作者机构:
[Jiang, Xingpeng; Yang, Jincai; Ma, Shunping] Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.
会议名称:
IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
会议时间:
NOV 18-21, 2019
会议地点:
San Diego, CA
会议主办单位:
[Yang, Jincai;Ma, Shunping;Jiang, Xingpeng] Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.
会议论文集名称:
IEEE International Conference on Bioinformatics and Biomedicine-BIBM
关键词:
lncRNA;disease;autoencoder;rotation forest
摘要:
In the past few years, most disease-related lncRNAs have been identified, but the experimental identification is cost-consuming and time-consuming. It is therefore very important to develop a reliable computational model to predict lncRNA-disease association. In this paper, we propose a method based on similarity, combining autoencoder and rotation forest to predict lncRNA-disease association (SARLDA). This method not only makes use of disease and lncRNA similarities, but also extracts latent low-dimension features and expand the gap between samples to make it easier to predict the associations. To evaluate our method, we conducted several experiments. Sufficient validations show that this method has significantly improved the prediction performance.
摘要:
Biomedical event extraction has wide applications in biomedicine field. As a prerequisite step in biomedical event extraction, event trigger identification has attracted growing attention in biomedical research. Although many approaches have been proposed for biomedical event trigger identification, two main challenges still remain for researchers: 1) most of the existing approaches treat each sentence separately in biomedical documents, failing to make full use of the semantics in the global document context; 2) the sparseness of event triggers leads to a serious issue of imbalanced class for trigger identification. In this paper, we propose an end-to-end framework for biomedical event trigger identification which addresses effectively the two mentioned challenges accordingly. Specifically, a hierarchical attention mechanism is used to model the global document context, including the semantic relationships both among words in the same sentence and among sentences in the same document. In addition, an adaptive class weight learning method is proposed to treat the class imbalance issue in biomedical event trigger identification. Experimental results on two commonly used datasets demonstrate the effectiveness of the proposed framework.
摘要:
Microbial ecosystems are complex, by analyzing co-occurrence modules of microbial communities, we can better understand the conditions of microbial interactions in each environment, and help understand the interaction patterns that maintain the stability of microbial communities. Imbalances in human microbiome are closely related to human disease. Previous modular clustering analysis was based only on the relationship between paired microorganisms. In this paper, we propose calculating the logical relationship between microbial triplet in human body by information entropy and construct a hypergraph based on the triplet network. Based on the hypergraph clustering, we proposed a novel hypergraph clustering algorithm based on intra-class scatter matrix (HCIS) to reconstruct hyperedge similarity, and selected the optimal cluster number by maximizing modularity to analyze higher-order module of microorganisms. The clustering results verify the effectiveness and feasibility of HCIS algorithm for higher-order microbial module analysis.
作者机构:
[Shen, Xianjun; Hu, Xiaohua; Zhu, Huan; Jiang, Xingpeng; Yang, Jincai] Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.;[Hu, Xiaohua] Drexel Univ, Coll Comp & Informat, Philadelphia, PA 19104 USA.
会议名称:
14th International Conference on Intelligent Computing (ICIC)
会议时间:
AUG 15-18, 2018
会议地点:
Wuhan, PEOPLES R CHINA
会议主办单位:
[Shen, Xianjun;Zhu, Huan;Jiang, Xingpeng;Hu, Xiaohua;Yang, Jincai] Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.^[Hu, Xiaohua] Drexel Univ, Coll Comp & Informat, Philadelphia, PA 19104 USA.
会议论文集名称:
Lecture Notes in Artificial Intelligence
关键词:
Microbe-disease associations;Bi-Random Walk;Computational prediction model
摘要:
An increasing number of clinical observations have confirmed that the microbes inhabiting in human body have critical impacts on the progression of human disease, which provides promising insights into understanding the mechanism of diseases. However, the known microbe-disease associations remain limited. So, we proposed Bi-Random Walk based on Multiple Path (BiRWMP) to predict microbe-disease associations. Leave-one-out cross-validation (LOOCV) and 5-fold cross-validation were adopted to demonstrate the capability of proposed method. BiRWMP performed better than other methods. Finally, we listed 2 common disease and potential microbes ranked at top 10, and we demonstrated its reasonableness through looking up literatures.