Fabio Ribeiro Cerqueira

Demoting redundant features to improve the discriminatory ability in cancer data

The identification of a set of relevant but not redundant features is an important first step in building predictive and diagnostic models from biomedical data sets. Most commonly, individual features are ranked in terms of a quality criterion, out of which the best (first) k features are selected. However, feature ranking methods do not sufficiently account for interactions and correlations between the features. Thus, redundancy is likely to be encountered in the selected features. We present a new algorithm, termed Redundancy Demoting (RD), that takes an arbitrary feature ranking as input, and improves this ranking by identifying redundant features and demoting them to positions in the ranking in which they are not redundant. Redundant features are those that are correlated with other features and not relevant in the sense that they do not improve the discriminatory ability of a set of features. Experiments on two cancer data sets, one melanoma image data set and one lung cancer microarray data set, show that our algorithm greatly improves the feature rankings provided by the methods information gain, ReliefF and Students t-test in terms of predictive power.

MUDE: a new approach for optimizing sensitivity in the target-decoy search strategy for large-scale peptide/protein identification.

The target-decoy search strategy has been successfully applied in shotgun proteomics for validating peptide and protein identifications. If, on one hand, this method has proven to be very efficient for error estimation, on the other hand, little attention has been paid to the resulting sensitivity. Only two scores are normally used and thresholds are explored in a very simplistic way. In this work, a multivariate decoy analysis is described, where many quality parameters are considered. This analysis is treated in our approach as an optimization problem for sensitivity maximization. Furthermore, an efficient heuristic is proposed to solve this problem. Experiments comparing our method, termed MUDE (multivariate decoy database analysis), with traditional bivariate decoy analysis and with Peptide/ProteinProphet showed that our procedure significantly enhances the retrieved number of identifications when comparing the same false discovery rates. Particularly for phosphopeptide/protein identifications, we could demonstrate more than a two-fold increase in sensitivity compared with the Trans-Proteomic Pipeline tools.

Modelos de tomada de decisão em bioética clínica: apontamentos para a abordagem computacional

Bioethics has become over the recent decades a central question to clinical practice, due to the fact that it provides theoretical tools for decision making in health care. The issue that arises concerns how to know whether the decision made is the most appropriate, considering that a clinic decision – whether working in primary, secondary, or tertiary care – must be accurate from both the technical and the ethical point of views. As a result, different models for decision making in clinical bioethics have been presented in the literature. Based on these considerations, the objective of this article is to point important issues about (i) decision making in the field of clinical bioethics and (ii) the possibilities of computational approaches to assist such decisions.Models of decision making in clinical bioethics: notes for a computational approach Bioethics has become over the recent decades a central question to clinical practice, due to the fact that it provides theoretical tools for decision making in health care. The issue that arises concerns how to know whether the decision made is the most appropriate, considering that a clinic decision – whether working in primary, secondary, or tertiary care – must be accurate from both the technical and the ethical point of views. As a result, different models for decision making in clinical bioethics have been presented in the literature. Based on these considerations, the objective of this article is to point important issues about (i) decision making in the field of clinical bioethics and (ii) the possibilities of computational approaches to assist such decisions.

NICeSim: An open-source simulator based on machine learning techniques to support medical research on prenatal and perinatal care decision making

OBJECTIVE 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. METHODS 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. RESULTS 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. CONCLUSIONS 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.

Linfócitos T CD4+CD25+ e a regulação do sistema imunológico: perspectivas para o entendimento fisiopatológico da sepse

The systemic inflammatory response represents the core pathogenic event of sepsis, underlying clinical manifestations and laboratory findings in patients. Numerous studies have shown that CD4+CD25+ T lymphocytes, also known as regulatory T lymphocytes (Treg), participate in the development of sepsis due to their ability to suppress the immune response. The present article discusses the role of Treg lymphocytes in sepsis based on a specific search strategy (Latin American and Caribbean Health Sciences / Literatura Latino-americana e do Caribe em Ciencias da Saude - LILACS, PubMed, and Scientific Electronic Library Online - SciELO) focusing on two main topics: the participation of Treg cells in inflammation and immunity as well as perspectives in the computational physiological investigation of sepsis.

As redes neurais artificiais e o ensino da medicina

The transformations that medical practice has undergone in recent years - especially with the incorporation of new information technologies - point to the need to broaden discussions on the teaching-learning process in medical education. The use of new computer technologies in medical education has shown many advantages in the process of acquiring skills in problem solving, which encourages creativity, critical thinking, curiosity and scientific spirit. In this context, it is important to highlight artificial neural networks (ANN) - computer systems with a mathematical structure inspired by the human brain - which proved to be useful in the evaluation process and the acquisition of knowledge among medical students. The purpose of this communication is to review aspects of the application of ANN in medical education.

