Karam Nader

Karam Nader

Auto-generated profile, based on publicly available information

Karam Nader

Department of Organic and Inorganic Chemistry, Faculty of Science and Technology, University of The Basque Country (UPV/EHU), PO Box 644, 48080 Bilbao, Spain

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 March 2025 in Physical Chemistry Chemical Physics
Verified
Journal Article
Open access
PDF file
MSMireia Sainz-Menchón
Mireia Sainz-Menchón
IAIñigo González de Arrieta
Iñigo González de Arrieta
TETelmo Echániz
Telmo Echániz
KNKaram Nader
Karam Nader
MIMaite Insausti
Maite Insausti
Gabriel A. LópezGabriel A. López
Gabriel A. López
FT-IR spectroscopy enables distinction of the isostructural magnetite and maghemite phases in magnetic nanoparticles, with potential implications for evaluating their stoichiometry in biomedical applications.

25 September 2025 in Machine Learning: Science and Technology
Verified
Journal Article
Open access
ARAndrea Ruiz-Escudero
Andrea Ruiz-Escudero
MBMaxim Belii
Maxim Belii
KNKaram Nader
Karam Nader
MIMaite Insausti
Maite Insausti
ICIdoia Castellanos-Rubio
Idoia Castellanos-Rubio
Humbert G. DíazHumbert G. Díaz
Humbert G. Díaz
Neurodegenerative diseases (NDDs) are a major global health concern, exacerbated by the blood–brain barrier (BBB), which limits effective drug delivery to the brain. Designing nanoparticles (NPs) to cross the BBB and deliver drugs could greatly improve the treatment of NDDs; however, current approaches to designing materials for drug delivery are generally slow. This study introduces an approach integrating information fusion, Python encoding, perturbation theory, and machine learning to predict the behaviour of NPs as drug delivery systems. Using an extensive pharmacokinetic database, random forest, extreme gradient boosting, and decision tree algorithms are trained and optimised. The random forest model achieves accuracies of 95.1% and 89.7% on training and testing data, respectively. As a proof of concept for the model’s utility, four novel Fe3O4 NP systems are synthesised via thermal decomposition and functionalised for water solubility. Structural, morphological, and magnetic characterisations are performed. The ML model is then applied to these synthesised NPs, with predictions identifying PMAO-coated NPs as promising candidates for BBB and neuronal cell lines. This design framework offers significant advancements in the efficient identification of promising potential NP candidates for NDDs drug delivery, enabling predictions of desirable bioactivity profiles.