Browsing by Author "Lin, Yu-Feng"

Now showing 1 - 15 of 15

A novel methodology for stock investment using high utility episode mining and genetic algorithm
(2017-10-01)
Lin, Yu-Feng
;
Huang, Chien-Feng
;
Tseng, Vincent S.
;
資訊工程學系
;
Department of Computer Science
In this paper, we present a novel methodology for stock investment using the technique of high utility episode mining and genetic algorithms. Our objective is to devise a profitable episode-based investment model to reveal hidden events that are associated with high utility in the stock market. The time series data of stock price and the derived technical indicators, including moving average, moving average convergence and divergence, random index and bias index, are used for the construction of episode events. We then employ the genetic algorithm for the simultaneous optimization on parameters and selection of subsets of models. The empirical results show that our proposed method significantly outperforms the state-of-the-art methods in terms of annualized returns of investment and precision. We also provide a set of Z-tests to statistically validate the effectiveness of our proposed method. Based upon the promising results obtained, we expect this novel methodology can advance the research in data mining for computational finance and provide an alternative to stock investment in practice. (C) 2017 Elsevier B.V. All rights reserved.
An Interactive Healthcare System with Personalized Diet and Exercise Guideline Recommendation
(2015)
Tseng, Jerry C. C.
;
Lin, Bo-Hau
;
Lin, Yu-Feng
;
Day, Miin-Luen
;
Wang, Shyh-Chyi
Recently people pay more and more attention on how to effectively and efficiently analyze the result of regular physical examinations to provide the most helpful information for individual health management. In this paper, we design and develop an interactive system of virtual healthcare assistant to help people, especially for those who suffer from chronic diseases (e.g., metabolic syndrome) to easily understand their health conditions and then well manage it. This system analyzes the result of regular physical examination to evaluate the health risk and provide personalized healthcare services for users in terms of diet and exercise guideline recommendations. We developed some interactive ways for users to easily feedback their vital signs to the system and quickly get the suggestions for health management from the system. Besides the browser-based system, we also developed a mobile App that can regularly remind users to carry out the recommendations, which are provided by the system. To prove the system is feasible in the real-world clinical environment, we also applied the Institutional Review Board (IRB) for a human subject research to validate this system. Other than the functional features, there are also several important non-functional features of the extensibility and the convenience for use. First, we use the physical examination result as the raw data to be analyzed. It\'s very convenient for users with very low cost. Second, the system design is extendable, so it can be easily adjusted to work for any chronic ills, even other kinds of diseases. Moreover, it can be extended to provide other kinds of healthcare guideline recommendations as well. These features constitute the main contributions of this work.
Improvement in Mortality and End-Stage Renal Disease in Patients With Type 2 Diabetes After Acute Kidney Injury Who Are Prescribed Dipeptidyl Peptidase-4 Inhibitors
(2018-12-01)
Chen, Cheng-Yi
;
Wu, Vin-Cent
;
Lin, Cheng-Jui
;
Lin, Chih-Sheng
;
Pan, Chi-Feng
Objective: To focus on the potential beneficial effects of the pleiotropic effects of dipeptidyl peptidase-4 inhibitors (DPP4is) on attenuating progression of diabetic kidney disease in reducing the long-term effect of the acute kidney injury (AKI) to chronic kidney disease (CKD) transition. Patients and Methods: Data from the National Health Insurance Research Database from January 1, 1999, to July 31, 2011, were analyzed, and patients with diabetes weaning from dialysis-requiring AKI were identified. Cox proportional hazards models and inverse-weighted estimates of the probability of treatment were used to adjust for treatment selection bias. The outcomes were incident end-stage renal disease (ESRD) and mortality, major adverse cardiovascular events, and hospitalized heart failure. Results: Of a total of 6165 patients with diabetes weaning from dialysis-requiring AKI identified, 5635 (91.4%) patients were DPP4i nonusers and 530 (8.6%) patients were DPP4i users. Compared with DPP4i nonusers, DPP4i users had a lower risk of ESRD (hazard ratio, 0.81; 95% CI, 0.70-0.94; P=.04) and all-cause mortality (hazard ratio, 0.28; 95% CI, 0.23-0.34; P<.001) after adjustments for CKD, advanced CKD, and angiotensin-converting enzyme inhibitor or angiotensin II receptor blocker use. In contrast, the risk of major adverse cardiovascular events and hospitalized heart failure did not differ significantly between groups. Conclusion: Dipeptidyl peptidase-4 inhibitor users had a lower risk of ESRD and mortality than did nonusers among patients with diabetes after weaning from dialysis-requiring AKI. Therefore, a prospective study of AKI to CKD transitions after episodes of AKI is needed to optimally target DPP4i interventions. (C) 2018 Mayo Foundation for Medical Education and Research
