Browsing by Author "Huang, Hui-Ling"

Now showing 1 - 20 of 50

A hydrophobic spine stabilizes a surface-exposed alpha-helix according to analysis of the solvent-accessible surface area
(2016-12-22)
Liou, Yi-Fan
;
Huang, Hui-Ling
;
Ho, Shinn-Ying
;
生物科技學系
;
生物資訊及系統生物研究所
Background: Most of hydrophilic and hydrophobic residues are thought to be exposed and buried in proteins, respectively. In contrast to the majority of the existing studies on protein folding characteristics using protein structures, in this study, our aim was to design predictors for estimating relative solvent accessibility (RSA) of amino acid residues to discover protein folding characteristics from sequences. Methods: The proposed 20 real-value RSA predictors were designed on the basis of the support vector regression method with a set of informative physicochemical properties (PCPs) obtained by means of an optimal feature selection algorithm. Then, molecular dynamics simulations were performed for validating the knowledge discovered by analysis of the selected PCPs. Results: The RSA predictors had the mean absolute error of 14.11% and a correlation coefficient of 0.69, better than the existing predictors. The hydrophilic-residue predictors preferred PCPs of buried amino acid residues to PCPs of exposed ones as prediction features. A hydrophobic spine composed of exposed hydrophobic residues of an a-helix was discovered by analyzing the PCPs of RSA predictors corresponding to hydrophobic residues. For example, the results of a molecular dynamics simulation of wild-type sequences and their mutants showed that proteins 1MOF and 2WRP_H16I (Protein Data Bank IDs), which have a perfectly hydrophobic spine, have more stable structures than 1MOF_I54D and 2WRP do (which do not have a perfectly hydrophobic spine). Conclusions: We identified informative PCPs to design high-performance RSA predictors and to analyze these PCPs for identification of novel protein folding characteristics. A hydrophobic spine in a protein can help to stabilize exposed alpha-helices.
A hydrophobic spine stabilizes a surface-exposed alpha-helix according to analysis of the solvent-accessible surface area
(2016-12-22)
Liou, Yi-Fan
;
Huang, Hui-Ling
;
Ho, Shinn-Ying
;
生物科技學系
;
生物資訊及系統生物研究所
Background: Most of hydrophilic and hydrophobic residues are thought to be exposed and buried in proteins, respectively. In contrast to the majority of the existing studies on protein folding characteristics using protein structures, in this study, our aim was to design predictors for estimating relative solvent accessibility (RSA) of amino acid residues to discover protein folding characteristics from sequences. Methods: The proposed 20 real-value RSA predictors were designed on the basis of the support vector regression method with a set of informative physicochemical properties (PCPs) obtained by means of an optimal feature selection algorithm. Then, molecular dynamics simulations were performed for validating the knowledge discovered by analysis of the selected PCPs. Results: The RSA predictors had the mean absolute error of 14.11% and a correlation coefficient of 0.69, better than the existing predictors. The hydrophilic-residue predictors preferred PCPs of buried amino acid residues to PCPs of exposed ones as prediction features. A hydrophobic spine composed of exposed hydrophobic residues of an a-helix was discovered by analyzing the PCPs of RSA predictors corresponding to hydrophobic residues. For example, the results of a molecular dynamics simulation of wild-type sequences and their mutants showed that proteins 1MOF and 2WRP_H16I (Protein Data Bank IDs), which have a perfectly hydrophobic spine, have more stable structures than 1MOF_I54D and 2WRP do (which do not have a perfectly hydrophobic spine). Conclusions: We identified informative PCPs to design high-performance RSA predictors and to analyze these PCPs for identification of novel protein folding characteristics. A hydrophobic spine in a protein can help to stabilize exposed alpha-helices.
