The Experts below are selected from a list of 290628 Experts worldwide ranked by ideXlab platform
Zhihua Zhou - One of the best experts on this subject based on the ideXlab platform.
-
Drosophila Gene Expression Pattern Annotation through Multi-Instance Multi-Label Learning
IEEE ACM Transactions on Computational Biology and Bioinformatics, 2012Co-Authors: Yingxin Li, Shuiwang Ji, Sudhir Kumar, Jieping Ye, Zhihua ZhouAbstract:In the studies of Drosophila embryogenesis, a large number of two-dimensional digital images of gene Expression Patterns have been produced to build an atlas of spatio-temporal gene Expression dynamics across developmental time. Gene Expressions captured in these images have been manually annotated with anatomical and developmental ontology terms using a controlled vocabulary (CV), which are useful in research aimed at understanding gene functions, interactions, and networks. With the rapid accumulation of images, the process of manual annotation has become increasingly cumbersome, and computational methods to automate this task are urgently needed. However, the automated annotation of embryo images is challenging. This is because the annotation terms spatially correspond to local Expression Patterns of images, yet they are assigned collectively to groups of images and it is unknown which term corresponds to which region of which image in the group. In this paper, we address this problem using a new machine learning framework, Multi-Instance Multi-Label (MIML) learning. We first show that the underlying nature of the annotation task is a typical MIML learning problem. Then, we propose two support vector machine algorithms under the MIML framework for the task. Experimental results on the FlyExpress database (a digital library of standardized Drosophila gene Expression Pattern images) reveal that the exploitation of MIML framework leads to significant performance improvement over state-of-the-art approaches.
-
drosophila gene Expression Pattern annotation through multi instance multi label learning
International Joint Conference on Artificial Intelligence, 2009Co-Authors: Yingxin Li, Shuiwang Ji, Sudhir Kumar, Jieping Ye, Zhihua ZhouAbstract:The Berkeley Drosophila Genome Project (BDGP) has produced a large number of gene Expression Patterns, many of which have been annotated textually with anatomical and developmental terms. These terms spatially correspond to local regions of the images; however, they are attached collectively to groups of images, such that it is unknown which term is assigned to which region of which image in the group. This poses a challenge to the development of the computational method to automate the textual description of Expression Patterns contained in each image. In this paper, we show that the underlying nature of this task matches well with a new machine learning framework, Multi-Instance Multi-Label learning (MIML). We propose a new MIML support vector machine to solve the problems that beset the annotation task. Empirical study shows that the proposed method outperforms the state-of-the-art Drosophila gene Expression Pattern annotation methods.
Yingxin Li - One of the best experts on this subject based on the ideXlab platform.
-
Drosophila Gene Expression Pattern Annotation through Multi-Instance Multi-Label Learning
IEEE ACM Transactions on Computational Biology and Bioinformatics, 2012Co-Authors: Yingxin Li, Shuiwang Ji, Sudhir Kumar, Jieping Ye, Zhihua ZhouAbstract:In the studies of Drosophila embryogenesis, a large number of two-dimensional digital images of gene Expression Patterns have been produced to build an atlas of spatio-temporal gene Expression dynamics across developmental time. Gene Expressions captured in these images have been manually annotated with anatomical and developmental ontology terms using a controlled vocabulary (CV), which are useful in research aimed at understanding gene functions, interactions, and networks. With the rapid accumulation of images, the process of manual annotation has become increasingly cumbersome, and computational methods to automate this task are urgently needed. However, the automated annotation of embryo images is challenging. This is because the annotation terms spatially correspond to local Expression Patterns of images, yet they are assigned collectively to groups of images and it is unknown which term corresponds to which region of which image in the group. In this paper, we address this problem using a new machine learning framework, Multi-Instance Multi-Label (MIML) learning. We first show that the underlying nature of the annotation task is a typical MIML learning problem. Then, we propose two support vector machine algorithms under the MIML framework for the task. Experimental results on the FlyExpress database (a digital library of standardized Drosophila gene Expression Pattern images) reveal that the exploitation of MIML framework leads to significant performance improvement over state-of-the-art approaches.
