Pub Date : 2012-10-04DOI: 10.1109/BIBMW.2012.6470249
Kyunga Kim, Min-Seok Kwon, Sungyoung Lee, J. Namkung, Ming D. Li, T. Park
Gene-gene interactions are important factors underlying a common complex trait that is mostly polygenic. While many methods have been proposed to analyze gene-gene interactions in genetic association studies, the interpretation of the identified gene-gene interactions is not straightforward. In order to aid the interpretation of gene-gene interactions, we developed the GxG-Viztool, an executable program for visualizing gene-gene interactions in genetic association analysis. The GxG-Viztool provides an effective way to recognize genotype combinations that enhance/repress a trait and to display polygenic structure of interactions. The GxG-Viztool implements six graphical tools: checkerboard, pairwise checkerboard, forest, funnel, 3D lattice and parallel coordinate plots, which make it effective to recognize certain patterns in gene-gene interactions. It is freely available at http ://bibs. snu. ac. kr/GxG-Viz tool.
{"title":"GxG-Viztool: A program for visualizing gene-gene interactions in genetic association analysis","authors":"Kyunga Kim, Min-Seok Kwon, Sungyoung Lee, J. Namkung, Ming D. Li, T. Park","doi":"10.1109/BIBMW.2012.6470249","DOIUrl":"https://doi.org/10.1109/BIBMW.2012.6470249","url":null,"abstract":"Gene-gene interactions are important factors underlying a common complex trait that is mostly polygenic. While many methods have been proposed to analyze gene-gene interactions in genetic association studies, the interpretation of the identified gene-gene interactions is not straightforward. In order to aid the interpretation of gene-gene interactions, we developed the GxG-Viztool, an executable program for visualizing gene-gene interactions in genetic association analysis. The GxG-Viztool provides an effective way to recognize genotype combinations that enhance/repress a trait and to display polygenic structure of interactions. The GxG-Viztool implements six graphical tools: checkerboard, pairwise checkerboard, forest, funnel, 3D lattice and parallel coordinate plots, which make it effective to recognize certain patterns in gene-gene interactions. It is freely available at http ://bibs. snu. ac. kr/GxG-Viz tool.","PeriodicalId":6392,"journal":{"name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76906289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-10-04DOI: 10.1109/BIBM.2012.6392716
Xiwei Tang, Jianxin Wang, Yi Pan
Essential proteins are vital for an organism's viability under a variety of conditions. Computational prediction of essential proteins based on the global protein-protein interaction (PPI) network is severely restricted because of the insufficiency of the PPI data, but fortunately the gene expression profiles help to make up the deficiency. In this work, Pearson correlation coefficient (PCC) is used to bridge the gap between PPI and gene expression data. Based on PCC and Edge Clustering Coefficient (ECC), a new centrality measure, i.e., the weighted degree centrality (WDC), is developed to achieve the reliable prediction of essential proteins. WDC is employed to identify essential proteins in the yeast PPI network in order to estimate its performance. For comparison, other prediction technologies are also performed to identify essential proteins. Some evaluation methods are used to analyze the results from various prediction approaches. The analyses prove that WDC outperforms other state-of-the-art ones. At the same time, the analyses also mean that it is an effective way to predict essential proteins by means of integrating different data sources.
