IAnimal: A cross-species omics knowledgebase for animals

IAnimal is a cross-species, multi-omics knowledgebase. It provides comprehensive structured multi-omics data for a wide range of animal species, abundant omics data mining and visualization tools, and intelligent integration analysis algorithms for multi-omics data. In the present version, IAnimal provides 61,191 WGS, RNA-Seq, ChIP-Seq, and ATAC-Seq individual information and genome annotation information for 21 species, such as mouse, pig, cow, chicken, and which the scale of clean data reaches about 846.46 TB. In order to better understand the biological significance of omics information, IAnimal built a deep learning model based on BioBERT and AutoNER to mine 'gene' and 'trait entity from the abstracts of 2,794,237 research papers, and this is helpful for users to understand how each different omics layer regulates genes to affect the traits.IAnimal是一款跨物种多组学（multi-omics）知识库。它为涵盖小鼠、猪、牛、鸡等在内的21个动物物种提供全面结构化的多组学数据，同时配备丰富的组学数据挖掘与可视化工具，以及面向多组学数据的智能化整合分析算法。在当前版本中，IAnimal已收录61,191份WGS、RNA-Seq、ChIP-Seq及ATAC-Seq的个体信息与基因组注释信息，其清洁数据总规模约达846.46 TB。为更好地理解组学信息的生物学意义，IAnimal构建了基于BioBERT与AutoNER的深度学习模型，从2,794,237篇研究论文的摘要中挖掘‘基因’与‘性状实体’，该功能可帮助用户明晰不同组学层级如何通过调控基因进而影响生物性状。

搜集汇总

背景与挑战

背景概述

IAnimal是一个跨物种多组学知识库，为包括小鼠、猪、牛、鸡等在内的21种动物提供涵盖WGS、RNA-Seq、ChIP-Seq和ATAC-Seq的61,191个样本数据及基因组注释信息，数据总量约846.46 TB。该知识库集成了多组学数据挖掘、可视化工具及智能分析算法，并利用深度学习模型从279万篇研究论文摘要中提取基因与性状实体，以帮助用户理解不同组学层面对性状的调控机制。