Institute Sistemas e Robotica

Lisbon, Portugal

Institute Sistemas e Robotica

Lisbon, Portugal
SEARCH FILTERS
Time filter
Source Type

Perdigao N.,University of Lisbon | Perdigao N.,Institute Sistemas e Robotica | Rosa A.C.,University of Lisbon | Rosa A.C.,Institute Sistemas e Robotica | And 3 more authors.
BioData Mining | Year: 2017

Background: Recently we surveyed the dark-proteome, i.e., regions of proteins never observed by experimental structure determination and inaccessible to homology modelling. Surprisingly, we found that most of the dark proteome could not be accounted for by conventional explanations (e.g., intrinsic disorder, transmembrane domains, and compositional bias), and that nearly half of the dark proteome comprised dark proteins, in which the entire sequence lacked similarity to any known structure. In this paper we will present the Dark Proteome Database (DPD) and associated web services that provide access to updated information about the dark proteome. Results: We assembled DPD from several external web resources (primarily Aquaria and Swiss-Prot) and stored it in a relational database currently containing ~10 million entries and occupying ~2 GBytes of disk space. This database comprises two key tables: one giving information on the darkness of each protein, and a second table that breaks each protein into dark and non-dark regions. In addition, a second version of the database is created using also information from the Protein Model Portal (PMP) to determine darkness. To provide access to DPD, a web server has been implemented giving access to all underlying data, as well as providing access to functional analyses derived from these data. Conclusions: Availability of this database and its web service will help focus future structural and computational biology efforts to study the dark proteome, thus providing a basis for understanding a wide variety of biological functions that currently remain unknown. Availability and implementation: DPD is available at http://darkproteome.ws. The complete database is also available upon request. Data use is permitted via the Creative Commons Attribution-NonCommercial International license (http://creativecommons. org/licenses/by-nc/4.0/). © 2017 The Author(s).


Perdigao N.,University of Lisbon | Perdigao N.,Institute Sistemas e Robotica | Heinrich J.,CSIRO | Stolte C.,CSIRO | And 12 more authors.
Proceedings of the National Academy of Sciences of the United States of America | Year: 2015

We surveyed the "dark" proteome-that is, regions of proteins never observed by experimental structure determination and inaccessible to homology modeling. For 546,000 Swiss-Prot proteins, we found that 44-54% of the proteome in eukaryotes and viruses was dark, compared with only ∼14% in archaea and bacteria. Surprisingly, most of the dark proteome could not be accounted for by conventional explanations, such as intrinsic disorder or transmembrane regions. Nearly half of the dark proteome comprised dark proteins, in which the entire sequence lacked similarity to any known structure. Dark proteins fulfill a wide variety of functions, but a subset showed distinct and largely unexpected features, such as association with secretion, specific tissues, the endoplasmic reticulum, disulfide bonding, and proteolytic cleavage. Dark proteins also had short sequence length, low evolutionary reuse, and few known interactions with other proteins. These results suggest new research directions in structural and computational biology.


Carneiro G.,University of Adelaide | Nascimento J.C.,Institute Sistemas e Robotica
Proceedings of the IEEE International Conference on Computer Vision | Year: 2011

Recently, there has been an increasing interest in the investigation of statistical pattern recognition models for the fully automatic segmentation of the left ventricle (LV) of the heart from ultrasound data. The main vulnerability of these models resides in the need of large manually annotated training sets for the parameter estimation procedure. The issue is that these training sets need to be annotated by clinicians, which makes this training set acquisition process quite expensive. Therefore, reducing the dependence on large training sets is important for a more extensive exploration of statistical models in the LV segmentation problem. In this paper, we present a novel incremental on-line semi-supervised learning model that reduces the need of large training sets for estimating the parameters of statistical models. Compared to other semi-supervised techniques, our method yields an on-line incremental re-training and segmentation instead of the off-line incremental re-training and segmentation more commonly found in the literature. Another innovation of our approach is that we use a statistical model based on deep learning architectures, which are easily adapted to this on-line incremental learning framework. We show that our fully automatic LV segmentation method achieves state-of-the-art accuracy with training sets containing less than twenty annotated images. © 2011 IEEE.


Martins A.F.T.,Carnegie Mellon University | Martins A.F.T.,Telecommunications Institute of Portugal | Smith N.A.,Carnegie Mellon University | Aguiar P.M.Q.,Institute Sistemas e Robotica | Figueiredo M.A.T.,Telecommunications Institute of Portugal
EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference | Year: 2011

Dual decomposition has been recently proposed as a way of combining complementary models, with a boost in predictive power. However, in cases where lightweight decompositions are not readily available (e.g., due to the presence of rich features or logical constraints), the original subgradient algorithm is inefficient. We sidestep that difficulty by adopting an augmented Lagrangian method that accelerates model consensus by regularizing towards the averaged votes. We show how first-order logical constraints can be handled efficiently, even though the corresponding subproblems are no longer combinatorial, and report experiments in dependency parsing, with state-of-the-art results. © 2011 Association for Computational Linguistics.