{"title":"Identifying essential proteins via integration of protein interaction and gene expression data","authors":"Xiwei Tang, Jianxin Wang, Yi Pan","doi":"10.1109/BIBM.2012.6392716","DOIUrl":"https://doi.org/10.1109/BIBM.2012.6392716","url":null,"abstract":"Essential proteins are vital for an organism's viability under a variety of conditions. Computational prediction of essential proteins based on the global protein-protein interaction (PPI) network is severely restricted because of the insufficiency of the PPI data, but fortunately the gene expression profiles help to make up the deficiency. In this work, Pearson correlation coefficient (PCC) is used to bridge the gap between PPI and gene expression data. Based on PCC and Edge Clustering Coefficient (ECC), a new centrality measure, i.e., the weighted degree centrality (WDC), is developed to achieve the reliable prediction of essential proteins. WDC is employed to identify essential proteins in the yeast PPI network in order to estimate its performance. For comparison, other prediction technologies are also performed to identify essential proteins. Some evaluation methods are used to analyze the results from various prediction approaches. The analyses prove that WDC outperforms other state-of-the-art ones. At the same time, the analyses also mean that it is an effective way to predict essential proteins by means of integrating different data sources.","PeriodicalId":6392,"journal":{"name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85736866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-10-04DOI: 10.1109/BIBMW.2012.6470203
Andrea Szabóová, Ondřej Kuželka, F. Železný
We apply relational machine learning techniques to predict antimicrobial activity of peptides. We follow our successful strategy (Szabóová et al., MLSB 2010) to prediction of DNA-binding propensity of proteins from structural features. We exploit structure prediction methods to obtain peptides' spatial structures, then we construct the structural relational features. We use these relational features as attributes in a regression model. We apply this methodology to antimicrobial activity prediction of peptides achieving better predictive accuracies than a state-of-the-art approach.
{"title":"Prediction of antimicrobial activity of peptides using relational machine learning","authors":"Andrea Szabóová, Ondřej Kuželka, F. Železný","doi":"10.1109/BIBMW.2012.6470203","DOIUrl":"https://doi.org/10.1109/BIBMW.2012.6470203","url":null,"abstract":"We apply relational machine learning techniques to predict antimicrobial activity of peptides. We follow our successful strategy (Szabóová et al., MLSB 2010) to prediction of DNA-binding propensity of proteins from structural features. We exploit structure prediction methods to obtain peptides' spatial structures, then we construct the structural relational features. We use these relational features as attributes in a regression model. We apply this methodology to antimicrobial activity prediction of peptides achieving better predictive accuracies than a state-of-the-art approach.","PeriodicalId":6392,"journal":{"name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88600424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-10-04DOI: 10.1109/BIBM.2012.6392686
Jie Cheng, J. Greshock, Leming Shi, Jeffery L. Painter, Xiwu Lin, Kwan R. Lee, Shu Zheng, R. Wooster, L. Pusztai, A. Menius
Feature selection is one of the most important research topics in high dimensional array data analysis. We propose a two-way filtering based method that utilizes a pair of statistics coupled with rigorous cross-validation to identify the most informative features from different types of distributions. We evaluate the utility of the proposed adaptive feature selection method on six MicroArray Quality Control Phase II (MAQC-II) datasets. The results show that our method yields models with significantly fewer features and can achieve comparable or superior classification performance compared to models generated from other feature selection methods, suggesting high quality feature selection.
{"title":"An adaptive feature selection method for microarray data analysis","authors":"Jie Cheng, J. Greshock, Leming Shi, Jeffery L. Painter, Xiwu Lin, Kwan R. Lee, Shu Zheng, R. Wooster, L. Pusztai, A. Menius","doi":"10.1109/BIBM.2012.6392686","DOIUrl":"https://doi.org/10.1109/BIBM.2012.6392686","url":null,"abstract":"Feature selection is one of the most important research topics in high dimensional array data analysis. We propose a two-way filtering based method that utilizes a pair of statistics coupled with rigorous cross-validation to identify the most informative features from different types of distributions. We evaluate the utility of the proposed adaptive feature selection method on six MicroArray Quality Control Phase II (MAQC-II) datasets. The results show that our method yields models with significantly fewer features and can achieve comparable or superior classification performance compared to models generated from other feature selection methods, suggesting high quality feature selection.","PeriodicalId":6392,"journal":{"name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87219497","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-10-04DOI: 10.1109/BIBMW.2012.6470368
Xia Wu, Hui-Jin Wang, Guo-ming Chen, Weiheng Zhu, Shun Long
This paper presents our works to tackle three key problems in modern research of traditional Chinese medicines. Based on a dataset of 100 medicines (each with 60 major ingredients), we evaluate various data mining approaches in order to unveil the underlying associations between these chemical ingredients and the pharmic qualities of the medicines. Based on our experiements, we conclude that these associations do exist and can be effectively unveiled. Various performance enhancement techniques are then evaluated, among which we identify the best classification approach for practice. These unveiled associations between pharmic quality and ingredients of traditional Chinese medicine can help guide future researches in this area, particularly in the development of new medicines.