Personalized epilepsy seizure detection using random forest classification over one-dimension transformed EEG data

This work presents a computational method for improving seizure detection for epilepsy diagnosis. Epilepsy isthe second most common neurological disease impacting between 40 and 50 million of patients in the world and it proper diagnosis using electroencephalographic signals implies a long and expensive process which involves medical specialists. The proposed system is a patient-dependent offline system which performs an automatic detection of seizures in brainwaves applying a random forest classifier. Features are extracted using one-dimension reduced information from a spectro-temporal transformation of the biosignals which pass through an envelope detector. The performance of this method reached 97.12% of specificity, 99.29% of sensitivity, and a 0.77 h−1 false positive rate. Thus, the method hereby proposed has great potential for diagnosis support in clinical environments.

Mirnacle: machine learning with SMOTE and random forest for improving selectivity in pre-miRNA ab initio prediction

BackgroundMicroRNAs (miRNAs) are key gene expression regulators in plants and animals. Therefore, miRNAs are involved in several biological processes, making the study of these molecules one of the most relevant topics of molecular biology nowadays. However, characterizing miRNAs in vivo is still a complex task. As a consequence, in silico methods have been developed to predict miRNA loci. A common ab initio strategy to find miRNAs in genomic data is to search for sequences that can fold into the typical hairpin structure of miRNA precursors (pre-miRNAs). The current ab initio approaches, however, have selectivity issues, i.e., a high number of false positives is reported, which can lead to laborious and costly attempts to provide biological validation. This study presents an extension of the ab initio method miRNAFold, with the aim of improving selectivity through machine learning techniques, namely, random forest combined with the SMOTE procedure that copes with imbalance datasets.ResultsBy comparing our method, termed Mirnacle, with other important approaches in the literature, we demonstrate that Mirnacle substantially improves selectivity without compromising sensitivity. For the three datasets used in our experiments, our method achieved at least 97% of sensitivity and could deliver a two-fold, 20-fold, and 6-fold increase in selectivity, respectively, compared with the best results of current computational tools.ConclusionsThe extension of miRNAFold by the introduction of machine learning techniques, significantly increases selectivity in pre-miRNA ab initio prediction, which optimally contributes to advanced studies on miRNAs, as the need of biological validations is diminished. Hopefully, new research, such as studies of severe diseases caused by miRNA malfunction, will benefit from the proposed computational tool.

Pro-Inflammatory Cytokines in Sepsis: Biological Studies and Prospects From In Silico Research

Sepsis is one of the leading causes of death in intensive care units (ICUs) and is responsible for thousands of annual deaths worldwide. The pro-inflammatory cytokines are necessary for the control of infection and are the primary focus of this paper. Due to their central role in the pathogenesis of sepsis, more emphasis is needed on the use of cytokine as biomarkers. Implementation of the cytokines in the AutoSimmune for immune system simulations may improve understanding of aspects of the physiopathology of disease in humans. We present the principal aspects of the pathogenesis of the pro-inflammatory response in sepsis and the possibilities of their modulation in order to alter the course of this illness. We highlight the main pro-inflammatory cytokines that may be used as biomarkers in clinical practice. We also discuss the perspectives of sepsis in silico investigation, using the AutoSimmune computational system. Sepsis remains a true challenge in contemporary clinical practice, especially in terms of diagnosis, therapeutics, and prognosis. A greater understanding of inflammation in sepsis – especially in relation to cellular and molecular participation in the development of the morbid process – has the potentiality for the development of new investigative methods and outcome prediction, elements that may aid in offering good patient care.

Geminivirus data warehouse: a database enriched with machine learning approaches

BackgroundThe Geminiviridae family encompasses a group of single-stranded DNA viruses with twinned and quasi-isometric virions, which infect a wide range of dicotyledonous and monocotyledonous plants and are responsible for significant economic losses worldwide. Geminiviruses are divided into nine genera, according to their insect vector, host range, genome organization, and phylogeny reconstruction. Using rolling-circle amplification approaches along with high-throughput sequencing technologies, thousands of full-length geminivirus and satellite genome sequences were amplified and have become available in public databases. As a consequence, many important challenges have emerged, namely, how to classify, store, and analyze massive datasets as well as how to extract information or new knowledge. Data mining approaches, mainly supported by machine learning (ML) techniques, are a natural means for high-throughput data analysis in the context of genomics, transcriptomics, proteomics, and metabolomics.ResultsHere, we describe the development of a data warehouse enriched with ML approaches, designated geminivirus.org. We implemented search modules, bioinformatics tools, and ML methods to retrieve high precision information, demarcate species, and create classifiers for genera and open reading frames (ORFs) of geminivirus genomes.ConclusionsThe use of data mining techniques such as ETL (Extract, Transform, Load) to feed our database, as well as algorithms based on machine learning for knowledge extraction, allowed us to obtain a database with quality data and suitable tools for bioinformatics analysis. The Geminivirus Data Warehouse (geminivirus.org) offers a simple and user-friendly environment for information retrieval and knowledge discovery related to geminiviruses.