-
drosophila gene Expression Pattern annotation through multi instance multi label learning
International Joint Conference on Artificial Intelligence, 2009Co-Authors: Yingxin Li, Shuiwang Ji, Sudhir Kumar, Jieping Ye, Zhihua ZhouAbstract:The Berkeley Drosophila Genome Project (BDGP) has produced a large number of gene Expression Patterns, many of which have been annotated textually with anatomical and developmental terms. These terms spatially correspond to local regions of the images; however, they are attached collectively to groups of images, such that it is unknown which term is assigned to which region of which image in the group. This poses a challenge to the development of the computational method to automate the textual description of Expression Patterns contained in each image. In this paper, we show that the underlying nature of this task matches well with a new machine learning framework, Multi-Instance Multi-Label learning (MIML). We propose a new MIML support vector machine to solve the problems that beset the annotation task. Empirical study shows that the proposed method outperforms the state-of-the-art Drosophila gene Expression Pattern annotation methods.
Yasuaki Kuroe - One of the best experts on this subject based on the ideXlab platform.
-
Synthesis method of gene regulatory networks having desired Expression-Pattern transition sequences
2013 9th Asian Control Conference (ASCC), 2013Co-Authors: Yoshihiro Mori, Yasuaki KuroeAbstract:Recently, synthesis of gene regulatory networks having desired behaviors has become of interest to many researchers and several studies have been done. We proposed a synthesis method of gene regulatory networks, in which desired behaviors are given by Expression Pattern sequences. Expression Pattern sequences describe approximate behavior of gene regulatory networks. There are information being not used for synthesis. In this paper, we propose a synthesis method of gene regulatory networks, in which desired behaviors are given by Expression Pattern sequences and transition times of the Expression Pattern. We formulate the synthesis problem as an optimization problem. We solve the optimization problem by using solutions of difference equations corresponding to Expression Pattern sequences without solving differential equations of gene regulatory network models. Therefore, we can solve the synthesis problem efficiently.
-
Synthesis method of gene regulatory networks having desired periodic Expression Pattern sequences
2012 IEEE International Conference on Systems Man and Cybernetics (SMC), 2012Co-Authors: Yoshihiro Mori, Yasuaki KuroeAbstract:Recently, synthesis of gene regulatory networks having desired behavior has become of interest to many researchers and several studies have been done. There exist periodic phenomena in cells and these periodic phenomena are considered to be generated by gene regulatory networks. We already proposed a synthesis method of gene regulatory networks having desired cyclic Expression Pattern sequences. In this paper, we propose a synthesis method for realizing not only desired cyclic Expression Pattern sequences but also desired periods. In the proposed method we derive a representation of periods and introduce Poincare map for realizing periodic solution trajectories with desired periods. We also introduce a discrete-time network which represent transition of Expression Pattern. In the problem, gene regulatory network model is given by differential equations. However, in order to synthesize gene regulatory networks we solve only the discrete-time network. Therefore desired behavior are realized efficiently. Numerical experiments are carried out to illustrate the performance of the proposed method.
-
A synthesis method of gene regulatory networks having cyclic Expression Pattern sequences and its evaluation
2012 12th International Conference on Control Automation and Systems, 2012Co-Authors: Yoshihiro Mori, Yasuaki KuroeAbstract:There exist periodic phenomena in cells and the phenomena are considered to be generated by gene regulatory networks. Therefore synthesis of gene regulatory networks having desired periodic behavior has become of interest to many researchers. In this paper, we discuss a synthesis problem of gene regulatory networks having desired periodic behavior. The desired behavior are given by cyclic Expression Pattern sequences. We proposed a synthesis method for realizing a periodic solution trajectory exhibiting a desired cyclic Expression Pattern sequence by using Poincarè map. In the method, we choose a point and make it become a fixed point of a Poincaré map. However it is not always possible to make the chosen point become a fixed point. In this paper we propose a synthesis method without choosing a fixed point. We evaluate the method by performing numerical experiments.
