Kernel-Based Microfluidic Constriction Assay for Tumor Sample Identification

Abstract

A high-throughput multiconstriction microfluidic channels device can distinguish human breast cancer cell lines (MDA-MB-231, HCC-1806, MCF-7) from immortalized breast cells (MCF-10A) with a confidence level of ∼81-85% at a rate of 50-70 cells/min based on velocity increment differences through multiconstriction channels aligned in series. The results are likely related to the deformability differences between nonmalignant and malignant breast cells. The data were analyzed by the methods/algorithms of Ridge, nonnegative garrote on kernel machine (NGK), and Lasso using high-dimensional variables, including the cell sizes, velocities, and velocity increments. In kernel learning based methods, the prediction values of 10-fold cross-validations are used to represent the difference between two groups of data, where a value of 100% indicates the two groups are completely distinct and identifiable. The prediction value is used to represent the difference between two groups using the established algorithm classifier from high-dimensional variables. These methods were applied to heterogeneous cell populations prepared using primary tumor and adjacent normal tissue obtained from two patients. Primary breast cancer cells were distinguished from patient-matched adjacent normal cells with a prediction ratio of 70.07%-75.96% by the NGK method. Thus, this high-throughput multiconstriction microfluidic device together with the kernel learning method can be used to perturb and analyze the biomechanical status of cells obtained from small primary tumor biopsy samples. The resultant biomechanical velocity signatures identify malignancy and provide a new marker for evaluation in risk assessment.

Sensing Cell Membrane Biophysical Properties for Detection of High Quality Human Oocytes

“…Liu et al and Wacogne et al developed a system that compresses the oocyte against several flexible beams by a holding pipet to detect oocyte quality. , A nanoforce sensor and a new force sensing platform using passive magnetic springs were presented to measure mechanical characteristics of oocytes. , It should be pointed out that these studies require complex equipment and are dependent on the experimental environment. , More recently, the genetic screening method was reported to optimize oocyte development rate and embryo quality. − However, the cost of genetic screening is high, and the process is complicated . Currently, the permeability parameter measurement has become an effective way to assess the viability and function of cells or tissues, , especially using microfluidic techniques. − This may be a novel way to detect high-quality oocytes. From the above, there is still the lack of a simple and efficient method for detecting high-quality oocytes.…”

Scalable nanolaminated SERS multiwell cell culture assay

“…In addition, both SVM and NNT are discriminative classifiers but are not dimension-reduction tools. NGK can be considered a hybrid approach that is a mixed nonparametric model and a kernel machine tool 45 . Using a training set, we built NGK classifiers that were required to estimate a nonparametric function but that did not assume a particular function form.…”

“…Analyzing cell mixtures that are present in a tissue sample by SERS is the next phase of development. Previously, we performed the biomechanical analysis of cell mixtures of normal and cancerous breast tissue obtained from patients with breast cancer 45 . We demonstrated that the biophysical attributes can be used to differentiate between the tumor tissue and adjacent normal tissue with machine learning algorithms.…”

Artificial Intelligence in Chemistry: Current Trends and Future Directions

“…In patents (Figure B), the trend is similar, but inventions in Energy Technology and Environmental Chemistry related to Industrial Chemistry and Chemical Engineering also show prominently. For example, journal documents using analytical chemistry techniques such as mass spectrometry and nuclear magnetic resonance, infrared, and Raman spectroscopies are augmented with machine learning for use in medical diagnostics, − studies of metabolomics, − and microbial identification, − while biochemistry-related analytical chemistry patents concentrate on the development of analytical devices and methods for use in similar studies. − AI-related journal documents with interest in Materials Science and Physical Chemistry discuss topics, such as the evaluation of structure–property relationships in materials by augmenting first-principles calculations with machine learning models, − using data from high-throughput experimentation to optimize the properties of functional materials, − and the use of published data to enable the discovery of new materials. − In patents, the combination of AI, Materials Science, and Physical Chemistry is used in methods for improving semiconductor device fabrication − and polymer performance. − …”