Papers by Fabio Cerqueira
Simulacc~ao in-silico do Sistema Imunol'ogico: Modelando o comportamento do Mast'ocito
NICeSim: An open-source simulator based on machine learning techniques to support medical research on prenatal and perinatal care decision making
Artificial Intelligence in Medicine, 2014
This paper describes NICeSim, an open-source simulator that uses machine learning (ML) techniques... more This paper describes NICeSim, an open-source simulator that uses machine learning (ML) techniques to aid health professionals to better understand the treatment and prognosis of premature newborns. The application was developed and tested using data collected in a Brazilian hospital. The available data were used to feed an ML pipeline that was designed to create a simulator capable of predicting the outcome (death probability) for newborns admitted to neonatal intensive care units. However, unlike previous scoring systems, our computational tool is not intended to be used at the patients bedside, although it is possible. Our primary goal is to deliver a computational system to aid medical research in understanding the correlation of key variables with the studied outcome so that new standards can be established for future clinical decisions. In the implemented simulation environment, the values of key attributes can be changed using a user-friendly interface, where the impact of each change on the outcome is immediately reported, allowing a quantitative analysis, in addition to a qualitative investigation, and delivering a totally interactive computational tool that facilitates hypothesis construction and testing. Our statistical experiments showed that the resulting model for death prediction could achieve an accuracy of 86.7% and an area under the receiver operating characteristic curve of 0.84 for the positive class. Using this model, three physicians and a neonatal nutritionist performed simulations with key variables correlated with chance of death. The results indicated important tendencies for the effect of each variable and the combination of variables on prognosis. We could also observe values of gestational age and birth weight for which a low Apgar score and the occurrence of respiratory distress syndrome (RDS) could be less or more severe. For instance, we have noticed that for a newborn with 2000 g or more the occurrence of RDS is far less problematic than for neonates weighing less. The significant accuracy demonstrated by our predictive model shows that NICeSim might be used for hypothesis testing to minimize in vivo experiments. We observed that the model delivers predictions that are in very good agreement with the literature, demonstrating that NICeSim might be an important tool for supporting decision making in medical practice. Other very important characteristics of NICeSim are its flexibility and dynamism. NICeSim is flexible because it allows the inclusion and deletion of variables according to the requirements of a particular study. It is also dynamic because it trains a just-in-time model. Therefore, the system is improved as data from new patients become available. Finally, NICeSim can be extended in a cooperative manner because it is an open-source system.
Predicting the Occurrence of Sepsis by In Silico Simulation
Lecture Notes in Computer Science, 2014
ABSTRACT From public health and clinical point of view, sepsis is a life-threatening complication... more ABSTRACT From public health and clinical point of view, sepsis is a life-threatening complication and its mechanisms are still not fully understood. This article claims that Multiagent Systems are suitable to help elucidate this phenomenon and that it is possible to carry out simulations that can be used in the observation of emergent behaviors, enabling a better understanding of the disease. Requirements for computational simulation of sepsis in AutoSimmune system are presented as also the simulation results. The results presented when using more aggressive pathogens are compatible with sepsis by simultaneously presenting symptoms such as fever, bacteria in the blood and Leukocytosis as reported in literature.
Theoretical Basis of a New Method for DNA Fragment Assembly in k-mer Graphs
2012 31st International Conference of the Chilean Computer Science Society, 2012
ABSTRACT The reduction of cost and running time provided by new generation sequencing technologie... more ABSTRACT The reduction of cost and running time provided by new generation sequencing technologies made possible the emergence of thousands of genome projects in the last few years. On the other hand, those technologies posed important computational challenges, pushing the advance of many research fields in computer science. Particularly, the de novo DNA fragment assembly, which is a fundamental stage in genome sequencing, is a complex problem that demands complex algorithms to solve it. Here, we provide a theoretical basis for the construction of a new method for de novo fragment assembly based on k-mer graphs. Our proposal encompasses many difficulties found in such problems using a unique procedure, in contrast with current methods that use several high-cost procedures to overcome the same issues. Furthermore, our approach is highly scalable since it allows the use of parallelism, being very suitable for solutions with graphics processing unit (GPU).
Immune system simulation: Modeling the mast cell
2012 IEEE International Conference on Bioinformatics and Biomedicine, 2012
ABSTRACT Among the possibilities for simulating the immune system, the multiagent systems approac... more ABSTRACT Among the possibilities for simulating the immune system, the multiagent systems approach has proved to be attractive, since only the behavior of the types of agents is specified. The global behavior emerges from the interactions among agents. This feature is similar to the behavior of the immune system, consisting of large amounts of cell types that interact to maintain the body health. The simulation of the immune system requires modeling various types of cells and substances. This paper presents the modeling of a software agent that simulates the behavior of the mast cells. Some simulations were performed to validate the model.
