{"title":"利用机器学习模型预测纳米粒子在小鼠体内的组织分布和肿瘤输送。","authors":"","doi":"10.1016/j.jconrel.2024.08.015","DOIUrl":null,"url":null,"abstract":"<div><p>Nanoparticles (NPs) can be designed for targeted delivery in cancer nanomedicine, but the challenge is a low delivery efficiency (DE) to the tumor site. Understanding the impact of NPs' physicochemical properties on target tissue distribution and tumor DE can help improve the design of nanomedicines. Multiple machine learning and artificial intelligence models, including linear regression, support vector machine, random forest, gradient boosting, and deep neural networks (DNN), were trained and validated to predict tissue distribution and tumor delivery based on NPs' physicochemical properties and tumor therapeutic strategies with the dataset from Nano-Tumor Database. Compared to other machine learning models, the DNN model had superior predictions of DE to tumors and major tissues. The determination coefficients (R<sup>2</sup>) for the test datasets were 0.41, 0.42, 0.45, 0.79, 0.87, and 0.83 for DE in tumor, heart, liver, spleen, lung, and kidney, respectively. All the R<sup>2</sup> and root mean squared error (RMSE) results of the test datasets were similar to the 5-fold cross validation results. Feature importance analysis showed that the core material of NPs played an important role in output predictions among all physicochemical properties. Furthermore, multiple NP formulations with greater DE to the tumor were determined by the DNN model. To facilitate model applications, the final model was converted to a web dashboard. This model could serve as a high-throughput pre-screening tool to support the design of new and efficient nanomedicines with greater tumor DE and serve as an alternative tool to reduce, refine, and partially replace animal experimentation in cancer nanomedicine research.</p></div>","PeriodicalId":15450,"journal":{"name":"Journal of Controlled Release","volume":null,"pages":null},"PeriodicalIF":10.5000,"publicationDate":"2024-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0168365924005546/pdfft?md5=f237aabb285d2316e044edc34cd440a0&pid=1-s2.0-S0168365924005546-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Predicting tissue distribution and tumor delivery of nanoparticles in mice using machine learning models\",\"authors\":\"\",\"doi\":\"10.1016/j.jconrel.2024.08.015\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Nanoparticles (NPs) can be designed for targeted delivery in cancer nanomedicine, but the challenge is a low delivery efficiency (DE) to the tumor site. Understanding the impact of NPs' physicochemical properties on target tissue distribution and tumor DE can help improve the design of nanomedicines. Multiple machine learning and artificial intelligence models, including linear regression, support vector machine, random forest, gradient boosting, and deep neural networks (DNN), were trained and validated to predict tissue distribution and tumor delivery based on NPs' physicochemical properties and tumor therapeutic strategies with the dataset from Nano-Tumor Database. Compared to other machine learning models, the DNN model had superior predictions of DE to tumors and major tissues. The determination coefficients (R<sup>2</sup>) for the test datasets were 0.41, 0.42, 0.45, 0.79, 0.87, and 0.83 for DE in tumor, heart, liver, spleen, lung, and kidney, respectively. All the R<sup>2</sup> and root mean squared error (RMSE) results of the test datasets were similar to the 5-fold cross validation results. Feature importance analysis showed that the core material of NPs played an important role in output predictions among all physicochemical properties. Furthermore, multiple NP formulations with greater DE to the tumor were determined by the DNN model. To facilitate model applications, the final model was converted to a web dashboard. This model could serve as a high-throughput pre-screening tool to support the design of new and efficient nanomedicines with greater tumor DE and serve as an alternative tool to reduce, refine, and partially replace animal experimentation in cancer nanomedicine research.