INFERRING MECHANISTIC PARAMETERS OF SOMATIC HYPERMUTATION USING NEURAL NETWORKS AND APPROXIMATE BAYESIAN COMPUTATION

• 成果类型: Article
• 署名作者: Fisher, Thayer; Sung, Kevin; Simon, Noah; Fukuyama, Julia; Matsen, Frederick A.
• 署名单位: University of Washington; University of Washington Seattle; Fred Hutchinson Cancer Center; Indiana University System; Indiana University Bloomington
• 刊物名称: ANNALS OF APPLIED STATISTICS
• ISSN/ISSBN: 1932-6157
• DOI: 10.1214/24-AOAS1985
• 发表日期: 2025
• 页码: 720-743
• 关键词: single-stranded-dna; immunoglobulin genes; detecting selection; polymerase-eta; igv(h) genes; Mutation; substitutions; mutability; SEQUENCES; hotspots

摘要

Somatic hypermutation (SHM) is a critical enzyme-mediated process of the adaptive immune response in which antibodies acquire mutations to enhance antigen binding. Despite abundant research elucidating the biochemical basis of SHM, and substantial sequence data available for parameterization, previous computational models of SHM have not been explicitly mechanistic. In this paper we bridge this gap by developing a probabilistic latent variable model encapsulating a sequence of interacting steps, thus formulating the biochemical underpinnings of SHM in a mathematical framework. However, fitting this latent variable model is challenging. To navigate this complexity, we employ an approximate Bayesian computation strategy integrated with neural networks. We are able to estimate almost all of the parameters of the model to good accuracy but find that the parameters involving the boundaries of the nucleotide stripping process are slightly more challenging, given the type of data available.