A machine learning-enhanced biosensor for mercury detection based on an hydrophobin chimera.

Abstract Marine waters are becoming contaminated by diverse pollutants at a fast rate, and detection of these water pollutants has become a major concern in recent years. Among these, mercury is considered the most toxic element for human health. At present, despite the commonly used methods for its detection are accurate, they often require sophisticated equipments, have relatively high costs, are demanding and time-consuming. Herein a novel solution to detect mercury (II) pollution in sea water is proposed, and an easy and portable detection method has been developed. Indeed, a hydrophobin based chimera able to both adhere to polystyrene multiwell plates and bind mercury (II) with a consequent fluorescent decrease was designed. The chimera was the recognition element in a fluorescence-based biosensor able to detect mercury (II) in the nM range. Indeed, this biosensor specifically measure Hg2+ concentration also in the presence of other metals, reaching a limit of detection of 0.4 nM in tap water and 0.3 nM in sea water. Moreover, the developed biosensor was coupled to machine learning methodologies with the big advantage of predicting mercury concentration levels without the use of classical reader devices, thus allowing in situ monitoring of sea pollution by non-skilled personnel.