Arlindo L. Oliveira

Arlindo L. Oliveira
Instituto Superior Técnico · Dept. of Computer Science and Engineering

PhD

About

254
Publications
39,782
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
6,316
Citations

Publications

Publications (254)
Chapter
The model-based reinforcement learning paradigm, which uses planning algorithms and neural network models, has recently achieved unprecedented results in diverse applications, leading to what is now known as deep reinforcement learning. These agents are quite complex and involve multiple components, factors that create challenges for research and d...
Article
Europe was hit hard by the COVID-19 pandemic and Portugal was severely affected, having suffered three waves in the first twelve months. Approximately between Jan 19th and Feb 5th 2021 Portugal was the country in the world with the largest incidence rate, with 14-days incidence rates per 100,000 inhabitants in excess of 1000. Despite its importance...
Chapter
Medical image segmentation is inherently uncertain. For a given image, there may be multiple plausible segmentation hypotheses, and physicians will often disagree on lesion and organ boundaries. To be suited to real-world application, automatic segmentation systems must be able to capture this uncertainty and variability. Thus far, this has been ad...
Article
Introduction and objectives Although automatic artificial intelligence (AI) coronary angiography (CAG) segmentation is arguably the first step toward future clinical application, it is underexplored. We aimed to (1) develop AI models for CAG segmentation and (2) assess the results using similarity scores and a set of criteria defined by expert phys...
Preprint
Full-text available
The model-based reinforcement learning paradigm, which uses planning algorithms and neural network models, has recently achieved unprecedented results in diverse applications, leading to what is now known as deep reinforcement learning. These agents are quite complex and involve multiple components, factors that can create challenges for research....
Preprint
Full-text available
Attention mechanisms have raised significant interest in the research community, since they promise significant improvements in the performance of neural network architectures. However, in any specific problem, we still lack a principled way to choose specific mechanisms and hyper-parameters that lead to guaranteed improvements. More recently, self...
Preprint
Full-text available
Medical image segmentation is inherently uncertain. For a given image, there may be multiple plausible segmentation hypotheses, and physicians will often disagree on lesion and organ boundaries. To be suited to real-world application, automatic segmentation systems must be able to capture this uncertainty and variability. Thus far, this has been ad...
Preprint
Full-text available
Given the inner complexity of the human nervous system, insight into the dynamics of brain activity can be gained from understanding smaller and simpler organisms, such as the nematode C. Elegans. The behavioural and structural biology of these organisms is well-known, making them prime candidates for benchmarking modelling and simulation technique...
Preprint
Full-text available
Coronary X-ray angiography is a crucial clinical procedure for the diagnosis and treatment of coronary artery disease, which accounts for roughly 16% of global deaths every year. However, the images acquired in these procedures have low resolution and poor contrast, making lesion detection and assessment challenging. Accurate coronary artery segmen...
Preprint
Full-text available
Europe was hit hard by the COVID-19 pandemic and Portugal was one of the most affected countries, having suffered three waves in the first twelve months. Approximately between Jan 19th and Feb 5th 2021 Portugal was the country in the world with the largest incidence rate, with 14-days incidence rates per 100,000 inhabitants in excess of 1000. Despi...
Chapter
Machine learning and other artificial intelligence techniques have been extensively used in a large number of medical applications, in diagnosis, treatment selection, mining of electronic health records, genetics, and image processing, among several others. Machine learning techniques can be used to infer predictive models, from labeled data, in ma...
Preprint
Full-text available
The significant increase in world population and urbanisation has brought several important challenges, in particular regarding the sustainability, maintenance and planning of urban mobility. At the same time, the exponential increase of computing capability and of available sensor and location data have offered the potential for innovative solutio...
Preprint
Full-text available
Coronary artery disease leading up to stenosis, the partial or total blocking of coronary arteries, is a severe condition that affects millions of patients each year. Automated identification and classification of stenosis severity from minimally invasive procedures would be of great clinical value, but existing methods do not match the accuracy of...
