Computationally guided high-throughput design of self-assembling drug nanoparticles

Abstract

Nanoformulations are transforming our capacity to effectively deliver and treat a myriad of conditions. However, many nanoformulation approaches still suffer from high production complexity and low drug loading. One potential solution relies on harnessing co-assembly of drugs and small molecular excipients to facilitate nanoparticle formation through solvent exchange without the need for chemical synthesis, generating nanoparticles with up to 95% drug loading. However, there is currently no understanding which of the millions of possible combinations of small molecules can result in the formation of these nanoparticles. Here we report the development of a high-throughput screening platform coupled to machine learning to enable the rapid evaluation of such nanoformulations. Our platform identified 101 novel self-assembling drug nanoparticles from 2.1 million pairings derived from 788 candidate drugs with one of 2686 excipients, spanning treatments for multiple diseases and often harnessing well-known food additives, vitamins, or approved drugs as carrier materials -with potential for accelerated approval and translation. Given their long-term stability and potential for clinical impact, we further characterize novel sorafenib-glycyrrhizin and terbinafine-taurocholic acid nanoparticles ex vivo and in vivo. We anticipate that this platform could accelerate the development of safer and more efficacious nanoformulations with high drug loadings for a wide range of therapeutics.

Nanoengineering Apolipoprotein A1‐Based Immunotherapeutics

“…From these screens, "laws" on structure-function relationships can be extracted through computational modeling methods, including machine learning. [128,129] To close the clinical translation gap, large animal models are highly valuable. For example, Binderup et al showed, in 2019, that producing and evaluating A1-nanotherapeutics is scalable from mice to larger animals, i.e., rabbits and porcine cardiovascular disease models.…”

High-throughput screening of nanoparticles in drug delivery

“… 137–139 In another example, the integration of high-throughput experimentation with machine learning led to the identification of 100 drug NPs with high loading capacity. 140 In addition, the use of machine learning tools can be envisioned as a strategy to identify new principles for more efficient release 141 and targeting 135 to specific cells.…”

Biomaterials by design: Harnessing data for future development

“…rapidly screened through 1440 pairings of drugs and excipients for co-aggregation into nanoparticles by using a combination of liquid handling and high throughput dynamic light scattering characterization ( Fig. 6 ) [ 53 ]. A random forest machine learning model was used to gain insight into the molecular features for co-aggregation, and subsequently used to predict additional co-aggregators (1.8%) from 2.1 million possible pairings of FDA approved drugs and excipients.…”

“…(e) The machine learning model was used to model 2.1 million pairs of drugs and excipients for ability to co-aggregate and form nanoparticles, and the six named pairs were validated experimentally. The novel component that was not part of the initial high throughput screen in part A are underscored [ 53 ]. …”