Ulisses Braga-Neto's Research


Research Areas

  1. Optimal State and Parameter Estimation for Boolean Dynamical Systems
  2. Discrete Prediction and Inference of Regulatory Networks
  3. Small-Sample Classification and Error Estimation
  4. Applications in Cancer Proteomic Biomarker Discovery and Validation
  5. Applications in Modeling Infectious Disease Processes


  1. Optimal State and Parameter Estimation for Boolean Dynamical Systems

    This research concerns a novel signal model for discrete-time Boolean dynamical systems under noisy observational conditions, which extends and unifies previously proposed models for biochemical regulatory networks, such as Boolean Network with perturbation (BNp) model and the Probabilistic Boolean Network (PBN) model. This novel signal model and its optimal state estimator, called the Boolean Kalman Filter, was introduced in a recent publication (see below). Joint estimation of state and parameters is considered for network inference under incomplete pathway knowledge. Current work involves several extensions and open research problems regarding this methodology, and its applicationin the inference and control of biochemical regulatory networks.

    Conference Paper:

    U.M. Braga-Neto, "Optimal State Estimation for Boolean Dynamical Systems," Proceedings of the 45th Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, November 2011. [Preprint]

  2. Discrete Prediction and Inference of Regulatory Networks

    This research concerns the modeling and inference of Boolean regulatory network models via the discrete Coefficient of Determination (CoD), with the goal of modeling complex dynamical processes occurring in living tissue, such as canalization of regulatory pathways and response to external stimuli.

    Funding: National Science Foundation, Award CCF-0845407

    Journal Papers:

    T. Chen and U.M. Braga-Neto, "Exact Performance of CoD Estimators in Discrete Prediction," EURASIP Journal on Advances in Signal Processing (JASP), Special Issue on Genomic Signal Processing, Volume 2010, Article ID 487893, 13 pages, 2010. doi:10.1155/2010/487893 [Hindawi Open Access]

    D.C. Martins, Jr., U.M. Braga-Neto, R.F. Hashimoto, M.L. Bittner and E.R. Dougherty, "Intrinsically Multivariate Predictive Genes," IEEE Journal of Selected Topics in Signal Processing, Vol. 2, No. 3, June 2008, pp. 424-439. [IEEE Explore] [Preprint]

    Conference Papers:

    T. Chen and U.M. Braga-Neto, "Sample-Based Estimators for the Intrinsically Multivariate Prediction Score," Proceedings of IEEE International Workshop on Genomic Signal Processing and Statistics (GENSIPS'2011), San Antonio, TX, December 2011.

    T. Chen and U.M. Braga-Neto, "Maximum Likelihood Estimation of the Binary Coefficient of Determination," Proceedings of the 45th Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, November 2011.

    T. Chen and Ulisses Braga-Neto, "Maximum Likelihood Estimation of the Binary Coefficient of Determination," Eighth Annual Conference of the MidSouth Computational Biology and Bioinformatics Society (MCBIOS'2011), College Station, TX, April 2011.

    T. Chen and U.M. Braga-Neto, "Approximate expressions for the variances of non-randomized error estimators and CoD estimators for the discrete histogram rule," Proceedings of IEEE International Workshop on Genomic Signal Processing and Statistics (GENSIPS'2009), Cold Spring Harbor, NY, November 2010.

    D.C. Martins, Jr., U.M. Braga-Neto, M.L. Bittner and E.R. Dougherty, "Network Properties of Intrinsically Multivariate Predictive Genes," Proceedings of VI IEEE International Workshop on Genomic Signal Processing and Statistics (GENSIPS'2008), Phoenix, AZ, June 2008.

  3. Small-Sample Classification and Error Estimation

    The research goals of this proposal concern the solution of significant computational and statistical problems in classification error estimation, with the purpose of improving the assessment of predictions made in classification and inference of genomic and proteomic signals based on small samples in high-dimensional spaces. This research critically impacts the discovery of reliable molecular biomarkers for disease diagnosis and prognosis in Genomics and Proteomics applications that rely on pattern recognition approaches. Some of the highlights of this research include the development of a small-RMS, small-sample, kernel-based error estimator ("boltered error estimation"), the detailed study of the variance of cross-validation methods in small-sample settings, and the analytical study of higher moments and sampling distributions of error estimators for Linear Discriminant Analysis.

