Pub Date : 2005-12-01DOI: 10.1142/9781860947292_0010
Hee-Jeong Jin, Hyeno Kim, Jeong-Hyeon Choi, Hwan-Gue Cho
One of the main issues in comparative genomics is the study of chromosomal gene order in one or more related species. Recently identifying sets of orthologous genes in several genomes has become getting important, since a cluster of similar genes helps us to predict the function of unknown genes. For this purpose, the whole genome alignment is usually used to determine horizontal gene transfer, gene duplication, and gene loss between two related genomes. Also it is well known that a novel visualization tool of the whole genome alignment would be very useful for understanding genome organization and the evolutionary process. In this paper, we propose a method for identifying and visualizing the alignment of the whole genome alignment, especially for detecting gene clusters between two aligned genomes. Since the current rigorous algorithm for finding gene clusters has strong and artificial constraints, they are not useful for coping with “noisy” alignments. We developed the system AlignScope to provide a simplified structure for genome alignment at any level, and also to help us to find gene clusters. In this experiment, we have tested AlignScope on several microbial genomes. Alignment is a procedure that compares two or more sequences by searching for a series of individual characters or character patterns that are in the same order in the sequences. This procedure assists in designating the functions of unknown proteins, determining the relatedness of organisms, and identifying structurally and functionally important elements and other useful functions. 9;12 Many widely divergent organisms are descended from a common ancestor through a process called evolution. The inheritance patterns and diversities of these organisms have significant information regarding the nature of small and large-scale evolutionary events. The complexity and the size of the genome make it difficult to analyze. Because the large amount of biological noises is present when visualizing genomes, it is not enough to simply draw the aligned pairs of various genomes. Therefore an alignment visualization tool needs to provide a method for viewing the global structure of whole genome alignment in a simplified form at any level of detail. Figure-1 clearly illustrates this problem. In Figure-1, the resolution of the snapshot is 800 by 600 pixels, so one pixel corresponds about 6000 bases of a given genome sequence. Currently there are several systems for visualizing the alignment of genomes. The NCBI Map Viewer 14 provides graphical displays of biological features on NCBI’s as
{"title":"AlignScope: A Visual Mining Tool for Gene Team Finding with Whole Genome Alignment","authors":"Hee-Jeong Jin, Hyeno Kim, Jeong-Hyeon Choi, Hwan-Gue Cho","doi":"10.1142/9781860947292_0010","DOIUrl":"https://doi.org/10.1142/9781860947292_0010","url":null,"abstract":"One of the main issues in comparative genomics is the study of chromosomal gene order in one or more related species. Recently identifying sets of orthologous genes in several genomes has become getting important, since a cluster of similar genes helps us to predict the function of unknown genes. For this purpose, the whole genome alignment is usually used to determine horizontal gene transfer, gene duplication, and gene loss between two related genomes. Also it is well known that a novel visualization tool of the whole genome alignment would be very useful for understanding genome organization and the evolutionary process. In this paper, we propose a method for identifying and visualizing the alignment of the whole genome alignment, especially for detecting gene clusters between two aligned genomes. Since the current rigorous algorithm for finding gene clusters has strong and artificial constraints, they are not useful for coping with “noisy” alignments. We developed the system AlignScope to provide a simplified structure for genome alignment at any level, and also to help us to find gene clusters. In this experiment, we have tested AlignScope on several microbial genomes. Alignment is a procedure that compares two or more sequences by searching for a series of individual characters or character patterns that are in the same order in the sequences. This procedure assists in designating the functions of unknown proteins, determining the relatedness of organisms, and identifying structurally and functionally important elements and other useful functions. 9;12 Many widely divergent organisms are descended from a common ancestor through a process called evolution. The inheritance patterns and diversities of these organisms have significant information regarding the nature of small and large-scale evolutionary events. The complexity and the size of the genome make it difficult to analyze. Because the large amount of biological noises is present when visualizing genomes, it is not enough to simply draw the aligned pairs of various genomes. Therefore an alignment visualization tool needs to provide a method for viewing the global structure of whole genome alignment in a simplified form at any level of detail. Figure-1 clearly illustrates this problem. In Figure-1, the resolution of the snapshot is 800 by 600 pixels, so one pixel corresponds about 6000 bases of a given genome sequence. Currently there are several systems for visualizing the alignment of genomes. The NCBI Map Viewer 14 provides graphical displays of biological features on NCBI’s as","PeriodicalId":74513,"journal":{"name":"Proceedings of the ... Asia-Pacific bioinformatics conference","volume":"51 1","pages":"69-78"},"PeriodicalIF":0.0,"publicationDate":"2005-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74803447","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 : 2005-12-01DOI: 10.1142/9781860947292_0005
P.C.H. Ma, Keith C. C. Chan
