DigChem: Identification of disease–gene–chemical relationships from Medline abstracts

Paper:Jeongkyun Kim, Jung-jae Kim, Hyunju Lee* (2019) DigChem: Identification of disease-gene-chemical relationships from Medline abstracts. PLoS Computational Biology, In press.Introduction:In this study, we propose a deep learning model based on bidirectional long short-term memory to identify the evidence sentences of relationships among genes, chemicals, and diseases from Medline abstracts. Then, we develop the search engine DigChem to enable disease–gene–chemical relationship searches for 35,124 genes, 56,382 chemicals, and 5,675 diseases. We show that the identified relationships are reliable by comparing them with manual curation and existing databases.Description:DigChem is available at http://gcancer.org/digchem. The unique triplets identified from DigChem can be downloaded from here.

论文：金炅均（Jeongkyun Kim）、金廷宰（Jung-jae Kim）、李贤珠*（Hyunju Lee）（2019）《DigChem：从Medline摘要中识别疾病-基因-化学物关联》，《公共科学图书馆·计算生物学（PLoS Computational Biology）》，即将刊出。
研究背景：本研究提出一种基于双向长短期记忆网络（bidirectional long short-term memory）的深度学习模型，用于从Medline摘要中识别基因、化学物质与疾病三者间关联的证据语句。随后，我们开发了搜索引擎DigChem，可针对35124个基因、56382种化学物质以及5675种疾病实现疾病-基因-化学物关联检索。本研究通过与人工编校结果及现有数据库比对，验证了所识别关联的可靠性。
数据集说明：DigChem 可通过访问网址 http://gcancer.org/digchem 获取。从DigChem中识别得到的唯一关联三元组可在此处下载。