Preprint
Full-text available
The combination of deep learning and Monte Carlo Tree Search (MCTS) has shown to be effective in various domains, such as board and video games. AlphaGo represented a significant step forward in our ability to learn complex board games, and it was rapidly followed by significant advances, such as AlphaGo Zero and AlphaZero. Recently, MuZero demonst...
Article
Full-text available
Abstract Bioinformaticians and biologists rely increasingly upon workflows for the flexible utilization of the many life science tools that are needed to optimally convert data into knowledge. We outline a pan-European enterprise to provide a catalogue (https://bio.tools) of tools and databases that can be used in these workflows. bio.tools not onl...
Article
Developments in biotechnology are increasingly dependent on the extensive use of big data, generated by modern high‐throughput instrumentation technologies and stored in thousands of databases, public and private. Future developments in this area depend, critically, on the ability of biotechnology researchers to master the skills required to effect...
Preprint
Full-text available
Gliomas are the most common primary brain malignancies, with different degrees of aggressiveness, variable prognosis and various heterogeneous histologic sub-regions, i.e., peritumoral edematous/invaded tissue, necrotic core, active and non-enhancing core. This intrinsic heterogeneity is also portrayed in their radio-phenotype, as their sub-regions...
Article
Full-text available
Performance of models highly depend not only on the used algorithm but also the data set it was applied to. This makes the comparison of newly developed tools to previously published approaches difficult. Either researchers need to implement others' algorithms first, to establish an adequate benchmark on their data, or a direct comparison of new an...
Preprint
Full-text available
Data availability by modern sequencing technologies represents a major challenge in oncological survival analysis, as the increasing amount of molecular data hampers the generation of models that are both accurate and interpretable. To tackle this problem, this work evaluates the introduction of graph centrality measures in classical sparse surviva...
Preprint
The Conditional Random Field as a Recurrent Neural Network layer is a recently proposed algorithm meant to be placed on top of an existing Fully-Convolutional Neural Network to improve the quality of semantic segmentation. In this paper, we test whether this algorithm, which was shown to improve semantic segmentation for 2D RGB images, is able to i...
Article
Background: Head and neck squamous cell carcinoma (HNSCC) is one of the most common malignancies in humans and the average 5-year survival rate is one of the lowest among aggressive cancers. Protein kinase C zeta (PKCZ) is highly expressed in head and neck tumors, and the inhibition of PKCZ reduces MAPK activation in five of seven head and neck tum...
Article
Full-text available
Ischemic stroke is a leading cause of disability and death worldwide among adults. The individual prognosis after stroke is extremely dependent on treatment decisions physicians take during the acute phase. In the last five years, several scores such as the ASTRAL, DRAGON, and THRIVE have been proposed as tools to help physicians predict the patien...
Chapter
This chapter describes evolution as a long-running algorithm that has designed all species on Earth. Evolution, a process discovered by Charles Darwin, has been working for more than four billion years to obtain, at first, simple unicellular organisms (prokaryotes) and, later, much more complex life forms, based on eukaryotic cells. Evolution worke...
Chapter
The chapter covers the developments in science that led to the digital computers of today. It all started with the understanding of electromagnetic phenomena, made possible by the discovery of Maxwell’s equations, and all the developments that followed and made possible the controlled used of electricity. Following up on the great developments of t...
Chapter
This chapter provides a brief introduction to the way the brain works. It starts by describing the physical mechanisms used by neurons to send and receive electrical signals, and some of the experiments that led to the understanding of these mechanisms. It then describes how neurons are organized in networks and uses some particular structures in t...
Chapter
This chapter introduces the idea that technology, invented millennia ago, is developing at an even increasing pace, creating the need for all systems to develop to avoid becoming obsolete. This is called the Red Queen effect. The current generation has seen the appearance and rapid development of many new technologies, from digital computers and ce...