MI6: Metal Ion-Binding Site Prediction and Docking Server
(2016-12)
Lin, Yu-Feng
;
Cheng, Chih-Wen
;
Shih, Chung-Shiuan
;
Hwang, Jenn-Kang
;
Yu, Chin-Sheng
The structure of a protein determines its biological function(s) and its interactions with other factors; the binding regions tend to be conserved in sequence and structure, and the interacting residues involved are usually in close 3D space. The Protein Data Bank currently contains more than 110 000 protein structures, approximately one-third of which contain metal ions. Identifying and characterizing metal ion-binding sites is thus essential for investigating a protein\'s function(s) and interactions. However, experimental approaches are time-consuming and costly. The web server reported here was built to predict metal ion-binding residues and to generate the predicted metal ion-bound 3D structure. Binding templates have been constructed for regions that bind 12 types of metal ion-binding residues have been used to construct binding templates. The templates include residues within 3.5 angstrom of the metal ion, and the fragment transformation method was used for structural comparison between query proteins and templates without any data training. Through the adjustment of scoring functions, which are based on the similarity of structure and binding residues. Twelve kinds of metal ions (Ca2+, Cu2+, Fe3+, Mn2+, Zn2+, Cd2+, Fe2+, Ni2+, Hg2+, Co2+, and Cu+) binding residues prediction are supported. MIB also provides the metal ions docking after prediction. The MIB server is available at http://bioinfo.cmu.edu.tw/MIB/.
Mining Disease Sequential Risk Patterns from Nationwide Clinical Databases for Early Assessment of Chronic Obstructive Pulmonary Disease
(2016)
Cheng, Yi-Ting
;
Lin, Yu-Feng
;
Chiang, Kuo-Hwa
;
Tseng, Vincent S.
;
資訊工程學系
Chronic diseases may cause heavy burden on health care resources and disturb the quality of life. Chronic Obstructive Pulmonary Disease (COPD) is an important chronic disease, which takes a long period of time to progress and hard to detect in early stage. In this work, we propose a novel approach for early assessment on COPD by mining COPD-related sequential risk patterns from diagnostic clinical records using sequential rule mining and classification techniques. Through experimental evaluation on a large-scale nationwide clinical database in Taiwan, our approach is shown to be not only capable of deriving many sequential risk patterns, but also reliable in prediction results. Moreover, the discovered sequential risk patterns may provide potential clues for physicians to derive novel markers for early detection on COPD. To our best knowledge, this is the first work that addresses the important issue of early assessment on COPD through mining sequential risk patterns from large-scale clinical databases.
Mining Sequential Risk Patterns From Large-Scale Clinical Databases for Early Assessment of Chronic Diseases: A Case Study on Chronic Obstructive Pulmonary Disease
(2017-03-01)
Cheng, Yi-Ting
;
Lin, Yu-Feng
;
Chiang, Kuo-Hwa
;
Tseng, Vincent S.
;
資訊工程學系
Chronic diseases have been among the major concerns in medical fields since they may cause a heavy burden on healthcare resources and disturb the quality of life. In this paper, we propose a novel framework for early assessment on chronic diseases by mining sequential risk patterns with time interval information from diagnostic clinical records using sequential rules mining, and classification modeling techniques. With a complete workflow, the proposed framework consists of four phases namely data preprocessing, risk pattern mining, classification modeling, and post analysis. For empiricasl evaluation, we demonstrate the effectiveness of our proposed framework with a case study on early assessment of COPD. Through experimental evaluation on a large-scale nationwide clinical database in Taiwan, our approach can not only derive rich sequential risk patterns but also extract novel patterns with valuable insights for further medical investigation such as discovering novel markers and better treatments. To the best of our knowledge, this is the first work addressing the issue of mining sequential risk patterns with time-intervals as well as classification models for early assessment of chronic diseases.
