International Institute "Solution Chemistry of Advanced Materials and Technologies", ITMO University, St. Petersburg, 191002, Russian Federation.
Small. 2023 Nov;19(48):e2303522. doi: 10.1002/smll.202303522. Epub 2023 Aug 10.
Magnetic nanoparticles are a prospective class of materials for use in biomedicine as agents for magnetic resonance imagining (MRI) and hyperthermia treatment. However, synthesis of nanoparticles with high efficacy is resource-intensive experimental work. In turn, the use of machine learning (ML) methods is becoming useful in materials design and serves as a great approach to designing nanomagnets for biomedicine. In this work, for the first time, an ML-based approach is developed for the prediction of main parameters of material efficacy, i.e., specific absorption rate (SAR) for hyperthermia and r /r relaxivities in MRI, with parameters of nanoparticles as well as experimental conditions as descriptors. For that, a unique database with more than 980 magnetic nanoparticles collected from scientific articles is assembled. Using this data, several tree-based ensemble models are trained to predict SAR, r and r relaxivity. After hyperparameter optimization, models reach performances of R = 0.86, R = 0.78, and R = 0.75, respectively. Testing the models on samples unseen during the training shows no performance drops. Finally, DiMag, an open access resource created to guide synthesis of novel nanosized magnets for MRI and hyperthermia treatment with machine learning and boost development of new biomedical agents, is developed.
磁性纳米粒子是一类有前途的材料，可用于生物医学领域，作为磁共振成像（MRI）和热疗的造影剂。然而，合成高效的纳米粒子是一项资源密集型的实验工作。反过来，机器学习（ML）方法的使用在材料设计中变得越来越有用，并且是为生物医学设计纳米磁体的一种很好的方法。在这项工作中，首次开发了一种基于机器学习的方法，用于预测材料功效的主要参数，即热疗的比吸收率（SAR）和 MRI 中的 r / r 弛豫率，将纳米粒子的参数以及实验条件作为描述符。为此，组装了一个包含超过 980 个从科学文章中收集的磁性纳米粒子的独特数据库。使用这些数据，训练了几个基于树的集成模型来预测 SAR、r 和 r 弛豫率。经过超参数优化后，模型的性能分别达到 R = 0.86、R = 0.78 和 R = 0.75。在训练过程中未见过的样本上测试模型，没有出现性能下降。最后，开发了 DiMag，这是一个开放访问的资源，旨在使用机器学习指导新型 MRI 和热疗治疗用纳米磁体的合成，并促进新型生物医学试剂的开发。