    Funding: National Science Foundation, Award CCF-0845407

    Journal Papers:

    A. Zollanvari, U.M. Braga-Neto and E.R. Dougherty, "Exact representation of the second-order moments for resubstitution and leave-one-out error estimation for linear discriminant analysis in the univariate heteroskedastic Gaussian model," Pattern Recognition, Vol. 45, No. 2, February 2012, pp. 908-917. [Preprint]

    C. Sima, T.T. Vu, U.M. Braga-Neto and E.R. Dougherty, "High-Dimensional Bolstered Error Estimation," Bioinformatics, Vol. 27, No. 21, September 2011, pp. 3056-3064. [PubMed]

    A. Zollanvari, U.M. Braga-Neto and E.R. Dougherty, "Analytic Study of Performance of Error Estimators for Linear Discriminant Analysis," IEEE Transactions on Signal Processing, Vol. 59, No. 9, September 2011, pp. 4238-4255. [IEEE Explore] [Preprint]

    E.R. Dougherty, A. Zollanvari and U.M. Braga-Neto, "The Illusion of Distribution-Free Small-Sample Classification in Genomics," Current Genomics, Vol. 12, No. 5, August 2011, pp. 333-341. [Preprint]

    T.T. Vu and U.M. Braga-Neto, "Small-Sample Error Estimation for Bagged Classification Rules," EURASIP Journal on Advances in Signal Processing (JASP), Special Issue on Genomic Signal Processing. Volume 2010, Article ID 548906, 12 pages, 2010. doi:10.1155/2010/548906 [Hindawi Open Access]

    A. Zollanvari, U.M. Braga-Neto and E.R. Dougherty, "Joint Sampling Distribution Between Actual and Estimated Classification Errors for Linear Discriminant Analysis," IEEE Transactions on Information Theory, Vol. 56, No. 2, February 2010, pp. 784-804. [Preprint]

    U.M. Braga-Neto and E.R. Dougherty, "Exact Correlation between Actual and Estimated Errors in Discrete Classification," Pattern Recogition Letters, Vol. 31, No. 5, April 2010, pp. 407-412. [Preprint]

    E.R. Dougherty, C. Sima, J. Hua, B. Hanczar and U.M. Braga-Neto, "Performance of Error Estimators for Classification," Current Bioinformatics, Vol. 5, No. 1, March 2010, pp. 53-67. [Preprint]

    Y. Sun, U.M. Braga-Neto and E.R. Dougherty, "Impact of Missing Value Imputation on Classification for DNA Microarray Gene Expression Data - A Model-Based Study," EURASIP Journal on Bioinformatics and Systems Biology, Volume 2009, Article ID 504069, November 2009, 17 pages, doi:10.1155/2009/504069 [PubMed] [Hindawi Open Access]

    U.M. Braga-Neto, "Classification and Error Estimation for Discrete Data," Current Genomics, Vol. 10, No. 7, November 2009, pp. 446-462. [PubMed] [Preprint]

    A. Zollanvari, U.M. Braga-Neto and E.R. Dougherty, "On the Sampling Distribution of Resubstitution and Leave-One-Out Error Estimators for Linear Classifiers," Pattern Recognition, Vol. 42, No. 11, November 2009, pp. 2705-2723. [Preprint]

    U.M. Braga-Neto, "Fads and Fallacies in the Name of Small-Sample Microarray Classification," IEEE Signal Processing Magazine, Special Issue on Signal Processing Methods in Genomics and Proteomics, Vol. 24, No. 1, January 2007, pp. 91-99. [IEEE Explore] [Preprint]

    Q. Xu, J. Hua, U.M. Braga-Neto, Z. Xiong, E. Suh and E.R. Dougherty, "Confidence Intervals for the True Classification Error Conditioned on the Estimated Error," Technology in Cancer Research and Treatment, Vol. 5, No. 6, December 2006, pp. 579-590. [PubMed]

    E. Dougherty and U.M. Braga-Neto, "Epistemology of Computational Biology: Mathematical Models and Experimental Prediction as the Basis of Their Validity," Journal of Biological Systems, Vol. 14, No. 1, March 2006, pp. 65-90.

