As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
The research of related genes is an extremely important issue in the study of human genes. Scientists could utilize related human genes to build huge, integrated gene regulatory network which enables scientists to discover the relationships between genes and diseases. In this research, we conduct the text mining through Natural Language Processing (NLP) by introducing a deep learning method. In order to obtain the association between genes based on the text information, we construct a parallel Convolutional Neural Network (CNN) with parallel convolutional layers and dynamic convolutional pooling layers to deduce the relationship – positive, negative, or nonexistent. Unlike other studies, we extract the positive and negative gene relationships, and apply the deep learning method to this field. For gene relationship recognition, the accuracy is 85.2%. The result of this algorithm turns out to be promising.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.