High-Content Analysis of Breast Cancer Using Single-Cell Deep Transfer Learning

High-content analysis has revolutionized cancer drug discovery by identifying substances that alter the phenotype of a cell, which prevents tumor growth and metastasis. The high-resolution biofluorescence images from assays allow precise quantitative measures enabling the distinction of small molecules of a host cell from a tumor. In this work, we are particularly interested in the application of deep neural networks (DNNs), a cutting-edge machine learning method, to the classification of compounds in chemical mechanisms of action (MOAs). Compound classification has been performed using image-based profiling methods sometimes combined with feature reduction methods such as principal component analysis or factor analysis. In this article, we map the input features of each cell to a particular MOA class without using any treatment-level profiles or feature reduction methods. To the best of our knowledge, this is the first application of DNN in this domain, leveraging single-cell information. Furthermore, we use deep transfer learning (DTL) to alleviate the intensive and computational demanding effort of searching the huge parameter's space of a DNN. Results show that using this approach, we obtain a 30% speedup and a 2% accuracy improvement.

Os modelos das demonstrações financeiras

Orientador: Doutor, José Manuel Veiga Pereira

SmallPower, Energias Renováveis, Lda.: tradução e gestão de conteúdos

Relatório de estágio realizado por: Tiago André Nogueira da Cruz Trabalho orientado pela Mestre Célia Sousa

Learning to manage in knowledge based organizations: the role of portfolios

Paper presented at the 8th European Conference on Knowledge Management, Barcelona, 6-7 Sep. 2008 URL: http://www.academic-conferences.org/eckm/eckm2007/eckm07-home.htm

Programas de self-management em pacientes com DPOC: uma revisão sistemática

Introdução: Programas de self-management têm como objectivo habilitar os pacientes com estratégias necessárias para levar a cabo procedimentos específicos para a patologia. A última revisão sistemática sobre selfmanagament em DPOC foi realizada em 2007, concluindo-se que ainda não era possível fornecer dados claros e suficientes acerca de recomendações sobre a estrutura e conteúdo de programas de self-managament na DPOC. A presente revisão tem o intuito de complementar a análise da revisão anterior, numa tentativa de inferir a influência do ensino do self-management na DPOC. Objectivos: verificar a influência dos programas de self-management na DPOC, em diversos indicadores relacionados com o estado de saúde do paciente e na sua utilização dos serviços de saúde. Estratégia de busca: pesquisa efectuada nas bases de dados PubMed e Cochrane Collaboration (01/01/2007 – 31/08/2010). Palavras-chave: selfmanagement education, self-management program, COPD e pulmonary rehabilitation. Critérios de Selecção: estudos randomizados sobre programas de selfmanagement na DPOC. Extracção e Análise dos Dados: 2 investigadores realizaram, independentemente, a avaliação e extracção de dados de cada artigo. Resultados: foram considerados 4 estudos randomizados em selfmanagement na DPOC nos quais se verificaram benefícios destes programas em diversas variáveis: qualidade de vida a curto e médio prazo, utilização dos diferentes recursos de saúde, adesões a medicação de rotina, controle das exacerbações e diminuição da sintomatologia. Parece não ocorrer alteração na função pulmonar e no uso de medicação de emergência, sendo inconclusivo o seu efeito na capacidade de realização de exercício. Conclusões: programas de self-management aparentam ter impacto positivo na qualidade de vida, recurso a serviços de saúde, adesão à medicação, planos de acção e níveis de conhecimento da DPOC. Discrepâncias nos critérios de selecção das amostras utilizadas, períodos de seguimento desiguais, consistência das variáveis mensuradas, condicionam a informação disponibilizada sobre este assunto.

Knowledge and technologies in innovative information systems

7th Mediterranean Conference on Information Systems, MCIS 2012, Guimaraes, Portugal, September 8-10, 2012, Proceedings Series: Lecture Notes in Business Information Processing, Vol. 129

Desenvolvimento de uma ferramenta colaborativa na área da gestão da informação/conhecimento para aplicação numa unidade de cuidados na comunidade

O presente projeto surgiu da necessidade de um instrumento de trabalho na área da gestão da informação / conhecimento a aplicar na Unidade de Cuidados na Comunidade dos Carvalhos (UCCC) que, pela sua estrutura de trabalho por projeto, abrange diversos grupos de utilizadores com perfis e necessidades específicas. Rapidamente assumiu maior dimensão, pois ao seu ponto de partida se conjugaram as oportunidades de utilização das tecnologias de informação na área da saúde, a divulgação da Unidade assim como a divulgação de informação sobre saúde e a interação com os utilizadores. O processo implicou a aplicação das metodologias de Investigação Ação e de Gestão de Projetos, resultando na criação e publicação de um espaço Web. Com o Content Management System (CMS) Joomla foi construído o Site UCC Carvalhos, que faculta simultaneamente informação sobre saúde, oportunidade de aconselhamento especializado e personalizado e permite a organização da documentação interna da Unidade referida. Nesta fase de início de vida do site estabeleceu-se como temáticas prioritárias a desenvolver a informação sobre a UCCC e o seu funcionamento assim como o projeto “Companhia das Barriguinhas”, mais concretamente a Preparação para o Parto e Parentalidade. O desenvolvimento deste projeto superou as expectativas de todos os elementos envolvidos, pois para além de permitir obter resposta às necessidades identificadas, permitiu também experimentar as metodologias referidas de forma integrada e aprofundar temáticas como a gestão da informação e conhecimento, o papel das tecnologias de informação e comunicação na Saúde e o papel do cidadão na utilização das mesmas no sentido de uma autonomia responsável na gestão da sua Saúde.

