Paula Raissa Silva

Abstract
With the advances of the big data era in biology, deep learning have been incorporated in analysis pipelines trying to transform biological information into valuable knowledge. Deep learning demonstrated its power in promoting bioinformatics field including sequence analysis, bio-molecular property and function prediction, automatic medical diagnosis and to analyse cell imaging data. The ambition of this work is to create an approach that can fully explore the relationships across modalities and subjects through mining and fusing features from multi-modality data for cell state classification. The system should be able to classify cell state through multimodal deep learning techniques using heterogeneous data such as biological images, genomics and clinical annotations. Our pilot study addresses the data acquisition process and the framework capable to extract biological parameters from cell images. © 2020 Owner/Author.

Abstract

Abstract
Formal concept analysis (FCA) is largely applied in different areas. However, in some FCA applications the volume of information that needs to be processed can become unfeasible. Thus, the demand for new approaches and algorithms that enable processing large amounts of information is increasing substantially. This article presents a new algorithm for extracting proper implications from high-dimensional contexts. The proposed algorithm, called ImplicPBDD, was based on the PropIm algorithm, and uses a data structure called binary decision diagram (BDD) to simplify the representation of the formal context and enhance the extraction of proper implications. In order to analyze the performance of the ImplicPBDD algorithm, we performed tests using synthetic contexts varying the number of objects, attributes and context density. The experiments show that ImplicPBDD has a better performance—up to 80% faster—than its original algorithm, regardless of the number of attributes, objects and densities.

Abstract

Abstract