Recent developments in large-scale monitoring of gene expression such as DNA microarrays have made the reconstruction of gene regulatory networks (GRNs) feasible. Before one can infer the structures of these networks, it is important to identify, for each gene in the network, which genes can affect its expression and how they affect it. Most of the existing approaches are useful exploratory tools in the sense that they allow the user to generate biological hypotheses about transcriptional regulations of genes that can then be tested in the laboratory. However, the patterns discovered by these approaches are not adequate for making accurate prediction on gene expression patterns in new or held-out experiments. Therefore, it is difficult to compare performance of different approaches or decide which approach is likely to generate plausible hypothesis. For this reason, we need an approach that not only can provide interpretable insight into the structures of GRNs but also can provide accurate prediction. In this paper, we present a novel fuzzy logic-based approach for this problem. The desired characteristics of the proposed algorithm are as follows: (i) it is able to directly mine the high-dimensional expression data without the need for additional feature selection procedures, (ii) it is able to distinguish between relevant and irrelevant expression data in predicting the expression patterns of predicted genes, (iii) based on the proposed objective interestingness measure, no user-specified thresholds are needed in advance, (iv) it can make explicit hidden patterns discovered for possible biological interpretation, (v) the discovered patterns can be used to predict gene expression patterns in other unseen tissue samples, and (vi) with fuzzy logic, it is robust to noise in the expression data as it hides the boundaries of the adjacent intervals of the quantitative attributes. Experimental results on real expression data show that it can be very effective and the discovered patterns reveal biologically meaningful regulatory relationships of genes that could help the user reconstructing the underlying structures of GRNs.
{"title":"Inference of Gene Regulatory Networks from Microarray Data: A Fuzzy Logic Approach","authors":"P.C.H. Ma, Keith C. C. Chan","doi":"10.1142/9781860947292_0005","DOIUrl":"https://doi.org/10.1142/9781860947292_0005","url":null,"abstract":"Recent developments in large-scale monitoring of gene expression such as DNA microarrays have made the reconstruction of gene regulatory networks (GRNs) feasible. Before one can infer the structures of these networks, it is important to identify, for each gene in the network, which genes can affect its expression and how they affect it. Most of the existing approaches are useful exploratory tools in the sense that they allow the user to generate biological hypotheses about transcriptional regulations of genes that can then be tested in the laboratory. However, the patterns discovered by these approaches are not adequate for making accurate prediction on gene expression patterns in new or held-out experiments. Therefore, it is difficult to compare performance of different approaches or decide which approach is likely to generate plausible hypothesis. For this reason, we need an approach that not only can provide interpretable insight into the structures of GRNs but also can provide accurate prediction. In this paper, we present a novel fuzzy logic-based approach for this problem. The desired characteristics of the proposed algorithm are as follows: (i) it is able to directly mine the high-dimensional expression data without the need for additional feature selection procedures, (ii) it is able to distinguish between relevant and irrelevant expression data in predicting the expression patterns of predicted genes, (iii) based on the proposed objective interestingness measure, no user-specified thresholds are needed in advance, (iv) it can make explicit hidden patterns discovered for possible biological interpretation, (v) the discovered patterns can be used to predict gene expression patterns in other unseen tissue samples, and (vi) with fuzzy logic, it is robust to noise in the expression data as it hides the boundaries of the adjacent intervals of the quantitative attributes. Experimental results on real expression data show that it can be very effective and the discovered patterns reveal biologically meaningful regulatory relationships of genes that could help the user reconstructing the underlying structures of GRNs.","PeriodicalId":74513,"journal":{"name":"Proceedings of the ... Asia-Pacific bioinformatics conference","volume":"15 1","pages":"17-26"},"PeriodicalIF":0.0,"publicationDate":"2005-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75733276","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 : 2005-12-01DOI: 10.1142/9781860947292_0019
Zhipeng Cai, M. Heydari, Guohui Lin
Microarray gene expression data often contains missing values resulted from various reasons. However, most of the gene expression data analysis algorithms, such as clustering, classification and network design, require complete information, that is, without any missing values. It is therefore very important to accurately impute the missing values before applying the data analysis algorithms. In this paper, anIterated Local Least Squares Imputation method (ILLsimpute) is proposed to estimate the missing values. In ILLsimpute, a similarity threshold is learned using known expression values and at every iteration it is used to obtain a set of coherent genes for every target gene containing missing values. The target gene is then represented as a linear combination of the coherent genes, using the least squares. The algorithm terminates after certain iterations or when the imputation converges. The experimental results on real microarray datasets show that ILLsimpute outperforms three most recent methods on several commonly tested datasets.