BMC Genomics, 2012
Background: The shotgun strategy (liquid chromatography coupled with tandem mass spectrometry) is... more Background: The shotgun strategy (liquid chromatography coupled with tandem mass spectrometry) is widely applied for identification of proteins in complex mixtures. This method gives rise to thousands of spectra in a single run, which are interpreted by computational tools. Such tools normally use a protein database from which peptide sequences are extracted for matching with experimentally derived mass spectral data. After the database search, the correctness of obtained peptide-spectrum matches (PSMs) needs to be evaluated also by algorithms, as a manual curation of these huge datasets would be impractical. The target-decoy database strategy is largely used to perform spectrum evaluation. Nonetheless, this method has been applied without considering sensitivity, i.e., only error estimation is taken into account. A recently proposed method termed MUDE treats the target-decoy analysis as an optimization problem, where sensitivity is maximized. This method demonstrates a significant increase in the retrieved number of PSMs for a fixed error rate. However, the MUDE model is constructed in such a way that linear decision boundaries are established to separate correct from incorrect PSMs. Besides, the described heuristic for solving the optimization problem has to be executed many times to achieve a significant augmentation in sensitivity. Results: Here, we propose a new method, termed MUMAL, for PSM assessment that is based on machine learning techniques. Our method can establish nonlinear decision boundaries, leading to a higher chance to retrieve more true positives. Furthermore, we need few iterations to achieve high sensitivities, strikingly shortening the running time of the whole process. Experiments show that our method achieves a considerably higher number of PSMs compared with standard tools such as MUDE, PeptideProphet, and typical target-decoy approaches. Conclusion: Our approach not only enhances the computational performance, and thus the turn around time of MS-based experiments in proteomics, but also improves the information content with benefits of a higher proteome coverage. This improvement, for instance, increases the chance to identify important drug targets or biomarkers for drug development or molecular diagnostics.
Among the possibilities for simulating the immune system, the multiagent systems approach has pro... more Among the possibilities for simulating the immune system, the multiagent systems approach has proved attractive, since only the behavior of the types of agents is specified. The global behavior emerges from the interactions among agents. This feature is similar to the behavior of the immune system, consisting of large amounts of cell types that interact to maintain the body health. The simulation of the immune system requires modeling various types of cells and substances. This paper presents the modeling of a software agent that simulates the behavior of the mast cells. Some simulations were performed to validate the model. Resumo. Dentre as possibilidades de simulação do sistema imunológico, a abordagem por meio de sistemas multiagentes tem se mostrado atraente, já que apenas o comportamento dos tipos de agentes é especificado. O comportamento global emerge das interações entre os agentes. Esta característica é semelhante ao comportamento do sistema imune, formado por numerosa quantidade de tipos de células que interagem para contribuir com a homeostase do organismo. A simulação do sistema imune exige a modelagem de vários tipos de células e substâncias. Este artigo apresenta a modelagem de um agente de software que simula o comportamento de células do tipo mastócito. Algumas simulações foram realizadas para validar o modelo.
The 30th anniversary of the International Symposium on Computer and Information Sciences (ISCIS) ... more The 30th anniversary of the International Symposium on Computer and Information Sciences (ISCIS) series, which have regularly over this long period of time brought together Computer Scientists from around the world and from Turkey, was held at Imperial College London, UK during 21–24 September 2015.
This year the conference attracted 82 submissions from 21 countries—with contributions coming mostly from Europe, America and the Far East—out of which 39 carefully refereed proposals were selected, along with two Invited Papers, for inclusion in the proceedings. Several other Invited Papers were presented orally.
In addition to the papers that are contained in these proceedings, the symposium was preceded by a conference comprising some 50 keynote and invited presenta- tions in honour of Prof. Erol Gelenbe, who started ISCIS back in 1986, and kept it going constantly with the help of several colleagues from Europe and Turkey.
This volume provides a compact yet broad view of recent developments in the Computer and Information sciences, and covers exciting research areas in the field including Green and Cloud computing, Performance Modelling, Cybersecurity, Big Data, and Smart Algorithm design for computer, biological and chemical systems. This symposium also highlights recent results from the EU FP7 NEMESYS Project.
We are very grateful to the authors of all of the submitted papers, and to the authors of accepted papers, for their contributions, and to the technical programme committee members who each evaluated several papers, without whom this exciting programme would not have been possible.