An intelligent two-stage evolutionary algorithm for dynamic pathway identification from gene expression profiles
(2007-10-01)
Ho, Shinn-Ying
;
Hsieh, Chih-Hung
;
Yu, Fu-Chieh
;
Huang, Hui-Ling
;
生物資訊及系統生物研究所
From gene expression profiles, it is desirable to rebuild cellular dynamic regulation networks to discover more delicate and substantial functions in molecular biology, biochemistry, bioengineering, and pharmaceutics. The S-system model is suitable to characterize biochemical network systems and capable of analyzing the regulatory system dynamics. However, the inference of an S-system model of N-gene genetic networks has 2N(N+1) parameters in a set of nonlinear differential equations to be optimized. This paper proposes an intelligent two-stage evolutionary algorithm (iTEA) to efficiently infer the S-system models of genetic networks from time-series data of gene expression. To cope with the curse of dimensionality, the proposed algorithm consists of two stages, where each uses a divide-and-conquer strategy. The optimization problem is first decomposed into N subproblems having 2(N+1) parameters each. At the first stage, each subproblem is solved using a novel intelligent genetic algorithm (IGA) with intelligent crossover based on an orthogonal experimental design (OED). At the second stage, the obtained N solutions to the N subproblems are combined and refined using an OED-based simulated annealing algorithm for handling noisy gene expression profiles. The effectiveness of iTEA is evaluated using simulated expression patterns with and without noise running on a single-processor PC. It is shown that 1) IGA is efficient enough to solve subproblems, 2) IGA is significantly superior to the existing method GA with simplex crossover (SPXGA), and 3) iTEA performs well in inferring S-system models for dynamic pathway identification.
Angiotensin Receptor Blockers Decrease the Risk of Major Adverse Cardiovascular Events in Patients with End-Stage Renal Disease on Maintenance Dialysis: A Nationwide Matched-Cohort Study
(2015-10-21)
Tzeng, Nian-Sheng
;
Yin, Yun-Ju
;
Li, Chien-Hsun
;
Chen, Hung-An
;
Chiu, Shih-Hsiang
Background Major adverse cardiovascular events (MACE) cause the leading cause of morbidity and mortality in patients with end-stage renal disease (ESRD) on maintenance Hemodialysis (HD) or peritoneal dialysis (PD). Many randomized-controlled trials (RCTs) have proved that angiotensin receptor blockers (ARBs) can reduce the risk of MACE in the people with normal or impaired kidney function without dialysis. This study seeks to clarify whether ARBs therapy could also attenuate this risk in patients with ESRD on maintenance dialysis. Materials and Methods The National Health Research Institute provided a database of one million random subjects for the study. A random sample was taken of 1800 patients >= 18 years y/o with ESRD on dialysis without a history of MACE and use of ARBs within 6-months prior to enrollment. Cox proportional hazard regression analysis was used to identify the risk factors and compute the hazard ratios accompanying 95% confidence intervals. Results In these 1800 patients, 1061 had never used ARBs, while 224 had used them for 1-90 days, and 515 had used them for more than 90 days. We found that ARBs significantly decrease the incidences of acute myocardial infarctions (AMI), coronary artery diseases (CAD) requiring coronary stent or percutaneous transluminal coronary angioplasty (PTCA), peripheral artery disease (PAD) requiring percutaneous transluminal angioplasty (PTA), and acute stroke. Cumulative prescription days of ARBs beyond 365-760 days or more were found to be negatively correlated with incidence of MACEs. For patients with dual comorbidity (i.e., mellitus and hyperlipidemia), 91-365 cumulative prescription days might also attenuate the risk. Conclusions For patients on maintenance dialysis, the use of ARBs could significantly attenuate the risk of major cardiovascular events: AMI, acute stroke, and PAD requiring PTA.
Association between Gastroenterological Malignancy and Diabetes Mellitus and Anti-Diabetic Therapy: A Nationwide, Population-Based Cohort Study
(2015-05-15)
Lin, Chien-Ming
;
Huang, Hui-Ling
;
Chu, Fang-Ying
;
Fan, Hueng-Chuen
;
Chen, Hung-An
Background The relationship between diabetes mellitus (DM) and cancer incidence has been evaluated in limited kinds of cancer. The effect of anti-diabetic therapy (ADT) on carcinogenesis among diabetic patients is also unclear. Materials and Methods Using population-based representative insurance claims data in Taiwan, 36,270 DM patients and 145,080 comparison subjects without DM were identified from claims from 2005 to 2010. The association between the top ten leading causes of cancer-related death in Taiwan and DM was evaluated. Whether ADT altered the risk of developing cancer was also investigated. Results Incidence of cancer at any site was significantly higher in patients with DM than in those without (p<0.001). The risk of carcinogenesis imparted by DM was greatest in gastroenterological malignancies (liver, pancreas, and colorectal cancer) as well as lung, breast and oral cancer (p<0.001). Among the oral types of ADT, metformin decreased the risk of lung and liver cancer, but had less effect on reducing the risk of colorectal cancer. alpha-glucosidase inhibitor decreased the risk of developing liver, colorectal, and breast cancer. Apart from intermediateacting insulin, rapid-acting, long-acting, and combination insulin treatment significantly reduced the overall cancer risk among all DM patients. In subgroup analysis, long-acting insulin treatment significantly decreased the risk of lung, liver, and colorectal cancer. Conclusion Our results supported the notion that pre-existing DM increases the incidence of gastroenterological cancer. ADT, especially metformin, alpha-glucosidase inhibitor, and long-acting insulin treatment, may protect patients with DM against these malignancies. It is crucial that oncologists should closely collaborate with endocrinologists to provide an optimal cancerspecific therapy and diabetic treatment to patients simultaneously with cancer and DM.
