Reconhecimento de seqüências de atividades funcionais em pacientes com acidente cascular encefálico

During the motor rehabilitation of patients with neurological pathologies, there are many factors that have an influence on the therapeutical process. It is possible that the demonstration using videotapes or photographs of movements that will be learned can assist the codification, classification and reorganization of the elements of the task in familiar diagrams and thus facilitate the process of motor rehabilitation. The aim of this study was to analyze the performance in the test of recognition of sequences of functional activities such as water drinking and hair combing presented partially (by photos) and completely (by video) to the patients with encephalic vascular accident . The sample was generated from 12 patients (62 ± 8 years) and 10 healthy subjects (53 ± 5 years), of both sex, divided in two groups for which 5 functional activities were presented partially and completely, in 4 sequences that varied between reached and not reached objectives and correct and incorrect movements, during 24 trials. The test t'Student was applied to verify differences in the recognition time between the groups, and to compare the performance between the tests carried through at 9:00 am and retests at 9:00 am and 4:00 pm. To compare the frequency between the types of reply, the test Qui-square was used. It was verified that the patients presented a greater recognition time and a lower number of correct answers than the healthy subjects, and had better performances in the recognition of the complete sequence than the partial one. Bigger frequency was observed in the reply that the objective and the movement were being presented correctly, however the healthy subjects had soon indicated the correct reply in the first trials. An improvement tendency was observed in the performance, when the stages of tests and retests had been carried through in the same schedule. According to the results, it is suggested that the patients with stroke can better recognize the correct movements of a functional activity when it is presented completely in video form, what can influence the choice of the therapeutical strategy during the process of motor rehabilitation

Reconhecimento de seqüências de atividades funcionais em pacientes com acidente cascular encefálico

During the motor rehabilitation of patients with neurological pathologies, there are many factors that have an influence on the therapeutical process. It is possible that the demonstration using videotapes or photographs of movements that will be learned can assist the codification, classification and reorganization of the elements of the task in familiar diagrams and thus facilitate the process of motor rehabilitation. The aim of this study was to analyze the performance in the test of recognition of sequences of functional activities such as water drinking and hair combing presented partially (by photos) and completely (by video) to the patients with encephalic vascular accident . The sample was generated from 12 patients (62 ± 8 years) and 10 healthy subjects (53 ± 5 years), of both sex, divided in two groups for which 5 functional activities were presented partially and completely, in 4 sequences that varied between reached and not reached objectives and correct and incorrect movements, during 24 trials. The test t'Student was applied to verify differences in the recognition time between the groups, and to compare the performance between the tests carried through at 9:00 am and retests at 9:00 am and 4:00 pm. To compare the frequency between the types of reply, the test Qui-square was used. It was verified that the patients presented a greater recognition time and a lower number of correct answers than the healthy subjects, and had better performances in the recognition of the complete sequence than the partial one. Bigger frequency was observed in the reply that the objective and the movement were being presented correctly, however the healthy subjects had soon indicated the correct reply in the first trials. An improvement tendency was observed in the performance, when the stages of tests and retests had been carried through in the same schedule. According to the results, it is suggested that the patients with stroke can better recognize the correct movements of a functional activity when it is presented completely in video form, what can influence the choice of the therapeutical strategy during the process of motor rehabilitation

As relações entre tectonismo e seqüências deposiconais no rifte potiguar - porção SW do Graben de Umbuzeiro, bacia potiguar emersa