Chapter
This chapter provides a brief review of the history of technology, covering pre-historical technologies, the agricultural revolution, the first two industrial revolutions, and the third industrial revolution, based on information technology. Evidence is provided that technological development tends to follow an exponential curve, leading to technol...
Chapter
This chapter presents an analysis of the different approaches that may lead to the creation of artificially intelligent and conscious systems, which I call digital minds. In particular, it considers three different avenues that may eventually lead to intelligent systems: synthetic intelligences, neuromorphic intelligent systems, and whole brain emu...
Chapter
This chapter, the last chapter in the book, presents some far-fetched ideas about the future of technology and the human species. It starts by discussing the concept of technological singularity, an even that would create a discontinuity in the evolution of technology. The idea that mind uploading may one day become possible leads many people to be...
Chapter
This chapter summarily describes some of the technologies that are currently being used to image living brains and understand brain behaviour. The important projects in this area are briefly enumerated, as are the many technologies used for brain imaging. The computer models that are used to integrate the obtained data, brain networks, are also bri...
Chapter
This chapter covers the development of computing, from its origins, with the analytical engine, to modern computer science. Babbage and Ada Lovelace’s contributions to the science of computing led, in time, to the idea of universal computers, proposed by Alan Turing. These universal computers, proposed by Turing, are conceptual devices that can com...
Book
This book addresses the connections between computers, life, evolution, brains, and minds. Digital computers are recent and have changed our society. However, they represent just the latest way to process information, using algorithms to create order out of chaos. Before computers, the job of processing information was done by living organisms, whi...
Chapter
This chapter describes how computers played a decisive role in the sequencing and understanding of the genomes of humans and other organisms. The discovery of the structure of DNA, by Watson and Crick, opened the way to a systematic approach to biology, based on the study of the way DNA encodes the proteins in all living cells. The area that became...
Chapter
Some of the challenges and promises that would stem from the creation of digital minds are presented and discussed. In particular, this chapter addresses the possibility that, in the future, there may exist digital persons, digital minds that have personhood rights and duties. The non-obvious possibilities raised by the creation of digital minds ar...
Chapter
This chapter addresses the question of whether a computer can become intelligent and how to test for that possibility. It introduces the idea of the Turing test, a test developed to determine, in an unbiased way, whether a program running in a computer is, or is not, intelligent. The development of artificial intelligence led, in time, to many appl...
Article
Full-text available
Background: Head and neck squamous cell carcinoma (HNSCC) is one of the most common malignancies in humans and the average 5-year survival rate is one of the lowest among aggressive cancers. Protein kinase C zeta (PKCZ) is highly expressed in head and neck tumors, and the inhibition of PKCZ reduces MAPK activation in five of seven head and neck tum...
Book
What do computers, cells, and brains have in common? Computers are electronic devices designed by humans; cells are biological entities crafted by evolution; brains are the containers and creators of our minds. But all are, in one way or another, information-processing devices. The power of the human brain is, so far, unequaled by any existing mach...
Article
Full-text available
Background Modeling survival oncological data has become a major challenge as the increase in the amount of molecular information nowadays available means that the number of features greatly exceeds the number of observations. One possible solution to cope with this dimensionality problem is the use of additional constraints in the cost function op...
Article
Full-text available
ELIXIR, the European life science infrastructure for biological information, is a unique initiative to consolidate Europe’s national centres, services, and core bioinformatics resources into a single, coordinated infrastructure. ELIXIR brings together Europe’s major life-science data archives and connects these with national bioinformatics infrastr...
Article
Full-text available
ELIXIR, the European life science infrastructure for biological information, is a unique initiative to consolidate Europe's national centres, services, and core bioinformatics resources into a single, coordinated infrastructure. ELIXIR brings together Europe's major life-science data archives and connects these with national bioinformatics infrastr...
Conference Paper
Full-text available
Complex diseases are typically caused by the combined effects of multiple genetic variations. When epistatic effects are present, these genetic variations show stronger effects when considered together than when considered individually. To identify groups of single nucleotide polymorphisms (SNP) that can be of use in the explanation of multifactori...
