Abstract
Accurate and rapid diagnostic tests that are simultaneously affordable remain elusive, typically due to trade-offs between performance and cost. Conventional nucleic acid tests offer high sensitivity but require complex, expensive steps such as amplification and purification, whereas lateral flow assays are simple and low-cost but lack the necessary sensitivity for many applications. New analytical approaches provide an opportunity to bridge this gap, raising sensitivity but not material expense. We present a miniaturized and simplified chip-based platform that combines three components into a single diagnostic pipeline: we use (i) spectrally distinct silver and gold nanoparticles (NPs) that form analyte-dependent clusters with unique spectral fingerprints, (ii) a one-pot, enzyme- and purification-free assay on a chip integrated with a high-throughput automated low-cost microscope, and (iii) a morphology-guided convolutional Graph Neural Network that embeds morphology information into convolutional kernels and performs graph-based relational learning across particle-level features. This integration captures spectral, spatial, and morphological quantification at the particle level, rather than relying on bulk spectral shifts, thereby addressing key limitations observed in representative nanoparticle (NP) assays and image-level deep learning baselines under particle-parallel analysis. Mc-GNN is able to process up to 5,000 particle crops per image in a single computational step, using less than 2 GB of GPU memory. This allows us to achieve femtomolar sensitivity with 98.2% recall for synthetic DNA and 94.8% for SARS-CoV-2 RNA from whole viruses, within in-domain experimental variability arising from different NP combinations and assay conditions. By embedding morphological information into the biosensing pipeline, our diagnostic platform is computationally efficient with millisecond-scale neural compute per raw image on a single consumer-grade GPU and is readily extensible to new analytes and multiplexing, offering a scalable solution for a fieldable diagnostic tool.
Data availability
Representative example data and processed outputs used for demonstration and reproducibility are publicly available at https://github.com/kartik05112000/Mc_GNN_Analysis.git. The datasets generated during and/or analysed during the current study are available from the corresponding author on reasonable request.
Code availability
The full source code for Mc-GNN, together with scripts for preprocessing, training, evaluation, and representative example data, is publicly available at https://github.com/kartik05112000/Mc_GNN_Analysis.git. Additional datasets and experimental data supporting the findings of this study are available from the corresponding author on reasonable request.
References
Rezaei, M. et al. Point of care diagnostics in the age of covid-19. Diagnostics 11, 9. https://doi.org/10.3390/diagnostics11010009 (2021).
Valera, E. et al. COVID-19 point-of-care diagnostics: Present and future. ACS Nano 15, 7899–7906. https://doi.org/10.1021/acsnano.1c02981 (2021).
Posthuma-Trumpie, G. A., Korf, J. & van Amerongen, A. Lateral flow (immuno)assay: Its strengths, weaknesses, opportunities and threats. a literature survey. Anal. Bioanal. Chem. 393, 569–582. https://doi.org/10.1007/s00216-008-2287-2 (2009).
Mistry, D. A., Wang, J. Y., Moeser, M.-E., Starkey, T. & Lee, L. Y. W. A systematic review of the sensitivity and specificity of lateral flow devices in the detection of SARS-CoV-2. BMC Infect. Dis. 21, 828 https://doi.org/10.1186/s12879-021-06528-3 (2021).
Mirkin, C. A., Letsinger, R. L., Mucic, R. C. & Storhoff, J. J. A DNA-based method for rationally assembling nanoparticles into macroscopic materials. Nature 382, 607–609. https://doi.org/10.1038/382607a0 (1996).
Alivisatos, A. P. et al. Organization of ‘nanocrystal molecules’ using dna. Nature 382, 609–611 (1996).
Kim, S. et al. Optokinetically encoded nanoprobe-based multiplexing strategy for microRNA profiling. J. Am. Chem. Soc. 139, 3558–3566 (2017).
Seo, J., Kim, S., Park, H. H., Choi, D. Y. & Nam, J.-M. Nano-bio-computing lipid nanotablet. Sci. Adv. 5, eaau2124 (2019).
Kim, S. et al. Nanoparticle-based computing architecture for nanoparticle neural networks. Sci. Adv. 6, eabb3348 (2020).
Tun, W. S. T. et al. A machine learning colorimetric biosensor based on acetylcholinesterase and silver nanoparticles for the detection of dichlorvos pesticides. Mater. Chem. Front. 6, 1487–1498 (2022).
Sajed, S., Kolahdouz, M., Sadeghi, M. A. & Razavi, S. F. High-performance estimation of lead ion concentration using smartphone-based colorimetric analysis and a machine learning approach. ACS Omega 5, 27675–27684 (2020).
Li, X. et al. Nucleic acid amplification-free biosensor for sensitive and specific cfdna detection based on crispr-cas12a and single nanoparticle dark-field microscopy (dfm) imaging. Sens. Actuators B Chem. 406, 135363 (2024).
