Mechanical properties of biological cells can serve as biomarkers for indicating various diseases like cancer and sickle cell disease. Hertzian model-based prediction of mechanical properties of biological cells, although most widely used, has shown to have limited potential in determining constitutive parameters of cells of uneven shape and non-linear force-indentation responses of AFM-based cell nanoindentation. We report a new artificial neural network-aided approach, which takes into account, the variation in cell shapes and their effect on the predictions in cell mechanophenotyping. We have developed an artificial neural network (ANN) model which could predict the mechanical properties of biological cells by utilizing the force vs. indentation curve of AFM and we obtained a recall of 0.98 ± 0.03 and 1 ± 0.0 for hyperelastic and elastic cells respectively for the prediction error of less than 10%. We envisage that the developed technique can be used for the validation of quantitative biomechanical markers for diagnoses of diseases like cancer and sickle cell disease which could help to improve clinical decision-making.

A lab-on-chip device that combines membrane-based blood plasma separation and a localized surface plasmon resonance (LSPR) based biosensor for on-chip detection of dengue NS1 antigen from a few drops of blood.

The artificial neural network (ANN) based models have shown the potential to provide alternate data-driven solutions in disease diagnostics, cell sorting and overcoming AFM-related limitations. Hertzian model-based prediction of mechanical properties of biological cells, although most widely used, has shown to have limited potential in determining constitutive parameters of cells of uneven shape and non-linear nature of force-indentation curves in AFM-based cell nanoindentation. We report a new artificial neural network-aided approach, which takes into account, the variation in cell shapes and their effect on the predictions in cell mechanophenotyping. We have developed an artificial neural network (ANN) model which could predict the mechanical properties of biological cells by utilizing the force vs. indentation curve of AFM. For cells with 1 µm contact length (Platelets), we obtained a recall of 0.97 ± 0.03 and 0.99 ± 0.0 for cells with hyperelastic and linear elastic constitutive properties respectively with a prediction error of less than 10%. Also, for cells with 6-8 µm contact length (RBCs), we obtained the recall of 0.975 in predicting mechanical properties with less than 15% error. We envisage that the developed technique can be used for better estimation of cells' constitutive parameters by incorporating cell topography into account.

This paper presents a novel approach for the stiffness characterization of thin membranes using the droplet motion characteristics over the membrane. The droplet motion over an inclined free hanging thin compliant membrane is investigated with the help of numerical model. Effect of substrate compliance over the displacement of the droplet has been studied. Further, the wall deformation of the substrate with the droplet motion has also been investigated. The numerical study has highlighted that the distance moved by a droplet over a membrane reduces with reduction in flexural rigidity of the membrane. Also, the dependency of motion of droplet with contact angle hysteresis (CAH) is presented. It was observed that the CAH increases with decrease in flexural rigidity of the membrane. These characteristics of the droplet motion over inclined free-hanging thin complaint membrane have been utilized to predict the Young's modulus of PDMS membranes using a novel Artificial Neural Network (ANN) model. The ANN model is developed for the same purpose. The input parameters for the ANN model are the droplet's displacement over a fixed time interval (𝑥), the PDMS membrane's deflection (𝑌), the angle of inclination (𝜃), the thickness of the membrane (𝑡), and the droplet's volume (𝑉). The output parameter of the ANN is the Young’s Modulus of the PDMS membrane. The created ANN network was found to have good accuracy (𝑅𝑜𝑣𝑒𝑟𝑎𝑙𝑙 = 0.992) in predicting the Young's modulus of the PDMS membrane. The proposed approach is a simple, low-cost method for prediction of Young’s modulus of PDMS membranes.

Mechanical property of biological cells can act as an indicator for the health state of a human being. Mathematical modelling of cells help to understand and predict the cell deformation patterns that might provide insightful finding for cell mechanics. Many models have been developed that tries to explain the cell mechanics at the cellular level. We propose an analytical model that considers the poroelastic nature of cells to understand their deformation behavior. The validity of the model is tested by comparing the predicted cell deformations against the experimental observations reported by Raj et al. (2017). Also, a computational study is performed, where we employ an in house Python code along with MS Excel GRG solver which incorporates the cell deformation predictions from developed poroelastic model and predicts the Young’s modulus value of the cells. The predictions using GRG based approach showed a good match with the experimental results with a maximum error of 12.09% in the case of MDA MB-231 cells. Further, we present an artificial neural network model to predict the Young’s modulus and viscosity of cells based on the experimentally measured input parameters such as entry time, transit velocity, initial cell diameter and extension ratio from the cell migration process through a micro-constriction channel. It was found that the neural network with architecture of 4-5-1 was best suited for the MCF-10A cells while the 4-8-1 architecture was giving better results for the MDA MB-231 cells. The developed ANN model is further tested for Young’s Modulus prediction of HeLa cells with completely new set of data. The predictions from ANN based model for HeLa cells matched well the experimental prediction within 4.5 % of error.