Artificial neural networks in diagnosis of liver diseases

Liver diseases have severe patients’ consequences, being one of the main causes of premature death. These facts reveal the centrality of one`s daily habits, and how important it is the early diagnosis of these kind of illnesses, not only to the patients themselves, but also to the society in general. Therefore, this work will focus on the development of a diagnosis support system to these kind of maladies, built under a formal framework based on Logic Programming, in terms of its knowledge representation and reasoning procedures, complemented with an approach to computing grounded on Artificial Neural Networks.

Logic programming and artificial neural networks in breast cancer detection

About 90% of breast cancers do not cause or are capable of producing death if detected at an early stage and treated properly. Indeed, it is still not known a specific cause for the illness. It may be not only a beginning, but also a set of associations that will determine the onset of the disease. Undeniably, there are some factors that seem to be associated with the boosted risk of the malady. Pondering the present study, different breast cancer risk assessment models where considered. It is our intention to develop a hybrid decision support system under a formal framework based on Logic Programming for knowledge representation and reasoning, complemented with an approach to computing centered on Artificial Neural Networks, to evaluate the risk of developing breast cancer and the respective Degree-of-Confidence that one has on such a happening.

Molecular regulation of flowering induction in Quercus suber

Dissertação de mestrado em Plant Molecular Biology, Biotechnology and Bioentrepeneurship

Automatic eye blink detection using consumer web cameras

This research aims to advance blinking detection in the context of work activity. Rather than patients having to attend a clinic, blinking videos can be acquired in a work environment, and further automatically analyzed. Therefore, this paper presents a methodology to perform the automatic detection of eye blink using consumer videos acquired with low-cost web cameras. This methodology includes the detection of the face and eyes of the recorded person, and then it analyzes the low-level features of the eye region to create a quantitative vector. Finally, this vector is classified into one of the two categories considered —open and closed eyes— by using machine learning algorithms. The effectiveness of the proposed methodology was demonstrated since it provides unbiased results with classification errors under 5%

Modelling and verifying smell-free architectures with the Archery language

Architectural (bad) smells are design decisions found in software architectures that degrade the ability of systems to evolve. This paper presents an approach to verify that a software architecture is smellfree using the Archery architectural description language. The language provides a core for modelling software architectures and an extension for specifying constraints. The approach consists in precisely specifying architectural smells as constraints, and then verifying that software architectures do not satisfy any of them. The constraint language is based on a propositional modal logic with recursion that includes: a converse operator for relations among architectural concepts, graded modalities for describing the cardinality in such relations, and nominals referencing architectural elements. Four architectural smells illustrate the approach.

Automatic distinction of Fernando Pessoas’ heteronyms

Text Mining has opened a vast array of possibilities concerning automatic information retrieval from large amounts of text documents. A variety of themes and types of documents can be easily analyzed. More complex features such as those used in Forensic Linguistics can gather deeper understanding from the documents, making possible performing di cult tasks such as author identi cation. In this work we explore the capabilities of simpler Text Mining approaches to author identification of unstructured documents, in particular the ability to distinguish poetic works from two of Fernando Pessoas' heteronyms: Alvaro de Campos and Ricardo Reis. Several processing options were tested and accuracies of 97% were reached, which encourage further developments.

Concise server-wide causality management for eventually consistent data stores

Large scale distributed data stores rely on optimistic replication to scale and remain highly available in the face of net work partitions. Managing data without coordination results in eventually consistent data stores that allow for concurrent data updates. These systems often use anti-entropy mechanisms (like Merkle Trees) to detect and repair divergent data versions across nodes. However, in practice hash-based data structures are too expensive for large amounts of data and create too many false conflicts. Another aspect of eventual consistency is detecting write conflicts. Logical clocks are often used to track data causality, necessary to detect causally concurrent writes on the same key. However, there is a nonnegligible metadata overhead per key, which also keeps growing with time, proportional with the node churn rate. Another challenge is deleting keys while respecting causality: while the values can be deleted, perkey metadata cannot be permanently removed without coordination. Weintroduceanewcausalitymanagementframeworkforeventuallyconsistentdatastores,thatleveragesnodelogicalclocks(BitmappedVersion Vectors) and a new key logical clock (Dotted Causal Container) to provides advantages on multiple fronts: 1) a new efficient and lightweight anti-entropy mechanism; 2) greatly reduced per-key causality metadata size; 3) accurate key deletes without permanent metadata.

