Information Extraction from Large Datasets Consensus Clustering Paradigm

讲座名称: Information Extraction from Large Datasets Consensus Clustering Paradigm
讲座时间: 2018-04-02
讲座人: Asoke Nandi
形式:
校区: 兴庆校区
实践学分:
讲座内容: 讲座题目:Information Extraction from Large Datasets Consensus Clustering Paradigm 讲座时间:2018年4月2日,上午10:00-12:00 讲座地点:北五楼319 讲座人: Professor Asoke K. Nandi PhD (Cambridge) , Department of Electronic and Computer Engineering, Brunel University London, Uxbridge, UB8 3PH, United Kingdom 讲座摘要:  Clustering algorithms are often used to extract information from large datasets. They represent model-free or data-driven approaches. They have been developed and applied in many areas for several decades. In particular, they have been used for gene clustering over the last two decades in bioinformatics and in brain signal processing. New algorithms are being developed and applied to address many different problems. However, in applications with real data with little a priori knowledge, it is often difficult to select an appropriate clustering algorithm and evaluate the quality of clustering results due to the unknown ground truth. It is also the case that conclusions based on only one specific algorithm might be biased, since each algorithm has its own assumptions of the structure of the data, which might not correspond to the real data. Another important issue relates to multiple datasets, which may have been generated either in the same laboratory or different laboratories at different times and with different settings yet trying to conduct the similar experiments. In such a scenario, one has essentially a collection of heterogeneous datasets from similar experiments. The challenge is how to reach consensus conclusions in such scenarios. This presentation will address these issues and report on the results from applying Bi-CoPaM and UNCLES recently to analyse fMRI data and gene data. The following papers form the basis of this presentation. 1. C Liu, E Brattico, B Abu Jamous, C Pereira, T Jacobsen, and A K Nandi, “Effect of explicit evaluation on neural connectivity related to listening to unfamiliar music", Frontiers in Human Neuroscience, DOI: 10.3389/fnhum.2017.00611, vol. 11, (13 pages), 2017. 2. B Abu Jamous, F M Buffa, A L Harris, and A K Nandi, “In vitro downregulated hypoxia transcriptome is associated with poor prognosis in breast cancer", Molecular Cancer, DOI: 10.1186/s12943-017-0673-0, vol. 16, no. 105, (19 pages), 2017. 3. C Liu, B Abu Jamous, E Brattico, and A K Nandi, “Towards tunable consensus clustering for studying functional brain connectivity during affective processing", International Journal of Neural Systems, DOI: 10.1142/S0129065716500428, vol. 27, no. 2, 1650042 (16 pages), 2017. 4. A T Merryweather-Clarke et al., "Distinct gene expression program dynamics during erythropoiesis from human induced pluripotent stem cells compared with adult and cord blood progenitors", BMC Genomics, vol. 17, no. 817, DOI: 10.1186/s12864-016-3134-z (20 pages), 2016. 5. B Abu Jamous, R Fa, D J Roberts, and A K Nandi, “UNCLES: method for the identification of genes differentially consistently co-expressed in a specific subset of datasets", BMC Bioinformatics, DOI: 10.1186/s12859-015-0614-0, vol. 16, no. 184, 2015. 6. B Abu Jamous, R Fa, D J Roberts, and A K Nandi, “Comprehensive analysis of forty yeast microarray datasets reveals a novel subset of genes (APha-RiB) consistently negatively associated with ribosome biogenesis", BMC Bioinformatics, DOI: 10.1186/1471-2105-15-322, vol. 15, no. 322, 2014. 7. F Cong et al., "Low-rank approximation based non-negative multi-way array decomposition of event-related potentials", International Journal of Neural Systems, DOI: 10.1142/S012906571440005X, vol. 24, 1440005 (19 pages), 2014. 8. V Alluri et al., "From Vivaldi to Beatles and back: predicting lateralized brain responses to music", NeuroImage, vol. 83, pp. 627-636, 2013. 9. F Cong et al., "Linking brain responses to naturalistic and continuous music through analysis of ongoing EEG and stimulus features", IEEE Transactions on Multi-Media, vol. 15, no. 5, pp. 1060-1069, 2013. 10. B Abu Jamous, R Fa, D J Roberts, and A K Nandi, “Paradigm of tunable clustering using binarization of consensus partition matrices (Bi-CoPaM) for gene discovery", PLoS ONE vol. 8, no. 2, Doi:10.1371/journal.pone.0056432, 2013. 11. B Abu Jamous, R Fa, D J Roberts, and A K Nandi, “Yeast gene CMR1/YDL156W is consistently co-expressed with genes participating in DNA-metabolic processes in a variety of stringent clustering experiments", J. R. Soc. Interface, vol. 10, no. 81, doi: 10.1098/rsif.2012.0990, 2013.    
相关视频