Nucleic Acid Quantification by Multi-Frequency Impedance Cytometry and Machine Learning

Abstract

Determining nucleic acid concentrations in a sample is an important step prior to proceeding with downstream analysis in molecular diagnostics. Given the need for testing DNA amounts and its purity in many samples, including in samples with very small input DNA, there is utility of novel machine learning approaches for accurate and high-throughput DNA quantification. Here, we demonstrated the ability of a neural network to predict DNA amounts coupled to paramagnetic beads. To this end, a custom-made microfluidic chip is applied to detect DNA molecules bound to beads by measuring the impedance peak response (IPR) at multiple frequencies. We leveraged electrical measurements including the frequency and imaginary and real parts of the peak intensity within a microfluidic channel as the input of deep learning models to predict DNA concentration. Specifically, 10 different deep learning architectures are examined. The results of the proposed regression model indicate that an R_Squared of 97% with a slope of 0.68 is achievable. Consequently, machine learning models can be a suitable, fast, and accurate method to measure nucleic acid concentration in a sample. The results presented in this study demonstrate the ability of the proposed neural network to use the information embedded in raw impedance data to predict the amount of DNA concentration.

Advancing Healthcare: Synergizing Biosensors and Machine Learning for Early Cancer Diagnosis

“…Machine learning (ML) has grown rapidly over the past few decades and has widely used applications not only limited to healthcare problems, such as predicting drug discoveries and diagnosing diseases, but also in other fields, such as mechanics, robotics, and image recognition [30][31][32][33][34]. In simple words, ML is a rapidly developing field of computational algorithms that aims to replicate human intelligence by adapting to their surroundings and learning from them [35].…”

“…During the model training process, the predicted output is compared to the actual output, and modifications are made to decrease the overall error between the two. Supervised machine learning algorithms have a broad range of applications in biosensors and healthcare, including tasks such as distinguishing cancer from non-cancer cells, detecting circulating tumor cells (CTCs), and predicting DNA quantities [ 31 , 38 , 39 ]. In the following sections, the most well-known and commonly supervised algorithms will be discussed.…”

A Short Review on Miniaturized Biosensors for the Detection of Nucleic Acid Biomarkers

“…Kokabi et al [ 116 ] proposed a neural network to prophesy nucleic acid quantities united to paramagnetic drops. To this end, a custom-built microfluidic channel was used to sense nucleic acid particles bound to slides by gauging the impedance peak response (IPR) at numerous occurrences.…”

“… ( A ) Overview of the process and microscopic cross section of channel and electrodes [ 116 ] ( B ) Schematic of the LoC developed by STMicroelectronics [ 117 ] ( C ) Schematic of meta surface biosensors [ 118 ] ( D ) Schematic of dielectric meta surface structure and the whole view of meta surface substrate [ 119 ]. …”

Robust machine−learning based prognostic index using cytotoxic T lymphocyte evasion genes highlights potential therapeutic targets in colorectal cancer

“…In recent decades, there has been rapid advancement in the field of machine learning. It is not only widely applied in healthcare−related fields, such as drug discovery and disease diagnosis, its utilization also extends widely to other domains, including mechanics, robotics, and image recognition [19][20][21][22][23]. Furthermore, machine learning has been widely used in emerging technologies, such as pathomics and radiomics.…”