Computational Intelligence Methods for Bioinformatics and Biostatistics 

About: Computational Intelligence Methods for Bioinformatics and Biostatistics is an academic conference. The conference publishes majorly in the area(s): Cluster analysis & Feature selection. Over the lifetime, 289 publications have been published by the conference receiving 997 citations.

A Deep Learning Approach to DNA Sequence Classification

Abstract: Deep learning neural networks are capable to extract significant features from raw data, and to use these features for classification tasks. In this work we present a deep learning neural network for DNA sequence classification based on spectral sequence representation. The framework is tested on a dataset of 16S genes and its performances, in terms of accuracy and F1 score, are compared to the General Regression Neural Network, already tested on a similar problem, as well as naive Bayes, random forest and support vector machine classifiers. The obtained results demonstrate that the deep learning approach outperformed all the other classifiers when considering classification of small sequence fragment 500 bp long.

Automatic unsupervised segmentation of retinal vessels using self-organizing maps and K-means clustering

Abstract: In this paper an automatic unsupervised method for the segmentation of retinal vessels is proposed. A Self-Organizing Map is trained on a portion of the same image that is tested and K-means clustering algorithm is used to divide the map units in 2 classes. The entire image is again input for the Self-Organizing Map, and the class of each pixel will be the class of the best matching unit on the Self-Organizing Map. Finally, the vessel network is post-processed using a hill climbing strategy on the connected components of the segmented image. The experimental evaluation on the publicly available DRIVE database shows accurate extraction of vessels network and a good agreement between our segmentation and the ground truth. The mean accuracy, 0.9459 with a standard deviation of 0.0094, is outperforming the manual segmentation rates obtained by other widely used unsupervised methods. A good kappa value of 0.6562 is inline with state-of-the-art supervised and unsupervised approaches.

Writing Generation Model for Health Care Neuromuscular System Investigation

Abstract: In this paper the use of handwriting for health investigation is addressed. For the purpose, the paper first presents the Delta-Log and Sigma-Log models to investigate on the handwriting generation processes carried out by the neuromuscular system. Successively, a computational system for handwriting analysis is presented and some considerations are exploited about the use of the model to investigate insurgence and monitoring of some neuromuscular diseases. The experimental results show the validity of the proposed approach and highlight some directions for further research.

Community Detection in Protein-Protein Interaction Networks Using Spectral and Graph Approaches

Abstract: Inferring significant communities of interacting proteins is a main trend of current biological research, as this task can help in revealing the functionality and the relevance of specific macromolecular assemblies or even in discovering possible proteins affecting a specific biological process. Efficient algorithms able to find suitable communities inside proteins networks may support drug discovery and diseases treatment even in earlier stages. This paper employs spectral and graph clustering methodologies for discovering protein-protein interactions communities in the Saccharomyces cerevisiae protein-protein interaction network.

Piecewise Exponential Artificial Neural Networks (PEANN) for Modeling Hazard Function with Right Censored Data

Abstract: The hazard function plays an important role in the study of disease dynamics in survival analysis. Longer follow-up for various kinds of cancer, particularly breast cancer, has made it possible the observation of complex shapes of the hazard function of occurrence of metastasis and death. The identification of the correct hazard shape is important both for formulation and support of biological hypotheses on the mechanism underlying the disease.