Sorting hidden patterns in nanoparticle performance for glioblastoma using machine learning algorithms

Unraveling rosmarinic acid anticancer mechanisms in oral cancer malignant transformation

Oral squamous cell carcinoma (OSCC) is expected to rise ca. 40 % by 2040. Rosmarinic acid (RA) has been recognized for its anticancer properties, although its role in OSCC has been neglected. This work exploits the activity of RA in 2D and 3D models of OSCC cells to compel a roadmap for its anticancer properties. The results demonstrated that RA significantly reduced cell mass and metabolic activity in a dose, time, and cell-type-dependent manner, predominantly in highly-invasive OSCC, without compromising normal mucosa in therapeutic doses. RA decreased mitochondria membrane potential and increased redox state, which was corroborated by pioneering observations on the metabolome landscape of OSCC cells (glutathione reduction and acetate and fumarate release). RA triggered autophagy, upregulating BNIP3 and BCNL1 and downregulating BIRC5. The upregulation of CADM1 and downregulation of VIM, CADM2, SNAIL1, and SOX9 highlighted the modulation of epithelial-mesenchymal transition and the remodeling of the extracellular matrix by the downregulation of MMP-2 and MMP-9. RA interacts with P-glycoprotein with the highest docking score of -6.4 kcal/mol. The HSC-3 cell surface charge decreased after RA treatment (-22.6 ± 0.3 mV vs. -26.3 ± 0.3 mV, p < 0.0001), suggesting a reversion of cell polarity and the impairment of invasion. RA also shrank the growth and the metabolic activity of multicellular tumor spheroids. Its modest protein binding with human saliva sheds light on its administration by the oromucosal route. Overall, this work supports the need for further research on the anticancer potential of RA in OSCC, either in monotherapy, combined with conventional treatments, or conveyed in nanosystems.

Structural Similarity, Activity, and Toxicity of Mycotoxins: Combining Insights from Unsupervised and Supervised Machine Learning Algorithms

A large number of mycotoxins and related fungal metabolites have not been assessed in terms of their toxicological impacts. Current methodologies often prioritize specific target families, neglecting the complexity and presence of co-occurring compounds. This work addresses a fundamental question: Can we assess molecular similarity and predict the toxicity of mycotoxins in silico using a defined set of molecular descriptors? We propose a rapid nontarget screening approach for multiple classes of mycotoxins, integrating both unsupervised and supervised machine learning models, alongside molecular and physicochemical descriptors to enhance the understanding of structural similarity, activity, and toxicity. Clustering analyses identify natural clusters corresponding to the known mycotoxin families, indicating that mycotoxins belonging to the same cluster share similar molecular properties. However, topological descriptors play a significant role in distinguishing between acutely toxic and nonacutely toxic compounds. Random forest (RF) and neural networks (NN), combined with molecular descriptors, contribute to improved knowledge and predictive capability regarding mycotoxin toxicity profiles. RF allows the prediction of toxicity using data reflecting mainly structural features and performs well in the presence of descriptors reflecting biological activity. NN models prove to be more sensitive to biological activity descriptors than RF. The use of descriptors encompassing structural complexity and diversity, chirality and symmetry, connectivity, atomic charge, and polarizability, together with descriptors representing lipophilicity, absorption, and permeation of molecules, is crucial for predicting toxicity, facilitating broader toxicological evaluations.

Review of machine learning for lipid nanoparticle formulation and process development

Lipid nanoparticles (LNPs) are a subset of pharmaceutical nanoparticulate formulations designed to encapsulate, stabilize, and deliver nucleic acid cargoes in vivo. Applications for LNPs include new interventions for genetic disorders, novel classes of vaccines, and alternate modes of intracellular delivery for therapeutic proteins. In the pharmaceutical industry, establishing a robust formulation and process to achieve target product performance is a critical component of drug development. Fundamental understanding of the processes for making LNPs and their interactions with biological systems have advanced considerably in the wake of the COVID-19 pandemic. Nevertheless, LNP formulation research remains largely empirical and resource intensive due to the multitude of input parameters and the complex physical phenomena that govern the processes of nanoparticle precipitation, self-assembly, structure evolution, and stability. Increasingly, artificial intelligence and machine learning (AI/ML) are being applied to improve the efficiency of research activities through in silico models and predictions, and to drive deeper fundamental understanding of experimental inputs to functional outputs. This review will identify current challenges and opportunities in the development of robust LNP formulations of nucleic acids, review studies that apply machine learning methods to experimental datasets, and provide discussion on associated data science challenges to facilitate collaboration between formulation and data scientists, aiming to accelerate the advancement of AI/ML applied to LNP formulation and process optimization.