    C. Sima, S. Attoor, U.M. Braga-Neto, J. Lowey, E. Suh and E. Dougherty, "Impact of Error Estimation on Feature-Selection Algorithms," Pattern Recognition, Vol. 38, No. 12, December 2005, pp. 2472-2482.

    U.M. Braga-Neto and E. Dougherty, "Exact Performance of Error Estimators for Discrete Classifiers," Pattern Recognition, Vol. 38, No. 11, November 2005, pp. 1799-1814. [Preprint]

    C. Sima, U.M. Braga-Neto and E. Dougherty, "Superior Feature-Set Ranking for Small Samples Using Bolstered Error Estimation," Bioinformatics, Vol. 21, No. 7, April 2005, pp. 1046-1054. [PubMed]

    U.M. Braga-Neto and E. Dougherty, "Bolstered Error Estimation," Pattern Recognition, Vol. 37, No. 6, June 2004, pp. 1267-1281. [Preprint]

    U.M. Braga-Neto and E. Dougherty, "Is Cross-Validation Valid for Small-Sample Microarray Classification?" Bioinformatics, Vol. 20, No. 3, February 2004, pp. 374-380. [PubMed]

    U.M. Braga-Neto, R. Hashimoto, E. Dougherty, D. Nguyen and R. Carroll, "Is Cross-Validation Better Than Resubstitution for Ranking Genes?" Bioinformatics, Vol. 20, No. 2, January 2004, pp. 253-258. [PubMed]

    Book Chapter:

    U.M. Braga-Neto and E. Dougherty, "Classification," In Genomic Signal Processing and Statistics, Edited by E. Dougherty, I. Shmulevich, J. Chen and Z. J. Wang, EURASIP Book Series on Signal Processing and Communication, Hindawi Publishing Corporation, 2005. [Preprint]
    Note: The preprint PDF contains the correct Figures 3.8 and 3.9 (see Errata).

    Conference Papers:

    E. Atashpaz-Gargari, C. Sima, U.M. Braga-Neto and E.R. Dougherty, Relationship Between the Accuracy of Classifier Error Estimation and Distribution Complexity," Proceedings of IEEE International Workshop on Genomic Signal Processing and Statistics (GENSIPS'2011), San Antonio, TX, December 2011.

    S. Afra and U.M. Braga-Neto, "Peaking Phenomenon and Error Estimation for Support Vector Machines," Proceedings of IEEE International Workshop on Genomic Signal Processing and Statistics (GENSIPS'2011), San Antonio, TX, December 2011.

    E. Atashpaz-Gargari, C. Sima, U.M. Braga-Neto and E.R. Dougherty, Relationship Between the Accuracy of Classifier Error Estimation and Distribution Complexity," Eighth Annual Conference of the MidSouth Computational Biology and Bioinformatics Society (MCBIOS'2011), College Station, TX, April 2011.

    A. Zollanvari, U.M. Braga-Neto and E.R. Dougherty, "RMS bounds and sample size considerations for error estimation in linear discriminant analysis," Proceedings of VIII IEEE International Workshop on Genomic Signal Processing and Statistics (GENSIPS'2009), Cold Spring Harbor, NY, November 2010.

    C. Sima, T.T. Vu, U.M. Braga-Neto and E.R. Dougherty, "Bolstered Error Estimation with Feature Selection," Proceedings of VII IEEE International Workshop on Genomic Signal Processing and Statistics (GENSIPS'2009), Minneapolis, MN, May 2009.