</p></div>\",\"PeriodicalId\":15450,\"journal\":{\"name\":\"Journal of Controlled Release\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":10.5000,\"publicationDate\":\"2024-08-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S0168365924005546/pdfft?md5=f237aabb285d2316e044edc34cd440a0&pid=1-s2.0-S0168365924005546-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Controlled Release\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0168365924005546\",\"RegionNum\":1,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"CHEMISTRY, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Controlled Release","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0168365924005546","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CHEMISTRY, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
摘要
纳米粒子(NPs)可设计用于癌症纳米药物的靶向递送,但面临的挑战是向肿瘤部位的递送效率(DE)较低。了解纳米粒子的理化性质对靶组织分布和肿瘤给药效率的影响有助于改进纳米药物的设计。利用纳米肿瘤数据库的数据集,训练并验证了多种机器学习和人工智能模型,包括线性回归、支持向量机、随机森林、梯度提升和深度神经网络(DNN),以预测基于纳米粒子理化性质和肿瘤治疗策略的组织分布和肿瘤给药。与其他机器学习模型相比,DNN模型对肿瘤和主要组织的DE预测更优。测试数据集对肿瘤、心脏、肝脏、脾脏、肺脏和肾脏中 DE 的判定系数(R2)分别为 0.41、0.42、0.45、0.79、0.87 和 0.83。所有测试数据集的R2和均方根误差(RMSE)结果与5倍交叉验证结果相似。特征重要性分析表明,在所有理化性质中,NPs的核心材料对输出预测起着重要作用。此外,DNN 模型还确定了多种对肿瘤具有更大毒性的 NP 配方。为了方便模型的应用,最终模型被转换成了一个网络仪表板。该模型可作为一种高通量预筛选工具,支持设计新型、高效、对肿瘤有更大杀伤力的纳米药物,也可作为一种替代工具,减少、完善并部分取代癌症纳米药物研究中的动物实验。
Predicting tissue distribution and tumor delivery of nanoparticles in mice using machine learning models
Nanoparticles (NPs) can be designed for targeted delivery in cancer nanomedicine, but the challenge is a low delivery efficiency (DE) to the tumor site. Understanding the impact of NPs' physicochemical properties on target tissue distribution and tumor DE can help improve the design of nanomedicines. Multiple machine learning and artificial intelligence models, including linear regression, support vector machine, random forest, gradient boosting, and deep neural networks (DNN), were trained and validated to predict tissue distribution and tumor delivery based on NPs' physicochemical properties and tumor therapeutic strategies with the dataset from Nano-Tumor Database. Compared to other machine learning models, the DNN model had superior predictions of DE to tumors and major tissues. The determination coefficients (R2) for the test datasets were 0.41, 0.42, 0.45, 0.79, 0.87, and 0.83 for DE in tumor, heart, liver, spleen, lung, and kidney, respectively. All the R2 and root mean squared error (RMSE) results of the test datasets were similar to the 5-fold cross validation results. Feature importance analysis showed that the core material of NPs played an important role in output predictions among all physicochemical properties. Furthermore, multiple NP formulations with greater DE to the tumor were determined by the DNN model. To facilitate model applications, the final model was converted to a web dashboard. This model could serve as a high-throughput pre-screening tool to support the design of new and efficient nanomedicines with greater tumor DE and serve as an alternative tool to reduce, refine, and partially replace animal experimentation in cancer nanomedicine research.
期刊介绍:
The Journal of Controlled Release (JCR) proudly serves as the Official Journal of the Controlled Release Society and the Japan Society of Drug Delivery System.
Dedicated to the broad field of delivery science and technology, JCR publishes high-quality research articles covering drug delivery systems and all facets of formulations. This includes the physicochemical and biological properties of drugs, design and characterization of dosage forms, release mechanisms, in vivo testing, and formulation research and development across pharmaceutical, diagnostic, agricultural, environmental, cosmetic, and food industries.
Priority is given to manuscripts that contribute to the fundamental understanding of principles or demonstrate the advantages of novel technologies in terms of safety and efficacy over current clinical standards. JCR strives to be a leading platform for advancements in delivery science and technology.