Boosting Evolutionary Support Vector Machine for Designing Tumor Classifiers from Microarray Data
(2007)
Huang, Hui-Ling
;
Chen, Yi-Hsiung
;
Koeberl, Dwight D.
;
Ho, Shinn-Ying
;
生物科技學系
Since there are multiple sets of relevant genes having the same high accuracy in fitting training data called model uncertainty, to identify a small set of informative genes from microarray data for designing an accurate tumor classifier for unknown samples is intractable. Support vector machine (SVM), a supervised machine learning technique, is one of the methods successfully applied to cancer diagnosis problems. This study proposes an SVM-based classifier with automatic feature selection associated with a boosting strategy. The proposed boosting evolutionary support vector machine (named BESVM) hybridizes the advantages of SVM, boosting using a majority-voting ensemble and an intelligent genetic algorithm for gene selection. The merits of the BESVM-based classifier are threefold: 1) a small set of used genes, 2) accurate test classification using leave-one-out cross-validation, and 3) robust performance by avoiding overfitting training data. Five benchmark datasets were used to evaluate the BESVM-based classifier. Simulation results reveal that BESVM performs well having a mean accuracy 94.26% using only 10.1 genes averagely, compared with the existing SVM and non-SVM based classifiers.
Bronchial asthma is associated with increased risk of chronic kidney disease
(2014-05-08)
Huang, Hui-Ling
;
Ho, Shinn-Ying
;
Li, Chien-Hsun
;
Chu, Fang-Ying
;
Ciou, Li-Ping
Background: Bronchial asthma influences some chronic diseases such as coronary heart disease, diabetes mellitus, and hypertension, but the impact of asthma on vital diseases such as chronic kidney disease is not yet verified. This study aims to clarify the association between bronchial asthma and the risk of developing chronic kidney disease. Methods: The National Health Research Institute provided a database of one million random subjects for the study. A random sample of 141 064 patients aged >= 18 years without a history of kidney disease was obtained from the database. Among them, there were 35 086 with bronchial asthma and 105 258 without asthma matched for sex and age for a ration of 1:3. After adjusting for confounding risk factors, a Cox proportional hazards model was used to compare the risk of developing chronic kidney disease during a three-year follow-up period. Results: Of the subjects with asthma, 2 196 (6.26%) developed chronic kidney disease compared to 4 120 (3.91%) of the control subjects. Cox proportional hazards regression analysis revealed that subjects with asthma were more likely to develop chronic kidney disease (hazard ratio [HR]: 1.56; 95% CI: 1.48-1.64; p < 0.001). After adjusting for sex, age, monthly income, urbanization level, geographic region, diabetes mellitus, hypertension, hyperlipidemia, and steroid use, the HR for asthma patients was 1.40 (95% CI: 1.33-1.48; p = 0.040). There was decreased HRs in steroid use (HR: 0.56; 95% CI: 0.62-0.61; p < 0.001) in the development of chronic kidney disease. Expectorants, bronchodilators, anti-muscarinic agents, airway smooth muscle relaxants, and leukotriene receptor antagonists may also be beneficial in attenuating the risk of chronic kidney disease. Conclusions: Patients with bronchial asthma may have increased risk of developing chronic kidney disease. The use of steroids or non-steroidal drugs in the treatment of asthma may attenuate this risk.