{"title":"Microarray Missing Value Imputation by Iterated Local Least Squares","authors":"Zhipeng Cai, M. Heydari, Guohui Lin","doi":"10.1142/9781860947292_0019","DOIUrl":"https://doi.org/10.1142/9781860947292_0019","url":null,"abstract":"Microarray gene expression data often contains missing values resulted from various reasons. However, most of the gene expression data analysis algorithms, such as clustering, classification and network design, require complete information, that is, without any missing values. It is therefore very important to accurately impute the missing values before applying the data analysis algorithms. In this paper, anIterated Local Least Squares Imputation method (ILLsimpute) is proposed to estimate the missing values. In ILLsimpute, a similarity threshold is learned using known expression values and at every iteration it is used to obtain a set of coherent genes for every target gene containing missing values. The target gene is then represented as a linear combination of the coherent genes, using the least squares. The algorithm terminates after certain iterations or when the imputation converges. The experimental results on real microarray datasets show that ILLsimpute outperforms three most recent methods on several commonly tested datasets.","PeriodicalId":74513,"journal":{"name":"Proceedings of the ... Asia-Pacific bioinformatics conference","volume":"38 1","pages":"159-168"},"PeriodicalIF":0.0,"publicationDate":"2005-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83623700","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 : 2005-12-01DOI: 10.1142/9781860947292_0021
Li Shen, E.C. Tan
Multiclass cancer classification based on microarray data is described. A generalized output-coding scheme combined with binary classifiers is used. Different coding strategies, decoding functions and feature selection methods are combined and validated on two cancer datasets: GCM and ALL. The effects of these different methods and their combinations are then discussed. The highest testing accuracies achieved are 78% and 100% for the two datasets respectively. The results are considered to be very good when compared with the other researchers’ work.
{"title":"A Generalized Output-Coding Scheme with SVM for Multiclass Microarray Classification","authors":"Li Shen, E.C. Tan","doi":"10.1142/9781860947292_0021","DOIUrl":"https://doi.org/10.1142/9781860947292_0021","url":null,"abstract":"Multiclass cancer classification based on microarray data is described. A generalized output-coding scheme combined with binary classifiers is used. Different coding strategies, decoding functions and feature selection methods are combined and validated on two cancer datasets: GCM and ALL. The effects of these different methods and their combinations are then discussed. The highest testing accuracies achieved are 78% and 100% for the two datasets respectively. The results are considered to be very good when compared with the other researchers’ work.","PeriodicalId":74513,"journal":{"name":"Proceedings of the ... Asia-Pacific bioinformatics conference","volume":"205 1","pages":"179-186"},"PeriodicalIF":0.0,"publicationDate":"2005-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72959754","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 : 2005-12-01DOI: 10.1142/9781860947292_0022
Derek A. Ruths, L. Nakhleh
The inference of evolutionary relationships is usually aid ed by a reconstruction method which is expected to produce a reasonably accurate estimation of the true evolutionary history. However, various factors are known to impede the reconstruction process and result in inaccurate estimates of the true evolutionary relationships. Detecting and removing errors (wrong branches) from tree estimates bear great significance on the results of phylogenetic analyses. Methods have been devised for assessing the support of (or confidence in) phylogenetic tree branches, wh ich is one way of quantifying inaccuracies in trees. In this paper, we study, via simulations, the perfo rmance of the most commonly used methods for assessing branch support: bootstrap of maximum likelihood and maximum parsimony trees, consensus of maximum parsimony trees, and consensus of Bayesian inference trees. Under the conditions of our experiments, our findings indicate that the actual amo unt of change along a branch does not have strong impact on the support of that branch. Further, we find t hat bootstrap and Bayesian estimates are generally comparable to each other, and superior to a consensus of maximum parsimony trees. In our opinion, the most significant finding of all is that there is no threshold value for any of the methods that would allow for the elimination of wrong branches while maintaining all correct ones—there are always weakly supported true positive branches.
