Computationally guided design and synthesis of dual-drug loaded polymeric nanoparticles for combination therapy

Single-drug therapies or monotherapies are often inadequate,particularly in the case of life-threatening diseases like cancer.Consequently,combination therapies emerge as an attractive strategy.Cancer nanomedicines have many benefits in addressing the challenges faced by small molecule therapeutic drugs,such as low water solubility and bioavailability,high toxicity,etc.However,it remains a significant challenge in encapsulating two drugs in a nanoparticle.To address this issue,computational methodologies are employed to guide the rational design and synthesis of dual-drug-loaded polymer nanoparticles while achieving precise control over drug loading.Based on the sequential nanoprecipitation technology,five factors are identified that affect the formulation of drug candidates into dual-drug loaded nanoparticles,and then screened 176 formulations under different experimental conditions.Based on these experimental data,machine learning methods are applied to pin down the key factors.The implementation of this methodology holds the potential to signif-icantly mitigate the complexities associated with the synthesis of dual-drug loaded nanoparticles,and the co-assembly of these compounds into nanoparticulate systems demonstrates a promising avenue for combination therapy.This approach provides a new strategy for enabling the streamlined,high-throughput screening and synthesis of new nanoscale drug-loaded entities.

Sensing in the presence of strong noise by deep learning of dynamic multimode fiber interference

A new approach to optical fiber sensing is proposed and demonstrated that allows for specific measurement even in the presence of strong noise from undesired environmental perturbations.A deep neural network model is trained to statistically learn the relation of the complex optical interference output from a multimode optical fiber(MMF)with respect to a measurand of interest while discriminating the noise.This technique negates the need to carefully shield against,or compensate for,undesired perturbations,as is often the case for traditional optical fiber sensors.This is achieved entirely in software without any fiber postprocessing fabrication steps or specific packaging required,such as fiber Bragg gratings or specialized coatings.The technique is highly generalizable,whereby the model can be trained to identify any measurand of interest within any noisy environment provided the measurand affects the optical path length of the MMF’s guided modes.We demonstrate the approach using a sapphire crystal optical fiber for temperature sensing under strong noise induced by mechanical vibrations,showing the power of the technique not only to extract sensing information buried in strong noise but to also enable sensing using traditionally challenging exotic materials.