Zhang, D., Wang, K., Wei, W., Liu, Y. & Liu, S. Multifunctional plasmonic core-satellites nanoprobe for cancer diagnosis and therapy based on a cascade reaction induced by microrna. Anal. Chem. 93, 9521–9530 (2021).
Bennett, D. et al. Machine learning color feature analysis of a high throughput nanoparticle conjugate sensing assay. Anal. Chem. 95, 6550–6558 (2023).
Orouji, A., Ghasemi, F. & Hormozi-Nezhad, M. R. Machine learning-assisted colorimetric assay based on Au@Ag nanorods for chromium speciation. Anal. Chem. 95, 10110–10118 (2023).
Wu, N. et al. Ratiometric 3d dna machine combined with machine learning algorithm for ultrasensitive and high-precision screening of early urinary diseases. ACS Nano 15, 19522–19534 (2021).
Yang, J. et al. Machine learning-assistant colorimetric sensor arrays for intelligent and rapid diagnosis of urinary tract infection. ACS Sens. 9, 1945–1956 (2024).
Li, B. et al. Colorimetric sensor array based on gold nanoparticles with diverse surface charges for microorganisms identification. Anal. Chem. 89, 10639–10643 (2017).
Song, C. et al. Deep learning-assisted ultrasensitive detection of gold nanoparticles using light microscopy images captured by a cellphone camera. Anal. Chem. 97, 5164–5170 (2025).
Wang, X.-Y. et al. Holistic prediction of AuNP aggregation in diverse aqueous suspensions based on machine vision and dark-field scattering imaging. Anal. Chem. 96, 1506–1514 (2024).
Shiaelis, N. et al. Virus detection and identification in minutes using single-particle imaging and deep learning. ACS Nano 17, 697–710 (2023).
Liu, S. et al. A deep learning-enabled smartphone platform for rapid and sensitive colorimetric detection of dimethoate pesticide. Anal. Bioanal. Chem. 415, 7127–7138 (2023).
Kang, J. et al. Deepgt: Deep learning-based quantification of nanosized bioparticles in bright-field micrographs of Gires-Tournois biosensor. Nano Today 52, 101968 (2023).
Jin, K.-X., Shen, J., Wang, Y.-J., Yang, Y. & Cao, S.-H. Enhanced nanoparticle recognition via deep learning-accelerated plasmonic sensing. Biosensors 14, 363 (2024).
McAffee, D. B., Hu, Q., Arnob, A., Wu, H.-J. & Groves, J. T. Machine-learning strategy for high error tolerance in image-based digital molecular assays. bioRxiv 2025–08, https://doi.org/10.1101/2025.08.14.670347 (2025). Preprint.
Watzinger, F., Ebner, K. & Lion, T. Detection and monitoring of virus infections by real-time PCR. Mol. Aspects Med. 27, 254–298 (2006).
Chu, D. K. W. et al. Molecular Diagnosis of a Novel Coronavirus (2019-nCoV) Causing an Outbreak of Pneumonia. Clin. Chem. 66, 549–555 (2020).
Bevilacqua, P. et al. Antifouling strategies of nanoparticles for diagnostic and therapeutic application: A systematic review of the literature. Nanomaterials https://doi.org/10.3390/nano11030780 (2021).
Hurst, S. J., Lytton-Jean, A. K. R. & Mirkin, C. A. Maximizing DNA loading on a range of gold nanoparticle sizes. Anal. Chem. 78, 8313–8318 (2006).
Patterson, E. I. et al. Methods of inactivation of SARS-CoV-2 for downstream biological assays. J. Infect. Dis. 222, 1462–1467 (2020).
Cover, T. M. & Hart, P. E. Nearest neighbor pattern classification. IEEE Trans. Inf. Theory 13, 21–27 (1967).
Fisher, R. A. The use of multiple measurements in taxonomic problems. Ann. Eugen. 7, 179–188 (1936).
Hastie, T., Tibshirani, R. & Friedman, J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction 2 edn. (Springer, 2009).
Cortes, C. & Vapnik, V. Support-vector networks. In Advances in Neural Information Processing Systems (NeurIPS) (1995).
Zuiderveld, K. Contrast limited adaptive histogram equalization, 474–485 (Academic Press Professional Inc, 1994).
Pawley, J. Handbook of biological confocal microscopy Vol. vol. 236 (Springer Science & Business Media, 2006).
Goldman, D. B. Vignette and exposure calibration and compensation. IEEE Trans. Pattern Anal. Mach. Intell. 32, 2276–2288. https://doi.org/10.1109/TPAMI.2010.55 (2010).
Demšar, J. Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7, 1–30 (2006).