Characterizing informative sequence descriptors and predicting binding affinities of heterodimeric protein complexes
(2015-12-09)
Srinivasulu, Yerukala Sathipati
;
Wang, Jyun-Rong
;
Hsu, Kai-Ti
;
Tsai, Ming-Ju
;
Charoenkwan, Phasit
Background: Protein-protein interactions (PPIs) are involved in various biological processes, and underlying mechanism of the interactions plays a crucial role in therapeutics and protein engineering. Most machine learning approaches have been developed for predicting the binding affinity of protein-protein complexes based on structure and functional information. This work aims to predict the binding affinity of heterodimeric protein complexes from sequences only. Results: This work proposes a support vector machine (SVM) based binding affinity classifier, called SVM-BAC, to classify heterodimeric protein complexes based on the prediction of their binding affinity. SVM-BAC identified 14 of 580 sequence descriptors (physicochemical, energetic and conformational properties of the 20 amino acids) to classify 216 heterodimeric protein complexes into low and high binding affinity. SVM-BAC yielded the training accuracy, sensitivity, specificity, AUC and test accuracy of 85.80%, 0.89, 0.83, 0.86 and 83.33%, respectively, better than existing machine learning algorithms. The 14 features and support vector regression were further used to estimate the binding affinities (Pkd) of 200 heterodimeric protein complexes. Prediction performance of a Jackknife test was the correlation coefficient of 0.34 and mean absolute error of 1.4. We further analyze three informative physicochemical properties according to their contribution to prediction performance. Results reveal that the following properties are effective in predicting the binding affinity of heterodimeric protein complexes: apparent partition energy based on buried molar fractions, relations between chemical structure and biological activity in principal component analysis IV, and normalized frequency of beta turn. Conclusions: The proposed sequence-based prediction method SVM-BAC uses an optimal feature selection method to identify 14 informative features to classify and predict binding affinity of heterodimeric protein complexes. The characterization analysis revealed that the average numbers of beta turns and hydrogen bonds at protein-protein interfaces in high binding affinity complexes are more than those in low binding affinity complexes.
Design of accurate predictors for DNA-binding sites in proteins using hybrid SVM-PSSM method
(2007-07-01)
Ho, Shinn-Ying
;
Yu, Fu-Chieh
;
Chang, Chia-Yun
;
Huang, Hui-Ling
;
生物科技學系
In this paper, we investigate the design of accurate predictors for DNA-binding sites in proteins from amino acid sequences. As a result, we propose a hybrid method using support vector machine (SVM) in conjunction with evolutionary information of amino acid sequences in terms of their position-specific scoring matrices (PSSMs) for prediction of DNA-binding sites. Considering the numbers of binding and non-binding residues in proteins are significantly unequal, two additional weights as well as SVM parameters are analyzed and adopted to maximize net prediction (NP, an average of sensitivity and specificity) accuracy. To evaluate the generalization ability of the proposed method SVM-PSSM, a DNA-binding dataset PDC-59 consisting of 59 protein chains with low sequence identity on each other is additionally established. The SVM-based method using the same six-fold cross-validation procedure and PSSM features has NP = 80.15% for the training dataset PDNA-62 and NP = 69.54% for the test dataset PDC-59, which are much better than the existing neural network-based method by increasing the NP values for training and test accuracies up to 13.45% and 16.53%, respectively. Simulation results reveal that SVM-PSSM performs well in predicting DNA-binding sites of novel proteins from amino acid sequences. (c) 2006 Elsevier Ireland Ltd. All rights reserved.
Designing predictors of DNA-binding proteinsusing an efficient physicochemical propertymining method
(2010-01-01)
Lin, Yih-Jer
;
Tsai, Chia-Ta
;
Hol, Shinn-Ying
;
Tsai, Chia-Ta
;
Huang, Hui-Ling
DNA-binding proteins play a pivotal role in various intra-and extra-cellular activities ranging from DNA replicationto gene expression control. Many researches mainly focused on prediction and analysis of protein binding sites in DNA. We are interested in predicting binding and non-binding proteins from protein sequences. Physicochemical properties are well recognized to be effective in designing various predictors for understanding the functions and characteristics of proteins. Generally, the domain knowledge of proteins to be analyzed from biologists is needed to select effective physicochemical properties. In this study, we propose an efficient method for designing predictors of binding and non-binding proteins using a set of informative physicochemical properties obtained from an inheritable bi-objective genetic algorithm without using the domain knowledge of binding and non-binding proteins. Three benchmark datasets were used to evaluate the proposed method using SVM and informative physicochemical properties as the features. The prediction accuracy of independent test is close to 80.0%. From the analysis of informative physicochemical properties, some knowledge of binding and non-binding proteins can be further investigated. The proposed physicochemical property mining method can be used conveniently as the core for designing predictors for various DNA-binding problems.
