牛津大学Jim R. Hughes和Gerton Lunter小组宣布他们研发了一种深层神经网络,利用兆碱基水平迁移学习预测三维基因组折叠。 该研究于2020年10月12日发表于《自然—方法学》。
研究组开发了deepC,是一种基于迁移学习(transfer learning)的深层神经网络,可以精确地预测兆碱基(megabase)水平DNA序列的基因组折叠。DeepC可以高分辨率地预测结构域边界、学习决定基因组折叠的序列、并预测大规模结构性和单一碱基对的变化产生的影响。DeepC使用了基于迁移学习的深度神经网络,用于根据兆碱基规模的DNA序列预测基因组折叠。
据悉,预测非编码遗传变异的影响需要在三维基因组架构的背景下对其进行解释。
附:英文原文
Title: DeepC: predicting 3D genome folding using megabase-scale transfer learning
Author: Ron Schwessinger, Matthew Gosden, Damien Downes, Richard C. Brown, A. Marieke Oudelaar, Jelena Telenius, Yee Whye Teh, Gerton Lunter, Jim R. Hughes
Issue&Volume: 2020-10-12
Abstract: Predicting the impact of noncoding genetic variation requires interpreting it in the context of three-dimensional genome architecture. We have developed deepC, a transfer-learning-based deep neural network that accurately predicts genome folding from megabase-scale DNA sequence. DeepC predicts domain boundaries at high resolution, learns the sequence determinants of genome folding and predicts the impact of both large-scale structural and single base-pair variations. DeepC uses transfer learning-based deep neural networks for predicting genome folding from megabase-scale DNA sequence.
DOI: 10.1038/s41592-020-0960-3
Source: https://www.nature.com/articles/s41592-020-0960-3
Nature Methods:《自然—方法学》,创刊于2004年。隶属于施普林格·自然出版集团,最新IF:47.99
官方网址:https://www.nature.com/nmeth/
投稿链接:https://mts-nmeth.nature.com/cgi-bin/main.plex
本期文章:《自然—方法学》:Online/在线发表