Feature selection environment for genomic applications

Background: Feature 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. Results: The 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. Conclusion: The 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.

Towards improving cluster-based feature selection with a simplified silhouette filter

This paper proposes a filter-based algorithm for feature selection. The filter is based on the partitioning of the set of features into clusters. The number of clusters, and consequently the cardinality of the subset of selected features, is automatically estimated from data. The computational complexity of the proposed algorithm is also investigated. A variant of this filter that considers feature-class correlations is also proposed for classification problems. Empirical results involving ten datasets illustrate the performance of the developed algorithm, which in general has obtained competitive results in terms of classification accuracy when compared to state of the art algorithms that find clusters of features. We show that, if computational efficiency is an important issue, then the proposed filter May be preferred over their counterparts, thus becoming eligible to join a pool of feature selection algorithms to be used in practice. As an additional contribution of this work, a theoretical framework is used to formally analyze some properties of feature selection methods that rely on finding clusters of features. (C) 2011 Elsevier Inc. All rights reserved.

U-curve: A branch-and-bound optimization algorithm for U-shaped cost functions on Boolean lattices applied to the feature selection problem

This paper presents the formulation of a combinatorial optimization problem with the following characteristics: (i) the search space is the power set of a finite set structured as a Boolean lattice; (ii) the cost function forms a U-shaped curve when applied to any lattice chain. This formulation applies for feature selection in the context of pattern recognition. The known approaches for this problem are branch-and-bound algorithms and heuristics that explore partially the search space. Branch-and-bound algorithms are equivalent to the full search, while heuristics are not. This paper presents a branch-and-bound algorithm that differs from the others known by exploring the lattice structure and the U-shaped chain curves of the search space. The main contribution of this paper is the architecture of this algorithm that is based on the representation and exploration of the search space by new lattice properties proven here. Several experiments, with well known public data, indicate the superiority of the proposed method to the sequential floating forward selection (SFFS), which is a popular heuristic that gives good results in very short computational time. In all experiments, the proposed method got better or equal results in similar or even smaller computational time. (C) 2009 Elsevier Ltd. All rights reserved.

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 Erdos-Renyi (ER), the small-world Watts-Strogatz (WS), the scale-free Barabasi-Albert (BA), and geographical networks (GG). The experimental results indicate that the inference method was sensitive to average degree k variation, decreasing its network recovery rate with the increase of k. 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.

Inference of gene regulatory networks from time series by Tsallis entropy

Background: The 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. Results: In 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. Conclusions: A 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/.

Support vector machines for detecting age-related changes in running kinematics

Age-related changes in running kinematics have been reported in the literature using classical inferential statistics. However, this approach has been hampered by the increased number of biomechanical gait variables reported and subsequently the lack of differences presented in these studies. Data mining techniques have been applied in recent biomedical studies to solve this problem using a more general approach. In the present work, we re-analyzed lower extremity running kinematic data of 17 young and 17 elderly male runners using the Support Vector Machine (SVM) classification approach. In total, 31 kinematic variables were extracted to train the classification algorithm and test the generalized performance. The results revealed different accuracy rates across three different kernel methods adopted in the classifier, with the linear kernel performing the best. A subsequent forward feature selection algorithm demonstrated that with only six features, the linear kernel SVM achieved 100% classification performance rate, showing that these features provided powerful combined information to distinguish age groups. The results of the present work demonstrate potential in applying this approach to improve knowledge about the age-related differences in running gait biomechanics and encourages the use of the SVM in other clinical contexts. (C) 2010 Elsevier Ltd. All rights reserved.

Supporting content-based image retrieval and computer-aided diagnosis systems with association rule-based techniques

In this work, we take advantage of association rule mining to support two types of medical systems: the Content-based Image Retrieval (CBIR) systems and the Computer-Aided Diagnosis (CAD) systems. For content-based retrieval, association rules are employed to reduce the dimensionality of the feature vectors that represent the images and to improve the precision of the similarity queries. We refer to the association rule-based method to improve CBIR systems proposed here as Feature selection through Association Rules (FAR). To improve CAD systems, we propose the Image Diagnosis Enhancement through Association rules (IDEA) method. Association rules are employed to suggest a second opinion to the radiologist or a preliminary diagnosis of a new image. A second opinion automatically obtained can either accelerate the process of diagnosing or to strengthen a hypothesis, increasing the probability of a prescribed treatment be successful. Two new algorithms are proposed to support the IDEA method: to pre-process low-level features and to propose a preliminary diagnosis based on association rules. We performed several experiments to validate the proposed methods. The results indicate that association rules can be successfully applied to improve CBIR and CAD systems, empowering the arsenal of techniques to support medical image analysis in medical systems. (C) 2009 Elsevier B.V. All rights reserved.

