Robust chemical analysis with graphene chemosensors and machine learning

• Published in: Nature (London) Vol. 634; no. 8034; pp. 572 - 578
• Main Authors: Pannone, Andrew, Raj, Aditya, Ravichandran, Harikrishnan, Das, Sarbashis, Chen, Ziheng, Price, Collin A., Sultana, Mahmooda, Das, Saptarshi
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 17.10.2024; Nature Publishing Group
• Subjects: 639/166/987; 639/925/918/1052; Accuracy; Algorithms; Arrays; Artificial neural networks; Chemical analysis; Chemical composition; Chemical sensors; Chemistry Techniques, Analytical - methods; Chemoreceptors; Classification; Datasets as Topic; Energy efficiency; Environmental changes; Environmental monitoring; Environmental Monitoring - instrumentation; Environmental Monitoring - methods; Field effect transistors; Food Contamination - analysis; Food safety; Food Safety - methods; Food spoilage; Fraud; Fraud - prevention & control; Graphene; Graphite - chemistry; Humanities and Social Sciences; Humans; Learning algorithms; Machine Learning; multidisciplinary; Neural networks; Neural Networks, Computer; Prediction models; Process control; Process controls; Robustness (mathematics); Science; Science (multidisciplinary); Semiconductor devices; Sensors; Spoilage; Technology assessment; Transistors; Transistors, Electronic
• ISSN: 0028-0836; 1476-4687; 1476-4687
• DOI: 10.1038/s41586-024-08003-w

Ion-sensitive field-effect transistors (ISFETs) have emerged as indispensable tools in chemosensing applications 1 – 4 . ISFETs operate by converting changes in the composition of chemical solutions into electrical signals, making them ideal for environmental monitoring 5 , 6 , healthcare diagnostics 7 and industrial process control 8 . Recent advancements in ISFET technology, including functionalized multiplexed arrays and advanced data analytics, have improved their performance 9 , 10 . Here we illustrate the advantages of incorporating machine learning algorithms to construct predictive models using the extensive datasets generated by ISFET sensors for both classification and quantification tasks. This integration also sheds new light on the working of ISFETs beyond what can be derived solely from human expertise. Furthermore, it mitigates practical challenges associated with cycle-to-cycle, sensor-to-sensor and chip-to-chip variations, paving the way for the broader adoption of ISFETs in commercial applications. Specifically, we use data generated by non-functionalized graphene-based ISFET arrays to train artificial neural networks that possess a remarkable ability to discern instances of food fraud, food spoilage and food safety concerns. We anticipate that the fusion of compact, energy-efficient and reusable graphene-based ISFET technology with robust machine learning algorithms holds the potential to revolutionize the detection of subtle chemical and environmental changes, offering swift, data-driven insights applicable across a wide spectrum of applications. Machine learning models trained with extensive datasets generated by ion-sensitive field-effect transistor sensors can classify complex liquids and quantify changes in chemical composition.