Peptide-Hitchhiking for the Development of Nanosystems in Glioblastoma

Glioblastoma (GBM) remains the epitome of aggressiveness and lethality in the spectrum of brain tumors, primarily due to the blood-brain barrier (BBB) that hinders effective treatment delivery, tumor heterogeneity, and the presence of treatment-resistant stem cells that contribute to tumor recurrence. Nanoparticles (NPs) have been used to overcome these obstacles by attaching targeting ligands to enhance therapeutic efficacy. Among these ligands, peptides stand out due to their ease of synthesis and high selectivity. This article aims to review single and multiligand strategies critically. In addition, it highlights other strategies that integrate the effects of external stimuli, biomimetic approaches, and chemical approaches as nanocatalytic medicine, revealing their significant potential in treating GBM with peptide-functionalized NPs. Alternative routes of parenteral administration, specifically nose-to-brain delivery and local treatment within the resected tumor cavity, are also discussed. Finally, an overview of the significant obstacles and potential strategies to overcome them are discussed to provide a perspective on this promising field of GBM therapy.

Nanomedical research and development in Spain: improving the treatment of diseases from the nanoscale

The new and unique possibilities that nanomaterials offer have greatly impacted biomedicine, from the treatment and diagnosis of diseases, to the specific and optimized delivery of therapeutic agents. Technological advances in the synthesis, characterization, standardization, and therapeutic performance of nanoparticles have enabled the approval of several nanomedicines and novel applications. Discoveries continue to rise exponentially in all disease areas, from cancer to neurodegenerative diseases. In Spain, there is a substantial net of researchers involved in the development of nanodiagnostics and nanomedicines. In this review, we summarize the state of the art of nanotechnology, focusing on nanoparticles, for the treatment of diseases in Spain (2017-2022), and give a perspective on the future trends and direction that nanomedicine research is taking.

A hierarchical machine learning model based on Glioblastoma patients' clinical, biomedical, and image data to analyze their treatment plans

AIM OF STUDY

Glioblastoma Multiforme (GBM) is an aggressive brain cancer in adults that kills most patients in the first year due to ineffective treatment. Different clinical, biomedical, and image data features are needed to analyze GBM, increasing complexities. Besides, they lead to weak performances for machine learning models due to ignoring physicians' knowledge. Therefore, this paper proposes a hierarchical model based on Fuzzy C-mean (FCM) clustering, Wrapper feature selection, and twelve classifiers to analyze treatment plans.

METHODOLOGY/APPROACH

The proposed method finds the effectiveness of previous and current treatment plans, hierarchically determining the best decision for future treatment plans for GBM patients using clinical data, biomedical data, and different image data. A case study is presented based on the Cancer Genome Atlas Glioblastoma Multiforme dataset to prove the effectiveness of the proposed model. This dataset is analyzed using data preprocessing, experts' knowledge, and a feature reduction method based on the Principal Component Analysis. Then, the FCM clustering method is utilized to reinforce classifier learning.

OUTCOMES OF STUDY

The proposed model finds the best combination of Wrapper feature selection and classifier for each cluster based on different measures, including accuracy, sensitivity, specificity, precision, F-score, and G-mean according to a hierarchical structure. It has the best performance among other reinforced classifiers. Besides, this model is compatible with real-world medical processes for GBM patients based on clinical, biomedical, and image data.

A Stepwise Framework for the Systematic Development of Lipid Nanoparticles

A properly designed nanosystem aims to deliver an optimized concentration of the active pharmaceutical ingredient (API) at the site of action, resulting in a therapeutic response with reduced adverse effects. Due to the vast availability of lipids and surfactants, producing stable lipid dispersions is a double-edged sword: on the one hand, the versatility of composition allows for a refined design and tuning of properties; on the other hand, the complexity of the materials and their physical interactions often result in laborious and time-consuming pre-formulation studies. However, how can they be tailored, and which premises are required for a “right at first time” development? Here, a stepwise framework encompassing the sequential stages of nanoparticle production for disulfiram delivery is presented. Drug in lipid solubility analysis leads to the selection of the most suitable liquid lipids. As for the solid lipid, drug partitioning studies point out the lipids with increased capacity for solubilizing and entrapping disulfiram. The microscopical evaluation of the physical compatibility between liquid and solid lipids further indicates the most promising core compositions. The impact of the outer surfactant layer on the colloidal properties of the nanosystems is evaluated recurring to machine learning algorithms, in particular, hierarchical clustering, principal component analysis, and partial least squares regression. Overall, this work represents a comprehensive systematic approach to nanoparticle formulation studies that serves as a basis for selecting the most suitable excipients that comprise solid lipid nanoparticles and nanostructured lipid carriers.