Through an integrated approach, using litho, chrono and biostratigraphic data, the relative importance of climate variations and tectonics were recognized in rift sediments of the onshore Potiguar Basin, Northeast Brazil. Concepts of sequence stratigraphy were applied as a template to integrate sedimentological and geochemical data (oxygen isotopes), as well as quantitative palynologic methods to address and recognize the main depositional patterns produced in a rift basin. The main objective was to address the relative importance of climate changes and tectonics to the resultant stratigraphic architecture. The results of computer simulations of sedimentary basin fills of rift basins were quite useful to test working hypothesis and mimic the process of filling a half graben during a rift event. The studied section includes a neovalanginian-eobarremian (Lower Cretaceous) rift interval from the Pendência Formation, located in the southwestern portion of Umbuzeiro Graben, in the offshore Potiguar Basin. The depositional setting is interpreted as progradational deltaic system entering a lake from its flexural margin. Sismoestratigraphyc and well logs analyses allowed to interpret two regressive intervals (Green and Yellow Sequences), separated by a broad transgressive interval (Orange Sequence), known as the Livramento Shale. The depositional history encompass three stages: two tectonically active phases, during the deposition of the Green and Yellow Sequences, and a tectonically quiescent phase, during the deposition of the Orange Sequence. Paleoclimatic interpretation, based on quantitative palynology and geochemical data (��18O), suggests a tendency to arid conditions during the tectonically active phases and wet conditions during the tectonically quiescent phase. Stratigraphic modeling and backstripping techniques, supported by paleoclimatic/paleoecologic interpretations provide a powerful methodology to evaluate the tectonic and climatic controls on tectonic lakes

Determinantes genéticos da hanseníase em uma população do Rio Grande do Norte

Background: Leprosy can cause severe disability and disfigurement and is still a major health in different parts of the world. Only a subset of those individuals exposed to the pathogen will go on to develop clinical disease and there is a broad clinical spectrum amongst leprosy patients. The outcome of infection is in part due to host genes that influence control of the initial infection and the host´s immune response to that infection. Aim: Evaluate if polymorphisms type SNP in the 17q118q21 chromosomic region contribute to development of leprosy in Rio Grande do Norte population. Material and methods: A sample composed of 215 leprosy patients and 229 controls drawn from the same population were genotyped by using a Snapshot assay for eight genes (NOS2A, CCL18, CRLF3, CCL23, TNFAIP1, STAT5B, CCR7 and CSF3) located in chromosomic region 17q118q21. The genotype and allele frequency were measured and statistical analysis was performed by chi-square in SPSS version 15 and graph prism pad version 4 software. Results: Ours results indicated that the markers NOS2A8277, NOS2A8rs16949, CCR78rs11574663 and CSF38rs2227322 presented strong association with leprosy and their risk genotype were GG, TT, AA and GG respectively. The risk genotypes for all markers associated to leprosy presented recessive inheritance standard. When we compared the interaction among the markers in different combination we find that the marker NOS2A8277 associated with CCR78rs11574663 presented highest risk probability to development of leprosy. When we evaluated the haplotype of the risk markers it was found a haplotype associated with increase of the protection (CSF38rs22273228CC, CCR78 rs115746638GA, NOS2A8rs169498CT and NOS2A82778GA). The association of the clinical forms paucibacilary and multibacilary with markers showed that to the markers NOS2A8 2778GG, CCR78rs115746638AA and CSF38rs22273228GG there were a strong influence to migration to multibacilary pole and to marker NOS2A8rs169498TT the high proportion was found to the paucibacilary form. Conclusions: Changes in the genes NOS2A, CCR7 and CSF3 can influence the immune response against Mycobacterium leprae. The combination among these polymorphisms alters the risk probability to develop leprosy. The markers type SNP associated to development of the leprosy also are linked to clinical forms and its severity being the polymorphism NOS2A8rs169498TT associated with paucibacilar form and the polymorphisms NOS2A82778GG, CCR78rs115746638AA and CSF38rs22273228GG associated to multibacilar form

Determinação de motivos de ligação à quitina em vicilinas de Canavalia ensiformis e Vigna unguiculata através de métodos in silico e relação com suas toxicidades para o bruquídeo Callosobruchus maculatus (Coleoptera:Bruchidae)