An association rule-based method to support medical image diagnosis with efficiency

In this paper, we propose a method based on association rule-mining to enhance the diagnosis of medical images (mammograms). It combines low-level features automatically extracted from images and high-level knowledge from specialists to search for patterns. Our method analyzes medical images and automatically generates suggestions of diagnoses employing mining of association rules. The suggestions of diagnosis are used to accelerate the image analysis performed by specialists as well as to provide them an alternative to work on. The proposed method uses two new algorithms, PreSAGe and HiCARe. The PreSAGe algorithm combines, in a single step, feature selection and discretization, and reduces the mining complexity. Experiments performed on PreSAGe show that this algorithm is highly suitable to perform feature selection and discretization in medical images. HiCARe is a new associative classifier. The HiCARe algorithm has an important property that makes it unique: it assigns multiple keywords per image to suggest a diagnosis with high values of accuracy. Our method was applied to real datasets, and the results show high sensitivity (up to 95%) and accuracy (up to 92%), allowing us to claim that the use of association rules is a powerful means to assist in the diagnosing task.

An Information Theory framework for two-stage binary image operator design

The design of translation invariant and locally defined binary image operators over large windows is made difficult by decreased statistical precision and increased training time. We present a complete framework for the application of stacked design, a recently proposed technique to create two-stage operators that circumvents that difficulty. We propose a novel algorithm, based on Information Theory, to find groups of pixels that should be used together to predict the Output Value. We employ this algorithm to automate the process of creating a set of first-level operators that are later combined in a global operator. We also propose a principled way to guide this combination, by using feature selection and model comparison. Experimental results Show that the proposed framework leads to better results than single stage design. (C) 2009 Elsevier B.V. All rights reserved.

Vegetative and fruit characteristics of papaya trees obtained by mass selection

The present work had as purpose to evaluate some characteristics of papaya trees (Carica papaya L.), Golden cultivar, obtained trough plant mass selection, regarding plant and fruit quality in the first months of production. The samples were evaluated in a commercial crop at: 0, 20, 40, 70, 130, 180, 230, 260, 280, 310 and 340 days after the planting (DAP) and the first fruits were harvested at 230 DAP. The results showed the low height (199cm in 340 DAP) and low first flowering`s heigth (71cm), which is important to facilitate the harvest process. The plants presented good yield with high number of leafs (allowing a great area of fruit cover) and about 60 fruits per plant. The fruits kept similar features to cv. Golden. The fruit`s fresh weight ranged from 302.4 to 467.5g, which is in the range of the Brazilian market. The pulp thickness was 2.35cm, which is a feature of great economic interest. The pulp thickness showed close relation with climatic factors, and great variations of temperature and precipitation accelerated the pulp loss of thickness.

SELECTION OF TRICHOGRAMMA PRETIOSUM LINEAGES FOR CONTROL OF GRAPHOLITA MOLESTA IN PEACH

Grapholita molesta (Lepidoptera: Tortricidae) is one of the main pests of peach trees in Brazil, causing fruit losses of 3-5%. Among possible biological control agents, Trichogramma pretiosum (Hymenoptera: Trichogrammatidae) has been found in peach orchards. Our objectives were to study the rearing of T pretiosum in eggs of G. molesta and Anagasta kuehniella (Lepidoptera: Pyralidae), and select lineages of this parasitoid that have the potential to control G. molesta. Selection of best lineages was made from 5 populations of T pretiosum collected from organically-cultivated peach orchards. The study was done under controlled temperature (25 +/- 2 degrees C), relative humidity (70 +/- 10%) and 14:10 h (light:dark) photoperiod conditions. Grapholita molesta eggs were found to be adequate hosts for the development of T pretiosum, and the parameters for number of parasitized eggs, percent parasitized eggs, and sex ratio were similar to those for A. kuehniella eggs. The highest rate of parasitism of G. molesta eggs occurred in eggs with up to 48 h of embryonic development. Among the lineages of T pretiosum that were collected, HO8, PO8, PEL, and L3M showed the best biological performance and are therefore indicated for semi-field and field studies for biological control of oriental fruit moth.