{"title":"Techniques for Assessing Phylogenetic Branch Support: A Performance Study","authors":"Derek A. Ruths, L. Nakhleh","doi":"10.1142/9781860947292_0022","DOIUrl":"https://doi.org/10.1142/9781860947292_0022","url":null,"abstract":"The inference of evolutionary relationships is usually aid ed by a reconstruction method which is expected to produce a reasonably accurate estimation of the true evolutionary history. However, various factors are known to impede the reconstruction process and result in inaccurate estimates of the true evolutionary relationships. Detecting and removing errors (wrong branches) from tree estimates bear great significance on the results of phylogenetic analyses. Methods have been devised for assessing the support of (or confidence in) phylogenetic tree branches, wh ich is one way of quantifying inaccuracies in trees. In this paper, we study, via simulations, the perfo rmance of the most commonly used methods for assessing branch support: bootstrap of maximum likelihood and maximum parsimony trees, consensus of maximum parsimony trees, and consensus of Bayesian inference trees. Under the conditions of our experiments, our findings indicate that the actual amo unt of change along a branch does not have strong impact on the support of that branch. Further, we find t hat bootstrap and Bayesian estimates are generally comparable to each other, and superior to a consensus of maximum parsimony trees. In our opinion, the most significant finding of all is that there is no threshold value for any of the methods that would allow for the elimination of wrong branches while maintaining all correct ones—there are always weakly supported true positive branches.","PeriodicalId":74513,"journal":{"name":"Proceedings of the ... Asia-Pacific bioinformatics conference","volume":"500 1","pages":"187-196"},"PeriodicalIF":0.0,"publicationDate":"2005-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78426686","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 : 2005-12-01DOI: 10.1142/9781860947292_0024
Christine Sinoquet
We address the issue of structured motif inference. This problem is stated as follows: given a set of n DNA sequences and a quorum q (%), find the optimal structured consensus motif described as gaps alternating with specific regions and shared by at least q x n sequences. Our proposal is in the domain of metaheuristics: it runs solutions to convergence through a cooperation between a sampling strategy of the search space and a quick detection of local similarities in small sequence samples. The contributions of this paper are: (1) the design of a stochastic method whose genuine novelty rests on driving the search with a threshold frequency f discrimining between specific regions and gaps; (2) the original way for justifying the operations especially designed; (3) the implementation of a mining tool well adapted to biologists' exigencies: few input parameters are required (quorum q, minimal threshold frequency f, maximal gap length g). Our approach proves efficient on simulated data, promoter sites in Dicot plants and transcription factor binding sites in E. coli genome. Our algorithm, Kaos, compares favorably with MEME and STARS in terms of accuracy.
