A Machine Learning Approach to COVID-19 Detection via Graphene Field-Effect-Transistor (GFET).

In the wake of the COVID-19 pandemic, there has been a need for reliable diagnostic testing. However, state-of-the-art detection methods rely on laboratory tests and also vary in accuracy. We evaluate that the usage of a graphene field-effect-transistor (GFET) coupled with machine learning can be a promising alternate diagnostic testing method. We processed the current-voltage data gathered from the GFET sensors to assess information about the presence of COVID-19 in biosamples. We perform binary classification using the following machine learning algorithms: Linear Discriminant Analysis (LDA), Support Vector Machines (SVM) with the Radial Basis Function (RBF) kernel, and K-Nearest Neighbors (KNN) in conjunction with Principal Component Analysis (PCA). We find that LDA and SVM with RBF proved to be the most accurate in identifying positive and negative samples, with accuracies of 99% and 98.5%, respectively. Based on these results, there is promise to develop a bioelectronic diagnostic method for COVID-19 detection by combining GFET technology with machine learning.

Capture of circulating metastatic cancer cell clusters from a lung cancer patient can reveal a unique genomic profile and potential anti-metastatic molecular targets: A proof of concept study.

Metastasis remains the leading cause of cancer deaths worldwide and lung cancer, known for its highly metastatic progression, remains among the most lethal of malignancies. The heterogeneous genomic profile of lung cancer metastases is often unknown. Since different metastatic events can selectively spread to multiple organs, strongly suggests more studies are needed to understand and target these different pathways. Unfortunately, access to the primary driver of metastases, the metastatic cancer cell clusters (MCCCs), remains difficult and limited. These metastatic clusters have been shown to be 100-fold more tumorigenic than individual cancer cells. Capturing and characterizing MCCCs is a key limiting factor in efforts to help treat and ultimately prevent cancer metastasis. Elucidating differentially regulated biological pathways in MCCCs will help uncover new therapeutic drug targets to help combat cancer metastases. We demonstrate a novel, proof of principle technology, to capture MCCCs directly from patients' whole blood. Our platform can be readily tuned for different solid tumor types by combining a biomimicry-based margination effect coupled with immunoaffinity to isolate MCCCs. Adopting a selective capture approach based on overexpressed CD44 in MCCCs provides a methodology that preferentially isolates them from whole blood. Furthermore, we demonstrate a high capture efficiency of more than 90% when spiking MCCC-like model cell clusters into whole blood. Characterization of the captured MCCCs from lung cancer patients by immunofluorescence staining and genomic analyses, suggests highly differential morphologies and genomic profiles., This study lays the foundation to identify potential drug targets thus unlocking a new area of anti-metastatic therapeutics.