A New AI Powered Biochip Can Help Reduce Resistance To Cancer Therapies

A multidisciplinary team of researchers from the University of California, Irvine has created a new biochip that can help study tumour heterogeneity to reduce resistance to cancer therapies.

What is tumour heterogeneity?
Tumour heterogeneity describes the observation that tumour cells can show distinct morphological and phenotypic profiles, including cellular morphology, gene expression, metabolism, motility, proliferation, and metastatic potential. This phenomenon occurs both between tumours and within tumours. This is a major problem as it increases resistance to cancer therapies.

The team combined AI, microfluidics and nanoparticle inkjet printing into this device which can examine and differentiate cancers and healthy tissues at the single-cell level.

A paper describing this device appeared recently in Advanced Biosystems journal. Kushal Joshi, a former UCI graduate student in biomedical engineering is the lead author of the paper.

“Cancer cell and tumour heterogeneity can lead to increased therapeutic resistance and inconsistent outcomes for different patients,” said Kushal Joshi. As mentioned above as well, this is a major problem which the team set out to solve with their biochip.

“Single-cell analysis is essential to identify and classify cancer types and study cellular heterogeneity. It’s necessary to understand tumour initiation, progression and metastasis in order to design better cancer treatment drugs,” said co-author Rahim Esfandyarpour, UCI assistant professor of electrical engineering & computer science as well as biomedical engineering.

The Problem
As you might have understood, we need to do single-cell analysis to study cellular heterogeneity. The problem is that the techniques and technologies traditionally used to study cancer are sophisticated, bulky, expensive, and require highly trained operators and long preparation times.“

The team overcame this problem by combining machine learning with accessible inkjet printing and microfluidics technology to develop low-cost, miniaturized biochips that are simple to prototype and capable of classifying various cell types. The innovation was getting a way to prototype key parts of the biochip in about 20 minutes with an inkjet printer, allowing for easy manufacturing in diverse settings.

Coming to the working of the apparatus, samples travel through microfluidic channels with carefully placed electrodes that monitor differences in the electrical properties of diseased versus healthy cells in a single pass.

Journal Reference:
Kushal Joshi, Alireza Javani, Joshua Park, Vanessa Velasco, Binzhi Xu, Olga Razorenova, Rahim Esfandyarpour. A Machine Learning‐Assisted Nanoparticle‐Printed Biochip for Real‐Time Single Cancer Cell Analysis. Advanced Biosystems, 2020; 2000160 DOI: 10.1002/adbi.202000160

Press Release: University of California – Irvine