Optical biosensors - Illuminating the path to personalized drug dosing.

Optical biosensors are low-cost, sensitive and portable devices that are poised to revolutionize the medical industry. Healthcare monitoring has already been transformed by such devices, with notable recent applications including heart rate monitoring in smartwatches and COVID-19 lateral flow diagnostic test kits. The commercial success and impact of existing optical sensors has galvanized research in expanding its application in numerous disciplines. Drug detection and monitoring seeks to benefit from the fast-approaching wave of optical biosensors, with diverse applications ranging from illicit drug testing, clinical trials, monitoring in advanced drug delivery systems and personalized drug dosing. The latter has the potential to significantly improve patients' lives by minimizing toxicity and maximizing efficacy. To achieve this, the patient's serum drug levels must be frequently measured. Yet, the current method of obtaining such information, namely therapeutic drug monitoring (TDM), is not routinely practiced as it is invasive, expensive, time-consuming and skilled labor-intensive. Certainly, optical sensors possess the capabilities to challenge this convention. This review explores the current state of optical biosensors in personalized dosing with special emphasis on TDM, and provides an appraisal on recent strategies. The strengths and challenges of optical biosensors are critically evaluated, before concluding with perspectives on the future direction of these sensors.

Harnessing machine learning for development of microbiome therapeutics.

The last twenty years of seminal microbiome research has uncovered microbiota's intrinsic relationship with human health. Studies elucidating the relationship between an unbalanced microbiome and disease are currently published daily. As such, microbiome big data have become a reality that provide a mine of information for the development of new therapeutics. Machine learning (ML), a branch of artificial intelligence, offers powerful techniques for big data analysis and prediction-making, that are out of reach of human intellect alone. This review will explore how ML can be applied for the development of microbiome-targeted therapeutics. A background on ML will be given, followed by a guide on where to find reliable microbiome big data. Existing applications and opportunities will be discussed, including the use of ML to discover, design, and characterize microbiome therapeutics. The use of ML to optimize advanced processes, such as 3D printing and in silico prediction of drug-microbiome interactions, will also be highlighted. Finally, barriers to adoption of ML in academic and industrial settings will be examined, concluded by a future outlook for the field.