Developing novel deep-learning based methods for deciphering non-coding gene regulatory code

开发基于深度学习的新型方法来破译非编码基因调控密码

• 批准号: 10451673
• 负责人: RAMANA V DAVULURI
• 金额: $ 33.07万
• 依托单位: STATE UNIVERSITY NEW YORK STONY BROOK
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-08-01 至 2025-04-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10451673
• 关键词: Address; Benchmarking; Binding; Bioinformatics; Biological Assay; Bipolar Disorder; CRISPR/Cas technology; ChIP-seq; ClinVar; Code; Communities; Complex; Computer Vision Systems; Consumption; DNA; DNA Sequence; DNA Sequence Analysis; Data; Data Set; Databases; Development; Disease; Distant; Family member; Future; Gene Expression Regulation; Genes; Genetic; Genetic Code; Genetic Databases; Genome; Goals; Human; Human Cell Line; Human Genome; Label; Language; Luciferases; Malignant Neoplasms; Methods; Modeling; Mus; Natural Language Processing; Neural Network Simulation; Organism; Parkinson Disease; Performance; Protein Isoforms; Proteins; Public Health; RNA Splicing; Regulator Genes; Regulatory Element; Reporter; Research; Research Personnel; Resources; Schizophrenia; Scientist; Semantics; Site; Source Code; Specificity; Techniques; Time; Tissues; Training; Translating; United States National Library of Medicine; Untranslated RNA; Variant; Visualization; autism spectrum disorder; base; cell type; database of Genotypes and Phenotypes; dbSNP; deep learning; deep neural network; genetic variant; genome editing; human DNA; insight; learning strategy; neuropsychiatric disorder; novel; prediction algorithm; predictive modeling; promoter; public health relevance; tool; transcriptome; transfer learning; web server

SUMMARY This project will contribute novel pre-trained DNA Bidirectional Encoder Representations from Transformers, called DNABERT, and associated deep-learning tools to decipher the language of non-coding DNA and facilitate integration of gene regulatory information from rapidly accumulating sequence data with NLM’s genetic databases (for example, dbSNP, dbGaP and ClinVar), which serve both scientists and the public health by helping identify the genetic components of disease. While the genetic code explaining how DNA is translated into proteins is universal, the regulatory code that determines when and how the genes are expressed varies across different cell-types and organisms. Non-coding DNA is highly complex due to the existence of polysemy and distant semantic relationship, from a language modeling perspective. Recently, deep learning methods have been used in unraveling the gene regulatory code, but failed to globally and robustly model such language features in the genome, especially in data-scarce scenarios. To address this challenge, we propose DNABERT to model DNA as a language, by adapting the idea of Bidirectional Encoder Representations from Transformers (BERT). Based on recent observations in natural language processing research, we hypothesize that pre-trained transformer-based neural network model offer a promising, and yet not fully explored, deep learning approach for a variety of sequence prediction tasks in the analysis of non-coding DNA. Our preliminary results showed that DNABERT on the human genome achieved state-of-the-art performance on promoter and splice-site prediction tasks, after easy fine-tuning on small task-specific data (Ji, Y. et al. 2020). The goal of our proposed research is to develop DNABERT for a variety of sequence prediction tasks, and benchmark with existing state- of-the-art deep-learning based methods. Specific aims are (1) develop novel deep-learning methods by adapting BERT; (2) apply the proposed deep-learning methods to specifically target non-coding DNA sequence analyses and predictions; and (3) predict and validate functional non-coding genetic variants by applying DNABERT prediction models. A major contribution of the proposed research is development of pre-trained DNABERT model and prediction algorithms, which present new powerful methods for analyses and predictions of DNA sequences. Since the pre-training of DNABERT is resource-intensive, we will provide the source code and pre-trained model at Github for future academic research. We will also develop an integrated web server to (1) deploy DNABERT model, (2) database to store the identified sequence features and predictions, and (3) tutorials to help users to apply DNABERT to their specific research problems. We anticipate that DNABERT can bring new advancements and insights to the bioinformatics community by bringing advanced language modeling perspective to gene regulation analyses.

概括 该项目将贡献来自 Transformers 的新型预训练 DNA 双向编码器表示， 称为 DNABERT 以及相关的深度学习工具，用于破译非编码 DNA 的语言并促进 将快速积累的序列数据中的基因调控信息与 NLM 的遗传整合 数据库（例如 dbSNP、dbGaP 和 ClinVar），通过以下方式为科学家和公共卫生服务： 帮助识别疾病的遗传成分。遗传密码解释了 DNA 是如何翻译的 蛋白质的表达是通用的，但决定基因表达时间和方式的调控代码各不相同 跨越不同的细胞类型和生物体。由于多义性的存在，非编码 DNA 非常复杂 从语言建模的角度来看，远程语义关系。近年来，深度学习方法 已被用于解开基因调控密码，但未能对此类语言进行全球稳健的建模 基因组的特征，特别是在数据稀缺的情况下。为了应对这一挑战，我们提出 DNABERT 通过采用 Transformers 的双向编码器表示的思想，将 DNA 建模为一种语言 （伯特）。根据最近对自然语言处理研究的观察，我们假设预训练 基于 Transformer 的神经网络模型提供了一种有前途但尚未充分探索的深度学习方法 用于非编码 DNA 分析中的各种序列预测任务。我们的初步结果显示 人类基因组上的 DNABERT 在启动子和剪接位点上实现了最先进的性能 在对小型任务特定数据进行轻松微调后，预测任务（Ji, Y. et al. 2020）。我们提出的目标 研究的目的是开发用于各种序列预测任务的DNABERT，并与现有状态进行基准测试 最先进的基于深度学习的方法。具体目标是（1）通过适应开发新颖的深度学习方法 伯特； (2) 将所提出的深度学习方法应用于专门针对非编码DNA序列分析 和预测； (3) 通过应用 DNABERT 预测和验证功能性非编码遗传变异 预测模型。本研究的主要贡献是开发预训练的 DNABERT 模型 和预测算法，为 DNA 序列分析和预测提供了新的强大方法。 由于DNABERT的预训练是资源密集型的，我们将提供源代码和预训练模型 在 Github 上进行未来的学术研究。我们还将开发一个集成的 Web 服务器来 (1) 部署 DNABERT 模型，(2) 存储已识别序列特征和预测的数据库，以及 (3) 帮助用户的教程 将 DNABERT 应用于他们的具体研究问题。我们期待DNABERT能够带来新的进步 通过将先进的语言建模视角引入基因，为生物信息学界提供见解 监管分析。