Hongbao Cao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Hongbao Cao has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Yu-Ping Wang
Department of Biomedical Engineering, Tulane University, New Orleans, LA, USA
3 shared publications - Hong-Wen Deng
School of Medicine, Tulane University, New Orleans, USA
2 shared publications - Junbo Duan
Department of Biomedical Engineering, Tulane University, New Orleans, USA
1 shared publication - Marilyn M. Li
Department of Molecular and Human Genetics, Baylor College of Medicine, One Baylor Plaza, BCM 320, Houston, TX 77030, USA
1 shared publication - Shu-Feng Lei
Center for Genetic Epidemiology and Genomics, School of Public Health, Medical College of Soochow University, Suzhou, 215123, Jiangsu, People's Republic of China.
1 shared publication - Wenlong Tang
Department of Biomedical Engineering, Tulane University, New Orleans, LA, USA.
1 shared publication
Latest Publications
- 1 August 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 109 (1094687X) , 5541-5544
Identification of genes for complex diseases by integrating multiple types of genomic data
Combining multi-types of genomic data for integrative analyses can take advantage of complementary information and thus can have higher power to identify genes/variables that would otherwise be impossible with individual data analysis. Here we proposed a sparse representation based clustering (SRC) method for integrative data analyses, and applied the SRC method to the integrative analysis of 376821 SNPs in 200 subjects (100 cases and 100 controls) and expression data for 22283 genes in 80 subjects (40 cases and 40 controls) to identify significant genes for osteoporosis (OP). Comparing our results with previous studies, we identified some genes known related to OP risk, as well as some uncovered novel osteoporosis susceptible genes (`DICER1', `PTMA', etc.) that may function importantly in osteoporosis etiology. In addition, the SRC method identified genes can lead to higher accuracy for the identification of osteoporosis subjects when compared with the traditional T-test and Fisher-exact test, which further validate the proposed SRC approach for integrative analysis.
- 1 August 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 109 (1094687X) , 5541-5544
Identification of genes for complex diseases by integrating multiple types of genomic data
Combining multi-types of genomic data for integrative analyses can take advantage of complementary information and thus can have higher power to identify genes/variables that would otherwise be impossible with individual data analysis. Here we proposed a sparse representation based clustering (SRC) method for integrative data analyses, and applied the SRC method to the integrative analysis of 376821 SNPs in 200 subjects (100 cases and 100 controls) and expression data for 22283 genes in 80 subjects (40 cases and 40 controls) to identify significant genes for osteoporosis (OP). Comparing our results with previous studies, we identified some genes known related to OP risk, as well as some uncovered novel osteoporosis susceptible genes (`DICER1', `PTMA', etc.) that may function importantly in osteoporosis etiology. In addition, the SRC method identified genes can lead to higher accuracy for the identification of osteoporosis subjects when compared with the traditional T-test and Fisher-exact test, which further validate the proposed SRC approach for integrative analysis.
- 30 May 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Nanobioscience
- Vol. 11 (2) , 111-118
Classification of Multicolor Fluorescence In Situ Hybridization (M-FISH) Images With Sparse Representation
There has been a considerable interest in sparse representation and compressive sensing in applied mathematics and signal processing in recent years but with limited success to medical image processing. In this paper we developed a sparse representation-based classification (SRC) algorithm based on L1-norm minimization for classifying chromosomes from multicolor fluorescence in situ hybridization (M-FISH) images. The algorithm has been tested on a comprehensive M-FISH database that we established, demonstrating improved performance in classification. When compared with other pixel-wise M-FISH image classifiers such as fuzzy c-means (FCM) clustering algorithms and adaptive fuzzy c-means (AFCM) clustering algorithms that we proposed earlier the current method gave the lowest classification error. In order to evaluate the performance of different SRC for M-FISH imaging analysis, three different sparse representation methods, namely, Homotopy method, Orthogonal Matching Pursuit (OMP), and Least Angle Regression (LARS), were tested and compared. Results from our statistical analysis have shown that Homotopy based method is significantly better than the other two methods. Our work indicates that sparse representations based classifiers with proper models can outperform many existing classifiers for M-FISH classification including those that we proposed before, which can significantly improve the multicolor imaging system for chromosome analysis in cancer and genetic disease diagnosis.