Designing predictors of halophilic and non-halophilic proteins using support vector machines
(2013)
Huang, Hui-Ling
;
Charoenkwan, Phasit
;
Srinivasulu, Yerukala Sathipati
;
Lee, Hua-Chin
;
Ho, Shinn-Ying
Finding the molecular features causes the halophilicity in the halostable organisms is helpful to understand the halophilic adaption. In this study, we proposed a prediction method for halophilic proteins by using a machine learning method. The stages of this study are six-fold. First, we establish a non-redundant dataset of the halophilic proteins, collected from NCBI, Uniprotkb and EMBL-EBI databases. The dataset consists of 245 positive and negative proteins with sequence identity < 25%. Second, the protein sequences are represented by three types of feature vector sets which include amino acid composition, dipeptide composition, and physicochemical properties. Third, we propose three classifiers based on support vector machine (SVM) to classify the halophilic proteins and non-halophilic proteins. Fourth, the independent test accuracies of the three efficient classifiers are larger than 83%. Fifth, an inheritable bi-objective combinatory genetic algorithm is utilized to select a set of 11 physicochemical properties (PCPs). Sixth, these abundant amino acids, high different dipeptides (amino acid pair) and 11 informative PCPs can support to analyze the halophilic and non-halophilic proteins.
Discovery of prognostic biomarkers for predicting lung cancer metastasis using microarray and survival data
(2015-02-21)
Huang, Hui-Ling
;
Wu, Yu-Chung
;
Su, Li-Jen
;
Huang, Yun-Ju
;
Charoenkwan, Phasit
Background: Few studies have investigated prognostic biomarkers of distant metastases of lung cancer. One of the central difficulties in identifying biomarkers from microarray data is the availability of only a small number of samples, which results overtraining. Recently obtained evidence reveals that epithelial-mesenchymal transition (EMT) of tumor cells causes metastasis, which is detrimental to patients' survival. Results: This work proposes a novel optimization approach to discovering EMT-related prognostic biomarkers to predict the distant metastasis of lung cancer using both microarray and survival data. This weighted objective function maximizes both the accuracy of prediction of distant metastasis and the area between the disease-free survival curves of the non-distant and distant metastases. Seventy-eight patients with lung cancer and a follow-up time of 120 months are used to identify a set of gene markers and an independent cohort of 26 patients is used to evaluate the identified biomarkers. The medical records of the 78 patients show a significant difference between the disease-free survival times of the 37 non-distant-and the 41 distant-metastasis patients. The experimental results thus obtained are as follows. 1) The use of disease-free survival curves can compensate for the shortcoming of insufficient samples and greatly increase the test accuracy by 11.10%; and 2) the support vector machine with a set of 17 transcripts, such as CCL16 and CDKN2AIP, can yield a leave-one-out cross-validation accuracy of 93.59%, a test accuracy of 76.92%, a large disease-free survival area of 74.81%, and a mean survival prediction error of 3.99 months. The identified putative biomarkers are examined using related studies and signaling pathways to reveal the potential effectiveness of the biomarkers in prospective confirmatory studies. Conclusions: The proposed new optimization approach to identifying prognostic biomarkers by combining multiple sources of data (microarray and survival) can facilitate the accurate selection of biomarkers that are most relevant to the disease while solving the problem of insufficient samples.