Rev Bras Ter Intensiva. 2012; 24(3):
Ontological aspects in the formalisation of the FrameNet inheritance relationship
International Journal of Metadata Semantics and Ontologies
ABSTRACT
Proposal of a New Method for de Novo DNA Sequence Assembly Using de Bruijn Graphs
Lecture Notes in Electrical Engineering, 2015
Ontological aspects in the formalisation of the FrameNet inheritance relationship
International Journal of Metadata, Semantics and Ontologies, 2015
ABSTRACT
Background / Purpose: In this study, we explore the de novo DNA fragment assembly problem modeled... more Background / Purpose: In this study, we explore the de novo DNA fragment assembly problem modeled as a k-mer graph. We also provide a theoretical basis for a new method of finding paths in these graphs, in order to simplify the complexity of the problem. Main conclusion: Here, we used a single procedure to find maximum matching in a bipartite version of the k-mer graph. We show that a matching in the bipartite graph is equivalent to paths in the original graph; these paths indicate an order of the given fragments so that a consensus sequence can be easily obtained. There are also polynomial algorithms to find maximum matching.
Improving Phosphopeptide/protein Identification using a New Data Mining Framework for MS/MS Spectra Preprocessing
Journal of Proteomics & Bioinformatics, 2009
Abstract Phosphopeptide/protein identification using tandem mass spectrometry (MS/MS) is a challe... more Abstract Phosphopeptide/protein identification using tandem mass spectrometry (MS/MS) is a challenging issue in proteomics research. In particular, phosphopeptides typically exhibit low intensity peaks of b and y ions in spectra when serine or threonine is phosphorylated. ...
Simulation of Scale Free Gene Regulatory Networks Based on Threshold Functions on GPU
2011 Simpasio em Sistemas Computacionais, 2011
Simulacc~ao in-silico do Sistema Imunol'ogico: Modelando o comportamento do Mast'ocito
NICeSim: An open-source simulator based on machine learning techniques to support medical research on prenatal and perinatal care decision making
Artificial Intelligence in Medicine, 2014
This paper describes NICeSim, an open-source simulator that uses machine learning (ML) techniques... more This paper describes NICeSim, an open-source simulator that uses machine learning (ML) techniques to aid health professionals to better understand the treatment and prognosis of premature newborns. The application was developed and tested using data collected in a Brazilian hospital. The available data were used to feed an ML pipeline that was designed to create a simulator capable of predicting the outcome (death probability) for newborns admitted to neonatal intensive care units. However, unlike previous scoring systems, our computational tool is not intended to be used at the patients bedside, although it is possible. Our primary goal is to deliver a computational system to aid medical research in understanding the correlation of key variables with the studied outcome so that new standards can be established for future clinical decisions. In the implemented simulation environment, the values of key attributes can be changed using a user-friendly interface, where the impact of each change on the outcome is immediately reported, allowing a quantitative analysis, in addition to a qualitative investigation, and delivering a totally interactive computational tool that facilitates hypothesis construction and testing. Our statistical experiments showed that the resulting model for death prediction could achieve an accuracy of 86.7% and an area under the receiver operating characteristic curve of 0.84 for the positive class. Using this model, three physicians and a neonatal nutritionist performed simulations with key variables correlated with chance of death. The results indicated important tendencies for the effect of each variable and the combination of variables on prognosis. We could also observe values of gestational age and birth weight for which a low Apgar score and the occurrence of respiratory distress syndrome (RDS) could be less or more severe. For instance, we have noticed that for a newborn with 2000 g or more the occurrence of RDS is far less problematic than for neonates weighing less. The significant accuracy demonstrated by our predictive model shows that NICeSim might be used for hypothesis testing to minimize in vivo experiments. We observed that the model delivers predictions that are in very good agreement with the literature, demonstrating that NICeSim might be an important tool for supporting decision making in medical practice. Other very important characteristics of NICeSim are its flexibility and dynamism. NICeSim is flexible because it allows the inclusion and deletion of variables according to the requirements of a particular study. It is also dynamic because it trains a just-in-time model. Therefore, the system is improved as data from new patients become available. Finally, NICeSim can be extended in a cooperative manner because it is an open-source system.