{"title":"Mining the associations between pharmic quality and ingredients of traditional Chinese medicines","authors":"Xia Wu, Hui-Jin Wang, Guo-ming Chen, Weiheng Zhu, Shun Long","doi":"10.1109/BIBMW.2012.6470368","DOIUrl":"https://doi.org/10.1109/BIBMW.2012.6470368","url":null,"abstract":"This paper presents our works to tackle three key problems in modern research of traditional Chinese medicines. Based on a dataset of 100 medicines (each with 60 major ingredients), we evaluate various data mining approaches in order to unveil the underlying associations between these chemical ingredients and the pharmic qualities of the medicines. Based on our experiements, we conclude that these associations do exist and can be effectively unveiled. Various performance enhancement techniques are then evaluated, among which we identify the best classification approach for practice. These unveiled associations between pharmic quality and ingredients of traditional Chinese medicine can help guide future researches in this area, particularly in the development of new medicines.","PeriodicalId":6392,"journal":{"name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83237341","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-10-04DOI: 10.1109/BIBM.2012.6392673
R. Murphy
The CellOrganizer project (http://cellorganizer.org) provides open source tools for learning generative models of cell organization directly from images and for synthesizing cell images (or other representations) from one or more of those models. Model learning captures variation among cells in a collection of images. Images used for model learning and instances synthesized from models can be two- or three-dimensional static images or movies. Current components of CellOrganizer can learn models of cell shape, nuclear shape, chromatin texture, vesicular organe lie number, size, shape and position, and microtubule distribution. These models can be conditional upon each other: for example, for a given synthesized cell instance, organelle position will be dependent upon the cell and nuclear shape of that instance. The models can be parametric, in which a choice is made about an explicit form to represent a particular structure, or non-parametric, in which distributions are learned empirically. One of the main uses of the system is in support of cell simulations: models learned from separate experiments can be combined into one or more synthetic cell instances that are output in a form compatible with cell simulation engines such as MCell, Virtual Cell and Smoldyn. Another important application of the system is in comparison of target patterns and perturbagen effects in high content screening and analysis. This is currently done using numerical features, but these are difficult to compare across different microscope systems or cell types since features can be affected by changes in more than one aspect of cell organization. More robust comparisons can be made using generative model parameters, since these can distinguish effects on cell size or shape from effects on organelle pattern. Ultimately, it is anticipated that collaborative efforts by many groups will enable creation of image-derived generative models that permit accurate modeling of cell behaviors, and that can be used to drive experimentation to improve them through active learning. [replace "perturbation" for the word "perturbagen"]
{"title":"(3) The CellOrganizer project: An open source system to learn image-derived models of subcellular organization over time and space","authors":"R. Murphy","doi":"10.1109/BIBM.2012.6392673","DOIUrl":"https://doi.org/10.1109/BIBM.2012.6392673","url":null,"abstract":"The CellOrganizer project (http://cellorganizer.org) provides open source tools for learning generative models of cell organization directly from images and for synthesizing cell images (or other representations) from one or more of those models. Model learning captures variation among cells in a collection of images. Images used for model learning and instances synthesized from models can be two- or three-dimensional static images or movies. Current components of CellOrganizer can learn models of cell shape, nuclear shape, chromatin texture, vesicular organe lie number, size, shape and position, and microtubule distribution. These models can be conditional upon each other: for example, for a given synthesized cell instance, organelle position will be dependent upon the cell and nuclear shape of that instance. The models can be parametric, in which a choice is made about an explicit form to represent a particular structure, or non-parametric, in which distributions are learned empirically. One of the main uses of the system is in support of cell simulations: models learned from separate experiments can be combined into