    A. Zollanvari, U.M. Braga-Neto and E.R. Dougherty, "Sample Size Calculation from Specified RMS of the Resubstitution Error for Linear Classifiers," Proceedings of VII IEEE International Workshop on Genomic Signal Processing and Statistics (GENSIPS'2009), Minneapolis, MN, May 2009.

    U.M. Braga-Neto, "An Asymptotically-Exact Expression for the Variance of Classification Error for the Discrete Histogram Rule," Proceedings of VI IEEE International Workshop on Genomic Signal Processing and Statistics (GENSIPS'2008), Phoenix, AZ, June 2008.

    T.T. Vu, U.M. Braga-Neto and E.R. Dougherty, "Preliminary Study on Bolstered Error Estimation in High-Dimensional Spaces," Proceedings of VI IEEE International Workshop on Genomic Signal Processing and Statistics (GENSIPS'2008), Phoenix, AZ, June 2008.

    U.M. Braga-Neto, Error Estimation Critically Impacts "Feature Selection in Genomics and Proteomics Applications," Presented at The Fifth Annual Conference of the MidSouth Computational Biology and Bioinformatics Society (MCBIOS 2008), Oklahoma City, OK, February 2008.

    U.M. Braga-Neto, "Why Error Estimation is Fundamental to the Estimation of Regulatory Networks," Presented at the Models for Genetic Regulatory Network Workshop, College Station, TX, November 2005.

    U.M. Braga-Neto, Small-Sample Error Estimation: Mythology Versus Mathematics. Proceedings of SPIE Vol. 5916: Mathematical Methods in Pattern and Image Analysis. Edited by J.T. Astola, I. Tabus and J. Barrera, San Diego, CA, August 2005.

  4. Applications in Cancer Proteomic Biomarker Discovery and Validation

    This work, which is developed in collaboration with Drs. Edward Dougherty (Texas A&M), Michael Bittner (Translational Genomics), and Michelle Zhang (University of Texas at San Antonio), concerns the discovery and validation of proteomic biomarkers from protein-expression data, particularly data from high-throughput Liquid Chromatography-Mass Spectrometry (LC-MS) assays. This is part of the Partnesrhip for Personalized Medicine (PPM) cancer biomarker project, and takes advantage of TGen's state-of-the-art facilities for LC-MS Proteomics. An early highlight of this research was the recent development of an accurate Bayesian method for peptide detection in LC-MS data, called BPDA.

    Funding: Partnership for Personal Medicine, TGen Contract C08-00904

    Journal Papers:

    Y. Sun, U.M. Braga-Neto and E.R. Dougherty, "Modeling and systematic analysis of the LC-MS proteomics pipeline," In press, BMC Genomics, GENSIPS'2011 Special Issue, 2012.

    Y. Sun, J. Zhang, U.M. Braga-Neto and E.R. Dougherty, "BPDA2d -- A 2D global optimization based Bayesian peptide detection algorithm for LC-MS," Bioinformatics, 2011 Dec 6 (Epub ahead of print) [PubMed]

    Y. Sun, J. Zhang, U.M. Braga-Neto and E.R. Dougherty, "BPDA - a Bayesian peptide detection algorithm for mass spectrometry," BMC Bioinformatics, Vol. 11, September 2010, p. 490, doi:10.1186/1471-2105-11-490 [PubMed] [BMC Open Access]

    T.T. Vu and U.M. Braga-Neto, "Is Bagging Effective in the Classification of Small-Sample Genomic and Proteomic Data?" EURASIP Journal on Bioinformatics and Systems Biology, Special Issue on Applications of Signal Processing Techniques to Bioinformatics, Genomics, and Proteomics, Volume 2009, Article ID 158368, 10 pages, 2009. doi:10.1155/2009/158368 [PubMed] [Hindawi Open Access]

    Conference Papers:

    Y. Sun, U.M. Braga-Neto and E.R. Dougherty, "Modeling and systematic analysis of LC-MS proteomics pipeline," Proceedings of IEEE International Workshop on Genomic Signal Processing and Statistics (GENSIPS'2011), San Antonio, TX, December 2011.

