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]
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.
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.
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.
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.
Return to main page
Last modified: 2012.4.26