SWnet: a deep learning model for drug response prediction from cancer genomic signatures and compound chemical structures.

Background: One of the major challenges in precision medicine is accurate prediction of individual patient's response to drugs. A great number of computational methods have been developed to predict compounds activity using genomic profiles or chemical structures, but more exploration is yet to be done to combine genetic mutation, gene expression, and cheminformatics in one machine learning model.

Results: We presented here a novel deep-learning model that integrates gene expression, genetic mutation, and chemical structure of compounds in a multi-task convolutional architecture.

Microfluidic integrated capacitive biosensor for C-reactive protein label-free and real-time detection.

A microfluidic chip has been integrated with a capacitive biosensor based on mass-producible three-dimensional (3D) interdigital electrode arrays. To achieve the monitoring of biosensor preparation and cardiac- and periodontitis-related biomarkers, all the processes were detected in a continuously on-site way. Fabrication steps for the microfluidic chip-bonded 3D interdigital capacitor biosensor include gold thiol modification, the activation of EDC/sulfo-NHS, and the bioconjugation of antibodies.

A Novel Mass-Producible Capacitive Sensor with Fully Symmetric 3D Structure and Microfluidics for Cells Detection.

Affinity biosensors of interdigitated electrodes have been widely used in cell detection. This research presents a mass-producible and disposable three-dimensional (3D) structure capacitive sensor based on the integrated circuit package lead frames for cell concentration detection. The fully symmetric 3D interdigital electrode structure makes the sensor more homogeneous and sensitive.