Giancarlo Raiconi

Clustering and visualization approaches for human cell cycle gene expression data analysis

In this work a comprehensive multi-step machine learning data mining and data visualization framework is introduced. The different steps of the approach are: preprocessing, clustering, and visualization. A preprocessing based on a Robust Principal Component Analysis Neural Network for feature extraction of unevenly sampled data is used. Then a Probabilistic Principal Surfaces approach combined with an agglomerative procedure based on Fishers and Negentropy information is applied for clustering and labeling purposes. Furthermore, a Multi-Dimensional Scaling approach for a 2-dimensional data visualization of the clustered and labeled data is used. The method, which provides a user-friendly visualization interface in both 2 and 3 dimensions, can work on noisy data with missing points, and represents an automatic procedure to get, with no a priori assumptions, the number of clusters present in the data. Analysis and identification of genes periodically expressed in a human cancer cell line (HeLa) using cDNA microarrays is carried out as test case.

Genetic approach helps to speed classical Price algorithm for global optimization

In this paper is presented an hybrid algorithm for finding the absolute extreme point of a multimodal scalar function of many variables. The algorithm is suitable when the objective function is expensive to compute, the computation can be affected by noise and/or partial derivatives cannot be calculated. The method used is a genetic modification of a previous algorithm based on the Price’s method. All information about behavior of objective function collected on previous iterates are used to chose new evaluation points. The genetic part of the algorithm is very effective to escape from local attractors of the algorithm and assures convergence in probability to the global optimum. The proposed algorithm has been tested on a large set of multimodal test problems outperforming both the modified Price’s algorithm and classical genetic approach.

Critical state in Josephson junction arrays as models of a bi-dimensional superconducting granular system

In order to analyze the diamagnetic properties of sintered granular superconductors, a circuital model consisting of a network of identical inductances (L0) and Josephson junctions is developed. In particular, the case of sufficiently high values of the maximum Josephson currents (Ij), such that L0Ij⪢Φ0, is considered. Neglecting thermal activation processes, the process of irreversible penetration of flux quanta is studied numerically. A critical state model follows.

Data mining of large astronomical databases with neural tools

The International Virtual Observatory will pose unprecedented problems to data mining. We shortly discuss the effectiveness of neural networks as aids to the decisional process of the astronomer, and present the AstroMining Package. This package was written in Matlab and C++ and provides an user friendly interactive platform for various data mining tasks. Two applications are also shortly outlined: the derivation of photometric redshifts for a subsample of objects extracted from the Sloan Digital Sky Survey Early Data Release, and the evaluation of systematic patterns in the telemetry data for the Telescopio Nazionale Galilo (TNG).

Clustering, Assessment and Validation: an application to gene expression data

In this work a multi-step approach for clustering assessment, visualization and data validation is introduced. Three main approaches for data clustering are used and compared: K-means, self organizing maps and probabilistic principal surfaces. A model explorer approach with different similarity measures is used to obtain the best parameters of the methods. The approach is used to identify genes periodically expressed in tumors related to the human cell cycle. Finally, clusters are validated by using GO term information.

Global optimization, Meta Clustering and consensus clustering for class prediction

Clustering of real-world data is often ill-posed. Because of noise and intrinsic ambiguity in data, optimization models attempting to maximize a fitness function can be misled by the assumption of uniqueness of the solution. In this work we present a methodology including classic and novel techniques to approach clustering in a systematic way, with two application examples to biological data sets. The methodology is based on a process that generates multiple clustering solutions (using global optimization), performs cluster analysis on such clusterings (i.e. Meta Clustering) and analyzes the obtained clusterings by the appropriate application of different consensus techniques. In order to validate the method, we seek for the solutions that best match the real class labels, exploiting only a random sample of them. Finally, we guess the class labels of the remaining patterns using cluster enrichment information and verify the percentage of correct assignments for each class. The optimization of clustering objective functions together with the use of partial labeling puts the described approach in between unsupervised and semi-supervised methods.

Data visualization methodologies for data mining systems in bioinformatics

Bioinformatics systems benefit from the use of data mining strategies to locate interesting and pertinent relationships within massive information. For example, data mining methods can ascertain and summarize the set of genes responding to a certain level of stress in an organism. Even a cursory glance through the literature in journals, reveals the persistent role of data mining in experimental biology. Integrating data mining within the context of experimental investigations is central to bioinformatics software. In this paper we describe the framework of probabilistic principal surfaces, a latent variable model which offers a large variety of appealing visualization capabilities and which can be successfully integrated in the context of microarray analysis. A preprocessing phase consisting of a nonlinear PCA neural network which seems to be very useful to deal with noisy and time dependent nature of microarray data has been added to this framework.

A Combinatoric biclustering algorithm

The unsupervised analysis of gene expression data plays a very important role in Genetics experiments. That is why a lot of clustering and biclustering techniques have been proposed. Our choice of biclustering methods is motivated by the accuracy in the obtained results and the possibility to find not only rows or columns that provide a partition of the dataset but also rows and columns together. Unfortunately, the experimental data yet contains many inaccuracy and errors, therefore the main task of mathematicians is to find algorithms that permit to analyze this data with maximal precision. In this work, a new biclustering algorithm that permits to find biclusters with an error less than a predefined threshold is presented. The comparison with other known biclustering algorithms is shown.

Gene ontology fuzzy-enrichment analysis to investigate drug mode-of-action

We investigated the possibility of gaining information on the mode of action of a set of compounds by means of Gene Ontology (GO) enrichment analysis.

DATA VISUALIZATION AND CLUSTERING: AN APPLICATION TO GENE EXPRESSION DATA

In this work we present a multi-step process that, starting from raw datasets, brings them through preprocessing, preclustering and agglomerative clustering stages, exploiting a visual and interactive environment for data analysis and exploration. At the core of the process lies the idea of subdividing the process of data clusterization into two main steps: the first one aimed to reduce the size of data and the second one to present the reduced and human-understandable dataset to the user. This last step allows him to participate in the process of clustering and helps him figuring out the data underlying structures. The approach is actually implemented in a group of user-friendly tools under the MATLAB environment, featuring a number of classical and novel data processing, visualization, assessment and interaction methods.