Fabrício Martins Lopes

Feature selection environment for genomic applications

BackgroundFeature selection is a pattern recognition approach to choose important variables according to some criteria in order to distinguish or explain certain phenomena (i.e., for dimensionality reduction). There are many genomic and proteomic applications that rely on feature selection to answer questions such as selecting signature genes which are informative about some biological state, e.g., normal tissues and several types of cancer; or inferring a prediction network among elements such as genes, proteins and external stimuli. In these applications, a recurrent problem is the lack of samples to perform an adequate estimate of the joint probabilities between element states. A myriad of feature selection algorithms and criterion functions have been proposed, although it is difficult to point the best solution for each application.ResultsThe intent of this work is to provide an open-source multiplataform graphical environment for bioinformatics problems, which supports many feature selection algorithms, criterion functions and graphic visualization tools such as scatterplots, parallel coordinates and graphs. A feature selection approach for growing genetic networks from seed genes (targets or predictors) is also implemented in the system.ConclusionThe proposed feature selection environment allows data analysis using several algorithms, criterion functions and graphic visualization tools. Our experiments have shown the software effectiveness in two distinct types of biological problems. Besides, the environment can be used in different pattern recognition applications, although the main concern regards bioinformatics tasks.

Networking the host immune response in Plasmodium vivax malaria.

BackgroundPlasmodium vivax malaria clinical outcomes are a consequence of the interaction of multiple parasite, environmental and host factors. The host molecular and genetic determinants driving susceptibility to disease severity in this infection are largely unknown. Here, a network analysis of large-scale data from a significant number of individuals with different clinical presentations of P. vivax malaria was performed in an attempt to identify patterns of association between various candidate biomarkers and the clinical outcomes.MethodsA retrospective analysis of 530 individuals from the Brazilian Amazon, including P. vivax-infected individuals who developed different clinical outcomes (148 asymptomatic malaria, 187 symptomatic malaria, 13 severe non-lethal malaria, and six severe lethal malaria) as well as 176 non-infected controls, was performed. Plasma levels of liver transaminases, bilirubins, creatinine, fibrinogen, C-reactive protein, superoxide dismutase (SOD)-1, haem oxygenase (HO)-1 and a panel composed by multiple cytokines and chemokines were measured and compared between the different clinical groups using network analysis.ResultsNon-infected individuals displayed several statistically significant interactions in the networks, including associations between the levels of IL-10 and IL-4 with the chemokine CXCL9. Individuals with asymptomatic malaria displayed multiple significant interactions involving IL-4. Subjects with mild or severe non-lethal malaria displayed substantial loss of interactions in the networks and TNF had significant associations more frequently with other parameters. Cases of lethal P. vivax malaria infection were associated with significant interactions between TNF ALT, HO-1 and SOD-1.ConclusionsThe findings imply that clinical immunity to P. vivax malaria is associated with multiple significant interactions in the network, mostly involving IL-4, while lethality is linked to a systematic reduction of complexity of these interactions and to an increase in connections between markers linked to haemolysis-induced damage.

A feature selection technique for inference of graphs from their known topological properties: Revealing scale-free gene regulatory networks

Abstract An important problem in bioinformatics is the inference of gene regulatory networks (GRNs) from expression profiles. In general, the main limitations faced by GRN inference methods are the small number of samples with huge dimensionalities and the noisy nature of the expression measurements. Alternatives are thus needed to obtain better accuracy for the GRNs inference problem. Many pattern recognition techniques rely on prior knowledge about the problem in addition to the training data to gain statistical estimation power. This work addresses the GRN inference problem by modeling prior knowledge about the network topology. The main contribution of this paper is a novel methodology that aggregates scale-free properties to a classical low-cost feature selection method, known as Sequential Floating Forward Selection (SFFS), for guiding the inference task. Such methodology explores the search space iteratively by applying a scale-free property to reduce the search space. In this way, the search space traversed by the method integrates the exploration of all combinations of predictors set when the number of combinations is small (dimensionality 〈 k 〉 ⩽ 2 ) with a floating search when the number of combinations becomes explosive (dimensionality 〈 k 〉 ⩾ 3 ). This process is guided by scale-free prior information. Experimental results using synthetic and real data show that this technique provides smaller estimation errors than those obtained without guiding the SFFS application by the scale-free model, thus maintaining the robustness of the SFFS method. Therefore, we show that the proposed framework may be applied in combination with other existing GRN inference methods to improve the prediction accuracy of networks with scale-free properties.

