Nano-Motion Analysis for Rapid and Label Free Assessing of Cancer Cell Sensitivity to Chemotherapeutics

Machine learning and artificial intelligence: Enabling the clinical translation of atomic force microscopy-based biomarkers for cancer diagnosis

The influence of biomechanics on cell function has become increasingly defined over recent years. Biomechanical changes are known to affect oncogenesis; however, these effects are not yet fully understood. Atomic force microscopy (AFM) is the gold standard method for measuring tissue mechanics on the micro- or nano-scale. Due to its complexity, however, AFM has yet to become integrated in routine clinical diagnosis. Artificial intelligence (AI) and machine learning (ML) have the potential to make AFM more accessible, principally through automation of analysis. In this review, AFM and its use for the assessment of cell and tissue mechanics in cancer is described. Research relating to the application of artificial intelligence and machine learning in the analysis of AFM topography and force spectroscopy of cancer tissue and cells are reviewed. The application of machine learning and artificial intelligence to AFM has the potential to enable the widespread use of nanoscale morphologic and biomechanical features as diagnostic and prognostic biomarkers in cancer treatment.

Accurate and rapid antibiotic susceptibility testing using a machine learning-assisted nanomotion technology platform

Antimicrobial resistance (AMR) is a major public health threat, reducing treatment options for infected patients. AMR is promoted by a lack of access to rapid antibiotic susceptibility tests (ASTs). Accelerated ASTs can identify effective antibiotics for treatment in a timely and informed manner. We describe a rapid growth-independent phenotypic AST that uses a nanomotion technology platform to measure bacterial vibrations. Machine learning techniques are applied to analyze a large dataset encompassing 2762 individual nanomotion recordings from 1180 spiked positive blood culture samples covering 364 Escherichia coli and Klebsiella pneumoniae isolates exposed to cephalosporins and fluoroquinolones. The training performances of the different classification models achieve between 90.5 and 100% accuracy. Independent testing of the AST on 223 strains, including in clinical setting, correctly predict susceptibility and resistance with accuracies between 89.5% and 98.9%. The study shows the potential of this nanomotion platform for future bacterial phenotype delineation.

A simplified version of rapid susceptibility testing of bacteria and yeasts using optical nanomotion detection

We present a novel optical nanomotion-based rapid antibiotic and antifungal susceptibility test. The technique consisted of studying the effects of antibiotics or antifungals on the nanometric scale displacements of bacteria or yeasts to assess their sensitivity or resistance to drugs. The technique relies on a traditional optical microscope, a video camera, and custom-made image analysis software. It provides reliable results in a time frame of 2-4 h and can be applied to motile, non-motile, fast, and slowly growing microorganisms. Due to its extreme simplicity and low cost, the technique can be easily implemented in laboratories and medical centers in developing countries.

Machine learning method for the classification of the state of living organisms' oscillations

The World Health Organization highlights the urgent need to address the global threat posed by antibiotic-resistant bacteria. Efficient and rapid detection of bacterial response to antibiotics and their virulence state is crucial for the effective treatment of bacterial infections. However, current methods for investigating bacterial antibiotic response and metabolic state are time-consuming and lack accuracy. To address these limitations, we propose a novel method for classifying bacterial virulence based on statistical analysis of nanomotion recordings. We demonstrated the method by classifying living Bordetella pertussis bacteria in the virulent or avirulence phase, and dead bacteria, based on their cellular nanomotion signal. Our method offers significant advantages over current approaches, as it is faster and more accurate. Additionally, its versatility allows for the analysis of cellular nanomotion in various applications beyond bacterial virulence classification.

Mechanical Properties and Nanomotion of BT-20 and ZR-75 Breast Cancer Cells Studied by Atomic Force Microscopy and Optical Nanomotion Detection Method

Cells of two molecular genetic types of breast cancer-hormone-dependent breast cancer (ZR-75 cell line) and triple-negative breast cancer (BT-20 cell line)-were studied using atomic force microscopy and an optical nanomotion detection method. Using the Peak Force QNM and Force Volume AFM modes, we revealed the unique patterns of the dependence of Young's modulus on the indentation depth for two cancer cell lines that correlate with the features of the spatial organization of the actin cytoskeleton. Within a 200-300 nm layer just under the cell membrane, BT-20 cells are stiffer than ZR-75 cells, whereas in deeper cell regions, Young's modulus of ZR-75 cells exceeds that of BT-20 cells. Two cancer cell lines also displayed a difference in cell nanomotion dynamics upon exposure to cytochalasin D, a potent actin polymerization inhibitor. The drug strongly modified the nanomotion pattern of BT-20 cells, whereas it had almost no effect on the ZR-75 cells. We are confident that nanomotion monitoring and measurement of the stiffness of cancer cells at various indentation depths deserve further studies to obtain effective predictive parameters for use in clinical practice.

Differences in bacteria nanomotion profiles and neutrophil nanomotion during phagocytosis

The main goal of this work is to highlight the connection between nanomotion and the metabolic activity of living cells. We therefore monitored the nanomotion of four different clinical strains of bacteria (prokaryotes) and the bacterial phagocytosis by neutrophil granulocytes (eukaryotes). All clinical strains of bacteria, regardless of their biochemical profile, showed pronounced fluctuations. Importantly, the nature of their nanomotions was different for the different strains. Flagellated bacteria (Escherichia coli, Proteus mirabilis) showed more pronounced movements than the non-flagellated forms (Staphylococcus aureus, Klebsiella pneumoniae). The unprimed neutrophil did not cause any difference in cantilever oscillations with control. However, in the process of phagocytosis of S. aureus (metabolically active state), a significant activation of neutrophil granulocytes was observed and cell nanomotions were maintained at a high level for up to 30 min of observation. These preliminary results indicate that nanomotion seems to be specific to different bacterial species and could be used to monitor, in a label free manner, basic cellular processes.