Mining relations between chemicals and proteins from the biomedical literature is an increasingly important task. The CHEMPROT track at BioCreative VI aims to promote the development and evaluation of systems that can automatically detect the chemical–protein relations in running text (PubMed abstracts). This work describes our CHEMPROT track entry, which is an ensemble of three systems, including a support vector machine, a convolutional neural network, and a recurrent neural network. Their output is combined using majority voting or stacking for final predictions. Our CHEMPROT system obtained 0.7266 in precision and 0.5735 in recall for an F-score of 0.6410 during the challenge, demonstrating the effectiveness of machine learning-based approaches for automatic relation extraction from biomedical literature and achieving the highest performance in the task during the 2017 challenge. Database URL: http://www.biocreative.org/tasks/biocreative-vi/track-5/

Yifan Peng

Anthony Rios

Ramakanth Kavuluru

Zhiyong Lu

Database

大量原始数据存档在众多开放存取数据库中，随着新一代技术在实验室中变得越来越普遍，大型数据集将变得更加普遍。所有这些数据的归档、管理、分析和解释都是一项挑战。数据库开发和生物管理处于努力理解这种不断增加的数据洪流的最前沿。数据库：生物数据库和管理杂志提供了一个开放访问平台，用于展示数据库研究和生物管理中的新思想，旨在帮助加强数据库开发人员、管理者和用户之间的桥梁。

As next-generation technologies become increasingly common in laboratories, a vast amount of raw data is being archived in numerous open-access databases, leading to the prevalence of large datasets. Effectively archiving, managing, analyzing, and interpreting this data presents a significant challenge. Database development and biological management are at the forefront of understanding this growing data deluge. "Database: The Journal of Biological Databases and Curation" offers an open-access platform to showcase new ideas in database research and biological management, aiming to strengthen the connections between database developers, managers, and users.

随着新一代技术在实验室中的普及，越来越多的原始数据被存档在众多开放存取数据库中，导致大型数据集的出现变得愈加普遍。如何有效地归档、管理、分析和解释这些数据，成为了一项巨大的挑战。数据库开发和生物管理正处于理解这一不断增加的数据洪流的前沿。"Database: The Journal of Biological Databases and Curation" 提供了一个开放获取的平台，旨在展示数据库研究和生物管理中的新思想，帮助加强数据库开发者、管理者与用户之间的联系。

Database : the journal of biological databases and curation

Extracting chemical–protein relations with ensembles of SVM and deep learning models

This work describes the CHEMPROT track entry, which is an ensemble of three systems, including a support vector machine, a convolutional neural network, and a recurrent neural network that is combined using majority voting or stacking for final predictions.

Category	Quartile
生物学	4
生物学, 数学与计算生物学	4

Extracting chemical–protein relations with ensembles of SVM and deep learning models

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info

Category	Quartile
MATHEMATICAL & COMPUTATIONAL BIOLOGY	1