Cao, J. et al. In Shapeconv: Shape-aware convolutional layer for indoor rgb-d semantic segmentation, 7088–7097 (Proceedings of the IEEE/CVF international conference on computer vision, 2021).
Tek, F. B., Cam, I. & Karlı, D. Adaptive convolution kernel for artificial neural networks. J. Vis. Commun. Image Represent. 75, 103015 (2021).
Li, X., Wang, W., Hu, X. & Yang, J. In Selective kernel networks, 510–519 Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, (2019).
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K. & Yuille, A. L. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40, 834–848 (2017).
Long, J., Shelhamer, E. & Darrell, T. In Fully convolutional networks for semantic segmentation, 3431–3440 Proceedings of the IEEE conference on computer vision and pattern recognition, (2015).
Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18, 234–241 (Springer, 2015).
Wang, J. et al. Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 43, 3349–3364 (2020).
Zhang, P., Zhu, J., Zhang, C., Rong, Z. & Wu, Y. Semi-global shape-aware attention network for image segmentation and retrieval. Neurocomputing 506, 369–379 (2022).
Kuo, W., Angelova, A., Malik, J. & Lin, T.-Y. In Shapemask: Learning to segment novel objects by refining shape priors, 9207–9216 (Proceedings of the IEEE/CVF international conference on computer vision, 2019).
Liu, S. et al. Advances in Neural Information Processing Systems 30 (2017).
Takikawa, T., Acuna, D., Jampani, V. & Fidler, S. In Gated-scnn: Gated shape cnns for semantic segmentation, 5229–5238 Proceedings of the IEEE/CVF international conference on computer vision, (2019).
Liu, X. et al. In Delving into shape-aware zero-shot semantic segmentation, 2999–3009 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2023).
Feng, A., You, C., Wang, S. & Tassiulas, L. In Kergnns: Interpretable graph neural networks with graph kernels, vol. 36, 6614–6622 Proceedings of the AAAI conference on artificial intelligence, (2022).
Zhang, L. et al. Dual graph convolutional network for semantic segmentation. arXiv preprint arXiv:1909.06121 (2019).
Xu, J., Dai, E., Luo, D., Zhang, X. & Wang, S. In Shape-aware graph spectral learning, 2692–2701 Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, (2024).
Bera, A., Wharton, Z., Liu, Y., Bessis, N. & Behera, A. Sr-gnn: Spatial relation-aware graph neural network for fine-grained image categorization. IEEE Trans. Image Process. 31, 6017–6031 (2022).
Zhou, Y. et al. In Cgc-net: Cell graph convolutional network for grading of colorectal cancer histology images, 0–0 (Proceedings of the IEEE/CVF international conference on computer vision workshops, 2019).
Morphognn: Morphological embedding for single neuron with graph neural networks. bioRxiv (2022).
Shen, Y., Zhou, B., Xiong, X., Gao, R. & Wang, Y. G. In How graph neural networks enhance convolutional neural networks towards mining the topological structures from histology, vol. 8 (ICML Workshop on Computational Biology, 2022).
Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M. & Monfardini, G. The graph neural network model. IEEE Trans. Neural Netw. 20, 61–80. https://doi.org/10.1109/TNN.2008.2005605 (2009).
Jeon, Y. & Kim, J. In Active convolution: Learning the shape of convolution for image classification, 4201–4209 Proceedings of the IEEE conference on computer vision and pattern recognition, (2017).
Dai, J. et al. In Deformable convolutional networks, 764–773 Proceedings of the IEEE international conference on computer vision, (2017).
Moddy2024. Resnet-9. https://github.com/Moddy2024/ResNet-9 (2024). Accessed: 2025-06-19.
Swin transformer: Hierarchical vision transformer using shifted windows. In ICCV (2021).
Convnext v2: Co-designing and scaling convnets with masked autoencoders. In CVPR (2023).
Anonymous. Clustervig: Efficient vision graph networks via token clustering. arXiv preprint arXiv:2509.25570 (2025).
Anonymous. Attentionvig: Vision graph models with attention-based token interaction. arXiv preprint arXiv:2501.10640 (2025).
Zhang, X., Zhou, X., Lin, M. & Sun, J. In Shufflenet: An extremely efficient convolutional neural network for mobile devices, 6848–6856 (Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018).
Howard, A. G. et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017).
Han, K. et al. In Ghostnet: More features from cheap operations, 1580–1589 (Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020).
Tan, M. & Le, Q. Efficientnet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning (ICML), 6105–6114 (Proceedings of Machine Learning Research (PMLR), 2019).
Sönnichsen, C., Reinhard, B. M., Liphardt, J. & Alivisatos, A. P. A molecular ruler based on plasmon coupling of single gold and silver nanoparticles. Nat. Biotechnol. 23, 741–745 (2005).