EEG-based Motion Sickness Classification system with Genetic Feature Selection
(2013)
Ko, Li-Wei
;
Lee, Hua-Chin
;
Tsai, Shu-Fang
;
Shih, Tsung-Chin
;
Chuang, Ya-Ting
People tend to get motion sickness on a moving boat, train, airplane, car, or amusement park rides. Many previous studies indicated that motion sickness sometimes led to traffic accidents, so it becomes an important issue in our daily life. In this study, we designed a VIZ-based motion-sickness platform with a 32-channel EEG system and a joystick which is used to report the motion sickness level (MSL) in real time during experiments. The results show it is feasible to estimate subject's MSL based on re-sampling frequency band proved by the high test accuracy. A comparison between general prediction models (such as LDA, QDA, KNN) and IBCGA shows that the IBCGA can be effectively increase the accuracy. In this paper, an extended-IBCGA (e-IBCGA) is proposed and it provides more accuracy than the prior-art research. The test results show that e-IBCGA increases at least 10% to 20% test accuracy in 6 subjects.
ESA-UbiSite: accurate prediction of human ubiquitination sites by identifying a set of effective negatives
(2017-03-01)
Wang, Jyun-Rong
;
Huang, Wen-Lin
;
Tsai, Ming-Ju
;
Hsu, Kai-Ti
;
Huang, Hui-Ling
Motivation: Numerous ubiquitination sites remain undiscovered because of the limitations of mass spectrometry-based methods. Existing prediction methods use randomly selected non-validated sites as non-ubiquitination sites to train ubiquitination site prediction models. Results: We propose an evolutionary screening algorithm (ESA) to select effective negatives among non-validated sites and an ESA-based prediction method, ESA-UbiSite, to identify human ubiquitination sites. The ESA selects non-validated sites least likely to be ubiquitination sites as training negatives. Moreover, the ESA and ESA-UbiSite use a set of well-selected physicochemical properties together with a support vector machine for accurate prediction. Experimental results show that ESA-UbiSite with effective negatives achieved 0.92 test accuracy and a Matthews's correlation coefficient of 0.48, better than existing prediction methods. The ESA increased ESA-UbiSite's test accuracy from 0.75 to 0.92 and can improve other post-translational modification site prediction methods.
Estimating survival time of patients with glioblastoma multiforme and characterization of the identified microRNA signatures
(2016-12-22)
Sathipati, Srinivasulu Yerukala
;
Huang, Hui-Ling
;
Ho, Shinn-Ying
;
生物科技學系
;
生物資訊及系統生物研究所
Background: Though glioblastoma multiforme (GBM) is the most frequently occurring brain malignancy in adults, clinical treatment still faces challenges due to poor prognoses and tumor relapses. Recently, microRNAs ( miRNAs) have been extensively used with the aim of developing accurate molecular therapies, because of their emerging role in the regulation of cancer-related genes. This work aims to identify the miRNA signatures related to survival of GBM patients for developing molecular therapies. Results: This work proposes a support vector regression (SVR)-based estimator, called SVR-GBM, to estimate the survival time in patients with GBM using their miRNA expression profiles. SVR-GBM identified 24 out of 470 miRNAs that were significantly associated with survival of GBM patients. SVR-GBM had a mean absolute error of 0.63 years and a correlation coefficient of 0.76 between the real and predicted survival time. The 10 top-ranked miRNAs according to prediction contribution are as follows: hsa-miR-222, hsa-miR-345, hsa-miR-587, hsa-miR-526a, hsa-miR-335, hsa-miR-122, hsa-miR-24, hsa-miR-433, hsa-miR-574 and hsa-miR-320. Biological analysis using the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway on the identified miRNAs revealed their influence in GBM cancer. Conclusion: The proposed SVR-GBM using an optimal feature selection algorithm and an optimized SVR to identify the 24 miRNA signatures associated with survival of GBM patients. These miRNA signatures are helpful to uncover the individual role of miRNAs in GBM prognosis and develop miRNA-based therapies.