    E. Atashpaz-Gargari, U.M. Braga-Neto and E.R. Dougherty, "Multiple Reaction Monitoring: Modeling and Systematic Analysis." Proceedings of IEEE International Workshop on Genomic Signal Processing and Statistics (GENSIPS'2011), San Antonio, TX, December 2011.

    Z. Zhang, Y. Sun, U.M. Braga-Neto, E.R. Dougherty and J. Zhang, "A parallel programming framework with Markovian messaging for LCMS peptide peak detection." Proceedings of IEEE International Conference on Bioinformatics and Biomedicine (BIBM'2011), Atlanta, GA, November 2011.

    Y. Sun, J. Zhang, U.M. Braga-Neto and E.R. Dougherty, "BPDA2D - An improved Bayesian peptide detection algorithm for Mass Spectrometry," 59th ASMS Conference on Mass Spectrometry and Allied Topics, Denver, Colorado, June 2001.

    Y. Sun, J. Zhang, U.M. Braga-Neto and E.R. Dougherty, "BPDA+ - An improved Bayesian peptide detection algorithm for Mass Spectrometry," Eighth Annual Conference of the MidSouth Computational Biology and Bioinformatics Society (MCBIOS'2011), College Station, TX, April 2011.

  5. Applications in Modeling Infectious Disease Processes

    This work is part of a long-standing collaboration with Dr. Ernesto Marques' research groups at the at the Johns Hopkins Medical School (Dr. Marques' previous affiliation), the University of Pittsburgh's Center for Vaccine Research, and the Oswaldo Cruz Foundation (FIOCRUZ), in Recife, Brazil. The focus of this collaboration is the application of Genomic Signal Processing methodology to the study of infectious diseases, for vaccine design, discovery of diagnostic/prognostic markers, and biodefense efforts, using data from a series of human patient cohort studies in dengue, yellow fever, hepatitis A, HIV-1, and rabis being conducted at FIOCRUZ in Brazil. Highlights of this research include identification of gene-expression, SNP, and blood-serum biomarkers for prognosis of a serious form of dengue fever, known as dengue hemorrhagic fever (DHF), and the development of a classifier for inexpensively diagnosing primary or secondary dengue infections using a single blood sample.

    Funding: National Science Foundation, Award CCF-0845407

    Journal Papers:

    A.B. Melo, M. Silva, C. Magalhaes, L.H.V.G. Gil, E.M.F. Carvalho, G.R. Bertani, U.M. Braga-Neto, E.T.A. Marques and M.T. Cordeiro, "Description of a Prospective 17DD Yellow Fever Vaccinee Cohort in Recife, Brazil," The American Journal of Tropical Medicine and Hygiene, Vol. 85, No. 4, Ocotber 2011, pp. 739-747. [PubMed]

    E.J.M. Nascimento, U.M. Braga-Neto, C. Calvazara, A.L. Gomes, F. Abath, B. Acioli, C.A.A. Brito, M.T. Cordeiro, A.M. Silva, C. Magalhaes, R. Andrade, L.H.V.G. Gil and E.T.A. Marques, Jr., "Gene Expression Profiling During Acute Stage of Dengue Infection," PLoS ONE, Vol. 4, No. 11, November 2009, p. e7892, doi:10.1371/journal.pone.0007892 [PubMed] [PLoS Open Access]

    E.J.M. Nascimento, A.M. Silva, M.T. Cordeiro, C.A.A. Brito, L.H.V.G. Gil, Ulisses Braga-Neto and E.T.A. Marques, Jr., "Alternative Complement Pathway Deregulation Is Correlated with Dengue Severity," PLoS ONE, Vol. 4, No. 8, August 2009, p. e6782. [PubMed] [PLoS Open Access]

    M.T. Cordeiro, U.M. Braga-Neto, R.M.R. Nogueira and E.T.A. Marques, Jr., "Reliable classifier to differentiate primary and secondary acute dengue infection based on IgG ELISA," PLoS ONE, Vol. 4, No. 4, April 2009, p. e4945. [PubMed] [PLoS Open Access]