Chitin is an important structural component of the cellular wall of fungi and exoskeleton of many invertebrate plagues, such as insects and nematodes. In digestory systems of insects it forms a named matrix of peritrophic membrane. One of the most studied interaction models protein-carbohydrate is the model that involves chitin-binding proteins. Among the involved characterized domains already in this interaction if they detach the hevein domain (HD), from of Hevea brasiliensis (Rubber tree), the R&R consensus domain (R&R), found in cuticular proteins of insects, and the motif called in this study as conglicinin motif (CD), found in the cristallography structure of the β-conglicinin bounded with GlcNac. These three chitin-binding domains had been used to determine which of them could be involved in silico in the interaction of Canavalia ensiformis and Vigna unguiculata vicilins with chitin, as well as associate these results with the WD50 of these vicilins for Callosobruchus maculatus larvae. The technique of comparative modeling was used for construction of the model 3D of the vicilin of V. unguiculata, that was not found in the data bases. Using the ClustalW program it was gotten localization of these domains in the vicilins primary structure. The domains R&R and CD had been found with bigger homology in the vicilins primary sequences and had been target of interaction studies. Through program GRAMM models of interaction ( dockings ) of the vicilins with GlcNac had been gotten. The results had shown that, through analysis in silico, HD is not part of the vicilins structures, proving the result gotten with the alignment of the primary sequences; the R&R domain, although not to have structural similarity in the vicilins, probably it has a participation in the activity of interaction of these with GlcNac; whereas the CD domain participates directly in the interaction of the vicilins with GlcNac. These results in silico show that the amino acid number, the types and the amount of binding made for the CD motif with GlcNac seem to be directly associates to the deleterious power that these vicilins show for C. maculatus larvae. This can give an initial step in the briefing of as the vicilins interact with alive chitin in and exert its toxic power for insects that possess peritrophic membrane

Metagenômica comparativa de solo de regiões de mata atlântica e caatinga do estado do Rio Grande do Norte - Brasil

The microorganisms play very important roles in maintaining ecosystems, which explains the enormous interest in understanding the relationship between these organisms as well as between them and the environment. It is estimated that the total number of prokaryotic cells on Earth is between 4 and 6 x 1030, constituting an enormous biological and genetic pool to be explored. Although currently only 1% of all this wealth can be cultivated by standard laboratory techniques, metagenomic tools allow access to the genomic potential of environmental samples in a independent culture manner, and in combination with third generation sequencing technologies, the samples coverage become even greater. Soils, in particular, are the major reservoirs of this diversity, and many important environments around us, as the Brazilian biomes Caatinga and Atlantic Forest, are poorly studied. Thus, the genetic material from environmental soil samples of Caatinga and Atlantic Forest biomes were extracted by direct techniques, pyrosequenced, and the sequences generated were analyzed by bioinformatics programs (MEGAN MG-RAST and WEBCarma). Taxonomic comparative profiles of the samples showed that the phyla Proteobacteria, Actinobacteria, Acidobacteria and Planctomycetes were the most representative. In addition, fungi of the phylum Ascomycota were identified predominantly in the soil sample from the Atlantic Forest. Metabolic profiles showed that despite the existence of environmental differences, sequences from both samples were similarly placed in the various functional subsystems, indicating no specific habitat functions. This work, a pioneer in taxonomic and metabolic comparative analysis of soil samples from Brazilian biomes, contributes to the knowledge of these complex environmental systems, so far little explored

Co-infecção pelo vírus da hepatite G em pacientes infectados pelo Leihsmania chagasi

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior

Ecogenômica de archaea e monitoramento de comunidades de procariotos redutores de sulfato: aplicações na indústria de petróleo e gás