Motor Nerve-Conduction Studies in Obstetric Brachial Plexopathy for a Selection of Patients with a Poor Outcome

Background: The criteria and timing for nerve surgery in infants with obstetric brachial plexopathy remain controversial. Our aim was to develop a new method for early prognostic assessment to assist this decision process. Methods: Fifty-four patients with unilateral obstetric brachial plexopathy who were ten to sixty days old underwent bilateral motor-nerve-conduction studies of the axillary, musculocutaneous, proximal radial, distal radial, median, and ulnar nerves. The ratio between the amplitude of the compound muscle action potential of the affected limb and that of the healthy side was called the axonal viability index. The patients were followed and classified in three groups according to the clinical outcome. We analyzed the receiver operating characteristic curve of each index to define the best cutoff point to detect patients with a poor recovery. Results: The best cutoff points on the axonal viability index for each nerve (and its sensitivity and specificity) were <10% (88% and 89%, respectively) for the axillary nerve, 0% (88% and 73%) for the musculocutaneous nerve, <20% (82% and 97%) for the proximal radial nerve, <50% (82% and 97%) for the distal radial nerve, and <50% (59% and 97%) for the ulnar nerve. The indices from the proximal radial, distal radial, and ulnar nerves had better specificities compared with the most frequently used clinical criterion: absence of biceps function at three months of age. Conclusions: The axonal viability index yields an earlier and more specific prognostic estimation of obstetric brachial plexopathy than does the clinical criterion of biceps function, and we believe it may be useful in determining surgical indications in these patients.

Selection of suitable housekeeping genes for expression analysis in glioblastoma using quantitative RT-PCR

Background: Considering the broad variation in the expression of housekeeping genes among tissues and experimental situations, studies using quantitative RT-PCR require strict definition of adequate endogenous controls. For glioblastoma, the most common type of tumor in the central nervous system, there was no previous report regarding this issue. Results: Here we show that amongst seven frequently used housekeeping genes TBP and HPRT1 are adequate references for glioblastoma gene expression analysis. Evaluation of the expression levels of 12 target genes utilizing different endogenous controls revealed that the normalization method applied might introduce errors in the estimation of relative quantities. Genes presenting expression levels which do not significantly differ between tumor and normal tissues can be considered either increased or decreased if unsuitable reference genes are applied. Most importantly, genes showing significant differences in expression levels between tumor and normal tissues can be missed. We also demonstrated that the Holliday Junction Recognizing Protein, a novel DNA repair protein over expressed in lung cancer, is extremely over-expressed in glioblastoma, with a median change of about 134 fold. Conclusion: Altogether, our data show the relevance of previous validation of candidate control genes for each experimental model and indicate TBP plus HPRT1 as suitable references for studies on glioblastoma gene expression.

SMALL MAMMAL PREY SELECTION BY TWO OWL SPECIES IN SOUTHEASTERN BRAZIL

A variety of factors influence prey selection by predators. Because Barn Owls (Tyto alba) and Burrowing Owls (Athene cunicularia) differ in size and foraging tactics, we expected differential predation on small mammal prey. We hypothesized that the Barn Owl, all active predator, would prey on smaller and younger individuals than the Burrowing Owl, a sit-and-wait predator. We used pellet analyses to evaluate selection of small mammals by the two owls in relation to prey), species, age, and size at the Ecological Station of Itirapina, state of Sao Paulo, in southeastern Brazil. Small mammals constituted most of the prey individuals and biomass in the diet of Barn Owls. Although Burrowing Owls consumed a wider range of taxa, small mammals represented one-third of all biomass consumed. With respect. to small mammals, Barn Owls foraged selectively relative to prey species, size, and age. Burrowing Owls foraged opportunistically relative to prey species, but selectively relative to prey size and age. Barn Owls selected smaller and younger (juvenile and subadult) individuals of the delicate vesper mouse (Calomys tener) and Burrowing Owls preyed more oil larger and older (subadult only) individuals. morphology and behavior of both prey and predators may explain this differential predation. Our data suggest that the active predator feeds oil smaller and younger prey, and the sit-and-wait predator took relatively larger and older prey.

Singing in the Rain Forest: How a Tropical Bird Song Transfers Information

How information transmission processes between individuals are shaped by natural selection is a key question for the understanding of the evolution of acoustic communication systems. Environmental acoustics predict that signal structure will differ depending on general features of the habitat. Social features, like individual spacing and mating behavior, may also be important for the design of communication. Here we present the first experimental study investigating how a tropical rainforest bird, the white-browed warbler Basileuterus leucoblepharus, extracts various information from a received song: species-specific identity, individual identity and location of the sender. Species-specific information is encoded in a resistant acoustic feature and is thus a public signal helping males to reach a wide audience. Conversely, individual identity is supported by song features susceptible to propagation: this private signal is reserved for neighbors. Finally, the receivers can locate the singers by using propagation-induced song modifications. Thus, this communication system is well matched to the acoustic constraints of the rain forest and to the ecological requirements of the species. Our results emphasize that, in a constraining acoustic environment, the efficiency of a sound communication system results from a coding/decoding process particularly well tuned to the acoustic properties of this environment.