On the relationship between residue structural environment and sequence conservation in proteins
(2017-09-01)
Liu, Jen-Wei
;
Lin, Jau-Ji
;
Cheng, Chih-Wen
;
Lin, Yu-Feng
;
Hwang, Jenn-Kang
Residues that are crucial to protein function or structure are usually evolutionarily conserved. To identify the important residues in protein, sequence conservation is estimated, and current methods rely upon the unbiased collection of homologous sequences. Surprisingly, our previous studies have shown that the sequence conservation is closely correlated with the weighted contact number (WCN), a measure of packing density for residue's structural environment, calculated only based on the C-alpha positions of a protein structure. Moreover, studies have shown that sequence conservation is correlated with environment-related structural properties calculated based on different protein substructures, such as a protein's all atoms, backbone atoms, side-chain atoms, or side-chain centroid. To know whether the C-alpha atomic positions are adequate to show the relationship between residue environment and sequence conservation or not, here we compared C-alpha atoms with other substructures in their contributions to the sequence conservation. Our results show that C-alpha positions are substantially equivalent to the other substructures in calculations of various measures of residue environment. As a result, the overlapping contributions between C-alpha atoms and the other substructures are high. yielding similar structure-conservation relationship. Take the WCN as an example, the average overlapping contribution to sequence conservation is 87% between C-alpha, and all-atom substructures. These results indicate that only C-alpha atoms of a protein structure could reflect sequence conservation at the residue level.
Osteoblast-secreted WISP-1 promotes adherence of prostate cancer cells to bone via the VCAM-1/integrin alpha 4 beta 1 system
(2018-01-01)
Chang, An-Chen
;
Chen, Po-Chun
;
Lin, Yu-Feng
;
Su, Chen-Ming
;
Liu, Ju-Fang
Bone metastasis is a frequent occurrence in prostate cancer (PCa) that is associated with severe complications such as fracture, bone pain and hypercalcemia. The cross-talk between metastatic cancer cells and bone is critical to the development and progression of bone metastases. In our previous data, we have described how the involvement of the Wnt-induced secreted protein-1/vascular cell adhesion molecule-1 (WISP-1/VCAM-1) system in this tumor bone interaction contributes to human PCa cell motility. In this study, we found that WISP-1 regulates bone mineralization by inducing bone morphogenetic protein-2 (BMP2), BMP4 and osteopontin (OPN) expression in osteoblasts. We also found that WISP-1 inhibited RANKL-dependent osteoclastogenesis. Moreover, osteoblast-derived WISP-1 enhanced VCAM-1 expression in PCa cells and subsequently promoted the adherence of cancer cells to osteoblasts. Furthermore, endothelin-1 (ET-1) expression in PCa cells was regulated by osteoblast-derived WISP-1, which promoted integrin alpha 4 beta 1 expression in osteoblasts via the MAPK pathway. Pretreatment of PCa cells with VCAM-1 antibody or osteoblasts with integrin alpha 4 beta 1 antibody attenuated the adherence of PCa cells to osteoblasts, suggesting that integrin alpha 4 beta 1 serves as a ligand that captures VCAM-1(+) metastatic tumor cells adhering to osteoblasts. Our findings reveal that osteoblast-derived WISP-1 plays a key role in regulating the adhesion of PCa cells to osteoblasts via the VCAM-1/integrin alpha 4 beta 1 system. Osteoblast-derived WISP-1 is a promising target for the prevention and inhibition of PCa-bone interaction. (C) 2018 Elsevier B.V. All rights reserved.
Periostin promotes epithelial-mesenchymal transition via the MAPK/miR-381 axis in lung cancer
(2017-09-05)
Hu, Wei-Wei
;
Chen, Po-Chun
;
Chen, Jun-Ming
;
Wu, Yue-Ming
;
Liu, Po-Yi
Periostin (POSTN, PN, or osteoblast-specific factor OSF-2) is a multifunctional cytokine that signals between the cell and the extracellular matrix. Periostin plays an important role in tumor development and is involved in carcinoma cell epithelial-mesenchymal transition (EMT), whereby mature epithelial cells undergo phenotypic morphological changes and become invasive, motile cells. Here, we discuss the molecular mechanisms involved in periostin-induced promotion of EMT in lung cancer cells. Online TCGA datasets demonstrate the prognostic relevance of periostin in lung cancer; a higher periostin level correlates with poor overall survival. Similarly, our IHC results show that high periostin expression is positively correlated with the EMT markers Snail and Twist, as well as stage of lung cancer. We found that recombinant periostin induces the EMT phenotype in lung cancer cells through the p38/ERK pathway, while pretreatment with chemical inhibitors prevented periostin-induced EMT induction. Moreover, we found that periostin regulates EMT by repressing microRNA-381 (miR-381) expression, which targets both Snail and Twist. Using the miR-381 mimic, we dramatically reversed periostin-induced Snail and Twist expression. Furthermore, periostin knockdown dramatically affected EMT markers and cell migration potential. The role of periostin in lung cancer progression is elucidated by the in vivo mouse model. Our findings indicate that changes in periostin expression in lung cancer may serve as a therapeutic target for the treatment of lung cancer metastasis.