The human activities responsible for the ambient degradation in the modern world are diverse. The industrial activities are preponderant in the question of the impact consequences for brazilian ecosystems. Amongst the human activities, the petroliferous industry in operation in Potiguar Petroliferous Basin (PPB) displays the constant risk of ambient impacts in the integrant cities, not only for the human populations and the environment, but also it reaches the native microorganisms of Caatinga ground and in the mangrove sediment. Not hindering, the elaboration of strategies of bioremediation for impacted areas pass through the knowledge of microbiota and its relations with the environment. Moreover, in the microorganism groups associated to oil, are emphasized the sulfate-reducing prokaryotes (SRP) that, in its anaerobic metabolism, these organisms participate of the sulfate reduction, discharging H2S, causing ambient risks and causing the corrosion of surfaces, as pipelines and tanks, resulting in damages for the industry. Some ancestries of PRS integrate the Archaea domain, group of microorganisms whose sequenced genomes present predominance of extremophilic adaptations, including surrounding with oil presence. This work has two correlated objectives: i) the detection and monitoring of the gene dsrB, gift in sulfate-reducing prokaryotes, through DGGE analysis in samples of mDNA of a mangrove sediment and semiarid soil, both in the BPP; ii) to relate genomic characteristics to the ecological aspects of Archaea through in silico studies, standing out the importance to the oil and gas industry. The results of the first work suggest that the petrodegraders communities of SRP persist after the contamination with oil in mangrove sediment and in semiarid soil. Comparing the populations of both sites, it reveals that there are variations in the size and composition during one year of experiments. In the second work, functional and structural factors are the probable cause to the pressure in maintenance of the conservation of the sequences in the multiple copies of the 16S rDNA gene. Is verified also the discrepancy established between total content GC and content GC of the same gene. Such results relating ribosomal genes and the ambient factors are important for metagenomic evaluations using PCR-DGGE. The knowledge of microbiota associated to the oil can contribute for a better destination of resources by the petroliferous industry and the development of bioremediation strategies. Likewise, search to lead to the best agreement of the performance of native microbiota in biogeochemical cycles in Potiguar Petroliferous Basin ecosystem

Análise do processo judicial eletrônico (PJe) sob os parâmetros da discursividade processual e do acesso democrático à justiça

The conceptions of the judicial function, the process and the factors of legitimacy of the norm of decision are changed according to the model of State (liberal, social democratic and constitutional). The right of access to justice, likewise, follows the ideals present in constitutional movements experienced in different historical moments. The deficit of legitimacy of the judiciary is recurring subject of study in the doctrine, especially in the face of democratic standards that permeate the current paradigm of state. Under the process law, the essential element for the distinction of the states based on the rule of law (formal and material) and the democratic constitutional state lies in the democratic guarantee of participation to the litigants in the process of elaborating the norm of decision. The concern about the participatory democracy and the concretion of fundamental rights has as presupposition the conception of popular sovereignty. Keeping this effort in mind, the civil procedure cannot be oblivious to such considerations, especially when it justifies its constitutional conformation from the institutionalization of discourse within the procedural field (democratic principle) and of the democratization of access to justice, leading to the necessary contestation of the theory of instrumentality of the process. The democratic prospects of civil procedure and the concern about the legitimacy of the rule of decision cannot be moved away from the analysis of the judicial function and the elements that influence the legal suit s progress. The computerization of the judicial process entails extensive modification in the way the judicial function is developed, in view of automation of activities held, of the eliminating of bureaucratic tasks, manual and repetitive, and of streamlining the procedure. The objective of this study is to analyze the dogmatic changes and resulting practices from the implementation of the Judicial Electronic Process (JEP), prepared by the National Council of Justice, under the parameters of procedural discourse and democratic access to justice. Two hypotheses are raised, which, based on a bibliographic-documentary, applied and exploratory research, are contested dialectically. The expansion of publicity of procedural acts and the facilitating of communication and practice of such acts are elements that contribute to the effective participation of the recipients of the norm of decision in its making process and, therefore, the democratic principle in the procedural field. Ensuring access (to the parts) to the case files and reasonable duration of the process along with the preservation of its founding principles (contradictory, legal defense and isonomy) are essential to ensure democratic access to justice within the virtual system

Contribuição à citogenética de testudines e análise de assimetria flutuante em Eretmochelys imbricata, Cheloniidae

