Machine Learning Algorithms at Myocardial Perfusion Imaging - a Preliminary Study

Introduction: A major focus of data mining process - especially machine learning researches - is to automatically learn to recognize complex patterns and help to take the adequate decisions strictly based on the acquired data. Since imaging techniques like MPI – Myocardial Perfusion Imaging on Nuclear Cardiology, can implicate a huge part of the daily workflow and generate gigabytes of data, there could be advantages on Computerized Analysis of data over Human Analysis: shorter time, homogeneity and consistency, automatic recording of analysis results, relatively inexpensive, etc.Objectives: The aim of this study relates with the evaluation of the efficacy of this methodology on the evaluation of MPI Stress studies and the process of decision taking concerning the continuation – or not – of the evaluation of each patient. It has been pursued has an objective to automatically classify a patient test in one of three groups: “Positive”, “Negative” and “Indeterminate”. “Positive” would directly follow to the Rest test part of the exam, the “Negative” would be directly exempted from continuation and only the “Indeterminate” group would deserve the clinician analysis, so allowing economy of clinician’s effort, increasing workflow fluidity at the technologist’s level and probably sparing time to patients. Methods: WEKA v3.6.2 open source software was used to make a comparative analysis of three WEKA algorithms (“OneR”, “J48” and “Naïve Bayes”) - on a retrospective study using the comparison with correspondent clinical results as reference, signed by nuclear cardiologist experts - on “SPECT Heart Dataset”, available on University of California – Irvine, at the Machine Learning Repository. For evaluation purposes, criteria as “Precision”, “Incorrectly Classified Instances” and “Receiver Operating Characteristics (ROC) Areas” were considered. Results: The interpretation of the data suggests that the Naïve Bayes algorithm has the best performance among the three previously selected algorithms. Conclusions: It is believed - and apparently supported by the findings - that machine learning algorithms could significantly assist, at an intermediary level, on the analysis of scintigraphic data obtained on MPI, namely after Stress acquisition, so eventually increasing efficiency of the entire system and potentially easing both roles of Technologists and Nuclear Cardiologists. In the actual continuation of this study, it is planned to use more patient information and significantly increase the population under study, in order to allow improving system accuracy.

Besnoitia besnoiti protein disulfide isomerase (BbPDI): molecular characterization, expression and in silico modelling

Besnoitia besnoiti is an apicomplexan parasite responsible for bovine besnoitiosis, a disease with a high prevalence in tropical and subtropical regions and re-emerging in Europe. Despite the great economical losses associated with besnoitiosis, this disease has been underestimated and poorly studied, and neither an effective therapy nor an efficacious vaccine is available. Protein disulfide isomerase (PDI) is an essential enzyme for the acquisition of the correct three-dimensional structure of proteins. Current evidence suggests that in Neosporacaninum and Toxoplasmagondii, which are closely related to B. besnoiti, PDI play an important role in host cell invasion, is a relevant target for the host immune response, and represents a promising drug target and/or vaccine candidate. In this work, we present the nucleotide sequence of the B. besnoiti PDI gene. BbPDI belongs to the thioredoxin-like superfamily (cluster 00388) and is included in the PDI_a family (cluster defined cd02961) and the PDI_a_PDI_a'_c subfamily (cd02995). A 3D theoretical model was built by comparative homology using Swiss-Model server, using as a template the crystallographic deduced model of Tapasin-ERp57 (PDB code 3F8U chain C). Analysis of the phylogenetic tree for PDI within the phylum apicomplexa reinforces the close relationship among B. besnoiti, N. caninum and T. gondii. When subjected to a PDI-assay based on the polymerisation of reduced insulin, recombinant BbPDI expressed in E. coli exhibited enzymatic activity, which was inhibited by bacitracin. Antiserum directed against recombinant BbPDI reacted with PDI in Western blots and by immunofluorescence with B. besnoiti tachyzoites and bradyzoites.

Analysis of a 17.9 kb region from Saccharomyces cerevisiae chromosome VII reveals the presence of eight open reading frames, including BRF1 (TFIIIB70) and GCN5 genes

We report the nucleotide sequence of a 17,893 bp DNA segment from the right arm of Saccharomyces cerevisiae chromosome VII. This fragment begins at 482 kb from the centromere. The sequence includes the BRF1 gene, encoding TFIIIB70, the 5' portion of the GCN5 gene, an open reading frame (ORF) previously identified as ORF MGA1, whose translation product shows similarity to heat-shock transcription factors and five new ORFs. Among these, YGR250 encodes a polypeptide that harbours a domain present in several polyA binding proteins. YGR245 is similar to a putative Schizosaccharomyces pombe gene, YGR248 shows significant similarity with three ORFs of S. cerevisiae situated on different chromosomes, while the remaining two ORFs, YGR247 and YGR251, do not show significant similarity to sequences present in databases.