Predicting the Occurrence of Sepsis by In Silico Simulation
Lecture Notes in Computer Science, 2014
ABSTRACT From public health and clinical point of view, sepsis is a life-threatening complication... more ABSTRACT From public health and clinical point of view, sepsis is a life-threatening complication and its mechanisms are still not fully understood. This article claims that Multiagent Systems are suitable to help elucidate this phenomenon and that it is possible to carry out simulations that can be used in the observation of emergent behaviors, enabling a better understanding of the disease. Requirements for computational simulation of sepsis in AutoSimmune system are presented as also the simulation results. The results presented when using more aggressive pathogens are compatible with sepsis by simultaneously presenting symptoms such as fever, bacteria in the blood and Leukocytosis as reported in literature.
Theoretical Basis of a New Method for DNA Fragment Assembly in k-mer Graphs
2012 31st International Conference of the Chilean Computer Science Society, 2012
ABSTRACT The reduction of cost and running time provided by new generation sequencing technologie... more ABSTRACT The reduction of cost and running time provided by new generation sequencing technologies made possible the emergence of thousands of genome projects in the last few years. On the other hand, those technologies posed important computational challenges, pushing the advance of many research fields in computer science. Particularly, the de novo DNA fragment assembly, which is a fundamental stage in genome sequencing, is a complex problem that demands complex algorithms to solve it. Here, we provide a theoretical basis for the construction of a new method for de novo fragment assembly based on k-mer graphs. Our proposal encompasses many difficulties found in such problems using a unique procedure, in contrast with current methods that use several high-cost procedures to overcome the same issues. Furthermore, our approach is highly scalable since it allows the use of parallelism, being very suitable for solutions with graphics processing unit (GPU).
Revista Brasileira de Educação Médica, 2014
Redes Neurais Artificiais; -Medicina. ResUMO As transformações da prática médica nos últimos anos... more Redes Neurais Artificiais; -Medicina. ResUMO As transformações da prática médica nos últimos anos -sobretudo com a incorporação de novas tecnologias da informação -apontam a necessidade de ampliar as discussões sobre o processo ensino-aprendizagem na educação médica. A utilização de novas tecnologias computacionais no ensino médico tem demonstrado inúmeras vantagens no processo de aquisição de habilidades para a identificação e a resolução de problemas, o que estimula a criatividade, o senso crítico, a curiosidade e o espírito científico. Nesse contexto, ganham destaque as Redes Neurais Artificiais (RNA) -sistemas computacionais cuja estrutura matemática é inspirada no funcionamento do cérebro humano -, as quais têm sido úteis no processo ensino-aprendizagem e na avaliação de estudantes de Medicina. Com base nessas ponderações, o escopo da presente comunicação é revisar aspectos da aplicação das RNA na educação médica.
Uploads
Papers by Fabio Cerqueira
This year the conference attracted 82 submissions from 21 countries—with contributions coming mostly from Europe, America and the Far East—out of which 39 carefully refereed proposals were selected, along with two Invited Papers, for inclusion in the proceedings. Several other Invited Papers were presented orally.
In addition to the papers that are contained in these proceedings, the symposium was preceded by a conference comprising some 50 keynote and invited presenta- tions in honour of Prof. Erol Gelenbe, who started ISCIS back in 1986, and kept it going constantly with the help of several colleagues from Europe and Turkey.
This volume provides a compact yet broad view of recent developments in the Computer and Information sciences, and covers exciting research areas in the field including Green and Cloud computing, Performance Modelling, Cybersecurity, Big Data, and Smart Algorithm design for computer, biological and chemical systems. This symposium also highlights recent results from the EU FP7 NEMESYS Project.
We are very grateful to the authors of all of the submitted papers, and to the authors of accepted papers, for their contributions, and to the technical programme committee members who each evaluated several papers, without whom this exciting programme would not have been possible.
This year the conference attracted 82 submissions from 21 countries—with contributions coming mostly from Europe, America and the Far East—out of which 39 carefully refereed proposals were selected, along with two Invited Papers, for inclusion in the proceedings. Several other Invited Papers were presented orally.
In addition to the papers that are contained in these proceedings, the symposium was preceded by a conference comprising some 50 keynote and invited presenta- tions in honour of Prof. Erol Gelenbe, who started ISCIS back in 1986, and kept it going constantly with the help of several colleagues from Europe and Turkey.
This volume provides a compact yet broad view of recent developments in the Computer and Information sciences, and covers exciting research areas in the field including Green and Cloud computing, Performance Modelling, Cybersecurity, Big Data, and Smart Algorithm design for computer, biological and chemical systems. This symposium also highlights recent results from the EU FP7 NEMESYS Project.
We are very grateful to the authors of all of the submitted papers, and to the authors of accepted papers, for their contributions, and to the technical programme committee members who each evaluated several papers, without whom this exciting programme would not have been possible.