Brazilian bibliometric coauthorship networks

The Brazilian Lattes Platform is an important academic/résumé data set that registers all academic activities of researchers associated with different major knowledge areas. The academic information collected in this data set is used to evaluate, analyze, and document the scientific production of research groups. Information about the interactions between Brazilian researchers in the form of coauthorships, however, has not been analyzed. In this article, we identified and characterized Brazilian academic coauthorship networks of researchers registered in the Lattes Platform using topological properties of graphs. For this purpose, we explored (a) strategies to develop a large Lattes curricula vitae data set, (b) an algorithm for identifying automatic coauthorships based on bibliographic information, and (c) topological metrics to investigate interactions among researchers. This study characterized coauthorship networks to gain an in‐depth understanding of the network structures and dynamics (social behavior) among researchers in all available major Brazilian knowledge areas. In this study, we evaluated information from a total of 1,131,912 researchers associated with the eight major Brazilian knowledge areas: agricultural sciences; biological sciences; exact and earth sciences; humanities; applied social sciences; health sciences; engineering; and linguistics, letters, and arts.

Inference of gene regulatory networks from time series by Tsallis entropy

BackgroundThe inference of gene regulatory networks (GRNs) from large-scale expression profiles is one of the most challenging problems of Systems Biology nowadays. Many techniques and models have been proposed for this task. However, it is not generally possible to recover the original topology with great accuracy, mainly due to the short time series data in face of the high complexity of the networks and the intrinsic noise of the expression measurements. In order to improve the accuracy of GRNs inference methods based on entropy (mutual information), a new criterion function is here proposed.ResultsIn this paper we introduce the use of generalized entropy proposed by Tsallis, for the inference of GRNs from time series expression profiles. The inference process is based on a feature selection approach and the conditional entropy is applied as criterion function. In order to assess the proposed methodology, the algorithm is applied to recover the network topology from temporal expressions generated by an artificial gene network (AGN) model as well as from the DREAM challenge. The adopted AGN is based on theoretical models of complex networks and its gene transference function is obtained from random drawing on the set of possible Boolean functions, thus creating its dynamics. On the other hand, DREAM time series data presents variation of network size and its topologies are based on real networks. The dynamics are generated by continuous differential equations with noise and perturbation. By adopting both data sources, it is possible to estimate the average quality of the inference with respect to different network topologies, transfer functions and network sizes.ConclusionsA remarkable improvement of accuracy was observed in the experimental results by reducing the number of false connections in the inferred topology by the non-Shannon entropy. The obtained best free parameter of the Tsallis entropy was on average in the range 2.5 ≤ q ≤ 3.5 (hence, subextensive entropy), which opens new perspectives for GRNs inference methods based on information theory and for investigation of the nonextensivity of such networks. The inference algorithm and criterion function proposed here were implemented and included in the DimReduction software, which is freely available at http://sourceforge.net/projects/dimreduction and http://code.google.com/p/dimreduction/.

Gene Expression Complex Networks: Synthesis, Identification, and Analysis

Thanks to recent advances in molecular biology, allied to an ever increasing amount of experimental data, the functional state of thousands of genes can now be extracted simultaneously by using methods such as cDNA microarrays and RNA-Seq. Particularly important related investigations are the modeling and identification of gene regulatory networks from expression data sets. Such a knowledge is fundamental for many applications, such as disease treatment, therapeutic intervention strategies and drugs design, as well as for planning high-throughput new experiments. Methods have been developed for gene networks modeling and identification from expression profiles. However, an important open problem regards how to validate such approaches and its results. This work presents an objective approach for validation of gene network modeling and identification which comprises the following three main aspects: (1) Artificial Gene Networks (AGNs) model generation through theoretical models of complex networks, which is used to simulate temporal expression data; (2) a computational method for gene network identification from the simulated data, which is founded on a feature selection approach where a target gene is fixed and the expression profile is observed for all other genes in order to identify a relevant subset of predictors; and (3) validation of the identified AGN-based network through comparison with the original network. The proposed framework allows several types of AGNs to be generated and used in order to simulate temporal expression data. The results of the network identification method can then be compared to the original network in order to estimate its properties and accuracy. Some of the most important theoretical models of complex networks have been assessed: the uniformly-random Erdös-Rényi (ER), the small-world Watts-Strogatz (WS), the scale-free Barabási-Albert (BA), and geographical networks (GG). The experimental results indicate that the inference method was sensitive to average degree variation, decreasing its network recovery rate with the increase of . The signal size was important for the inference method to get better accuracy in the network identification rate, presenting very good results with small expression profiles. However, the adopted inference method was not sensible to recognize distinct structures of interaction among genes, presenting a similar behavior when applied to different network topologies. In summary, the proposed framework, though simple, was adequate for the validation of the inferred networks by identifying some properties of the evaluated method, which can be extended to other inference methods.