- 30 May 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Nanobioscience
- Vol. 11 (2) , 111-118
Classification of Multicolor Fluorescence In Situ Hybridization (M-FISH) Images With Sparse Representation
There has been a considerable interest in sparse representation and compressive sensing in applied mathematics and signal processing in recent years but with limited success to medical image processing. In this paper we developed a sparse representation-based classification (SRC) algorithm based on L1-norm minimization for classifying chromosomes from multicolor fluorescence in situ hybridization (M-FISH) images. The algorithm has been tested on a comprehensive M-FISH database that we established, demonstrating improved performance in classification. When compared with other pixel-wise M-FISH image classifiers such as fuzzy c-means (FCM) clustering algorithms and adaptive fuzzy c-means (AFCM) clustering algorithms that we proposed earlier the current method gave the lowest classification error. In order to evaluate the performance of different SRC for M-FISH imaging analysis, three different sparse representation methods, namely, Homotopy method, Orthogonal Matching Pursuit (OMP), and Least Angle Regression (LARS), were tested and compared. Results from our statistical analysis have shown that Homotopy based method is significantly better than the other two methods. Our work indicates that sparse representations based classifiers with proper models can outperform many existing classifiers for M-FISH classification including those that we proposed before, which can significantly improve the multicolor imaging system for chromosome analysis in cancer and genetic disease diagnosis.
- Open Access
- 1 October 2011
- Published by World Scientific Pub Co Pte Ltd in Journal of Bioinformatics and Computational Biology
- Vol. 09 (05) , 631-645
A COMPRESSED SENSING BASED APPROACH FOR SUBTYPING OF LEUKEMIA FROM GENE EXPRESSION DATA
With the development of genomic techniques, the demand for new methods that can handle high-throughput genome-wide data effectively is becoming stronger than ever before. Compressed sensing (CS) is an emerging approach in statistics and signal processing. With the CS theory, a signal can be uniquely reconstructed or approximated from its sparse representations, which can therefore better distinguish different types of signals. However, the application of CS approach to genome-wide data analysis has been rarely investigated. We propose a novel CS-based approach for genomic data classification and test its performance in the subtyping of leukemia through gene expression analysis. The detection of subtypes of cancers such as leukemia according to different genetic markups is significant, which holds promise for the individualization of therapies and improvement of treatments. In our work, four statistical features were employed to select significant genes for the classification. With our selected genes out of 7,129 ones, the proposed CS method achieved a classification accuracy of 97.4% when evaluated with the cross validation and 94.3% when evaluated with another independent data set. The robustness of the method to noise was also tested, giving good performance. Therefore, this work demonstrates that the CS method can effectively detect subtypes of leukemia, implying improved accuracy of diagnosis of leukemia.
- 1 October 2011
- Published by World Scientific Pub Co Pte Ltd in Journal of Bioinformatics and Computational Biology
- Vol. 09 (05) , 631-645
Open AccessA COMPRESSED SENSING BASED APPROACH FOR SUBTYPING OF LEUKEMIA FROM GENE EXPRESSION DATA
With the development of genomic techniques, the demand for new methods that can handle high-throughput genome-wide data effectively is becoming stronger than ever before. Compressed sensing (CS) is an emerging approach in statistics and signal processing. With the CS theory, a signal can be uniquely reconstructed or approximated from its sparse representations, which can therefore better distinguish different types of signals. However, the application of CS approach to genome-wide data analysis has been rarely investigated. We propose a novel CS-based approach for genomic data classification and test its performance in the subtyping of leukemia through gene expression analysis. The detection of subtypes of cancers such as leukemia according to different genetic markups is significant, which holds promise for the individualization of therapies and improvement of treatments. In our work, four statistical features were employed to select significant genes for the classification. With our selected genes out of 7,129 ones, the proposed CS method achieved a classification accuracy of 97.4% when evaluated with the cross validation and 94.3% when evaluated with another independent data set. The robustness of the method to noise was also tested, giving good performance. Therefore, this work demonstrates that the CS method can effectively detect subtypes of leukemia, implying improved accuracy of diagnosis of leukemia.