Comment on "Proteoliposomes on 2D-MoS₂ Plasmonic Nanocavities for Enhanced Raman Spectroscopy with Machine Learning-based Identification and Classification"
DOI:
https://doi.org/10.66535/tks5j179Keywords:
Surface-Enhanced Raman Spectroscopy (SERS), Machine Learning, 2D materials (specifically MoS₂)Abstract
The integration of engineered lipid vesicles with surface-enhanced Raman spectroscopy (SERS) and supervised machine learning represents a productive strategy for label-free molecular profiling of nanoparticle biomarkers. The recent paper by Shiekh et al.1 describes a library of synthetic proteoliposomes functionalized with cancer-associated surface markers and a 2D molybdenum disulfide (MoS₂) plasmonic nanocavity microchip (MoSERS) for SERS classification. The authors report Random Forest Classifier (RFC) and Support Vector Machine (SVM) test accuracies of 82% and 76%, respectively, with area under the ROC curve (AUC) values of approximately 0.97–0.98. While the experimental platform and its concept are noteworthy, this comment identifies several methodological concerns—encompassing biomarker identification, machine learning evaluation practice, enhancement factor definition, and the impact of partial protein incorporation—whose resolution would substantially strengthen the reproducibility and comparability of the reported findings.
References
1.Shiekh, S.; Zhou, Y.; del Real Mata, C.; Jalali, M.; McCormack-Ilersich, J.; Hosseini, I. I.; Liu, Z.; Pessoa, M. A. S.; Hamidi, S. V.; Montermini, L.; Rak, J.; Reisner, W.; Mahshid, S. Proteoliposomes on 2D-MoS₂ Plasmonic Nanocavities for Enhanced Raman Spectroscopy with Machine Learning-based Identification and Classification. npj 2D Mater. Appl. 2025, 9, 115.
2.Sonnenberg, A.; Linders, C. J. T.; Daams, J. H.; Kennel, S. J. The α6β1 (VLA-6) and α6β4 Protein Complexes: Tissue Distribution and Biochemical Properties. J. Cell Sci. 1990, 96, 207–217.
3.Varoquaux, G. Cross-validation failure: Small sample sizes lead to large error bars. NeuroImage 2018, 166, 518–534.
4.Filzmoser, P.; Liebmann, B.; Varmuza, K. Repeated double cross validation. J. Chemom. 2009, 23, 160–171.
5.Hastie, T.; Tibshirani, R.; Friedman, J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed.; Springer: New York, 2009.
6.Ho, C.-S.; Jean, N.; Hogan, C. A.; Blackmon, L.; Jeffrey, S. S.; Holodniy, M.; Banaei, N.; Bhatt, D. L.; Boxer, S. G.; Bhatt, D. Rapid Identification of Pathogenic Bacteria Using Raman Spectroscopy and Deep Learning. Nat. Commun. 2019, 10, 4927.
7.Seifert, S. Application of Random Forest Based Approaches to Surface-Enhanced Raman Scattering Data. Sci. Rep. 2020, 10, 5436.
8.Le Ru, E. C.; Blackie, E.; Meyer, M.; Etchegoin, P. G. Surface Enhanced Raman Scattering Enhancement Factors: A Comprehensive Study. J. Phys. Chem. C 2007, 111, 13794–13803.
9.Rigaud, J.-L.; Lévy, D. Reconstitution of Membrane Proteins into Liposomes. Methods Enzymol. 2003, 372, 65–86.
10.Veit, S.; Paweletz, L. C.; Pomorski, T. G. Determination of Membrane Protein Orientation upon Liposomal Reconstitution down to the Single Vesicle Level. Biol. Chem. 2023, 404, 647–661.
11.Jalali, M.; Lu, Y.; del Real Mata, C.; Rak, J.; Mahshid, S. Nanoscopic Technologies toward Molecular Profiling of Single Extracellular Vesicles for Cancer Liquid Biopsy. Appl. Phys. Rev. 2025, 12, 011312.
12.Jalali, M.; Mahshid, S. et al. MoS₂-Plasmonic Nanocavities for Raman Spectra of Single Extracellular Vesicles Reveal Molecular Progression in Glioblastoma. ACS Nano 2023, 17, 12052–12071.
Downloads
Published
Versions
- 2026-04-03 (2)
- 2026-01-01 (1)