A database for the taxonomic and phylogenetic identification of the genus Bradyrhizobium using multilocus sequence analysis

BackgroundBiological nitrogen fixation, with an emphasis on the legume-rhizobia symbiosis, is a key process for agriculture and the environment, allowing the replacement of nitrogen fertilizers, reducing water pollution by nitrate as well as emission of greenhouse gases. Soils contain numerous strains belonging to the bacterial genus Bradyrhizobium, which establish symbioses with a variety of legumes. However, due to the high conservation of Bradyrhizobium 16S rRNA genes - considered as the backbone of the taxonomy of prokaryotes - few species have been delineated. The multilocus sequence analysis (MLSA) methodology, which includes analysis of housekeeping genes, has been shown to be promising and powerful for defining bacterial species, and, in this study, it was applied to Bradyrhizobium, species, increasing our understanding of the diversity of nitrogen-fixing bacteria.DescriptionClassification of bacteria of agronomic importance is relevant to biodiversity, as well as to biotechnological manipulation to improve agricultural productivity. We propose the construction of an online database that will provide information and tools using MLSA to improve phylogenetic and taxonomic characterization of Bradyrhizobium, allowing the comparison of genomic sequences with those of type and representative strains of each species.ConclusionA database for the taxonomic and phylogenetic identification of the Bradyrhizobium, genus, using MLSA, will facilitate the use of biological data available through an intuitive web interface. Sequences stored in the on-line database can be compared with multiple sequences of other strains with simplicity and agility through multiple alignment algorithms and computational routines integrated into the database. The proposed database and software tools are available at http://mlsa.cnpso.embrapa.br, and can be used, free of charge, by researchers worldwide to classify Bradyrhizobium, strains; the database and software can be applied to replicate the experiments presented in this study as well as to generate new experiments. The next step will be expansion of the database to include other rhizobial species.

Entropic Biological Score: a cell cycle investigation for GRNs inference

Inference of gene regulatory networks (GRNs) is one of the most challenging research problems of Systems Biology. In this investigation, a new GRNs inference methodology, called Entropic Biological Score (EBS), which linearly combines the mean conditional entropy (MCE) from expression levels and a Biological Score (BS), obtained by integrating different biological data sources, is proposed. The EBS is validated with the Cell Cycle related functional annotation information, available from Munich Information Center for Protein Sequences (MIPS), and compared with some existing methods like MRNET, ARACNE, CLR and MCE for GRNs inference. For real networks, the performance of EBS, which uses the concept of integrating different data sources, is found to be superior to the aforementioned inference methods. The best results for EBS are obtained by considering the weights w1=0.2 and w2=0.8 for MCE and BS values, respectively, where approximately 40% of the inferred connections are found to be correct and significantly better than related methods. The results also indicate that expression profile is able to recover some true connections, that are not present in biological annotations, thus leading to the possibility of discovering new relations between its genes.

Comparative study of GRNS inference methods based on feature selection by mutual information

Feature selection is a crucial topic in pattern recognition applications, especially in the genetic regulatory networks (GRNs) inference problem which usually involves data with a large number of variables and small number of observations. In this context, the application of dimensionality reduction approaches such as those based on feature selection becomes a mandatory step in order to select the most important predictor genes that can explain some phenomena associated with the target genes. Given its importance in GRN inference, many feature selection methods (algorithms and criterion functions) have been proposed. However, it is decisive to validate such results in order to better understand its significance. The present work proposes a comparative study of feature selection techniques involving information theory concepts, applied to the estimation of GRNs from simulated temporal expression data generated by an artificial gene network (AGN) model. Four GRN inference methods are compared in terms of global network measures. Some interesting conclusions can be drawn from the experimental results.

3D facial expression analysis by using 2D AND 3D wavelet transforms

This work presents a new approach for the 3D human facial expressions analysis. Our methodology is based on 2D and 3D wavelet transforms, which are used to estimate multi-scale features from real a face acquired by a 3D scanner. The proposed methodology starts by considering a dataset composed by faces displaying seven different facial expressions. An automatic pre-processing method, adopting an ellipsoidal cropping, is applied to the dataset. Thereafter, the 2D and 3D descriptors are extracted from different scales of wavelet transforms for the purpose of obtaining the facial expression features. The multi-scale features are represented in a multi-variate feature space, which is analysed by the Sequential Forward Floating Selection algorithm using an entropy criterion function to select the subset of features that best represents each facial expression model. The obtained results corroborate the potential of multi-scale feature extraction for analysis of 3D facial expression.