Article
Full-text available
The YEASTRACT (http://www.yeastract.com) information system is a tool for the analysis and prediction of transcription regulatory associations in Saccharomyces cerevisiae. Last updated in June 2013, this database contains over 200 000 regulatory associations between transcription factors (TFs) and target genes, including 326 DNA binding sites for 1...
Article
Full-text available
It is widely agreed that complex diseases are typically caused by the joint effects of multiple instead of a single genetic variation. These genetic variations may show stronger effects when considered together than when considered individually, a phenomenon known as epistasis or multilocus interaction. In this work, we explore the applicability of...
Article
Full-text available
The human interaction through the web generates both implicit and explicit knowledge. An example of an implicit contribution is searching, as people contribute with their knowledge by clicking on retrieved documents. When this information is available, an important and interesting challenge is to extract relations from query logs, and, in particula...
Article
Full-text available
This document provides supplementary material describing related work on biclustering algorithms for time series gene expression data analysis. We describe in detail three state of the art biclustering approaches specifically design to discover biclusters in gene expression time series and identify their strengths and weaknesses.
Article
Despite the high level of success attained by keyword based information retrieval methods, a significant fraction of information retrieval tasks still needs to take into account the semantics of the data. We propose a method that combines an hand-crafted ontology with a robust inductive inference method to assign semantic labels to pieces of techni...
Article
In this study we address the problem of finding a quantitative mathematical model for the genetic network regulating the stress response of the yeast Saccharomyces cerevisiae to the agricultural fungicide mancozeb. An S-system formalism was used to model the interactions of a five-gene network encoding four transcription factors (Yap1, Yrr1, Rpn4 a...
Article
Full-text available
Motivation: Uncovering mechanisms underlying gene expression control is crucial to understand complex cellular responses. Studies in gene regulation often aim to identify regulatory players involved in a biological process of interest, either transcription factors coregulating a set of target genes or genes eventually controlled by a set of regula...
Article
Suffix trees are by far the most important data structure in stringology, with a myriad of applications in fields like bioinformatics and information retrieval. Classical representations of suffix trees require Θ(n log n) bits of space, for a string of size n. This is considerably more than the n log2 σ bits needed for the string itself, where σ is...
Article
Full-text available
Qualitative models allow understanding the relation between the structure and the dynamics of gene regulatory networks. The dynamical properties of these models can be automatically analysed by means of formal verification methods, like model checking. This facilitates the model-validation process and the test of new hypotheses to reconcile model p...
Conference Paper
We address the problem of finding a mathematical model for the genetic network regulating the stress response of the yeast Saccharomyces cerevisiae to the fungicide mancozeb. An S-system formalism was used to model the interactions of this 5 gene network. Parameter estimation was accomplished by decoupling the resulting system of nonlinear ordinary...
Article
Full-text available
We propose an efficient and parameter-free scoring criterion, the factorized conditional log-likelihood (fCLL), for learning Bayesian network classifiers. The proposed score is an approximation of the conditional log-likelihood criterion. The approximation is devised in order to guarantee decomposability over the network structure, as well as effic...
Article
Full-text available
Over the past few years, new massively parallel DNA sequencing technologies have emerged. These platforms generate massive amounts of data per run, greatly reducing the cost of DNA sequencing. However, these techniques also raise important computational difficulties mostly due to the huge volume of data produced, but also because of some of their s...
Data
Full-text available
Detailed set up and evaluation methodology of GRISOTTO. This additional file presents in detail three topics needed to make the paper self-contained. First, is describes the call to RISOTTO algorithm found in Step 1 of the Algorithm 1. Second, it includes the inter-motif distance used to compute successful predictions from motif discoverers, along...
Data
Full-text available
Detailed results of GRISOTTO. Additional details about experimental results of GRISOTTO presenting actual predictions sequence-set by sequence-set for various positional priors. It also presents results of PRIORITY taken from the supplementary material of the original papers.