A influência do eWOM gerado pelos grupos de referência no Facebook, em Portugal

Dissertação apresentada ao Instituto Superior de Contabilidade e Administração do Porto para a obtenção do Grau de Mestre em Marketing Digital. Orientado por Mestre Inês Veiga Pereira

NCRF Nº 1 - estrutura e conteúdos das demosntrações financeiras e implicações fiscais e em auditoria

Dissertação apresentada ao Instituto obtenção do grau de Mestre em Auditoria orientador: Dr. Rodrigo Mário de Oliveira Carvalho

VPPs information needs for effective operation in competitive electricity markets

The large increase of renewable energy sources and Distributed Generation (DG) of electricity gives place to the Virtual Power Producer (VPP) concept. VPPs may turn electricity generation by renewable sources valuable in electricity markets. Information availability and adequate decision-support tools are crucial for achieving VPPs’ goals. This involves information concerning associated producers and market operation. This paper presents ViProd, a simulation tool that allows simulating VPPs operation, focusing mainly in the information requirements for adequate decision making.

Decision support system with incomplete and domain incoherent information management

Many of the most common human functions such as temporal and non-monotonic reasoning have not yet been fully mapped in developed systems, even though some theoretical breakthroughs have already been accomplished. This is mainly due to the inherent computational complexity of the theoretical approaches. In the particular area of fault diagnosis in power systems however, some systems which tried to solve the problem, have been deployed using methodologies such as production rule based expert systems, neural networks, recognition of chronicles, fuzzy expert systems, etc. SPARSE (from the Portuguese acronym, which means expert system for incident analysis and restoration support) was one of the developed systems and, in the sequence of its development, came the need to cope with incomplete and/or incorrect information as well as the traditional problems for power systems fault diagnosis based on SCADA (supervisory control and data acquisition) information retrieval, namely real-time operation, huge amounts of information, etc. This paper presents an architecture for a decision support system, which can solve the presented problems, using a symbiosis of the event calculus and the default reasoning rule based system paradigms, insuring soft real-time operation with incomplete, incorrect or domain incoherent information handling ability. A prototype implementation of this system is already at work in the control centre of the Portuguese Transmission Network.

A study on dynamic state information (DSI) around users for safe urban life

To select each node by devices and by contexts in urban computing, users have to put their plan information and their requests into a computing environment (ex. PDA, Smart Devices, Laptops, etc.) in advance and they will try to keep the optimized states between users and the computing environment. However, because of bad contexts, users may get the wrong decision, so, one of the users’ demands may be requesting the good server which has higher security. To take this issue, we define the structure of Dynamic State Information (DSI) which takes a process about security including the relevant factors in sending/receiving contexts, which select the best during user movement with server quality and security states from DSI. Finally, whenever some information changes, users and devices get the notices including security factors, then an automatic reaction can be possible; therefore all users can safely use all devices in urban computing.

Information and communication technologies in education – a web-based intelligent tutoring system on teaching and learning electrical project

Electrical activity is extremely broad and distinct, requiring by one hand, a deep knowledge on rules, regulations, materials, equipments, technical solutions and technologies and assistance in several areas, as electrical equipment, telecommunications, security and efficiency and rational use of energy, on the other hand, also requires other skills, depending on the specific projects to be implemented, being this knowledge a characteristic that belongs to the professionals with relevant experience, in terms of complexity and specific projects that were made.

Can power laws help us understand gene and proteome information?

Proteins are biochemical entities consisting of one or more blocks typically folded in a 3D pattern. Each block (a polypeptide) is a single linear sequence of amino acids that are biochemically bonded together. The amino acid sequence in a protein is defined by the sequence of a gene or several genes encoded in the DNA-based genetic code. This genetic code typically uses twenty amino acids, but in certain organisms the genetic code can also include two other amino acids. After linking the amino acids during protein synthesis, each amino acid becomes a residue in a protein, which is then chemically modified, ultimately changing and defining the protein function. In this study, the authors analyze the amino acid sequence using alignment-free methods, aiming to identify structural patterns in sets of proteins and in the proteome, without any other previous assumptions. The paper starts by analyzing amino acid sequence data by means of histograms using fixed length amino acid words (tuples). After creating the initial relative frequency histograms, they are transformed and processed in order to generate quantitative results for information extraction and graphical visualization. Selected samples from two reference datasets are used, and results reveal that the proposed method is able to generate relevant outputs in accordance with current scientific knowledge in domains like protein sequence/proteome analysis.

A hybrid recommendation approach for a tourism system

Many current e-commerce systems provide personalization when their content is shown to users. In this sense, recommender systems make personalized suggestions and provide information of items available in the system. Nowadays, there is a vast amount of methods, including data mining techniques that can be employed for personalization in recommender systems. However, these methods are still quite vulnerable to some limitations and shortcomings related to recommender environment. In order to deal with some of them, in this work we implement a recommendation methodology in a recommender system for tourism, where classification based on association is applied. Classification based on association methods, also named associative classification methods, consist of an alternative data mining technique, which combines concepts from classification and association in order to allow association rules to be employed in a prediction context. The proposed methodology was evaluated in some case studies, where we could verify that it is able to shorten limitations presented in recommender systems and to enhance recommendation quality.