Machine learning models to accelerate the design of polymeric long-acting injectables

Abstract

Long-acting injectables are considered one of the most promising therapeutic strategies for the treatment of chronic diseases as they can afford improved therapeutic efficacy, safety, and patient compliance. The use of polymer materials in such a drug formulation strategy can offer unparalleled diversity owing to the ability to synthesize materials with a wide range of properties. However, the interplay between multiple parameters, including the physicochemical properties of the drug and polymer, make it very difficult to intuitively predict the performance of these systems. This necessitates the development and characterization of a wide array of formulation candidates through extensive and time-consuming in vitro experimentation. Machine learning is enabling leap-step advances in a number of fields including drug discovery and materials science. The current study takes a critical step towards data-driven drug formulation development with an emphasis on long-acting injectables. Here we show that machine learning algorithms can be used to predict experimental drug release from these advanced drug delivery systems. We also demonstrate that these trained models can be used to guide the design of new long acting injectables. The implementation of the described data-driven approach has the potential to reduce the time and cost associated with drug formulation development.

Drug Delivery Systems for Localized Cancer Combination Therapy

“…This model also identified polymer molecular weight and drug molecular weight as the two most influential factors to the observed release rate where higher molecular weights of both drug and polymer correlate to "slow" release rates whereas low molecular weights reveal "fast" release rates. 145 Although these results are limited to in vitro release studies, it demonstrates a useful method to identify general release rates that correlate to various polymeric formulations for localized delivery platforms.…”

Navigating the Expansive Landscapes of Soft Materials: A User Guide for High-Throughput Workflows

“…Machine learning and Bayesian approaches are popular active learning schemes that have been successfully applied to diverse chemical challenges including the synthesis of metallic alloys , and nanoparticles, drug discovery, , catalyst development, and the evaluation of properties of bulk polymers ranging from electronic bandgap to thermal transitions . Examples of high-throughput synthesis coupled to iterative sampling include the design of protein-stabilizing random copolymers using automated polymer synthesis, , the identification of 19 F MRI contrast agents using continuous-flow chemistry, and the development of polymeric injectables for drug delivery …”

“…74 Examples of high-throughput synthesis coupled to iterative sampling include the design of protein-stabilizing random copolymers using automated polymer synthesis, 47,75 the identification of 19 F MRI contrast agents using continuousflow chemistry, 51 and the development of polymeric injectables for drug delivery. 3 Virtual screening also rapidly narrows a design space through computationally inexpensive simulations. 76−78 Genetic algorithms, a type of optimization algorithm inspired by mutations and natural selection, have harnessed virtual screening to identify novel materials such as photovoltaics 79 and dielectrics 80 by optimizing property criteria such as glass transition temperature or electronic bandgap.…”

“…However, identifying structure–property and resulting structure–function relationships in these materials remains challenging. Diverse efforts toward modern multifunctional materials, from antifungal activity to drug delivery injectables, have underscored the intricacies and complexities of macromolecular properties. Nonintuitive and emergent characteristics in these materials challenge rational design, limiting the use of existing design principles and stepwise iteration.…”

Security risks in the software development lifecycle: A review

“…The authors in [114] have examined the predictive performance of TD indicators in envisaging software security risks both at project level and at class level of granularity. This was facilitated by building different machine learning (ML) models [163]- [166]. On the other hand, by several experts in the field have identified some close relationship between TD and software security [44], [46]], [45], [48].…”