{"title":"A Novel Approach for Structured Consensus Motif Inference Under Specificity and Quorum Constraints","authors":"Christine Sinoquet","doi":"10.1142/9781860947292_0024","DOIUrl":"https://doi.org/10.1142/9781860947292_0024","url":null,"abstract":"We address the issue of structured motif inference. This problem is stated as follows: given a set of n DNA sequences and a quorum q (%), find the optimal structured consensus motif described as gaps alternating with specific regions and shared by at least q x n sequences. Our proposal is in the domain of metaheuristics: it runs solutions to convergence through a cooperation between a sampling strategy of the search space and a quick detection of local similarities in small sequence samples. The contributions of this paper are: (1) the design of a stochastic method whose genuine novelty rests on driving the search with a threshold frequency f discrimining between specific regions and gaps; (2) the original way for justifying the operations especially designed; (3) the implementation of a mining tool well adapted to biologists' exigencies: few input parameters are required (quorum q, minimal threshold frequency f, maximal gap length g). Our approach proves efficient on simulated data, promoter sites in Dicot plants and transcription factor binding sites in E. coli genome. Our algorithm, Kaos, compares favorably with MEME and STARS in terms of accuracy.","PeriodicalId":74513,"journal":{"name":"Proceedings of the ... Asia-Pacific bioinformatics conference","volume":"37 1","pages":"207-216"},"PeriodicalIF":0.0,"publicationDate":"2005-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85727941","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 : 2005-12-01DOI: 10.1142/9781860947292_0011
Francis Y. L. Chin, Henry C. M. Leung
Finding common patterns, motifs, in a set of DNA sequences is an important problem in bioinformatics. One common representation of motifs is a string with symbols A, C, G, T and N where N stands for the wildcard symbol. In this paper, we introduce a more general motif discovery problem without any weaknesses of the Planted (l,d)-Motif Problem and also a set of control sequences as an additional input. The existing algorithms using brute force approach for solving similar problem take O(n(t+f)l5) times where t and f are the number of input sequences and control sequences respectively, n is the length of each sequence and l is the length of the motif. We propose an efficient algorithm, called VAS, which has an expected running time O(nfl(nt)(4+1/4)) using O((nt)(4+1/4)) space for any integer k. In particular when k = 3, the time and space complexities are O(nlf (nt)(1.0625)) and O((nt)(1.0625)) respectively. This algorithm makes use of voting and graph representation for better time and space complexities. This technique can also be used to improve the performances of some existing algorithms.
{"title":"An Efficient Algorithm for String Motif Discovery","authors":"Francis Y. L. Chin, Henry C. M. Leung","doi":"10.1142/9781860947292_0011","DOIUrl":"https://doi.org/10.1142/9781860947292_0011","url":null,"abstract":"Finding common patterns, motifs, in a set of DNA sequences is an important problem in bioinformatics. One common representation of motifs is a string with symbols A, C, G, T and N where N stands for the wildcard symbol. In this paper, we introduce a more general motif discovery problem without any weaknesses of the Planted (l,d)-Motif Problem and also a set of control sequences as an additional input. The existing algorithms using brute force approach for solving similar problem take O(n(t+f)l5) times where t and f are the number of input sequences and control sequences respectively, n is the length of each sequence and l is the length of the motif. We propose an efficient algorithm, called VAS, which has an expected running time O(nfl(nt)(4+1/4)) using O((nt)(4+1/4)) space for any integer k. In particular when k = 3, the time and space complexities are O(nlf (nt)(1.0625)) and O((nt)(1.0625)) respectively. This algorithm makes use of voting and graph representation for better time and space complexities. This technique can also be used to improve the performances of some existing algorithms.","PeriodicalId":74513,"journal":{"name":"Proceedings of the ... Asia-Pacific bioinformatics conference","volume":"6 1","pages":"79-88"},"PeriodicalIF":0.0,"publicationDate":"2005-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87194360","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 : 2005-12-01DOI: 10.1142/9781860947292_0001
Wen-Hsiung Li
Advances in genomics have led to the production of various functional genomic data as well as genomic sequence data. This is particularly true in yeasts. Such data have proved to be highly useful for inferring regulatory elements and modules. I shall present studies that I have done with my colleagues and collaborators on the following topics. (1) Detection of transcription factors (including their interactions) involved in a specific function such as the cell cycle, (2) inference of the cis elements (binding sites and sequences) of a transcription factor, (3) reconstruction of the regulatory circuits of genes, and (4) inference of regulatory modules. In all these topics, we have developed methods and have applied them to analyze data from yeasts.
{"title":"On the Inference of Regulatory Elements, Circuits, and Modules","authors":"Wen-Hsiung Li","doi":"10.1142/9781860947292_0001","DOIUrl":"https://doi.org/10.1142/9781860947292_0001","url":null,"abstract":"Advances in genomics have led to the production of various functional genomic data as well as genomic sequence data. This is particularly true in yeasts. Such data have proved to be highly useful for inferring regulatory elements and modules. I shall present studies that I have done with my colleagues and collaborators on the following topics. (1) Detection of transcription factors (including their interactions) involved in a specific function such as the cell cycle, (2) inference of the cis elements (binding sites and sequences) of a transcription factor, (3) reconstruction of the regulatory circuits of genes, and (4) inference of regulatory modules. In all these topics, we have developed methods and have applied them to analyze data from yeasts.","PeriodicalId":74513,"journal":{"name":"Proceedings of the ... Asia-Pacific bioinformatics conference","volume":"186 1","pages":"1"},"PeriodicalIF":0.0,"publicationDate":"2005-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83456772","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 : 2005-12-01DOI: 10.1142/9781860947292_0035
K. Arun, C. Langmead
Protein nuclear magnetic resonance (NMR) chemical shifts are among the most accurately measurable spectroscopic parameters and are closely correlated to protein structure because of their dependence on the local electronic environment. The precise nature of this correlation remains largely unknown. Accurate prediction of chemical shifts from existing structures’ atomic co-ordinates will permit close study of this relationship. This paper presents a novel non- linear regression based approach to chemical shift prediction from protein structure. The regression model employed combines quantum, classical and empirical variables and provides statistically signifi cant improved prediction accuracy over existing chemical shift predictors, across protein backbone atom types. The results presented here were obtained using the Random Forest regression algorithm on a protein entry data set derived from the RefDB re-referenced chemical shift database.