Immersiveness of ubiquitous computing environments prototypes: A case study

The development of ubiquitous computing (ubicomp) environments raises several challenges in terms of their evaluation. Ubicomp virtual reality prototyping tools enable users to experience the system to be developed and are of great help to face those challenges, as they support developers in assessing the consequences of a design decision in the early phases of development. Given the situated nature of ubicomp environments, a particular issue to consider is the level of realism provided by the prototypes. This work presents a case study where two ubicomp prototypes, featuring different levels of immersion (desktop-based versus CAVE-based), were developed and compared. The goal was to determine the cost/benefits relation of both solutions, which provided better user experience results, and whether or not simpler solutions provide the same user experience results as more elaborate one.

Exploring scenario exploration

Model finders are very popular for exploring scenarios, helping users validate specifications by navigating through conforming model instances. To be practical, the semantics of such scenario exploration operations should be formally defined and, ideally, controlled by the users, so that they are able to quickly reach interesting scenarios. This paper explores the landscape of scenario exploration operations, by formalizing them with a relational model finder. Several scenario exploration operations provided by existing tools are formalized, and new ones are proposed, namely to allow the user to easily explore very similar (or different) scenarios, by attaching preferences to model elements. As a proof-of-concept, such operations were implemented in the popular Alloy Analyzer, further increasing its usefulness for (user-guided) scenario exploration.

Monitoring for a decidable fragment of MTL-∫

Temporal logics targeting real-time systems are traditionally undecidable. Based on a restricted fragment of MTL-R, we propose a new approach for the runtime verification of hard real-time systems. The novelty of our technique is that it is based on incremental evaluation, allowing us to e↵ectively treat duration properties (which play a crucial role in real-time systems). We describe the two levels of operation of our approach: offline simplification by quantifier removal techniques; and online evaluation of a three-valued interpretation for formulas of our fragment. Our experiments show the applicability of this mechanism as well as the validity of the provided complexity results.

Metaphorisms in programming

This paper introduces the metaphorism pattern of relational specification and addresses how specification following this pattern can be refined into recursive programs. Metaphorisms express input-output relationships which preserve relevant information while at the same time some intended optimization takes place. Text processing, sorting, representation changers, etc., are examples of metaphorisms. The kind of metaphorism refinement proposed in this paper is a strategy known as change of virtual data structure. It gives sufficient conditions for such implementations to be calculated using relation algebra and illustrates the strategy with the derivation of quicksort as example.

New bio-strategies for ochratoxin A detoxification using lactic acid bacteria

The occurrence of mycotoxigenic moulds such as Aspergillus, Penicillium and Fusarium in food and feed has an important impact on public health, by the appearance of acute and chronic mycotoxicoses in humans and animals, which is more severe in the developing countries due to lack of food security, poverty and malnutrition. This mould contamination also constitutes a major economic problem due the lost of crop production. A great variety of filamentous fungi is able to produce highly toxic secondary metabolites known as mycotoxins. Most of the mycotoxins are carcinogenic, mutagenic, neurotoxic and immunosuppressive, being ochratoxin A (OTA) one of the most important. OTA is toxic to animals and humans, mainly due to its nephrotoxic properties. Several approaches have been developed for decontamination of mycotoxins in foods, such as, prevention of contamination, biodegradation of mycotoxins-containing food and feed with microorganisms or enzymes and inhibition or absorption of mycotoxin content of consumed food into the digestive tract. Some group of Gram-positive bacteria named lactic acid bacteria (LAB) are able to release some molecules that can influence the mould growth, improving the shelf life of many fermented products and reducing health risks due to exposure to mycotoxins. Some LAB are capable of mycotoxin detoxification. Recently our group was the first to describe the ability of LAB strains to biodegrade OTA, more specifically, Pediococcus parvulus strains isolated from Douro wines. The pathway of this biodegradation was identified previously in other microorganisms. OTA can be degraded through the hydrolysis of the amide bond that links the L-β-phenylalanine molecule to the ochratoxin alpha (OTα) a non toxic compound. It is known that some peptidases from different origins can mediate the hydrolysis reaction like, carboxypeptidase A an enzyme from the bovine pancreas, a commercial lipase and several commercial proteases. So, we wanted to have a better understanding of this OTA degradation process when LAB are involved and identify which molecules where present in this process. For achieving our aim we used some bioinformatics tools (BLAST, CLUSTALX2, CLC Sequence Viewer 7, Finch TV). We also designed specific primers and realized gene specific PCR. The template DNA used came from LAB strains samples of our previous work, and other DNA LAB strains isolated from elderberry fruit, silage, milk and sausages. Through the employment of bioinformatics tools it was possible to identify several proteins belonging to the carboxypeptidase family that participate in the process of OTA degradation, such as serine type D-Ala-D-Ala carboxypeptidase and membrane carboxypeptidase. In conclusions, this work has identified carboxypeptidase proteins being one of the molecules present in the OTA degradation process when LAB are involved.