Sequencing of a 9.9 kb segment on the right arm of yeast chromosome VII reveals four open reading frames, including PFK1, the gene coding for succinyl-CoA synthetase (beta-chain) and two ORFs sharing homology with ORFs of the yeast chromosome VIII

A 9.9 kb DNA fragment from the right arm of chromosome VII of Saccharomyces cerevisiae has been sequenced and analysed. The sequence contains four open reading frames (ORFs) longer than 100 amino acids. One gene, PFK1, has already been cloned and sequenced and the other one is the probable yeast gene coding for the beta-subunit of the succinyl-CoA synthetase. The two remaining ORFs share homology with the deduced amino acid sequence (and their physical arrangement is similar to that) of the YHR161c and YHR162w ORFs from chromosome VIII.

Characterization of a polyubiquitin gene in T. thermophila and of ubiquitin gene expression during sexual reproduction and under stress conditions

A 5-unit polyubiquitin gene, TTU3, was isolated from a T. thermophila genomic library and sequenced. This gene presents an extra triplet coding for Phe, a AGAGA motif and a putative HSE element in its 5'-non-coding region. The ubiquitin gene expression in this ciliate was investigated by Northern blot hybridization in conjugating cells or cells under stress conditions. Exponentially growing cells express two ubiquitin mRNAs of 0.75 and 1.8 kb and a new species of 1.4 kb is induced under hyperthermic stress. During sexual reproduction of the cells (conjugation) the 1.8-kb mRNA is still transcribed whereas the steady-state population of the 0.75 mRNA transcripts is strongly diminished. Southern blot analysis suggests that ubiquitin in T. thermophila constitutes a large family of about ten members.

Sequencing of a 17.6 kb segment on the right arm of yeast chromosome VII reveals 12 ORFs, including CCT, ADE3 and TR-I genes, homologues of the yeast PMT and EF1G genes, of the human and bacterial electron-transferring flavoproteins (beta-chain) and of the Escherichia coli phosphoserine phosphohydrolase, and five new ORFs.

A 17.6 kb DNA fragment from the right arm of chromosome VII of Saccharomyces cerevisiae has been sequenced and analysed. The sequence contains twelve open reading frames (ORFs) longer than 100 amino acids. Three genes had already been cloned and sequenced: CCT, ADE3 and TR-I. Two ORFs are similar to other yeast genes: G7722 with the YAL023 (PMT2) and PMT1 genes, encoding two integral membrane proteins, and G7727 with the first half of the genes encoding elongation factors 1gamma, TEF3 and TEF4. Two other ORFs, G7742 and G7744, are most probably yeast orthologues of the human and Paracoccus denitrificans electron-transferring flavoproteins (beta chain) and of the Escherichia coli phosphoserine phosphohydrolase. The five remaining identified ORFs do not show detectable homology with other protein sequences deposited in data banks. The sequence has been deposited in the EMBL data library under Accession Number Z49133.

Clusters of 5S rRNAs in the intergenic region of ubiquitin genes in Tetrahymena pyriformis

Here, we report the molecular analysis of two independent 5S rRNA clusters found in the intergenic region of two ubiquitin genomic clones isolated from Tetrahymena pyriformis. Each cluster contains two 120-bp-long coding regions organized in tandem with 142/145-bp-long spacers.

The Tetrahymena chaperonin subunit CCT eta gene is coexpressed with CCT gamma gene during cilia biogenesis and cell sexual reproduction

We report here the cloning and the characterization of the T. pyriformis CCT eta gene (TpCCT eta) and also a partial sequence of the corresponding T. thermophila gene (TtCCT eta). The TpCCt eta gene encodes a protein sharing a 60.3% identity with the mouse CCT eta. We have studied the expression of these genes in Tetrahymena exponentially growing cells, cells regenerating their cilia for different periods and during different stages of the cell sexual reproduction. These genes have similar patterns of expression to those of the previously identified TpCCt gamma gene. Indeed, the Tetrahymena CCT eta and CCT gamma genes are up-regulated at 60-120 min of cilia recovery, and in conjugation when vegetative growth was resumed and cell division took place. Our results seem to indicate that both CCT subunits play an important role in the biogenesis of the newly synthesized cilia of Tetrahymena and during its cell division.

