Nanoinformatics: spanning scales, systems and solutions

• Iseult Lynch,
• Diego S. T. Martinez,
• Kunal Roy and
• Georgia Melagraki

Beilstein J. Nanotechnol. 2026, 17, 423–427, doi:10.3762/bjnano.17.28

• . Improving the efficacy of targeted therapies and minimizing off-target effects are key challenges in nanomedicine. To address these, Dasgupta et al. mapped the structural fingerprints of ligands governing the cellular uptake of MeOx nanomaterials based on classification-based ML models (i.e., Bayesian

• classification, random forest, support vector classifier, and linear discriminant analysis) applied to multiple cell types (pancreatic cancer cells (PaCa2), human endothelial cells (HUVEC) and human macrophage cells (U937)). The best model for each cell type was identified, and the structural fingerprints

Identification of structural features of surface modifiers in engineered nanostructured metal oxides regarding cell uptake through ML-based classification

• Indrasis Dasgupta,
• Totan Das,
• Biplab Das and
• Shovanlal Gayen

Beilstein J. Nanotechnol. 2024, 15, 909–924, doi:10.3762/bjnano.15.75

• , shape, and surface charge of NPs, as well as their surface functionalization. In the current study, classification-based ML models (i.e., Bayesian classification, random forest, support vector classifier, and linear discriminant analysis) have been developed to identify the features/fingerprints that

• governing the cellular uptake of ENMOs. The study will direct scientists in the design of ENMOs of higher cellular uptake efficiency for better therapeutic response. Keywords: Bayesian classification; cellular uptake; machine learning; nanoparticles (NPs); Introduction In recent years, the rapid

• modifiers in the training set (70%) and 21 modifiers in the test set (30%) for the different classification-based QSAR analyses. Bayesian classification study Bayesian classification was carried out via the “Create Bayesian model” protocol in Discovery Studio 3.0 [35]. To develop a model, various