Novas bio-estratégias para a destoxificação de ocratoxina A utilizando bactérias do ácido láctico

A ocorrência de bolores micotoxigénicos pertencentes aos géneros Aspergillus, Penicillium e Fusarium em alimentos para consumo Humano e animal, tem um impacto importante sobre a saúde pública e constitui também um importante problema económico. Isto é devido à síntese por este tipo de fungos filamentosos de metabolitos altamente tóxicos conhecidos como micotoxinas. A maioria das micotoxinas são substâncias cancerígenas, mutagénicas, neurotóxicas e imunossupressoras, sendo a ocratoxina A (OTA) uma das mais importantes. A OTA é uma micotoxina, tóxica para os animais e Humanos principalmente devido às suas propriedades nefrotóxicas. Alguns grupos de bactérias gram positivas nomeadamente as bactérias do ácido láctico (BAL) são capazes de controlar o crescimento de fungos, melhorando e aumentando a vida útil de muitos produtos fermentados e, assim, reduzir os riscos para a saúde provocados pela exposição às micotoxinas. Algumas BAL são, também, capazes de destoxificar certas micotoxinas. Em trabalhos anteriores do nosso grupo foi observada a biodegradação da OTA por estirpes de Pediococcus parvulus isoladas de vinhos do Douro. Assim, com este trabalho, pretendeu-se compreender com maior detalhe o processo de biodegradação da OTA pelas referidas estirpes e identificar quais as enzimas que estão associadas à sua biodegradação. Para atingir este objetivo utilizaram-se algumas ferramentas ioinformáticas (BLAST, CLUSTALX2, CLC Sequence Viewer 7, Finch TV), desenharam-se primers específicos e realizaram-se PCR específicos para os genes envolvidos. Através da utilização de ferramentas de bioinformática, foi possível identificar várias proteínas que pertencem à família das carboxipeptidases e que podem eventualmente participar no processo da degradação da OTA, tais como D-Ala-D-Ala carboxipeptidase serínica e carboxipeptidase membranar. Estas BAL podem desempenhar um papel importante na destoxificação da OTA, sendo as carboxipeptidases uma das enzimas envolvidas na sua biodegradação.

A critical evaluation of methods for the reconstruction of tissue-specific models

Under the framework of constraint based modeling, genome-scale metabolic models (GSMMs) have been used for several tasks, such as metabolic engineering and phenotype prediction. More recently, their application in health related research has spanned drug discovery, biomarker identification and host-pathogen interactions, targeting diseases such as cancer, Alzheimer, obesity or diabetes. In the last years, the development of novel techniques for genome sequencing and other high-throughput methods, together with advances in Bioinformatics, allowed the reconstruction of GSMMs for human cells. Considering the diversity of cell types and tissues present in the human body, it is imperative to develop tissue-specific metabolic models. Methods to automatically generate these models, based on generic human metabolic models and a plethora of omics data, have been proposed. However, their results have not yet been adequately and critically evaluated and compared. This work presents a survey of the most important tissue or cell type specific metabolic model reconstruction methods, which use literature, transcriptomics, proteomics and metabolomics data, together with a global template model. As a case study, we analyzed the consistency between several omics data sources and reconstructed distinct metabolic models of hepatocytes using different methods and data sources as inputs. The results show that omics data sources have a poor overlapping and, in some cases, are even contradictory. Additionally, the hepatocyte metabolic models generated are in many cases not able to perform metabolic functions known to be present in the liver tissue. We conclude that reliable methods for a priori omics data integration are required to support the reconstruction of complex models of human cells.

Construction of an innocuous Salmonella phage

Dissertação de mestrado em Bioengenharia