Article
Full-text available
Position-specific priors (PSP) have been used with success to boost EM and Gibbs sampler-based motif discovery algorithms. PSP information has been computed from different sources, including orthologous conservation, DNA duplex stability, and nucleosome positioning. The use of prior information has not yet been used in the context of combinatorial...
Article
The fast development of sequencing techniques in the recent past has required an urgent development of efficient and accurate haplotype inference tools. Besides being a crucial issue in genetics, haplotype inference is also a challenging computational problem. Among others, pure parsimony is a viable modeling approach to solve the problem of haplot...
Conference Paper
The sliding window (SW) Lempel-Ziv (LZ) 77 algorithms are widely used for universal lossless data compression. The LZ77 encoding component performs repeated substring search. Data structures, such as hash tables and trees have been used for fast search, at the expense of memory usage. Recently, suffix arrays (SA) have been used for dictionary repre...
Conference Paper
Multidrug resistance (MDR), a phenomenon with impact in Human Health and in Agro-Food and Environmental Biotechnology, often results from the activation of drug efflux pumps, many times controlled at the transcriptional level. The complex transcriptional control of these genes has been on the focus of our research, guided by the information gathere...
Article
Full-text available
The YEAst Search for Transcriptional Regulators And Consensus Tracking (YEASTRACT) information system (http://www.yeastract.com) was developed to support the analysis of transcription regulatory associations in Saccharomyces cerevisiae. Last updated in June 2010, this database contains over 48,200 regulatory associations between transcription facto...
Chapter
A core in a graph is usually taken as a set of highly connected vertices. Although general, this definition is intuitive and useful for studying the structure of many real networks. Nevertheless, depending on the problem, different formulations of graph core may be required, leading us to the known concept of generalized core. In this paper we stud...
Article
Full-text available
Community detection or graph clustering is an important problem in the analysis of computer networks, social networks, biological networks and many other natural and artificial networks. These networks are in general very large and, thus, finding hidden structures and functional modules is a very hard task. In this paper we propose new data structu...
Conference Paper
Despite the remarkable success of computational biology methods in some areas of application like gene finding and sequence alignment, there are still topics for which no definitive approaches have been proposed. One of these is the accurate detection of biologically significant cis-regulatory motifs, that remains an open problem, despite intensive...
Conference Paper
The human interaction through the web generates both implicit and explicit knowledge. An example of an implicit contribution is searching, as people contribute with their knowledge by clicking on retrieved documents. Thus, an important and interesting challenge is to extract semantic relations among queries and their terms from query logs. In this...
Poster
Advances on the Computational modeling and analysis of the yeast FLR1 regulatory network in mancozeb-challenged cells
Article
Full-text available
Multidrug resistance is often the result of the activation of drug efflux pumps able to catalyze the extrusion of the toxic compound to the outer medium, this activation being frequently controlled at the transcriptional level. Transcriptional regulation in the model eukaryote S. cerevisiae is the result of the interaction and cross-talk between ne...
Article
Given a set of genotypes from a population, the process of recovering the haplotypes that explain the genotypes is called haplotype inference. The haplotype inference problem under the assumption of pure parsimony consists in finding the smallest number of haplotypes that explain a given set of genotypes. This problem is NP-hard. The original formu...
Conference Paper
We study parallel and distributed compressed indexes. Compressed indexes are a new and functional way to index text strings. They exploit the compressibility of the text, so that their size is a function of the compressed text size. Moreover, they support a considerable amount of functions, more than many classical indexes. We make use of this exte...
Poster
Refining current knowledge on the regulatory network underlying the transcriptional control of the multidrug resistance gene FLR1 combining experimental and computational approaches
Article
Full-text available
Although most biclustering formulations are NP-hard, in time series expression data analysis, it is reasonable to restrict the problem to the identification of maximal biclusters with contiguous columns, which correspond to coherent expression patterns shared by a group of genes in consecutive time points. This restriction leads to a tractable prob...