Análise de eficiência energética de transportes rodoviários

Projecto para obtenção do grau de Mestre em Engenharia Informática e de computadores

Clustering of variables with a three-way approach for health sciences

TPM Vol. 21, No. 4, December 2014, 435-447 – Special Issue © 2014 Cises.

Descoberta de conhecimento em Logs de tentativas de intrusão. Um estudo de caso em Instituições de Ensino Superior

Perante a evolução constante da Internet, a sua utilização é quase obrigatória. Através da web, é possível conferir extractos bancários, fazer compras em países longínquos, pagar serviços sem sair de casa, entre muitos outros. Há inúmeras alternativas de utilização desta rede. Ao se tornar tão útil e próxima das pessoas, estas começaram também a ganhar mais conhecimentos informáticos. Na Internet, estão também publicados vários guias para intrusão ilícita em sistemas, assim como manuais para outras práticas criminosas. Este tipo de informação, aliado à crescente capacidade informática do utilizador, teve como resultado uma alteração nos paradigmas de segurança informática actual. Actualmente, em segurança informática a preocupação com o hardware é menor, sendo o principal objectivo a salvaguarda dos dados e continuidade dos serviços. Isto deve-se fundamentalmente à dependência das organizações nos seus dados digitais e, cada vez mais, dos serviços que disponibilizam online. Dada a mudança dos perigos e do que se pretende proteger, também os mecanismos de segurança devem ser alterados. Torna-se necessário conhecer o atacante, podendo prever o que o motiva e o que pretende atacar. Neste contexto, propôs-se a implementação de sistemas de registo de tentativas de acesso ilícitas em cinco instituições de ensino superior e posterior análise da informação recolhida com auxílio de técnicas de data mining (mineração de dados). Esta solução é pouco utilizada com este intuito em investigação, pelo que foi necessário procurar analogias com outras áreas de aplicação para recolher documentação relevante para a sua implementação. A solução resultante revelou-se eficaz, tendo levado ao desenvolvimento de uma aplicação de fusão de logs das aplicações Honeyd e Snort (responsável também pelo seu tratamento, preparação e disponibilização num ficheiro Comma Separated Values (CSV), acrescentando conhecimento sobre o que se pode obter estatisticamente e revelando características úteis e previamente desconhecidas dos atacantes. Este conhecimento pode ser utilizado por um administrador de sistemas para melhorar o desempenho dos seus mecanismos de segurança, tais como firewalls e Intrusion Detection Systems (IDS).

Extracção de regras de associação com itens raros e frequentes

Ao longo dos últimos anos, as regras de associação têm assumido um papel relevante na extracção de informação e de conhecimento em base de dados e vêm com isso auxiliar o processo de tomada de decisão. A maioria dos trabalhos de investigação desenvolvidos sobre regras de associação têm por base o modelo de suporte e confiança. Este modelo permite obter regras de associação que envolvem particularmente conjuntos de itens frequentes. Contudo, nos últimos anos, tem-se explorado conjuntos de itens que surgem com menor frequência, designados de regras de associação raras ou infrequentes. Muitas das regras com base nestes itens têm particular interesse para o utilizador. Actualmente a investigação sobre regras de associação procuram incidir na geração do maior número possível de regras com interesse aglomerando itens raros e frequentes. Assim, este estudo foca, inicialmente, uma pesquisa sobre os principais algoritmos de data mining que abordam as regras de associação. A finalidade deste trabalho é examinar as técnicas e algoritmos de extracção de regras de associação já existentes, verificar as principais vantagens e desvantagens dos algoritmos na extracção de regras de associação e, por fim, desenvolver um algoritmo cujo objectivo é gerar regras de associação que envolvem itens raros e frequentes.

Sistemas de informação para executivos (EIS). Uma experiência de aplicação

Tese submetida à Universidade Portucalense para obtenção do grau de Mestre em Informática, elaborada sob a orientação de Prof. Doutor Reis Lima e Eng. Jorge S. Coelho.

Knowledge discovery from trajectories

Dissertation submitted in partial fulfilment of the requirements for the Degree of Master of Science in Geospatial Technologies

Digital disease detection and participatory surveillance: overview and perspectives for Brazil

ABSTRACT This study aimed to describe the digital disease detection and participatory surveillance in different countries. The systems or platforms consolidated in the scientific field were analyzed by describing the strategy, type of data source, main objectives, and manner of interaction with users. Eleven systems or platforms, developed from 1996 to 2016, were analyzed. There was a higher frequency of data mining on the web and active crowdsourcing as well as a trend in the use of mobile applications. It is important to provoke debate in the academia and health services for the evolution of methods and insights into participatory surveillance in the digital age.