    B. Acioli-Santos, L. Segat, R. Dhalia, C.A.A. Brito, U.M. Braga-Neto, E.T.A. Marques and S. Crovella, "MBL2 Gene Polymorphisms Protect Against Development of Thrombocytopenia Associated with Severe Dengue Phenotype," Human Immunology, Vol. 69, No. 2, February 2008, pp. 122-128. [PubMed]

    U.M. Braga-Neto and E.A.T. Marques, Jr., "From Functional Genomics to Functional Immunomics: New Challenges, Old Problems, Big Rewards," PLoS Computational Biology, Vol. 2, No. 7, July 2006, p. e81 [PubMed] [PLoS Open Access]

    Book Chapter:

    R. Dhalia, L. Gil, E. Nascimento, U.M. Braga-Neto and E.T.A. Marques Jr., "Epitope Mapping: Rational Search for the Development of vaccines Against Chronic Diseases" (in Portuguese), In Epidemiology, Policy, and Determining Factors of Chronic Diseases in Brazil (in Portuguese). Edited by Eduardo Freese. Editora Universitária UFPE, Recife, Brazil, 2006, pp. 321-340.

    Conference Papers:

    E. Nascimento, U.M. Braga-Neto, C. Calzavara-Silva, A. Gomes F. Abath, C Brito, M.Cordeiro, A. Silva, C. Magalhaes, R. Andrade, L. Gil and E.T.A. Marques, Jr., "Gene expression profiling during acute stage of dengue infection can predict patient outcome," Proceedings of First Pan American Dengue Research Network Meeting, Recife, Brazil, July 2008.

    E. Nascimento, A. Silva, B. Acioli-Silva, C. Calzavara-Silva, U.M. Braga-Neto, M. Cordeiro, C. Brito, M. Magalhaes, L. Gil and E.T.A. Marques, Jr., "Analysis of Complement System Reveals That Increased Alternative Pathway Activation Is correlated With Dengue Severity," Proceedings of First Pan American Dengue Research Network Meeting, Recife, Brazil, July 2008.

    B. Acioli-Silva, E. Nascimento, F. Pastor, C. Calzavara-Silva, A. Gomes, A. Silva, M. Cordeiro, U.M. Braga-Neto, S. Crovella and E.T.A. Marques, Jr., "Complement Factor H (CFH) Promoter Polymorphism C-257T is Correlated with High Levels of CFH mRNA and Protein Expression and Resistance to Dengue Hemorrhagic Fever," Proceedings of First Pan American Dengue Research Network Meeting, Recife, Brazil, July 2008.

    E. Nascimento, U.M. Braga-Neto, M. Magalhaes, C. Brito, M. Cordeiro, A. Silva and E.T.A. Marques, Jr., "HLA-C alleles are associated with resistance to sequential dengue infection and clinical outcomes," Proceedings of First Pan American Dengue Research Network Meeting, Recife, Brazil, July 2008.

    M. Pereira, A. Pastor, B. Acioli-Santos, L. Segat, R. Dhalia, U.M. Braga-Neto, E.T.A. Marques, Jr. and S. Crovella, "MBL2 gene polymorphisms protect against severe dengue manifestation associated with thrombocytopenia phenotype development," Proceedings of XVIII Brazilian Virology Meeting, Buzios, Brazil, 2007.

    L. Alencar, A. Barbosa, K. Barbosa, M. Tenorio, C. Brito, P. Chiklinkar, E. Nascimento, R. Dhalia, U.M. Braga-Neto, E.T.A. Marques, Jr., "Analysis of epitope mapping of the dengue-3 envelope protein on dengue patients: comparison between the enzyme-linked immunospot (elispot) and the multipred epitope predictive computational program," Proceedings of XVII Brazilian Virology Meeting, Campos do Jordao, Brazil, 2006.


Home Return to main page

Last modified: 2012.4.26