{"title":"Structure-Based Chemical Shift Prediction Using Random Forests Non-Linear Regression","authors":"K. Arun, C. Langmead","doi":"10.1142/9781860947292_0035","DOIUrl":"https://doi.org/10.1142/9781860947292_0035","url":null,"abstract":"Protein nuclear magnetic resonance (NMR) chemical shifts are among the most accurately measurable spectroscopic parameters and are closely correlated to protein structure because of their dependence on the local electronic environment. The precise nature of this correlation remains largely unknown. Accurate prediction of chemical shifts from existing structures’ atomic co-ordinates will permit close study of this relationship. This paper presents a novel non- linear regression based approach to chemical shift prediction from protein structure. The regression model employed combines quantum, classical and empirical variables and provides statistically signifi cant improved prediction accuracy over existing chemical shift predictors, across protein backbone atom types. The results presented here were obtained using the Random Forest regression algorithm on a protein entry data set derived from the RefDB re-referenced chemical shift database.","PeriodicalId":74513,"journal":{"name":"Proceedings of the ... Asia-Pacific bioinformatics conference","volume":"41 1","pages":"317-326"},"PeriodicalIF":0.0,"publicationDate":"2005-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74202289","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 : 2005-12-01DOI: 10.1142/9781860947292_0032
Xiaoxu Han
The gene tree and species tree problem remains a central problem in phylogenomics. To overcome this problem, gene concatenation approaches have been used to combine a certain number of genes randomly from a set of widely distributed orthologous genes selected from genome data to conduct phylogenetic analysis. The random concatenation mechanism prevents us from the further investigations of the inner structures of the gene data set employed to infer the phylogenetic trees and locates the most phylogenetically informative genes. In this work, a phylogenomic mining approach is described to gain knowledge from a gene data set by clustering genes in the gene set through a self-organizing map (SOM) to explore the gene dataset inner structures. From this, the most phylogenetically informative gene set is created by picking the maximum entropy gene from each cluster to infer phylogenetic trees by phylogenetic analysis. Using the same data set, the phylogenetic mining approach performs better than the random gene concatenation approach.
{"title":"Resolving the Gene Tree and Species Tree Problem by Phylogenetic Mining","authors":"Xiaoxu Han","doi":"10.1142/9781860947292_0032","DOIUrl":"https://doi.org/10.1142/9781860947292_0032","url":null,"abstract":"The gene tree and species tree problem remains a central problem in phylogenomics. To overcome this problem, gene concatenation approaches have been used to combine a certain number of genes randomly from a set of widely distributed orthologous genes selected from genome data to conduct phylogenetic analysis. The random concatenation mechanism prevents us from the further investigations of the inner structures of the gene data set employed to infer the phylogenetic trees and locates the most phylogenetically informative genes. In this work, a phylogenomic mining approach is described to gain knowledge from a gene data set by clustering genes in the gene set through a self-organizing map (SOM) to explore the gene dataset inner structures. From this, the most phylogenetically informative gene set is created by picking the maximum entropy gene from each cluster to infer phylogenetic trees by phylogenetic analysis. Using the same data set, the phylogenetic mining approach performs better than the random gene concatenation approach.","PeriodicalId":74513,"journal":{"name":"Proceedings of the ... Asia-Pacific bioinformatics conference","volume":"120 1","pages":"287-296"},"PeriodicalIF":0.0,"publicationDate":"2005-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73544007","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：