Characterizing uncertainty in predictions of genomic sequence-to-activity models.
Characterizing uncertainty in predictions of genomic sequence-to-activity models.
复制标题
描述基因组序列到活性模型预测的不确定性。
DOI：
10.1101/2023.12.21.572730
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Ioannidis,NilahM
中科院分区：
文献类型：
--
作者：
Bajwa,Ayesha;Rastogi,Ruchir;Kathail,Pooja;Shuai,RichardW;Ioannidis,NilahM
基因组序列-活性模型越来越多地用于理解基因调控语法和探测调控变异的功能后果。目前的模型可以准确预测整个人类参考基因组的相对活性水平，但它们的性能在预测遗传变异的影响方面更为有限，例如解释个体间的基因表达变异。为了更好地理解这些缺点的原因，我们使用Basenji 2模型复制的集合来研究基因组序列-活性模型预测的不确定性。我们描述了四种类型的序列的预测一致性：参考基因组序列，参考基因组序列与TF基序，eQTL和个人基因组序列扰动。我们观察到，模型倾向于对参考序列进行高置信度预测，即使是不正确的，而对具有变体的序列进行低置信度预测。对于eQTL和个人基因组序列，我们发现模型重复在> 50%的情况下做出不一致的预测。我们的研究结果提出了改善这些模型性能的策略。
Genomic sequence-to-activity models are increasingly utilized to understand gene regulatory syntax and probe the functional consequences of regulatory variation. Current models make accurate predictions of relative activity levels across the human reference genome, but their performance is more limited for predicting the effects of genetic variants, such as explaining gene expression variation across individuals. To better understand the causes of these shortcomings, we examine the uncertainty in predictions of genomic sequence-to-activity models using an ensemble of Basenji2 model replicates. We characterize prediction consistency on four types of sequences: reference genome sequences, reference genome sequences perturbed with TF motifs, eQTLs, and personal genome sequences. We observe that models tend to make high-confidence predictions on reference sequences, even when incorrect, and low-confidence predictions on sequences with variants. For eQTLs and personal genome sequences, we find that model replicates make inconsistent predictions in> 50% of cases. Our findings suggest strategies to improve performance of these models.