one or more synthetic cell instances that are output in a form compatible with cell simulation engines such as MCell, Virtual Cell and Smoldyn. Another important application of the system is in comparison of target patterns and perturbagen effects in high content screening and analysis. This is currently done using numerical features, but these are difficult to compare across different microscope systems or cell types since features can be affected by changes in more than one aspect of cell organization. More robust comparisons can be made using generative model parameters, since these can distinguish effects on cell size or shape from effects on organelle pattern. Ultimately, it is anticipated that collaborative efforts by many groups will enable creation of image-derived generative models that permit accurate modeling of cell behaviors, and that can be used to drive experimentation to improve them through active learning. [replace \"perturbation\" for the word \"perturbagen\"]","PeriodicalId":6392,"journal":{"name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91411354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-10-04DOI: 10.1109/BIBM.2012.6392626
M. Aziz, Philemon Chan, J. Osorio, B. F. Minhas, Vaisak Parekatt, G. Caetano-Anollés
Metabolomic networks describe correlated change in metabolite levels that crucially link the transcriptome and proteome with the complex matter and energy dynamics of small molecule metabolism. These networks are atypical. They do not directly portray regulatory and pathway information, yet they embed both. Here we study how stress rewires the metabolomic networks of Escherichia coli. Networks with vertices describing metabolites and edges representing correlated changes in metabolite concentrations were used to study time resolved bacterial responses to four non-lethal stress perturbations, cold, heat, lactose diauxie, and oxidative stress. We find notable patterns that are common to all stress responses examined: (1) networks are random rather than scale-free, i.e. metabolite connectivity is dictated by large network components rather than `hubs' (2) networks rewire quickly even in the absence of stress and are therefore highly dynamic; (3) rewiring occurs minutes after exposure to the Stressor and results in significant decreases in network connectivity, and (4) at longer time frames connectivity is regained. The common biphasic-rewiring pattern revealed in our time-resolved exploration of metabolite connectivity also uncovers unique structural and functional features. We find that stress-induced decreases in connectivity were always counterbalanced by increases in network modularity. Remarkably, rewiring begins with energetics and carbon metabolism that is needed for growth and then focuses on lipids, hubs and metabolic centrality needed for membrane restructuring. While these patterns may simply represent the need of the cell to stop growing and to prepare for uncertainty, the biphasic modularization of the network is an unanticipated result that links the effects of environmental perturbations and the generation of modules in biology.
{"title":"Stress induces biphasic-rewiring and modularization patterns in the metabolomic networks of Escherichia coli","authors":"M. Aziz, Philemon Chan, J. Osorio, B. F. Minhas, Vaisak Parekatt, G. Caetano-Anollés","doi":"10.1109/BIBM.2012.6392626","DOIUrl":"https://doi.org/10.1109/BIBM.2012.6392626","url":null,"abstract":"Metabolomic networks describe correlated change in metabolite levels that crucially link the transcriptome and proteome with the complex matter and energy dynamics of small molecule metabolism. These networks are atypical. They do not directly portray regulatory and pathway information, yet they embed both. Here we study how stress rewires the metabolomic networks of Escherichia coli. Networks with vertices describing metabolites and edges representing correlated changes in metabolite concentrations were used to study time resolved bacterial responses to four non-lethal stress perturbations, cold, heat, lactose diauxie, and oxidative stress. We find notable patterns that are common to all stress responses examined: (1) networks are random rather than scale-free, i.e. metabolite connectivity is dictated by large network components rather than `hubs' (2) networks rewire quickly even in the absence of stress and are therefore highly dynamic; (3) rewiring occurs minutes after exposure to the Stressor and results in significant decreases in network connectivity, and (4) at longer time frames connectivity is regained. The common biphasic-rewiring pattern revealed in our time-resolved exploration of metabolite connectivity also uncovers unique structural and functional features. We find that stress-induced decreases in connectivity were always counterbalanced by increases in network modularity. Remarkably, rewiring begins with energetics and carbon metabolism that is needed for growth and then focuses on lipids, hubs and metabolic centrality needed for membrane restructuring. While these patterns may simply represent the need of the cell to stop growing and to prepare for uncertainty, the biphasic modularization of the network is an unanticipated result that links the effects of environmental perturbations and the generation of modules in biology.","PeriodicalId":6392,"journal":{"name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90909497","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-10-04DOI: 10.1109/BIBM.2012.6392655
