINE: Biological Products, Artificial Intelligence, Green Chemistry Technology. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Narodowa Agencja Wymiany Akademickiej.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) have evolved into versatile tools of the 21st century, simplifying repetitive and labor-intensive tasks in everyday life. Here, we aimed to test the feasibility of using different LLMs to assess the greenness of analytical procedures according to the “Analytical GREEnness Metric Approach” (AGREE) by extracting specific data corresponding to the 12 principles of green analytical chemistry from scientific articles. Seven open-access articles on plant natural products using different analytical techniques were evaluated with the five most popular artificial intelligence (AI) tools (ChatGPT, Copilot, Perplexity, Claude, and Gemini), which were tasked to obtain specific data, along with a justification for the selection of this data. Additionally, different versions (basic and advanced) of the same tool (Perplexity and Perplexity Pro), output types (PDF file and link to the online version), and repeatability (three times the same task) were compared. All extracted data were used to calculate AGREE scores, and the final results were compared with those obtained by experts. AI tools were able to assess greenness with a high degree of accuracy, similar to that of trained researchers. Furthermore, a verification/comparison study demonstrated the possibility of critically examining the greenness assessment of developed methods to facilitate standardizing greenness evaluation. The final application of advanced AI tools dedicated to scientific research confirmed the greenness scores, indicating high consistency between all considered evaluation methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Biological ProductsArtificial IntelligenceGreen Chemistry TechnologyLarge Language Models

Substanzen

Biological Products

Autor:innen und Institutionen

  • Institute of Chemistry, Faculty of Science and Technology, University of Silesia in Katowice, Szkolna 9, Katowice40-006, Poland.
  • Institute of Pharmacy, Department of Pharmacognosy, University of Innsbruck, Innrain 80-82, Innsbruck6020, Austria.

ORCID-Profile: Paweł Świt, Fabian Hammerle, Markus Ganzera

Förderung

  • Narodowa Agencja Wymiany Akademickiej

Zitieren

APA

Świt, P., Hammerle, F., & Ganzera, M. (2026). AI-Driven Data Extraction and AGREE-Based Greenness Evaluation of Analytical Methods for Natural Products: Insights from Selected Studies. Analytical Chemistry, 98(31), 22595-22608. https://doi.org/10.1021/acs.analchem.6c02529

Vancouver

Świt P, Hammerle F, Ganzera M. AI-Driven Data Extraction and AGREE-Based Greenness Evaluation of Analytical Methods for Natural Products: Insights from Selected Studies. Analytical Chemistry. 2026;98(31):22595-22608. doi:10.1021/acs.analchem.6c02529

BibTeX
@article{wit2026,
  author = {Świt, Paweł and Hammerle, Fabian and Ganzera, Markus},
  title = {AI-Driven Data Extraction and AGREE-Based Greenness Evaluation of Analytical Methods for Natural Products: Insights from Selected Studies},
  journal = {Analytical Chemistry},
  year = {2026},
  volume = {98},
  number = {31},
  pages = {22595--22608},
  doi = {10.1021/acs.analchem.6c02529}
}
Kostenlos starten →