This work has contributed to knowledge of the order Testudines from cytogenetic and morphological point of view. With regard to the aspects proposed cytogenetic characterization of the species Mesoclemmys tuberculata (n = 5), endemic to the Caatinga biomes, through conventional techniques of cytogenetics and molecular levels. This species presented 2n = 58, NF = 64, the first submetacentric pair, the second metacentric and third subtelocentric, and the other microchromosome telocentric. This species showed a nucleolar bearing pair, coincident with the 18S ribosomal rDNA and that proved to be heterochromatic. Small heterochromatic blocks were also found in the centromeres of the largest chromosomes, as well as terminal regions in most other chromosomes of the complement, that were GC +. Telomeric sequences showed variable patterns of signal intensity, with some repeats more intense in microchromosomes and subtly in the larger ones. When compared with other species of the genus, the G-banding patterns showed a marked similarity between them. The first karyotypic description of the species will aid in future studies and the understanding of evolutionary aspects of this family. From the morphological point of view, we carried out studies of fluctuating asymmetry in sea turtle Eretmochelys imbricata, using methods of benchmarking between hatchlings and adults and their implications for natural selection. Data were collected at two different times: first during the spawning female and the second during the outbreak and birth of the nest. The analyzed characteristics consisted of measurements of length and width of front and rear flippers (CANT, LANT, CPOS and LPOS) also collected data on the number of hull plates, side plates (NPL), the surrounding plates (NPCIRC), and plastron; plates power plants (NPP), inframarginais plates (NPIM). With the values of asymmetry we calculated the value of strict heritability for these traits, the calculation was based on only one parent. A nonparametric analysis Mann-Whitneywas performed to compare the groups (females X hatchlings, newborn hatchlings X dead hatchlings). Adult females showed no bilateral fluctuating asymmetry (FA = 0) on the number plates of the hull and plastron, while offspring, living and dead, showed a greater level of variation in these meristic parameters. In the analysis of females x hatchlings we found a significant difference between the levels of asymmetry in hoof plates (p=0.006) an the width of hindlimbs (p=0.001). Levels of FA suggest an accurate indicator as to the viability or maintenance of the individual to the reproductive phase. The coefficient of heritability (h2) of FA , obtained from the regression analysis, showed that both have low and not statistically significant values(p> 0.1). In the case of exclusion of the effective role of genetics in the generation of FA, reproductive strategies based on high number of subsidiaries products, such as those observed in E. imbricata seems to implicate the production of individuals with high level of developmental instability

Alfabetizar crianças na escola pública: fazeres docentes em discussão

The most recent data of the Brazilian Test (BRAZIL, 2005) and of the SAEB (BRAZIL, 2007) have reaffirmed the serious situation of the Brazilian public school, where great part of the students, after to conclude 4º year of basic education, does not present minimum knowledge of reading and writing. In this picture, the situation of the state of Rio Grande do Norte, whose students had presented, in the last evaluation is particularly difficult, the worse performances of the country, in this area. The data also discloses that the failure pertaining to school, closely tied with the failure in the literacy, not only remains, as takes other aspects. In consequence of this picture, the literacy, even so widely argued in the last few decades, still instigates inquiries, as it is the case of this work. Our study got shaped due to reflections, as much to the theorizations to which we had access, as of the emergent questions of ours pedagogical practice. Through the past three decades, the studies in the area of literacy with the purpose to understand the constituent nature of the process, its aspects and its determinative ones has been intensified. The produced knowledge has contributed for the overcoming of the reductionist form as if it thought/thinks, in some contexts - this process. Such statements impel them to reflect concerning what is happening in the school, limiting or making possible the pertaining to school success. With these concerns, we delimit, as focus of study, the teaching action, having the following stunning question: What to make professors, in the context of the public school, to propitiate or hinder the process of literacy of the children? In this direction, our object of study is to make them professors who can propitiate or hinder the process of literacy of the children, in the context of the public school. The objective work to investigate, from practical of professors the teachers, that to make professors related to the literacy process - they can propitiate or hinder the learning of the written language, for the pupils of the public school, at the beginning of the school process. The work if inscribes in the qualitative boarding of research and if it configures as a case study, with characteristics of Research-Action, inspired by the following principles: authenticity and commitment and systematic restitution. For the retraction of the data, they had been used: half-structuralized interview; participant comment; meeting of studies and reflection; register in daily of field. We define as locus of study, a school of public net and, more specifically, a group of the initial years of school process that integrates the cycle of literacy . Of the five invited teachers, only one demonstrated interest in participating of the work. Its group of first year of the First Cycle of basic education is composed for 34 children, with ages between six the nine years. The data constructed by means of the described procedures, as well as its analysis, make possible to identify, between the many aspects and to make that they compose the pedagogical dynamics in the context of classroom, the following categories to make articulated with the literacy process: 1. To make of practical the relative ones to the planning, understood as To make relative: 1,1 distribution of the time-space/routine; 1.2 to the didactic activities and/or sequences and teaching interventions; 1.3 to the organization/election of the contents; 1.4 to the materials/didactic resources and 1.5 to the evaluation. 2. To make relative to the interaction professor-pupil, systemize in: 2.1 attention to the diversity; 2.2 to the affectivity. These to make, in the form as if materialized in the practical one observed, had been reflected, jointly with the teacher, as constituting parts of obstacles to a perspective of literacy. By means of the sharing of the reflections, anchored in theoretical conceptions concerning the practical one of teach-learning and, more specifically, of literacy, we register indications of new meanings of these to make on the part of the teacher in conducting them as providers of learning of its pupils, first purpose of its teaching performance. This finishing, possible synthesis at this moment is, therefore, point of fond and departure for new studies

