arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.16940cs.LGq-bio.GN
收藏

GV-Rep:一个用于遗传变异表征学习的大规模数据集

GV-Rep: A Large-Scale Dataset for Genetic Variant Representation Learning

Imperial College London(帝国理工学院);Vector Institute(向量研究院);University Health Network(大学健康网络);Hospital for Sick Children(病童医院);University of Toronto(多伦多大学)

Zehui Li, Vallijah Subasri, Guy-Bart Stan, Yiren Zhao, Bo Wang

AI总结:

本文提出大规模遗传变异数据集 GV-Rep,含700万条记录及多类临床与实验注释,并通过预训练 GFM 实验揭示其在准确 GV 表征上的显著能力差距。

摘要:

遗传变异(GV)被定义为个体之间 DNA 序列的差异,在遗传疾病的诊断和治疗中发挥着关键作用。下一代测序成本的快速下降导致患者层面的 GV 数据呈指数级增长。这种增长给临床医生带来了挑战,他们必须高效地确定患者特异性 GV 的优先级,并将其与现有基因组数据库整合,从而为患者管理提供依据。为了解决 GV 的解释问题,基因组基础模型(GFM)已经出现。然而,这些模型缺乏标准化的性能评估,导致模型评估存在相当大的差异。这就提出了一个问题:深度学习方法对未知 GV 进行分类并将其与经临床验证的 GV 对齐的效果如何?我们认为,表征学习能够将原始数据转换为有意义的特征空间,是同时应对索引和分类挑战的有效方法。我们介绍了一个名为 GV-Rep 的大规模遗传变异数据集,该数据集具有可变长度上下文和详细注释,旨在供深度学习模型学习跨各种性状、疾病、组织类型和实验环境的 GV 表征。我们的贡献有三个方面:(i)构建了一个包含 700 万条记录的综合数据集,每条记录都标注了相应变异的特征,此外还有来自 1,107 种细胞类型的 17,548 项基因敲除测试、1,808 种变异组合以及来自真实患者的 156 个独特的经临床验证的 GV 的额外数据。(ii)分析了该数据集的结构和属性。(iii)使用预训练 GFM 在该数据集上进行实验。结果表明,GFM 当前的能力与准确的 GV 表征之间存在显著差距。我们希望该数据集将有助于推动基因组深度学习的发展,以弥合这一差距。

英文摘要:

Genetic variants (GVs) are defined as differences in the DNA sequences among individuals and play a crucial role in diagnosing and treating genetic diseases. The rapid decrease in next generation sequencing cost has led to an exponential increase in patient-level GV data. This growth poses a challenge for clinicians who must efficiently prioritize patient-specific GVs and integrate them with existing genomic databases to inform patient management. To addressing the interpretation of GVs, genomic foundation models (GFMs) have emerged. However, these models lack standardized performance assessments, leading to considerable variability in model evaluations. This poses the question: How effectively do deep learning methods classify unknown GVs and align them with clinically-verified GVs? We argue that representation learning, which transforms raw data into meaningful feature spaces, is an effective approach for addressing both indexing and classification challenges. We introduce a large-scale Genetic Variant dataset, named GV-Rep, featuring variable-length contexts and detailed annotations, designed for deep learning models to learn GV representations across various traits, diseases, tissue types, and experimental contexts. Our contributions are three-fold: (i) Construction of a comprehensive dataset with 7 million records, each labeled with characteristics of the corresponding variants, alongside additional data from 17,548 gene knockout tests across 1,107 cell types, 1,808 variant combinations, and 156 unique clinically verified GVs from real-world patients. (ii) Analysis of the structure and properties of the dataset. (iii) Experimentation of the dataset with pre-trained GFMs. The results show a significant gap between GFMs current capabilities and accurate GV representation. We hope this dataset will help advance genomic deep learning to bridge this gap.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