Predicting Flavin and Nicotinamide Adenine Dinucleotide-Binding Sites in Proteins Using the Fragment Transformation Method
(2015-01-01)
Lu, Chih-Hao
;
Yu, Chin-Sheng
;
Lin, Yu-Feng
;
Chen, Jin-Yi
;
生物資訊及系統生物研究所
We developed a computational method to identify NAD- and FAD-binding sites in proteins. First, we extracted from the Protein Data Bank structures of proteins that bind to at least one of these ligands. NAD-/FAD-binding residue templates were then constructed by identifying binding residues through the ligand-binding database BioLiP. The fragment transformation method was used to identify structures within query proteins that resembled the ligand-binding templates. By comparing residue types and their relative spatial positions, potential binding sites were identified and a ligand-binding potential for each residue was calculated. Setting the false positive rate at 5%, our method predicted NAD- and FAD-binding sites at true positive rates of 67.1% and 68.4%, respectively. Our method provides excellent results for identifying FAD- and NAD-binding sites in proteins, and the most important is that the requirement of conservation of residue types and local structures in the FAD- and NAD-binding sites can be verified.
Prediction of Metal Ion-Binding Sites in Proteins Using the Fragment Transformation Method
(2012-06-18)
Lu, Chih-Hao
;
Lin, Yu-Feng
;
Lin, Jau-Ji
;
Yu, Chin-Sheng
;
生物資訊及系統生物研究所
The structure of a protein determines its function and its interactions with other factors. Regions of proteins that interact with ligands, substrates, and/or other proteins, tend to be conserved both in sequence and structure, and the residues involved are usually in close spatial proximity. More than 70,000 protein structures are currently found in the Protein Data Bank, and approximately one-third contain metal ions essential for function. Identifying and characterizing metal ion-binding sites experimentally is time-consuming and costly. Many computational methods have been developed to identify metal ion-binding sites, and most use only sequence information. For the work reported herein, we developed a method that uses sequence and structural information to predict the residues in metal ion-binding sites. Six types of metal ion-binding templates-those involving Ca2+, Cu2+, Fe3+, Mg2+, Mn2+, and Zn2+-were constructed using the residues within 3.5 angstrom of the center of the metal ion. Using the fragment transformation method, we then compared known metal ion-binding sites with the templates to assess the accuracy of our method. Our method achieved an overall 94.6 % accuracy with a true positive rate of 60.5 % at a 5 % false positive rate and therefore constitutes a significant improvement in metal-binding site prediction.
Relationships between residue Voronoi volume and sequence conservation in proteins
(2018-02-01)
Liu, Jen-Wei
;
Cheng, Chih-Wen
;
Lin, Yu-Feng
;
Chen, Shao-Yu
;
Hwang, Jenn-Kang
Background: Functional and biophysical constraints can cause different levels of sequence conservation in proteins. Previously, structural properties, e.g., relative solvent accessibility (RSA) and packing density of the weighted contact number (WCN), have been found to be related to protein sequence conservation (CS). The Voronoi volume has recently been recognized as a new structural property of the local protein structural environment reflecting CS. However, for surface residues, it is sensitive to water molecules surrounding the protein structure. Herein, we present a simple structural determinant termed the relative space of Voronoi volume (RSV); it uses the Voronoi volume and the van der Waals volume of particular residues to quantify the local structural environment. Methods: RSV (range, 0-1) is defined as (Voronoi volume - van der Waals volume)/Voronoi volume of the target residue. The concept of RSV describes the extent of available space for every protein residue. Results: RSV and Voronoi profiles with and without water molecules (RSVw, RSV, VOw, and VO) were compared for 554 non-homologous proteins. RSV (without water) showed better Pearson's correlations with CS than did RSVw, VO, or VOw values. The mean correlation coefficient between RSV and CS was 0.51, which is comparable to the correlation between RSA and CS (0.49) and that between WCN and CS (0.56). Conclusions: RSV is a robust structural descriptor with and without water molecules and can quantitatively reflect evolutionary information in a single protein structure. Therefore, it may represent a practical structural determinant to study protein sequence, structure, and function relationships.
Reliable Early Classification on Multivariate Time Series with Numerical and Categorical Attributes
(2015-01-01)
Lin, Yu-Feng
;
Chen, Hsuan-Hsu
;
Tseng, Vincent S.
