Genomic Interpreter: A Hierarchical Genomic Deep Neural Network with 1D Shifted Window Transformer
Genomic Interpreter: A Hierarchical Genomic Deep Neural Network with 1D Shifted Window Transformer
复制标题
DOI：
10.48550/arxiv.2306.05143
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Zehui Li;Akashaditya Das;W. Beardall;Yiren Zhao;G. Stan
中科院分区：
文献类型：
--
作者：
Zehui Li;Akashaditya Das;W. Beardall;Yiren Zhao;G. Stan
鉴于基因组学数据的数量和质量不断增加，提取新的见解需要可解释的机器学习模型。本工作介绍了基因组解释器：一种用于基因组分析预测的新架构。该模型优于基因组测定预测任务的最新模型。我们的模型可以识别基因组位点的层次依赖关系。这是通过集成1D-Swin来实现的，1D-Swin是我们设计的一种新型基于transformer的模块，用于对远程分层数据进行建模。在包含38，171个17 K碱基对的DNA片段的数据集上进行评估，Genomic Interpreter在染色质可及性和基因表达预测方面表现出上级性能，并揭示了基因调控的潜在“语法”。
Given the increasing volume and quality of genomics data, extracting new insights requires interpretable machine-learning models. This work presents Genomic Interpreter: a novel architecture for genomic assay prediction. This model outperforms the state-of-the-art models for genomic assay prediction tasks. Our model can identify hierarchical dependencies in genomic sites. This is achieved through the integration of 1D-Swin, a novel Transformer-based block designed by us for modelling long-range hierarchical data. Evaluated on a dataset containing 38,171 DNA segments of 17K base pairs, Genomic Interpreter demonstrates superior performance in chromatin accessibility and gene expression prediction and unmasks the underlying `syntax' of gene regulation.