/Categorizing-figures-from-biomedical-research-articles-using-deep-neural-networks-and-Bioassays

The project’s main objective is to extract knowledge from the biomedical research papers that contain diagrams/charts, i.e., bar graphs, line graph, boxplot, images of CT scans, cells, and other types of biological tests (known as assays). Research papers contain panels that have information in images or diagrams. The goal is to identify each panel from given datasets and categorize it into BioAssay Ontology categories with the help of machine learning and deep neural networks model. An additional focus of the project is to predict and identify the similarities between BioAssay Ontology categories and find their correlation. The dataset we are using is from SourceData, an initiative by EMBO (European Molecular Biology Organization). So, this project will record details of the correlation of BioAssay Ontology categories, predict and identify the panel with the help of a Convolutional neural network model.

Primary LanguageJupyter Notebook

Categorizing-figures-from-biomedical-research-articles-using-deep-neural-networks-and-Bioassays

The project’s main objective is to extract knowledge from the biomedical research papers that contain diagrams/charts, i.e., bar graphs, line graph, boxplot, images of CT scans, cells, and other types of biological tests (known as assays). Research papers contain panels that have information in images or diagrams. The goal is to identify each panel from given datasets and categorize it into BioAssay Ontology categories with the help of machine learning and deep neural networks model. An additional focus of the project is to predict and identify the similarities between BioAssay Ontology categories and find their correlation. The dataset we are using is from SourceData, an initiative by EMBO (European Molecular Biology Organization). So, this project will record details of the correlation of BioAssay Ontology categories, predict and identify the panel with the help of a Convolutional neural network model.