Chen, J. I. L., Chen, Y. & Ginger, D. S. Plasmonic nanoparticle dimers for optical sensing of dna in complex media. J. Am. Chem. Soc. 132, 9600–9601 (2010).
Pennacchio, A. et al. A bacterial biosensor based on gold nanoparticles functionalized by a hydrophobin-chimera and combined with machine learning for user-friendly detection. Sens. Actuators B Chem. 410, 135645 (2024).
Pickering, S. et al. Comparative performance of SARS-CoV-2 lateral flow antigen tests and association with detection of infectious virus in clinical specimens: A single-centre laboratory evaluation study. Lancet Microbe 2, e461–e471 (2021).
Cubas-Atienzar, A. I. et al. Limit of detection in different matrices of 19 commercially available rapid antigen tests for the detection of SARS-CoV-2. Sci. Rep. 11, 18313. https://doi.org/10.1038/s41598-021-97489-9 (2021).
Sun, D. & Hu, T. Y. A low cost mobile phone dark-field microscope for nanoparticle-based quantitative studies. Biosens. Bioelectron. 99, 513–518 (2018).
de León Derby, M. D. et al. Ntdscope: A multi-contrast portable microscope for disease diagnosis. medRxiv 2025.03.17.25324136 (2025).
Loretan, M. et al. Direct single-molecule detection and super-resolution imaging with a low-cost portable smartphone-based microscope. Nat. Commun. 16, 8937. https://doi.org/10.1038/s41467-025-63993-z (2025).
Heo, J. H. et al. Ultrastable-stealth large gold nanoparticles with DNA directed biological functionality. Langmuir 31, 13773–13782 (2015).
Xu, S., Yuan, H., Xu, A., Wang, J. & Wu, L. Rapid synthesis of stable and functional conjugates of DNA/gold nanoparticles mediated by Tween 80. Langmuir 27, 13629–13634 (2011).
Zadeh, J. N. et al. NUPACK: Analysis and design of nucleic acid systems. J. Comput. Chem. 32, 170–173 (2011).
Fornace, M. E. et al. NUPACK: Analysis and Design of Nucleic Acid Structures, Devices, and Systems. ChemRxiv Version 1 (2022). Preprint.
Wu, R., Jiang, L.-P., Zhu, J.-J. & Liu, J. Effects of small molecules on DNA adsorption by gold nanoparticles and a case study of Tris(2-carboxyethyl)phosphine (TCEP). Langmuir 35, 13461–13468 (2019).
Liu, B., Wu, P., Huang, Z., Ma, L. & Liu, J. Bromide as a robust backfiller on gold for precise control of DNA conformation and high stability of spherical nucleic acids. J. Am. Chem. Soc. 140, 4499–4502 (2018).
Amasino, R. M. Acceleration of nucleic acid hybridization rate by polyethylene glycol. Anal. Biochem. 152, 304–307 (1986).
Donnelly, T., Faulds, K. & Graham, D. Investigation of silver nanoparticle assembly following hybridization with different lengths of DNA. Part. Part. Syst. Charact. 33, 404–411 (2016).
Bender, A. T., Sullivan, B. P., Lillis, L. & Posner, J. D. Enzymatic and chemical-based methods to inactivate endogenous blood ribonucleases for nucleic acid diagnostics. J. Mol. Diagn. 22, 1030–1040 (2020).
Acknowledgements
We thank Professor Atul N. Parikh (NTU - Singapore and UC Davis) for valuable discussions and for reviewing the final manuscript. This research is supported by the Ministry of Education, Singapore, under its Research Centre of Excellence award to the Institute for Digital Molecular Analytics and Science, NTU (IDMxS, grant: EDUNC-33-18-279-V12). Figure 2a contains art adapted from Servier Medical Art (https://smart.servier.com/), licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/).
Funding
This research is supported by the Ministry of Education, Singapore, under its Research Centre of Excellence award to the Institute for Digital Molecular Analytics and Science, NTU (IDMxS, grant: EDUNC-33-18-279-V12).
Author information
Authors and Affiliations
Contributions
K.J., X-L.C., and J.B.D. contributed equally to this work. K.J., X-L.C., J.B.D., P.T. and L.W. performed conceptualization. X-L.C., J.B.D., L.A.P., S.B., and F.N.N.M.H. performed experimental investigation. K.J. developed the data processing and deep learning method, carried out model training, and analyzed the results. Y.Y. and Y.W. contributed to model-related discussions. P.T. and L.W. performed supervision. K.J., X-L.C., and J.B.D. wrote the original manuscript draft. All authors contributed to review and editing of the final manuscript.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Jhawar, K., Chu, XL., DeGrandchamp, J.B. et al. Morphology-guided deep learning for nanoparticle agglomeration diagnostic assays. Sci Rep (2026). https://doi.org/10.1038/s41598-026-45423-2
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-45423-2
