AI-Assisted Molecular Structure Prediction from Tandem Mass Spectra: Reliability and Validation
- 1College of Pharmacy, Jeju National University, Jeju 63243, Republic of Korea
- 2Pharmacomicrobiomics Research Center, College of Pharmacy, Hanyang University, Ansan 15588, Republic of Korea
- 3GENECT, Konkuk University Campus Town, Seoul 05073, Republic of Korea
Abstract
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.
Related
- Discriminating betacoronavirus receptor usage across subgenera using protein structure prediction and molecular dynamics
- Resistance Gene Pyramiding in Wheat (Triticum aestivum L.): From Marker-Assisted Selection to Functional Validation
- Total Synthesis-Assisted Structure Determination and Biological Evaluation of Cytotoxic Cyclodepsipeptide Destruxin F
- Lectin-Assisted Imaging Mass Cytometry (Lectin-IMC) Enables Spatial Validation of Disease-Associated Glyco-Niches within a Multimodal Glycoprotein Analysis Framework
- KAT-Net: a hyperbolic routing framework for joint lysine acylation site prediction with shared sequence–structure representations
BibTeX
@article{yu2026aiassisted,
title = {{AI-Assisted Molecular Structure Prediction from Tandem Mass Spectra: Reliability and Validation}},
author = {Jun Sang Yu and Sung Hue Jeong and Yejin Kim and Dong Keun Lee and Hye Hyun Yoo},
journal = {International Journal of Molecular Sciences},
year = {2026},
month = nov,
doi = {10.3390/ijms272110012},
url = {https://www.mdpi.com/1422-0067/27/21/10012},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - AI-Assisted Molecular Structure Prediction from Tandem Mass Spectra: Reliability and Validation
AU - Jun Sang Yu
AU - Sung Hue Jeong
AU - Yejin Kim
AU - Dong Keun Lee
AU - Hye Hyun Yoo
PY - 2026
DA - 2026/11/08
JO - International Journal of Molecular Sciences
DO - 10.3390/ijms272110012
UR - https://www.mdpi.com/1422-0067/27/21/10012
AB - 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.
SN - 1422-0067
ER -