Machine Learning-Assisted Array-Based Detection of Proteins in Serum Using Functionalized MoS₂ Nanosheets and Green Fluorescent Protein Conjugates

Abstract

Abnormal concentrations of a specific protein or the presence of some biomarker proteins may indicate life-threatening diseases. Pattern-based detection of specific analytes using affinity-regulated receptors is one of the potential alternatives to specific antigen–antibody-based detection. In this report, we have schemed a sensor array by using various functionalized two-dimensional (2D)-MoS 2 nanosheets and green fluorescent protein (GFP) as the receptor and the signal transducer, respectively. Two-dimensional MoS 2 has been used as a promising candidate for recognition of the bioanalytes because of its high surface-to-volume ratio compared to those of other nanomaterials. Easy surface tunability of this material provides additional advantages to analyze the target of interest. The optimized 2D-MoS 2 –GFP conjugates are able to discriminate 15 different proteins at 50 nM concentration with a detection limit of 1 nM. Moreover, proteins in the binary mixture and in the presence of serum were discriminated successfully. Ten different proteins in serum media at relevant concentrations were classified successfully with 100% jackknifed classification accuracy, which proves the potentiality of the above system. We have also implemented and discussed the implication of using different machine learning models on the pattern recognition problem associated with array-based sensing.

Surface‐Engineered Nanomaterials for Optical Array Based Sensing

“…By using GFP as STs, the sensor array was constructed based on IDA (Figure 13a) and able to identify 15 different proteins at 50 nM (Figure 13c). [63] Later we explored the efficacy of the sensing platform for detection of various drug resistant bacteria (Figure 13d). [64] Successfully it was able to discriminate five wild type strain from its drug resistant strains.…”

Cell-Based Chemical Safety Assessment and Therapeutic Discovery Using Array-Based Sensors

“…Pan et al used LDA and other machine learning methods to assist with surface-functionalized carbon dot sensor arrays for discriminating different types of proteins [ 52 ]. De et al used different machine learning methods to analyze the sensitivity of cationic MoS2 and GFP conjugates for discriminating protein types in serum media and compared the classification accuracy of different methods [ 53 ]. Unsupervised learning methods such as PCA are important in identifying trends in large sets of data using statistical parameters.…”

Molybdenum Disulfide (MoS2): An Emerging Multifunctional Nanomaterial for Sensing and Removal of Agricultural Contaminants

“…In the past few years, great effort has been devoted to the development and improvement of techniques that are utilized in the detection of contaminants to ensure agricultural security . The emerging photoelectric detection strategies, such as surface enhanced Raman scattering (SERS), electrochemical methods, and fluorescence, have opened the door to real-time monitoring of agricultural contaminants and have the potential to keep up with the pace of agricultural modernization . Although these novel detection technologies are expected to have groundbreaking implications in agriculture, they are still in the infancy stage.…”