-
Controller design method of gene regulatory networks for realizing cyclic Expression Pattern sequences
2011 8th Asian Control Conference (ASCC), 2011Co-Authors: Yoshihiro Mori, Yasuaki KuroeAbstract:Recently, synthesis of gene regulatory networks having desired functions has become of interest to many researchers because it is a complementary approach to understanding gene regulatory networks, and it could be the first step in controlling living cells. There exist several periodic phenomena in cells, e.g. circadian rhythm. These phenomena are considered to be generated by gene regulatory networks. In this paper we propose a controller design method of gene regulatory networks, in which desired behavior are given by cyclic Expression Pattern sequences. In order that objective gene regulatory networks have desired cyclic Expression Pattern sequences, it is required that Expression Pattern sequences of the controller gene regulatory network are cyclic. Moreover, the solution trajectories corresponding to the desired Expression Pattern sequences are need to be periodic. The proposed method consists of two steps. Firstly, we design a controller gene regulatory network such that the objective one has desired cyclic Expression Pattern sequences. Secondly, we design controller gene regulatory networks such that the objective one has desired Expression Pattern sequences together with their corresponding solution trajectories being periodic. Numerical experiments are carried out to illustrate the performance of the proposed method.
-
Synthesis method of gene regulatory networks having cyclic Expression Pattern sequences — Realization by introducing Poincarè map
SICE Annual Conference 2011, 2011Co-Authors: Yoshihiro Mori, Yasuaki KuroeAbstract:Recently, synthesis of gene regulatory networks having desired behavior has become of interest to many researchers and several studies have been done. There exist periodic phenomena in cells and those are considered to be generated by gene regulatory networks such as circadian rhythm. In this paper, we discuss a synthesis problem of gene regulatory networks possessing desired cyclic Expression Pattern sequences. It does not imply persistent oscillations of gene Expression quantities that gene regulatory networks have cyclic Expression Pattern sequences. Therefore we have proposed a synthesis method in which periodicity of solution trajectories of gene regulatory networks is ensured by specifying passing points of the trajectories. However there does not always exist a gene regulatory network having a solution trajectory passing through the points. In this paper, we propose a synthesis method in which we introduce Poincarè maps for desired cyclic Expression Pattern sequences and make a Poincaré map have a fixed point. As a result, synthesized gene regulatory networks have desired cyclic Expression Pattern sequences together with their corresponding solution trajectories being periodic. Numerical experiments are carried out to illustrate the performance of the proposed method.
Jieping Ye - One of the best experts on this subject based on the ideXlab platform.
-
Drosophila Gene Expression Pattern Annotation through Multi-Instance Multi-Label Learning
IEEE ACM Transactions on Computational Biology and Bioinformatics, 2012Co-Authors: Yingxin Li, Shuiwang Ji, Sudhir Kumar, Jieping Ye, Zhihua ZhouAbstract:In the studies of Drosophila embryogenesis, a large number of two-dimensional digital images of gene Expression Patterns have been produced to build an atlas of spatio-temporal gene Expression dynamics across developmental time. Gene Expressions captured in these images have been manually annotated with anatomical and developmental ontology terms using a controlled vocabulary (CV), which are useful in research aimed at understanding gene functions, interactions, and networks. With the rapid accumulation of images, the process of manual annotation has become increasingly cumbersome, and computational methods to automate this task are urgently needed. However, the automated annotation of embryo images is challenging. This is because the annotation terms spatially correspond to local Expression Patterns of images, yet they are assigned collectively to groups of images and it is unknown which term corresponds to which region of which image in the group. In this paper, we address this problem using a new machine learning framework, Multi-Instance Multi-Label (MIML) learning. We first show that the underlying nature of the annotation task is a typical MIML learning problem. Then, we propose two support vector machine algorithms under the MIML framework for the task. Experimental results on the FlyExpress database (a digital library of standardized Drosophila gene Expression Pattern images) reveal that the exploitation of MIML framework leads to significant performance improvement over state-of-the-art approaches.