Nascimento J.C.,Institute Sistemas e Robotica
Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference | Year: 2010

We propose a improved Gradient Vector Flow (iGVF) for active contour detection. The algorithm herein proposed allows to surpass the problems of the GVF, which occur in noisy images with cluttered background. We experimentally illustrate that the proposed modified version of the GVF algorithm has a better performance in noisy images. The main difference concerns the use of more robust and informative features (edge segments) which significantly reduce the influence of noise. Experiments with real data from several image modalities are presented to illustrate the performance of the proposed approach.


Martins A.F.T.,Carnegie Mellon University | Martins A.F.T.,Telecommunications Institute of Portugal | Smith N.A.,Carnegie Mellon University | Aguiar P.M.Q.,Institute Sistemas e Robotica | Figueiredo M.A.T.,Telecommunications Institute of Portugal
EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference | Year: 2011

Linear models have enjoyed great success in structured prediction in NLP. While a lot of progress has been made on efficient training with several loss functions, the problem of endowing learners with a mechanism for feature selection is still unsolved. Common approaches employ ad hoc filtering or L 1-regularization; both ignore the structure of the feature space, preventing practicioners from encoding structural prior knowledge. We fill this gap by adopting regularizers that promote structured sparsity, along with efficient algorithms to handle them. Experiments on three tasks (chunking, entity recognition, and dependency parsing) show gains in performance, compactness, and model interpretability. © 2011 Association for Computational Linguistics.


Nascimento J.C.,Institute Sistemas e Robotica | Marques J.S.,Institute Sistemas e Robotica | Figueiredo M.A.T.,Telecommunications Institute of Portugal
Proceedings - International Conference on Image Processing, ICIP | Year: 2010

We propose a method to classify human trajectories, modeled by a set of motion vector fields, each tailored to describe a specific motion regime. Trajectories are modeled as being composed of segments corresponding to different motion regimes, each generated by one of the underlying motion fields. Switching among the motion fields follows a probabilistic mechanism, described by a field of stochastic matrices. This yields a space-dependent motion model which can be estimated using an expectation-maximization (EM) algorithm. To address the model selection question (how many fields to use?), we adopt a discriminative criterion based on classification accuracy on a held out set. Experiments with real data (human trajectories in a shopping mall) illustrate the ability of the proposed approach to classify complex trajectories into high level classes (client versus non-client). © 2010 IEEE.


Nascimento J.C.,Institute Sistemas e Robotica | Marques J.S.,Institute Sistemas e Robotica | Marques J.S.,University of Lisbon
2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10 | Year: 2010

We propose a improved Gradient Vector Flow (iGVF) for active contour detection. The algorithm herein proposed allows to surpass the problems of the GVF, which occur in noisy images with cluttered background. We experimentally illustrate that the proposed modified version of the GVF algorithm has a better performance in noisy images. The main difference concerns the use of more robust and informative features (edge segments) which significantly reduce the influence of noise. Experiments with real data from several image modalities are presented to illustrate the performance of the proposed approach. © 2010 IEEE.


Seabra J.C.,Institute Sistemas e Robotica | Sanches J.M.,Institute Sistemas e Robotica
2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings | Year: 2010

The information encoded in ultrasound speckle is often discarded but it is widely recognized that this phenomenon is dependent of the intrinsic acoustic properties of tissues. In this paper we propose a robust method to estimate the despeckled and speckle components from the ultrasound data with the purpose of tissue characterization. A de-speckling method, which can conveniently work with either Radio Frequency (RF) or B-mode data, contributes to an improvement on the visualization of anatomical details, while providing useful fields from where echogenicity and texture features can be extracted. The adequacy of the RF image retrieval and despeckling methods are tackled using both synthetic and real ultrasonic data. ©2010 IEEE.


Martins A.F.T.,Carnegie Mellon University | Smith N.A.,Carnegie Mellon University | Xing E.P.,Carnegie Mellon University | Aguiar P.M.Q.,Institute Sistemas e Robotica | And 3 more authors.
EMNLP 2010 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference | Year: 2010

We present a unified view of two state-of-the-art non-projective dependency parsers, both approximate: the loopy belief propagation parser of Smith and Eisner (2008) and the relaxed linear program of Martins et al. (2009). By representing the model assumptions with a factor graph, we shed light on the optimization problems tackled in each method. We also propose a new aggressive online algorithm to learn the model parameters, which makes use of the underlying variational representation. The algorithm does not require a learning rate parameter and provides a single framework for a wide family of convex loss functions, including CRFs and structured SVMs. Experiments show state-of-the-art performance for 14 languages. © 2010 Association for Computational Linguistics.

Loading Institute Sistemas e Robotica collaborators
Loading Institute Sistemas e Robotica collaborators