Deep learning assisted logic gates for real-time identification of natural tetracycline antibiotics.

The overuse and misuse of tetracycline (TCs) antibiotics, including tetracycline (TTC), oxytetracycline (OTC), doxycycline (DC), and chlortetracycline (CTC), pose a serious threat to human health. However, current rapid sensing platforms for tetracyclines can only quantify the total amount of TCs mixture, lacking real-time identification of individual components. To address this challenge, we integrated a deep learning strategy with fluorescence and colorimetry-based multi-mode logic gates in our self-designed smartphone-integrated toolbox for the real-time identification of natural TCs. Our ratiometric fluorescent probe (CD-Au NCs@ZIF-8) encapsulated carbon dots and Au NCs in ZIF-8 to prevent false negative or positive results. Additionally, our independently developed WeChat app enabled linear quantification of the four natural TCs using the fluorescence channels. The colorimetric channels were also utilized as outputs of logic gates to achieve real-time identification of the four individual natural tetracyclines. We anticipate this strategy could provide a new perspective for effective control of antibiotics.

Real-time intelligent detection of ethephon based on a high-throughput ratiometric fluorescent probe.

Ethephon (ETH) is a common pesticide, and its overuse has resulted in a variety of health problems for humans. However, the existing ETH detection methods are tedious and time-consuming, and real-time ETH identification remains a significant difficulty. To mitigate this concern, a dual-emission ratiometric fluorescent probe Ru@ZrMOF was rationally synthesized for the detection of ETH. In the presence of ETH, the emission peak at 435 nm gradually increased, while the peak at 600 nm remained constant, accompanied by the fluorescence color change from red, pink, blue-violet to blue. The fluorescence intensity ratio (F435/F600) demonstrated two linear relations with the ETH concentration ranges at 3 - 50 µM and 50 - 500 µM, with a lowest detection limit at 1 µM. This was attributed to the formation of Zr-O-P bonds which attenuated the ligand-metal charge transfer (LMCT) process, resulting in the recovery of blue fluorescence of the ligand 2-Aminoterephthalic acid (2-APDC). To validate the practical application of the developed platform, a YOLO v5x-based WeChat applet "96 Speckles" was developed, and a 96-well plate and smartphone-embedded 3D-printed portable toolbox was designed for the real-time intelligent detection of ETH. This smart platform allows for real-time and efficient ETH analysis in various real samples including apples, pears and tomatoes.

Machine Learning-Assisted High-Throughput Strategy for Real-Time Detection of Spermine Using a Triple-Emission Ratiometric Probe.

In this study, we designed and fabricated a spermine-responsive triple-emission ratiometric fluorescent probe using dual-emissive carbon nanoparticles and quantum dots, which improve the sensor's accuracy and reduce interfering environmental effects. The probe is advantageous for the proportionate detection of spermine because it has good emission resolution, and the maximum points of the two emission peaks differ by 95 nm. As a proof of concept, cuvettes and a 96-well plate were combined with a smartphone and YOLO series algorithms to accomplish real-time, visual, and high-throughput detection of seafood and meat freshness. In addition, the reaction mechanism was verified by density functional theory and fundamental characterizations. Upon exposure to different amounts of spermine, the intensity of the fluorescent probe changed linearly, and the fluorescent color shifted from yellow-green to red, with a limit of detection of 0.33 µM. To enable visual identification of food-originated spermine, a hydrogel-based visual sensing platform was successfully developed utilizing the triple-emission fluorescent probe. Consequently, spermine could be identified and quantified without complicated equipment.