Trabalho e formação docente na rede municipal de ensino de natal

The study Teacher work and education in the municipal schools of Natal objectifies the analysis of the education and work conditions of the teachers in the municipal schools of Natal, placing them within the scenario of the public policies outlined for Basic Education (2005-2010). The thesis is based on the perspective that the educational reforms implemented by the Brazilian government in an attempt to answer to the new contextual demands originated from the world of work and globalization, demanding increasingly higher levels of qualification and constant extension of the teaching functions in school from the teachers, have been configured withal as a strategy for intensifying the teacher s work. The empirical field of study was constituded by thirteen municipal schools that offer basic education. Four hundred and seventeen teacher subjects that work in the municipal school system of Natal, two representatives of the Secretaria Municipal de Educação de Natal (SME)1 that work in the pedagogical team and one representative of the Sindicato dos Trabalhadores em Educação do Rio Grande do Norte2 took part in the study. The procedures/instruments used in the research were: bibliographic review, document research, questionnaires and recording of information in a field journal. The study confirmed that the majority of the teachers that work in the municipal school system were admitted by means of public entry exams, therefore meeting the requirements set by Law 9.394/96. Most of the teachers have the initial education demanded to work in basic education, although with some limitations due to the fact that they do not correspond to the needs of the educational system. The SME has a plan for continued training of the teachers in accordance to the current ideas defended by researchers of this field. There is, although, a disconnection between the purpose of the plan and the training strategies, because, in truth, predominate repetitive and specific actions that do not contemplate the training needs of the teachers, nor the demands of the system. Although the work conditions are evaluated, by the teachers, as relatively good, limits in relation to the physical structure of the schools are observed (dirty walls with holes in them, broken ceiling fans, old chairs and desks, old and stained black boards, inadequate restroom installations, poor maintenance of the computers, amongst other items). It was also verified the an increase in the functions of the teachers and an intensification of their work, materialized through an overburden of activities undertaken daily at school (and outside of it) and through the demand in taking part in activities that go beyond those inherent to the teaching process, such as the elaboration of political-pedagogical projects, participation in collegiate, registration of student information solicited by the SME and the participation in commissions, has been happening

Enumeração de espectro de distâncias de esquemas de modulação codificada em treliça empregando codificação turbo

In this work, a performance analysis of transmission schemes employing turbo trellis coded modulation. In general, the performance analysis of such schemes is guided by evaluating the error probability of these schemes. The exact evaluation of this probability is very complex and inefficient from the computational point of view, a widely used alternative is the use of union bound of error probability, because of its easy implementation and computational produce bounds that converge quickly. Since it is the union bound, it should use to expurge some elements of distance spectrum to obtain a tight bound. The main contribution of this work is that the listing proposal is carried out from the puncturing at the level of symbol rather than bit-level as in most works of literature. The main reason for using the symbol level puncturing lies in the fact that the enummerating function of the turbo scheme is obtained directly from complex sequences of signals through the trellis and not indirectly from the binary sequences that require further binary to complex mapping, as proposed by previous works. Thus, algorithms can be applied through matrix from the adjacency matrix, which is obtained by calculating the distances of the complex sequences of the trellis. This work also presents two matrix algorithms for state reduction and the evaluation of the transfer function of this. The results presented in comparisons of the bounds obtained using the proposed technique with some turbo codes of the literature corroborate the proposition of this paper that the expurgated bounds obtained are quite tight and matrix algorithms are easily implemented in any programming software language