Estimating survival time of patients with glioblastoma multiforme and characterization of the identified microRNA signatures
(2016-12-22)
Sathipati, Srinivasulu Yerukala
;
Huang, Hui-Ling
;
Ho, Shinn-Ying
;
生物科技學系
;
生物資訊及系統生物研究所
Background: Though glioblastoma multiforme (GBM) is the most frequently occurring brain malignancy in adults, clinical treatment still faces challenges due to poor prognoses and tumor relapses. Recently, microRNAs ( miRNAs) have been extensively used with the aim of developing accurate molecular therapies, because of their emerging role in the regulation of cancer-related genes. This work aims to identify the miRNA signatures related to survival of GBM patients for developing molecular therapies. Results: This work proposes a support vector regression (SVR)-based estimator, called SVR-GBM, to estimate the survival time in patients with GBM using their miRNA expression profiles. SVR-GBM identified 24 out of 470 miRNAs that were significantly associated with survival of GBM patients. SVR-GBM had a mean absolute error of 0.63 years and a correlation coefficient of 0.76 between the real and predicted survival time. The 10 top-ranked miRNAs according to prediction contribution are as follows: hsa-miR-222, hsa-miR-345, hsa-miR-587, hsa-miR-526a, hsa-miR-335, hsa-miR-122, hsa-miR-24, hsa-miR-433, hsa-miR-574 and hsa-miR-320. Biological analysis using the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway on the identified miRNAs revealed their influence in GBM cancer. Conclusion: The proposed SVR-GBM using an optimal feature selection algorithm and an optimized SVR to identify the 24 miRNA signatures associated with survival of GBM patients. These miRNA signatures are helpful to uncover the individual role of miRNAs in GBM prognosis and develop miRNA-based therapies.
FRKAS: Knowledge Acquisition Using a Fuzzy Rule Base Approach to Insight of DNA-Binding Domains/Proteins
(2013-03-01)
Huang, Hui-Ling
;
Chang, Fang-Lin
;
Ho, Shinn-Jang
;
Shu, Li-Sun
;
Huang, Wen-Lin
Numerous prediction methods of DNA-binding domains/proteins were proposed by identifying informative features and designing effective classifiers. These researches reveal that the DNA-protein binding mechanism is complicated and existing accurate predictors such as support vector machine (SVM) with position specific scoring matrices (PSSMs) are regarded as black-box methods which are not easily interpretable for biologists. In this study, we propose an ensemble fuzzy rule base classifier consisting of a set of interpretable fuzzy rule classifiers (iFRCs) using informative physicochemical properties as features. In designing iFRCs, feature selection, membership function design, and fuzzy rule base generation are all simultaneously optimized using an intelligent genetic algorithm (IGA). IGA maximizes prediction accuracy, minimizes the number of features selected, and minimizes the number of fuzzy rules to generate an accurate and concise fuzzy rule base. Benchmark datasets of DNA-binding domains are used to evaluate the proposed ensemble classifier of 30 iFRCs. Each iFRC has a mean test accuracy of 77.46%, and the ensemble classifier has a test accuracy of 83.33%, where the method of SVM with PSSMs has the accuracy of 82.81%. The physicochemical properties of the first two ranks according to their contribution are positive charge and Van Der Waals volume. Charge complementarity between protein and DNA is thought to be important in the first step of recognition between protein and DNA. The amino acid residues of binding peptides have larger Van Der Waals volumes and positive charges than those of non-binding ones. The proposed knowledge acquisition method by establishing a fuzzy rule-based classifier can also be applicable to predict and analyze other protein functions from sequences.
HCS-Neurons: identifying phenotypic changes in multi-neuron images upon drug treatments of high-content screening
(2013-10-22)
Charoenkwan, Phasit
;
Hwang, Eric
;
Cutler, Robert W.
;
Lee, Hua-Chin
;
Ko, Li-Wei
Background: High-content screening (HCS) has become a powerful tool for drug discovery. However, the discovery of drugs targeting neurons is still hampered by the inability to accurately identify and quantify the phenotypic changes of multiple neurons in a single image (named multi-neuron image) of a high-content screen. Therefore, it is desirable to develop an automated image analysis method for analyzing multi-neuron images. Results: We propose an automated analysis method with novel descriptors of neuromorphology features for analyzing HCS-based multi-neuron images, called HCS-neurons. To observe multiple phenotypic changes of neurons, we propose two kinds of descriptors which are neuron feature descriptor (NFD) of 13 neuromorphology features, e. g., neurite length, and generic feature descriptors (GFDs), e. g., Haralick texture. HCS-neurons can 1) automatically extract all quantitative phenotype features in both NFD and GFDs, 2) identify statistically significant phenotypic changes upon drug treatments using ANOVA and regression analysis, and 3) generate an accurate classifier to group neurons treated by different drug concentrations using support vector machine and an intelligent feature selection method. To evaluate HCS-neurons, we treated P19 neurons with nocodazole (a microtubule depolymerizing drug which has been shown to impair neurite development) at six concentrations ranging from 0 to 1000 ng/mL. The experimental results show that all the 13 features of NFD have statistically significant difference with respect to changes in various levels of nocodazole drug concentrations (NDC) and the phenotypic changes of neurites were consistent to the known effect of nocodazole in promoting neurite retraction. Three identified features, total neurite length, average neurite length, and average neurite area were able to achieve an independent test accuracy of 90.28% for the six-dosage classification problem. This NFD module and neuron image datasets are provided as a freely downloadable MatLab project at http://iclab.life.nctu.edu.tw/HCS-Neurons. Conclusions: Few automatic methods focus on analyzing multi-neuron images collected from HCS used in drug discovery. We provided an automatic HCS-based method for generating accurate classifiers to classify neurons based on their phenotypic changes upon drug treatments. The proposed HCS-neurons method is helpful in identifying and classifying chemical or biological molecules that alter the morphology of a group of neurons in HCS.