Brian S. Olson, Amarda Shehu
The vast and rugged protein energy surface can be effectively represented in terms of local minima. The basin-hopping framework, where a structural perturbation is followed by an energy minimization, is particularly suited to obtaining this coarse-grained representation. Basin hopping is effective for small systems both in locating lower-energy minima and obtaining conformations near the native structure. The efficiency decreases for large systems. Our recent work improves efficiency on large systems through molecular fragment replacement. In this paper, we conduct a detailed investigation of two components in basin hopping, perturbation and minimization, and how they work in concert to affect the sampling of near-native local minima. We show that controlling the magnitude of perturbation jumps is related to the ability to effectively steer the exploration towards conformations near the protein native state. In minimization, we show that a simple greedy search is just as effective as Metropolis Monte Carlo-based minimization. Finally, we show that an evolutionary-inspired approach based on the Pareto front is particularly effective in reducing the ensemble of sampled local minima and obtains a simpler representation of the probed energy surface.
{"title":"Efficient basin hopping in the protein energy surface","authors":"Brian S. Olson, Amarda Shehu","doi":"10.1109/BIBM.2012.6392655","DOIUrl":"https://doi.org/10.1109/BIBM.2012.6392655","url":null,"abstract":"The vast and rugged protein energy surface can be effectively represented in terms of local minima. The basin-hopping framework, where a structural perturbation is followed by an energy minimization, is particularly suited to obtaining this coarse-grained representation. Basin hopping is effective for small systems both in locating lower-energy minima and obtaining conformations near the native structure. The efficiency decreases for large systems. Our recent work improves efficiency on large systems through molecular fragment replacement. In this paper, we conduct a detailed investigation of two components in basin hopping, perturbation and minimization, and how they work in concert to affect the sampling of near-native local minima. We show that controlling the magnitude of perturbation jumps is related to the ability to effectively steer the exploration towards conformations near the protein native state. In minimization, we show that a simple greedy search is just as effective as Metropolis Monte Carlo-based minimization. Finally, we show that an evolutionary-inspired approach based on the Pareto front is particularly effective in reducing the ensemble of sampled local minima and obtains a simpler representation of the probed energy surface.","PeriodicalId":6392,"journal":{"name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82748561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-10-04DOI: 10.1109/BIBMW.2012.6470316
Tayo Obafemi-Ajayi, R. Kanawong, Dong Xu, Shao Li, Y. Duan
Inspection of the tongue is a key component in Traditional Chinese Medicine. Chinese medical practitioners diagnose the health status of a patient based on observation of the color, shape, and texture characteristics of the tongue. The condition of the tongue can objectively reflect the presence of certain diseases and aid in the differentiation of syndromes, prognosis of disease and establishment of treatment methods. Tongue shape is a very important feature in tongue diagnosis. A different tongue shape other than ellipse could indicate presence of certain pathologies. In this paper, we propose a novel set of features, based on shape geometry and polynomial equations, for automated recognition and classification of the shape of a tongue image using supervised machine learning techniques. We also present a novel method to correct the orientation/deflection of the tongue based on the symmetry of axis detection method. Experimental results obtained on a set of 303 tongue images demonstrate that the proposed method improves the current state of the art method.