Predição de promotores de Bacillus subtilis usando técnicas de aprendizado de máquina

One of the most important goals of bioinformatics is the ability to identify genes in uncharacterized DNA sequences on world wide database. Gene expression on prokaryotes initiates when the RNA-polymerase enzyme interacts with DNA regions called promoters. In these regions are located the main regulatory elements of the transcription process. Despite the improvement of in vitro techniques for molecular biology analysis, characterizing and identifying a great number of promoters on a genome is a complex task. Nevertheless, the main drawback is the absence of a large set of promoters to identify conserved patterns among the species. Hence, a in silico method to predict them on any species is a challenge. Improved promoter prediction methods can be one step towards developing more reliable ab initio gene prediction methods. In this work, we present an empirical comparison of Machine Learning (ML) techniques such as Na¨ýve Bayes, Decision Trees, Support Vector Machines and Neural Networks, Voted Perceptron, PART, k-NN and and ensemble approaches (Bagging and Boosting) to the task of predicting Bacillus subtilis. In order to do so, we first built two data set of promoter and nonpromoter sequences for B. subtilis and a hybrid one. In order to evaluate of ML methods a cross-validation procedure is applied. Good results were obtained with methods of ML like SVM and Naïve Bayes using B. subtilis. However, we have not reached good results on hybrid database

Aplicação de técnicas de aprendizado de máquina no reconhecimento de classes estruturais de proteínas

Nowadays, classifying proteins in structural classes, which concerns the inference of patterns in their 3D conformation, is one of the most important open problems in Molecular Biology. The main reason for this is that the function of a protein is intrinsically related to its spatial conformation. However, such conformations are very difficult to be obtained experimentally in laboratory. Thus, this problem has drawn the attention of many researchers in Bioinformatics. Considering the great difference between the number of protein sequences already known and the number of three-dimensional structures determined experimentally, the demand of automated techniques for structural classification of proteins is very high. In this context, computational tools, especially Machine Learning (ML) techniques, have become essential to deal with this problem. In this work, ML techniques are used in the recognition of protein structural classes: Decision Trees, k-Nearest Neighbor, Naive Bayes, Support Vector Machine and Neural Networks. These methods have been chosen because they represent different paradigms of learning and have been widely used in the Bioinfornmatics literature. Aiming to obtain an improvment in the performance of these techniques (individual classifiers), homogeneous (Bagging and Boosting) and heterogeneous (Voting, Stacking and StackingC) multiclassification systems are used. Moreover, since the protein database used in this work presents the problem of imbalanced classes, artificial techniques for class balance (Undersampling Random, Tomek Links, CNN, NCL and OSS) are used to minimize such a problem. In order to evaluate the ML methods, a cross-validation procedure is applied, where the accuracy of the classifiers is measured using the mean of classification error rate, on independent test sets. These means are compared, two by two, by the hypothesis test aiming to evaluate if there is, statistically, a significant difference between them. With respect to the results obtained with the individual classifiers, Support Vector Machine presented the best accuracy. In terms of the multi-classification systems (homogeneous and heterogeneous), they showed, in general, a superior or similar performance when compared to the one achieved by the individual classifiers used - especially Boosting with Decision Tree and the StackingC with Linear Regression as meta classifier. The Voting method, despite of its simplicity, has shown to be adequate for solving the problem presented in this work. The techniques for class balance, on the other hand, have not produced a significant improvement in the global classification error. Nevertheless, the use of such techniques did improve the classification error for the minority class. In this context, the NCL technique has shown to be more appropriated