The Experts below are selected from a list of 2730 Experts worldwide ranked by ideXlab platform
Shufan Ji - One of the best experts on this subject based on the ideXlab platform.
-
Identification Exon Skipping Events From High-Throughput RNA Sequencing Data
IEEE Transactions on NanoBioscience, 2015Co-Authors: Shufan Ji, Qinghua Jiang, Yadong Wang*Abstract:The emergence of next-generation High-throughput RNA sequencing (RNA-Seq) provides tremendous opportunities for researchers to analyze alternative splicing on a genome-wide scale. However, accurate identification of alternative splicing events from RNA-Seq data has remained an unresolved challenge in next-generation sequencing (NGS) studies. Identifying exon skipping (ES) events is an essential part in genome-wide alternative splicing event identification. In this paper, we propose a novel method ESFinder, a random forest classifier to identify ES events from RNA-Seq data. ESFinder conducts thorough studies on predicting features and figures out proper features according to their relevance for ES event identification. Experimental results on real human skeletal muscle and brain RNA-Seq data show that ESFinder could effectively predict ES events with High Predictive Accuracy.
-
BIBM - ESclassifier: A random forest classifier for detection of exon skipping events from RNA-Seq data
2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2014Co-Authors: Shufan Ji, Yadong WangAbstract:Detecting exon skipping (ES) events is an essential part in genome-wide alternative splicing event detection. In this paper, we propose a novel method ESclassifier to detect ES events from RNA-seq data. ESclassifier conducts thorough studies on predicting features and figures out proper features according to their relevance for ES event detection. Experimental results on real human heart and liver RNA-seq data show that ESclassifier could effectively filter out false positives with High Predictive Accuracy. The codes of ESclassifier are available at http://mlg.hit.edu.cn/ybai/ES/ESclass.html.
-
ESclassifier: A random forest classifier for detection of exon skipping events from RNA-Seq data
2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2014Co-Authors: Shufan Ji, Yadong WangAbstract:Detecting exon skipping (ES) events is an essential part in genome-wide alternative splicing event detection. In this paper, we propose a novel method ESclassifier to detect ES events from RNA-seq data. ESclassifier conducts thorough studies on predicting features and figures out proper features according to their relevance for ES event detection. Experimental results on real human heart and liver RNA-seq data show that ESclassifier could effectively filter out false positives with High Predictive Accuracy. The codes of ESclassifier are available at http://mlg.hit.edu.cn/ybai/ES/ESclass.html.
Kimito Funatsu - One of the best experts on this subject based on the ideXlab platform.
-
Adaptive database management based on the database monitoring index for long-term use of adaptive soft sensors
Chemometrics and Intelligent Laboratory Systems, 2015Co-Authors: Hiromasa Kaneko, Kimito FunatsuAbstract:Soft sensors are an essential tool for controlling chemical and industrial plants. To adapt to new process states, these soft sensors require adaptation mechanisms. As the performance of adaptive soft sensors depends on the quality of its database and the size of which will have some upper limit, a database monitoring index (DMI) has been developed. Additional information is only added to the database if it has a sufficiently High DMI value. In this study, we propose a DMI optimization method and adaptive database management scheme. DMI hyperparameters are set automatically using an initial database, and the main database adapts to new process states by storing data with large prediction errors. Case studies using simulated and real industrial datasets confirm that the proposed scheme enables soft sensors to operate with High Predictive Accuracy over the long term.
-
KES - Adaptive Soft Sensor Model Using Online Support Vector Regression with Time Variable and Discussion of Appropriate Parameter Settings
Procedia Computer Science, 2013Co-Authors: Hiromasa Kaneko, Kimito FunatsuAbstract:Abstract Soft sensors are used in chemical plants to estimate process variables that are difficult to measure online. However, the Predictive Accuracy of adaptive soft sensor models decreases when sudden process changes occur. An online support vector regression (OSVR) model with a time variable can adapt to rapid changes among process variables. One problem faced by the proposed model is finding appropriate hyperparameters for the OSVR model; we discussed three methods to select parameters based on Predictive Accuracy and computation time. The proposed method was applied to simulation data and industrial data, and achieved High Predictive Accuracy when time-varying changes occurred.
