EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

AI-Assisted Molecular Structure Prediction from Tandem Mass Spectra: Reliability and Validation

Jun Sang Yu iD, Sung Hue Jeong, Yejin Kim iD, Dong Keun Lee, Hye Hyun Yoo iD

International Journal of Molecular Sciences · 08.11.2026 · 27 (21) · 10012

DOI: 10.3390/ijms272110012 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift International Journal of Molecular Sciences, online erschienen am 08.11.2026. Verfasst von Jun Sang Yu und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Pharmacy, Jeju National University, Jeju 63243, Republic of Korea. Hauptthemen laut MEDLINE: Tandem Mass Spectrometry, Artificial Intelligence. Die Arbeit nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Forensic Institute, National Research Foundation of Korea, National Forensic Service.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial intelligence (AI) has broadened the interpretation of tandem mass spectra (MS/MS) beyond experimental library matching, enabling molecular fingerprint prediction, candidate ranking, and generation of previously unlisted structures. Yet these outputs do not all support the same claim about chemical identity. This review briefly summarizes database-restricted retrieval, database-free generation, and scaffold-guided hybrid methods, and then asks what additional evidence is needed to turn a plausible structure into a defensible annotation. We examine failure modes involving incomplete candidate spaces, erroneous precursor assignments, structurally related isomers, leakage between training and test data, and misinterpreted confidence scores. The review contributes two practical elements: a candidate-discrimination workflow, in which alternative structures are retained and targeted measurements such as multienergy fragmentation, retention behavior, ion mobility, and authentic standards are selected according to the unresolved structural question; and an evidence-to-claim checklist that links each question to the most informative measurement and to the strongest supportable identification confidence level. Both synthesize established analytical principles for small-molecule electrospray LC–HRMS/MS rather than constituting a validated scoring algorithm. By making the basis of each annotation transparent, they are intended to improve the practical value of AI-assisted MS/MS in metabolomics, pharmaceutical analysis, environmental screening, and forensic toxicology.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tandem Mass SpectrometryArtificial IntelligenceMolecular StructureReproducibility of ResultsAlgorithms

Stichwörter der Autor:innen

artificial intelligencedatabase retrievalmolecular generationstructure predictiontandem mass spectrometry

Autor:innen und Institutionen

  • College of Pharmacy, Jeju National University, Jeju 63243, Republic of Korea.
  • Pharmacomicrobiomics Research Center, College of Pharmacy, Hanyang University, Ansan 15588, Republic of Korea.
  • GENECT, Konkuk University Campus Town, Seoul 05073, Republic of Korea.

ORCID-Profile: Jun Sang Yu, Yejin Kim, Hye Hyun Yoo

Förderung

  • National Forensic Institute
  • National Research Foundation of Korea
  • National Forensic Service

Zitieren

APA

Yu, J. S., Jeong, S. H., Kim, Y., Lee, D. K., & Yoo, H. H. (2026). AI-Assisted Molecular Structure Prediction from Tandem Mass Spectra: Reliability and Validation. International Journal of Molecular Sciences, 27(21), 10012. https://doi.org/10.3390/ijms272110012

Vancouver

Yu JS, Jeong SH, Kim Y, Lee DK, Yoo HH. AI-Assisted Molecular Structure Prediction from Tandem Mass Spectra: Reliability and Validation. International Journal of Molecular Sciences. 2026;27(21):10012. doi:10.3390/ijms272110012

BibTeX
@article{Yu2026,
  author = {Yu, Jun Sang and Jeong, Sung Hue and Kim, Yejin and Lee, Dong Keun and Yoo, Hye Hyun},
  title = {AI-Assisted Molecular Structure Prediction from Tandem Mass Spectra: Reliability and Validation},
  journal = {International Journal of Molecular Sciences},
  year = {2026},
  volume = {27},
  number = {21},
  pages = {10012},
  doi = {10.3390/ijms272110012}
}
Kostenlos starten →