Accelerated discovery of synthetic polymers for ribonucleoprotein delivery through the integration of active learning, machine learning, and polymer science

通过整合主动学习、机器学习和聚合物科学，加速发现用于核糖核蛋白递送的合成聚合物

• 批准号: 10195432
• 负责人: Connor Wilson Coley
• 金额: $ 19.76万
• 依托单位: MASSACHUSETTS INSTITUTE OF TECHNOLOGY
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-22 至 2023-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10195432
• 关键词: Active Learning; Algorithms; Amines; Architecture; Biocompatible Materials; Biological Assay; Biological Process; CRISPR/Cas technology; Capsid; Cell Survival; Cell model; Cells; Chemicals; Clinical Trials; Complex; DNA; Data; Development; Equilibrium; Esters; Evaluation; Exhibits; Experimental Designs; Gene Delivery; Genes; Genetic Diseases; Guide RNA; Human; Knock-in; Knock-out; Learning; Length; Libraries; Lipids; Machine Learning; Maps; Mediating; Messenger RNA; Metabolic; Methods; Modeling; Outcome; Performance; Plasmids; Polymer Chemistry; Polymers; Property; Proteins; RNA; RNA delivery; Reporter; Research; Ribonucleoproteins; Ribonucleotides; Safety; Science; Specificity; Structure; System; Techniques; Technology; Testing; Therapeutic; Tissues; Training; Translations; Urea; Validation; Viral Vector; Work; base; biomaterial compatibility; candidate selection; cell type; cheminformatics; cost; cytotoxicity; design; exhaustion; experimental study; gene therapy; immunogenicity; improved; in silico; in vivo; manufacturability; manufacturing process; novel; nucleic acid delivery; polypeptide; relating to nervous system; tool; virtual; virtual screening

PROJECT SUMMARY/ABSTRACT Gene editing systems such as CRISPR/Cas9 have rapidly grown in popularity as research tools and hold the potential to cure a diverse set of genetic disorders. However, effective, safe, and effective delivery remains a significant challenge for therapeutic translation and for application to cell types that are difficult to culture ex vivo. Ideally, intact Cas9 protein would be delivered with its guide RNA (sgRNA) as a purified ribonucleoprotein (RNP), as opposed to Cas9-encoding mRNA or plasmids, to minimize off-target effects. Viral vectors (e.g., AAVs) cannot deliver such large cargo due to their limited capsid size, which exhibit additional challenges with respect to immunogenicity, cost, and manufacturability. Fortunately, synthetic polymers--widely studied in the context of nucleic acid delivery and as biomaterials--have recently shown promise as vehicles for in vivo delivery of sgRNA- Cas9 RNPs. However, there are no consistent design principles by which novel synthetic polymers with improved delivery efficiency, tissue specificity, and safety can be developed. There are far too many polymer structures to test exhaustively or through ad hoc experimentation, so a systematic approach to polymer design, synthesis, and evaluation is required to identify promising candidates. This proposal presents a framework for the discovery of functional polymers through Bayesian experimental design. Machine learning models trained on experimental outcomes will serve as surrogates for experimentation in order to virtually screen a massive library of potential polymer candidates. Polymer candidates will be selected algorithmically through Bayesian Optimization to balance exploration of unknown chemical space and exploitation of structures known to effectively deliver RNPs. Aim 1 will involve (a) the synthesis of a diverse library of biodegradable poly(ester urea amines) (PEUAs), (b) the evaluation of their functional performance using a model fluorescent reporter knock-in/knock-out assay, a cell viability assay, and a metabolic activity assay, and (c) the development and validation of a machine learning model to learn a quantitative relationship between polymer structure/composition and these multiple performance metrics. Aim 2 will involve (a) the enumeration of the chemical space of synthetically accessible PEUAs, and (b) the development and application of a Bayesian Optimization framework leveraging the machine learning model from Aim 1 to guide the selection of candidate polymers from the enumerated space through iterative rounds of experimentation. The outcome of the proposed work will be an integrated tool combining machine learning and polymer science for the unbiased exploration of a broad biomaterial design space, validated through the development of effective and safe RNP delivery vehicles for gene editing that outperform existing commercial polymeric vehicle solutions.

项目摘要/摘要 诸如CRISPR/CAS9之类的基因编辑系统作为研究工具迅速增长，并持有 治愈各种遗传疾病的潜力。但是，有效，安全和有效的交付仍然是 治疗翻译和应用于难以在体内培养的细胞类型的重大挑战。 理想情况下，完整的Cas9蛋白将用其引导RNA（SGRNA）作为纯化的核糖核蛋白（RNP）传递， 与CAS9编码mRNA或质粒相反，以最大程度地减少脱靶效应。病毒向量（例如AAVS）不能 由于其封盖尺寸有限，因此交付了如此大的货物，在 免疫原性，成本和制造性。幸运的是，合成聚合物 - 在 核酸的递送和作为生物材料的递送 - 最近显示出有望作为体内递送sgrna-的车辆 CAS9 RNP。但是，没有一致的设计原理，可以通过这些原理进行改进的新型合成聚合物 可以开发递送效率，组织特异性和安全性。聚合物结构太多了 详尽或通过临时实验进行测试，因此是一种系统的聚合物设计，合成的方法 需要评估以确定有希望的候选人。该提案为发现的框架提出了一个框架 通过贝叶斯实验设计的功能聚合物。在实验中训练的机器学习模型 结果将作为实验的替代物，以便几乎筛选出潜在的巨大库 聚会候选人。将通过贝叶斯优化选择聚合物候选算法 平衡对未知化学空间的探索和对已知有效传递RNP的结构的开发。 AIM 1将涉及（a）合成可生物降解的聚（酯尿素胺）（PEUAS）（b）的多元化库。 使用模型荧光记者敲入/敲除测定法，对其功能性能的评估 细胞活力测定和代谢活性测定，以及（c）机器学习的开发和验证 学习聚合物结构/组成与这些多重性能之间的定量关系的模型 指标。 AIM 2将涉及（a）合成可访问的PEUA的化学空间和（b） 贝叶斯优化框架的开发和应用利用机器学习模型 从AIM 1指导从枚举空间选择候选聚合物到迭代弹的选择 实验。拟议工作的结果将是结合机器学习和的集成工具 聚合物科学对广泛的生物材料设计空间的无偏探索，通过 开发有效且安全的RNP递送工具，用于基因编辑，以优于现有商业 聚合物车辆溶液。