{"title":"Features for automated tongue image shape classification","authors":"Tayo Obafemi-Ajayi, R. Kanawong, Dong Xu, Shao Li, Y. Duan","doi":"10.1109/BIBMW.2012.6470316","DOIUrl":"https://doi.org/10.1109/BIBMW.2012.6470316","url":null,"abstract":"Inspection of the tongue is a key component in Traditional Chinese Medicine. Chinese medical practitioners diagnose the health status of a patient based on observation of the color, shape, and texture characteristics of the tongue. The condition of the tongue can objectively reflect the presence of certain diseases and aid in the differentiation of syndromes, prognosis of disease and establishment of treatment methods. Tongue shape is a very important feature in tongue diagnosis. A different tongue shape other than ellipse could indicate presence of certain pathologies. In this paper, we propose a novel set of features, based on shape geometry and polynomial equations, for automated recognition and classification of the shape of a tongue image using supervised machine learning techniques. We also present a novel method to correct the orientation/deflection of the tongue based on the symmetry of axis detection method. Experimental results obtained on a set of 303 tongue images demonstrate that the proposed method improves the current state of the art method.","PeriodicalId":6392,"journal":{"name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83091461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-10-04DOI: 10.1109/BIBM.2012.6392618
Narjes S. Movahedi, Elmira Forouzmand, H. Chitsaz
Recent progress in DNA amplification techniques, particularly multiple displacement amplification (MDA), has made it possible to sequence and assemble bacterial genomes from a single cell. However, the quality of single cell genome assembly has not yet reached the quality of normal multiceli genome assembly due to the coverage bias and errors caused by MDA. Using a template of more than one cell for MDA or combining separate MDA products has been shown to improve the result of genome assembly from few single cells, but providing identical single cells, as a necessary step for these approaches, is a challenge. As a solution to this problem, we give an algorithm for de novo co-assembly of bacterial genomes from multiple single cells. Our novel method not only detects the outlier cells in a pool, it also identifies and eliminates their genomic sequences from the final assembly. Our proposed co-assembly algorithm is based on colored de Bruijn graph which has been recently proposed for de novo structural variation detection. Our results show that de novo co-assembly of bacterial genomes from multiple single cells outperforms single cell assembly of each individual one in all standard metrics. Moreover, co-assembly outperforms mixed assembly in which the input datasets are simply concatenated. We implemented our algorithm in a software tool called HyDA which is available from http://compbio.cs.wayne.edu/software/hyda.
{"title":"De novo co-assembly of bacterial genomes from multiple single cells","authors":"Narjes S. Movahedi, Elmira Forouzmand, H. Chitsaz","doi":"10.1109/BIBM.2012.6392618","DOIUrl":"https://doi.org/10.1109/BIBM.2012.6392618","url":null,"abstract":"Recent progress in DNA amplification techniques, particularly multiple displacement amplification (MDA), has made it possible to sequence and assemble bacterial genomes from a single cell. However, the quality of single cell genome assembly has not yet reached the quality of normal multiceli genome assembly due to the coverage bias and errors caused by MDA. Using a template of more than one cell for MDA or combining separate MDA products has been shown to improve the result of genome assembly from few single cells, but providing identical single cells, as a necessary step for these approaches, is a challenge. As a solution to this problem, we give an algorithm for de novo co-assembly of bacterial genomes from multiple single cells. Our novel method not only detects the outlier cells in a pool, it also identifies and eliminates their genomic sequences from the final assembly. Our proposed co-assembly algorithm is based on colored de Bruijn graph which has been recently proposed for de novo structural variation detection. Our results show that de novo co-assembly of bacterial genomes from multiple single cells outperforms single cell assembly of each individual one in all standard metrics. Moreover, co-assembly outperforms mixed assembly in which the input datasets are simply concatenated. We implemented our algorithm in a software tool called HyDA which is available from http://compbio.cs.wayne.edu/software/hyda.","PeriodicalId":6392,"journal":{"name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83125168","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}