Yadong Wang* - One of the best experts on this subject based on the ideXlab platform.
-
Identification Exon Skipping Events From High-Throughput RNA Sequencing Data
IEEE Transactions on NanoBioscience, 2015Co-Authors: Shufan Ji, Qinghua Jiang, Yadong Wang*Abstract:The emergence of next-generation High-throughput RNA sequencing (RNA-Seq) provides tremendous opportunities for researchers to analyze alternative splicing on a genome-wide scale. However, accurate identification of alternative splicing events from RNA-Seq data has remained an unresolved challenge in next-generation sequencing (NGS) studies. Identifying exon skipping (ES) events is an essential part in genome-wide alternative splicing event identification. In this paper, we propose a novel method ESFinder, a random forest classifier to identify ES events from RNA-Seq data. ESFinder conducts thorough studies on predicting features and figures out proper features according to their relevance for ES event identification. Experimental results on real human skeletal muscle and brain RNA-Seq data show that ESFinder could effectively predict ES events with High Predictive Accuracy.
Hiromasa Kaneko - One of the best experts on this subject based on the ideXlab platform.
-
Adaptive database management based on the database monitoring index for long-term use of adaptive soft sensors
Chemometrics and Intelligent Laboratory Systems, 2015Co-Authors: Hiromasa Kaneko, Kimito FunatsuAbstract:Soft sensors are an essential tool for controlling chemical and industrial plants. To adapt to new process states, these soft sensors require adaptation mechanisms. As the performance of adaptive soft sensors depends on the quality of its database and the size of which will have some upper limit, a database monitoring index (DMI) has been developed. Additional information is only added to the database if it has a sufficiently High DMI value. In this study, we propose a DMI optimization method and adaptive database management scheme. DMI hyperparameters are set automatically using an initial database, and the main database adapts to new process states by storing data with large prediction errors. Case studies using simulated and real industrial datasets confirm that the proposed scheme enables soft sensors to operate with High Predictive Accuracy over the long term.
-
KES - Adaptive Soft Sensor Model Using Online Support Vector Regression with Time Variable and Discussion of Appropriate Parameter Settings
Procedia Computer Science, 2013Co-Authors: Hiromasa Kaneko, Kimito FunatsuAbstract:Abstract Soft sensors are used in chemical plants to estimate process variables that are difficult to measure online. However, the Predictive Accuracy of adaptive soft sensor models decreases when sudden process changes occur. An online support vector regression (OSVR) model with a time variable can adapt to rapid changes among process variables. One problem faced by the proposed model is finding appropriate hyperparameters for the OSVR model; we discussed three methods to select parameters based on Predictive Accuracy and computation time. The proposed method was applied to simulation data and industrial data, and achieved High Predictive Accuracy when time-varying changes occurred.
Robin J. Shields - One of the best experts on this subject based on the ideXlab platform.
-
Rapid determination of bulk microalgal biochemical composition by Fourier-Transform Infrared spectroscopy
Bioresource Technology, 2013Co-Authors: Joshua J. Mayers, Kevin J Flynn, Robin J. ShieldsAbstract:Analysis of bulk biochemical composition is a key in fundamental and applied studies of microalgae and is essential to understanding responses to different cultivation scenarios. Traditional biochemical methods for the quantification of lipids, carbohydrates and proteins are often time-consuming, often involve hazardous reagents, require significant amounts of biomass and are Highly dependent on practitioner proficiency. This study presents a rapid and non-destructive method, utilising Fourier-Transform Infrared (FTIR) spectroscopy for the simultaneous determination of lipid, protein and carbohydrate content in microalgal biomass. A simple univariate regression was applied to sets of reference microalgal spectra of known composition and recognised IR peak integrals. A robust single-species model was constructed, with coefficients of determination r2>0.95, High Predictive Accuracy and relative errors below 5%. The applicability of this methodology is demonstrated by monitoring the time-resolved changes in biochemical composition of the marine alga Nannochloropsis sp. grown to nitrogen starvation. © 2013 Elsevier Ltd.