Increased Risk of Chronic Kidney Disease in Rheumatoid Arthritis Associated with Cardiovascular Complications - A National Population-Based Cohort Study
(2015-09-25)
Chiu, Hsien-Yi
;
Huang, Hui-Ling
;
Li, Chien-Hsun
;
Chen, Hung-An
;
Yeh, Chia-Lun
Background and Objectives There have been few large population-based studies of the association between rheumatoid arthritis (RA) and chronic kidney disease (CKD) and glomerulonephritis. This nationwide cohort study investigated the risks of developing CKD and glomerulonephritis in patients with RA, and the associated risks for cardiovascular complications. Methods From the Taiwan National Health Insurance Research Database, we identified a study cohort of 12,579 patients with RA and randomly selected 37,737 subjects without RA as a control cohort. Each subject was individually followed for up for 5 years, and the risk of CKD was analyzed using Cox proportional hazards regression models. Results During the follow-up period, after adjusting for traditional cardiovascular risk factors RA was independently associated with a significantly increased risk of CKD (adjusted hazard ratio [aHR] 1.31; 95% confidence interval [CI] 1.23-1.40) and glomerulonephritis (aHR 1.55; 95% CI 1.37-1.76). Increased risk of CKD was also associated with the use of non-steroidal anti-inflammatory drugs, cyclosporine, glucocorticoids, mycophenolate mofetil, and cyclophosphamide. Patients with comorbidities had even greater increased risk of CKD. Moreover, RA patients with concurrent CKD had significantly higher likelihood of developing ischemic heart disease and stroke. Conclusions RA patients had higher risk of developing CKD and glomerulonephritis, independent of traditional cardiovascular risk factors. Their increased risk of CKD may be attributed to glomerulonephritis, chronic inflammation, comorbidities, and renal toxicity of antirheumatic drugs. Careful monitoring of renal function in RA patients and tight control of their comorbid diseases and cardiovascular risk factors are warranted.
Increased risk of epilepsy in children with Tourette syndrome: A population-based case-control study
(2016-04-05)
Wong, Lee Chin
;
Huang, Hui-Ling
;
Weng, Wen-Chin
;
Jong, Yuh-Jyh
;
Yin, Yun-Ju
The association between epilepsy and Tourette syndrome has rarely been investigated. In this retrospective cohort study, we analyzed a dataset of 1,000,000 randomly sampled individuals from the Taiwan National Health Insurance Research Database to determine the risk of epilepsy in children with Tourette syndrome. The study cohort consisted of 1062 patients with Tourette syndrome aged <= 18 years, and the control group consisted of three times the number of age- and sex-matched patients without Tourette syndrome, who were insurants, from the same database during the same period. The Tourette syndrome group had an 18.38-fold increased risk of epilepsy than the control group [hazard ratio = 18.38, 95% confidence interval (Cl) = 8.26-40.92; P < 0.001]. Even after adjusting for the comorbidities, the risk of epilepsy in the Tourette syndrome group with comorbidities remained high (hazard ratio = 16.27, 95% CI = 6.26-18.46; P < 0.001), indicating that the increased risk was not associated with comorbidities. This population-based retrospective cohort study provides the first and strong evidence that Tourette syndrome is associated with a higher risk of epilepsy. A close follow-up of children with Tourette syndrome for the development of epilepsy is warranted. (C) 2015 Elsevier Ltd. All rights reserved.