;
Pei, Jian
;
資訊工程學系
Early classification on multivariate time series has recently emerged as a novel and important topic in data mining fields with wide applications such as early detection of diseases in healthcare domains. Most of the existing studies on this topic focused only on univariate time series, while some very recent works exploring multivariate time series considered only numerical attributes and are not applicable to multivariate time series containing both of numerical and categorical attributes. In this paper, we present a novel methodology named REACT (Reliable EArly ClassificaTion), which is the first work addressing the issue of constructing an effective classifier on multivariate time series with numerical and categorical attributes in serial manner so as to guarantee stability of accuracy compared to the classifiers using full-length time series. Furthermore, we also employ the GPU parallel computing technique to develop an extended mechanism for building the early classifier efficiently. Experimental results on real datasets show that REACT significantly outperforms the state-of-the-art method in terms of accuracy and earliness, and the GPU implementation is verified to substantially enhance the efficiency by several orders of magnitudes.
Thrombospondin 2 promotes tumor metastasis by inducing matrix metalloproteinase-13 production in lung cancer cells
(2018-09-01)
Liu, Ju-Fang
;
Lee, Chiang-Wen
;
Tsai, Ming-Horng
;
Tang, Chih-Hsin
;
Chen, Po-Chun
Thrombospondin (TSP)-2, a matricellular glycoprotein of the TSP family, regulates multiple biological functions, including proliferation, angiogenesis, cell adhesion, and extracellular matrix (ECM) modeling. The clinical relevance of TSP-2 has been explored in many different cancers. TSP-2 expression levels vary between different cancer types, and their role in tumor progression remains controversial. Although previous studies have reported higher serum TSP-2 levels in patients with non-small cell lung cancer, the role of TSP-2 in lung cancer progression remains to be addressed. A total of 585 lung adenocarcinoma datasets, including mRNA sequencing and clinical data, were retrieved from The Cancer Genome Atlas (TCGA). Forty paired adjacent normal tissues and lung tumor tissue datasets were used to examine TSP-2 expression levels. Tumor microarray were performed with immunohistochemical staining to examine TSP-2 expression in lung cancer patients. Transwell migration assay, quantitative real-time PCR and Western blot were used to investigate molecular mechanism of TSP-2 in lung cancer cell. TSP-2 promotes matrix metalloproteinase-13 (MMP-13) expression, cell migration, and cell invasion by mediating integrin alpha v beta 3/FAK/Akt/NF-kappa B signal transduction. Using TSP-2 knockdown stable cell lines, we found that TSP-2 knockdown reduces MMP-13 expression and cell mobility. When we manipulated the tumor tissue microarray and TCGA datasets to investigate the clinical relevance of TSP-2, we found high TSP-2 expression levels in lung cancer specimens. The present study demonstrates that TSP-2 regulates cell mobility through MMP-13 expression in lung cancer cells. In addition, TSP-2 expression was associated with MMP-13 expression and poor prognosis in lung cancer. TSP-2 may therefore be a promising novel target for lung cancer treatment.
Understanding the functional properties of bio-inorganic nanoflowers as biocatalysts by deciphering the metal-binding sites of enzymes
(2017-06-21)
Escobar, Sindy
;
Velasco-Lozano, Susana
;
Lu, Chih-Hao
;
Lin, Yu-Feng
;
Mesa, Monica
The biomineralisation of metal phosphates is a promising approach to develop more efficient nano-biocatalysts; however, the interactions between the protein and the inorganic mineral are poorly understood. Elucidating which protein regions most likely participate in the mineral formation will guide the fabrication of more efficient biocatalysts based on metal-phosphate nanoflowers. We have biomineralised the lipase from Thermomyces lanuginosus using three calcium, zinc and copper phosphates to fabricate different types of bio-inorganic nanoflowers. To better understand how the biomineralisation process affects the enzyme properties, we have computationally predicted the protein regions with a higher propensity for binding Ca2+, Cu2+ and Zn2+. These binding sites can be considered as presumable nucleation points where the biomineralisation process starts and explain why different metals can form bio-inorganic nanoflowers of the same enzyme with different functional properties. The formation of calcium, copper and zinc phosphates in the presence of this lipase gives rise to nanoflowers with different morphologies and different enzymatic properties such as activity, stability, hyperactivation and activity-pH profile; these functional differences are supported by structural studies based on fluorescence spectroscopy and can be explained by the different locations of the predicted nucleation sites for the different metals. Among the three metals used herein, the mineralisation of this lipase with zinc-phosphate enables the fabrication of bio-inorganic nanoflowers 34 times more stable than the soluble enzyme. These bio-inorganic nanoflowers were reused for 8 reaction cycles achieving 100% yield in the hydrolysis of p-nitrophenol butyrate but losing more than 50% of their initial activity after 6 operational cycles. Finally, this heterogeneous biocatalyst was more active and enantioselective than the soluble enzyme (ee = 79%(R)) towards the kinetic resolution of rac-1-phenylethyl acetate yielding the R enantiomer with ee = 84%.