-
drosophila gene Expression Pattern annotation through multi instance multi label learning
International Joint Conference on Artificial Intelligence, 2009Co-Authors: Yingxin Li, Shuiwang Ji, Sudhir Kumar, Jieping Ye, Zhihua ZhouAbstract:The Berkeley Drosophila Genome Project (BDGP) has produced a large number of gene Expression Patterns, many of which have been annotated textually with anatomical and developmental terms. These terms spatially correspond to local regions of the images; however, they are attached collectively to groups of images, such that it is unknown which term is assigned to which region of which image in the group. This poses a challenge to the development of the computational method to automate the textual description of Expression Patterns contained in each image. In this paper, we show that the underlying nature of this task matches well with a new machine learning framework, Multi-Instance Multi-Label learning (MIML). We propose a new MIML support vector machine to solve the problems that beset the annotation task. Empirical study shows that the proposed method outperforms the state-of-the-art Drosophila gene Expression Pattern annotation methods.
Sudhir Kumar - One of the best experts on this subject based on the ideXlab platform.
-
Drosophila Gene Expression Pattern Annotation through Multi-Instance Multi-Label Learning
IEEE ACM Transactions on Computational Biology and Bioinformatics, 2012Co-Authors: Yingxin Li, Shuiwang Ji, Sudhir Kumar, Jieping Ye, Zhihua ZhouAbstract:In the studies of Drosophila embryogenesis, a large number of two-dimensional digital images of gene Expression Patterns have been produced to build an atlas of spatio-temporal gene Expression dynamics across developmental time. Gene Expressions captured in these images have been manually annotated with anatomical and developmental ontology terms using a controlled vocabulary (CV), which are useful in research aimed at understanding gene functions, interactions, and networks. With the rapid accumulation of images, the process of manual annotation has become increasingly cumbersome, and computational methods to automate this task are urgently needed. However, the automated annotation of embryo images is challenging. This is because the annotation terms spatially correspond to local Expression Patterns of images, yet they are assigned collectively to groups of images and it is unknown which term corresponds to which region of which image in the group. In this paper, we address this problem using a new machine learning framework, Multi-Instance Multi-Label (MIML) learning. We first show that the underlying nature of the annotation task is a typical MIML learning problem. Then, we propose two support vector machine algorithms under the MIML framework for the task. Experimental results on the FlyExpress database (a digital library of standardized Drosophila gene Expression Pattern images) reveal that the exploitation of MIML framework leads to significant performance improvement over state-of-the-art approaches.
-
drosophila gene Expression Pattern annotation through multi instance multi label learning
International Joint Conference on Artificial Intelligence, 2009Co-Authors: Yingxin Li, Shuiwang Ji, Sudhir Kumar, Jieping Ye, Zhihua ZhouAbstract:The Berkeley Drosophila Genome Project (BDGP) has produced a large number of gene Expression Patterns, many of which have been annotated textually with anatomical and developmental terms. These terms spatially correspond to local regions of the images; however, they are attached collectively to groups of images, such that it is unknown which term is assigned to which region of which image in the group. This poses a challenge to the development of the computational method to automate the textual description of Expression Patterns contained in each image. In this paper, we show that the underlying nature of this task matches well with a new machine learning framework, Multi-Instance Multi-Label learning (MIML). We propose a new MIML support vector machine to solve the problems that beset the annotation task. Empirical study shows that the proposed method outperforms the state-of-the-art Drosophila gene Expression Pattern annotation methods.
