Moving the needle: Employing deep reinforcement learning to push the boundaries of coarse-grained vaccine models.
Moving the needle: Employing deep reinforcement learning to push the boundaries of coarse-grained vaccine models.
复制标题
移动针头：采用深厚的增强学习来推动粗粒疫苗模型的边界。
DOI：
10.3389/fimmu.2022.1029167
复制
发表时间：
2022
影响因子：
7.3
通讯作者：
中科院分区：
文献类型：
--
作者：
艾滋病毒和流感等高度易变的传染病病原体的进化速度超过了人类免疫系统所能控制的速度，使它们能够绕过传统的疫苗接种方法，每年造成100多万人死亡。基于agent的模型可用于模拟在亲和成熟过程中免疫细胞与hm- idp样蛋白（抗原）之间发生的复杂相互作用-抗体进化的过程。与现有的实验方法相比，基于主体的模型提供了一种安全、低成本和快速的途径来研究疫苗对多种设计变量的免疫反应。然而，亲和成熟的高度随机性和hm-IDPs的巨大序列空间使得暴力搜索难以探索所有相关的疫苗设计变量和其中包含的免疫方案子集。为了应对这一挑战，我们采用深度强化学习来驱动最近开发的基于代理的亲和成熟模型，将采样集中在免疫方案上，这些方案有更大的潜力来改善所选择的保护指标，即广泛中和抗体（bnAb）滴度或产生的bnAb的分数。使用这种方法，我们能够粗粒化广泛的疫苗设计变量，并探索相关的设计空间。我们的工作为如何制定疫苗以最大限度地提高对难民-境内流离失所者的保护性免疫反应以及如何最低限度地调整疫苗以解释人类免疫反应异质性的主要来源和各种社会经济因素提供了新的可测试的见解。我们的研究结果表明，根据保护指标，前3至5次免疫接种应该特别定制，以实现强大的保护性免疫反应，但超过这一点，进一步的免疫接种只需要在配方上进行细微的改变，以维持持久的bnAb反应。
Highly mutable infectious disease pathogens (hm-IDPs) such as HIV and influenza evolve faster than the human immune system can contain them, allowing them to circumvent traditional vaccination approaches and causing over one million deaths annually. Agent-based models can be used to simulate the complex interactions that occur between immune cells and hm-IDP-like proteins (antigens) during affinity maturation—the process by which antibodies evolve. Compared to existing experimental approaches, agent-based models offer a safe, low-cost, and rapid route to study the immune response to vaccines spanning a wide range of design variables. However, the highly stochastic nature of affinity maturation and vast sequence space of hm-IDPs render brute force searches intractable for exploring all pertinent vaccine design variables and the subset of immunization protocols encompassed therein. To address this challenge, we employed deep reinforcement learning to drive a recently developed agent-based model of affinity maturation to focus sampling on immunization protocols with greater potential to improve the chosen metrics of protection, namely the broadly neutralizing antibody (bnAb) titers or fraction of bnAbs produced. Using this approach, we were able to coarse-grain a wide range of vaccine design variables and explore the relevant design space. Our work offers new testable insights into how vaccines should be formulated to maximize protective immune responses to hm-IDPs and how they can be minimally tailored to account for major sources of heterogeneity in human immune responses and various socioeconomic factors. Our results indicate that the first 3 to 5 immunizations, depending on the metric of protection, should be specially tailored to achieve a robust protective immune response, but that beyond this point further immunizations require only subtle changes in formulation to sustain a durable bnAb response.
登录
查看更多内容
影响因子：
56.9
作者：
Allen, Christopher D. C.;Okada, Takaharu;Cyster, Jason G.
通讯作者：
Cyster, Jason G.
影响因子：
64.5
作者：
Briney, Bryan;Sok, Devin;Jardine, Joseph G.;Kulp, Daniel W.;Skog, Patrick;Menis, Sergey;Jacak, Ronald;Kalyuzhniy, Oleksandr;de Val, Natalia;Sesterhenn, Fabian;Le, Khoa M.;Ramos, Alejandra;Jones, Meaghan;Saye-Francisco, Karen L.;Blane, Tanya R.;Spencer, Skye;Georgeson, Erik;Hu, Xiaozhen;Ozorowski, Gabriel;Adachi, Yumiko;Kubitz, Michael;Sarkar, Anita;Wilson, Ian A.;Ward, Andrew B.;Nemazee, David;Burton, Dennis R.;Schief, William R.
通讯作者：
Schief, William R.
定义和操纵B细胞免疫优势层次结构，以广泛中和针对流感病毒的抗体反应。
影响因子：
9.3
作者：
Amitai A;Sangesland M;Barnes RM;Rohrer D;Lonberg N;Lingwood D;Chakraborty AK
通讯作者：
Chakraborty AK
影响因子：
30.3
作者：
Haynes BF;Shaw GM;Korber B;Kelsoe G;Sodroski J;Hahn BH;Borrow P;McMichael AJ
通讯作者：
McMichael AJ
影响因子：
64.5
作者：
Bonsignori M;Zhou T;Sheng Z;Chen L;Gao F;Joyce MG;Ozorowski G;Chuang GY;Schramm CA;Wiehe K;Alam SM;Bradley T;Gladden MA;Hwang KK;Iyengar S;Kumar A;Lu X;Luo K;Mangiapani MC;Parks RJ;Song H;Acharya P;Bailer RT;Cao A;Druz A;Georgiev IS;Kwon YD;Louder MK;Zhang B;Zheng A;Hill BJ;Kong R;Soto C;NISC Comparative Sequencing Program;Mullikin JC;Douek DC;Montefiori DC;Moody MA;Shaw GM;Hahn BH;Kelsoe G;Hraber PT;Korber BT;Boyd SD;Fire AZ;Kepler TB;Shapiro L;Ward AB;Mascola JR;Liao HX;Kwong PD;Haynes BF
通讯作者：
Haynes BF