Nai-Wen Chang

miRTarBase 2016: updates to the experimentally validated miRNA-target interactions database

MicroRNAs (miRNAs) are small non-coding RNAs of approximately 22 nucleotides, which negatively regulate the gene expression at the post-transcriptional level. This study describes an update of the miRTarBase (http://miRTarBase.mbc.nctu.edu.tw/) that provides information about experimentally validated miRNA-target interactions (MTIs). The latest update of the miRTarBase expanded it to identify systematically Argonaute-miRNA-RNA interactions from 138 crosslinking and immunoprecipitation sequencing (CLIP-seq) data sets that were generated by 21 independent studies. The database contains 4966 articles, 7439 strongly validated MTIs (using reporter assays or western blots) and 348 007 MTIs from CLIP-seq. The number of MTIs in the miRTarBase has increased around 7-fold since the 2014 miRTarBase update. The miRNA and gene expression profiles from The Cancer Genome Atlas (TCGA) are integrated to provide an effective overview of this exponential growth in the miRNA experimental data. These improvements make the miRTarBase one of the more comprehensively annotated, experimentally validated miRNA-target interactions databases and motivate additional miRNA research efforts.

miRTarBase update 2018: a resource for experimentally validated microRNA-target interactions

Abstract MicroRNAs (miRNAs) are small non-coding RNAs of ∼ 22 nucleotides that are involved in negative regulation of mRNA at the post-transcriptional level. Previously, we developed miRTarBase which provides information about experimentally validated miRNA-target interactions (MTIs). Here, we describe an updated database containing 422 517 curated MTIs from 4076 miRNAs and 23 054 target genes collected from over 8500 articles. The number of MTIs curated by strong evidence has increased ∼1.4-fold since the last update in 2016. In this updated version, target sites validated by reporter assay that are available in the literature can be downloaded. The target site sequence can extract new features for analysis via a machine learning approach which can help to evaluate the performance of miRNA-target prediction tools. Furthermore, different ways of browsing enhance user browsing specific MTIs. With these improvements, miRTarBase serves as more comprehensively annotated, experimentally validated miRNA-target interactions databases in the field of miRNA related research. miRTarBase is available at http://miRTarBase.mbc.nctu.edu.tw/.

Coronary artery disease risk assessment from unstructured electronic health records using text mining

Coronary artery disease (CAD) often leads to myocardial infarction, which may be fatal. Risk factors can be used to predict CAD, which may subsequently lead to prevention or early intervention. Patient data such as co-morbidities, medication history, social history and family history are required to determine the risk factors for a disease. However, risk factor data are usually embedded in unstructured clinical narratives if the data is not collected specifically for risk assessment purposes. Clinical text mining can be used to extract data related to risk factors from unstructured clinical notes. This study presents methods to extract Framingham risk factors from unstructured electronic health records using clinical text mining and to calculate 10-year coronary artery disease risk scores in a cohort of diabetic patients. We developed a rule-based system to extract risk factors: age, gender, total cholesterol, HDL-C, blood pressure, diabetes history and smoking history. The results showed that the output from the text mining system was reliable, but there was a significant amount of missing data to calculate the Framingham risk score. A systematic approach for understanding missing data was followed by implementation of imputation strategies. An analysis of the 10-year Framingham risk scores for coronary artery disease in this cohort has shown that the majority of the diabetic patients are at moderate risk of CAD.

A context-aware approach for progression tracking of medical concepts in electronic medical records

Electronic medical records (EMRs) for diabetic patients contain information about heart disease risk factors such as high blood pressure, cholesterol levels, and smoking status. Discovering the described risk factors and tracking their progression over time may support medical personnel in making clinical decisions, as well as facilitate data modeling and biomedical research. Such highly patient-specific knowledge is essential to driving the advancement of evidence-based practice, and can also help improve personalized medicine and care. One general approach for tracking the progression of diseases and their risk factors described in EMRs is to first recognize all temporal expressions, and then assign each of them to the nearest target medical concept. However, this method may not always provide the correct associations. In light of this, this work introduces a context-aware approach to assign the time attributes of the recognized risk factors by reconstructing contexts that contain more reliable temporal expressions. The evaluation results on the i2b2 test set demonstrate the efficacy of the proposed approach, which achieved an F-score of 0.897. To boost the approachs ability to process unstructured clinical text and to allow for the reproduction of the demonstrated results, a set of developed .NET libraries used to develop the system is available at https://sites.google.com/site/hongjiedai/projects/nttmuclinicalnet.

Improving the dictionary lookup approach for disease normalization using enhanced dictionary and query expansion.

The rapidly increasing biomedical literature calls for the need of an automatic approach in the recognition and normalization of disease mentions in order to increase the precision and effectivity of disease based information retrieval. A variety of methods have been proposed to deal with the problem of disease named entity recognition and normalization. Among all the proposed methods, conditional random fields (CRFs) and dictionary lookup method are widely used for named entity recognition and normalization respectively. We herein developed a CRF-based model to allow automated recognition of disease mentions, and studied the effect of various techniques in improving the normalization results based on the dictionary lookup approach. The dataset from the BioCreative V CDR track was used to report the performance of the developed normalization methods and compare with other existing dictionary lookup based normalization methods. The best configuration achieved an F-measure of 0.77 for the disease normalization, which outperformed the best dictionary lookup based baseline method studied in this work by an F-measure of 0.13. Database URL: https://github.com/TCRNBioinformatics/DiseaseExtract

Section Heading Recognition in Electronic Health Records Using Conditional Random Fields

Electronic health records (EHRs) contain a wealth of information, such as discharge diagnoses, laboratory results, and pharmacy orders, which can be used to support clinical decision support systems and enable clinical and translational research. Unfortunately, the information is represented in a highly heterogeneous semi-structured or unstructured format with author- and domain-specific idiosyncrasies, acronyms and abbreviations. To take full advantage of health data, text-mining techniques have been applied by researchers to recognize named entities (NEs) mentioned in EHRs. However, the judgment of clinical data cannot be known solely from the NE level. For instance, a disease mention in the section of past medical history has different clinical significance when mentioned in the family medical history section. To obtain high-quality information and improve the understanding of clinical records, this work developed a machine learning-based section heading recognition system and evaluated its performance on a manually annotated corpus. The experiment results showed that the machine learning-based system achieved a satisfactory F-score of 0.939, which outperformed a dictionary-based system by 0.321.

An Interaction Pattern Kernel Approach for Protein-Protein Interaction Extraction from Biomedical Literature

Discovering the interactions between proteins mentioned in biomedical literature is one of the core topics of text mining in the life sciences. In this paper, we propose an interaction pattern generation approach to capture frequent PPI patterns in text. We also present an interaction pattern tree kernel method that integrates the PPI pattern with convolution tree kernel to extract protein-protein interactions. Empirical evaluations on LLL, IEPA, and HPRD50 corpora demonstrate that our method is effective and outperforms several well-known PPI extraction methods.

Preheated Carbon Source for Carbon Nanotube Synthesis

In this paper, we synthesized single-walled carbon nanotubes (SWCNTs) using chemical vapor deposition (CVD) process in a furnace with three different heating regions. Ferritin nanoparticles were used as catalyst for the CNTs synthesis through carbon source which are methane and ethylene mixture. The reason we used a three stage furnace is to preheat the carbon source at higher temperatures and to synthesize CNTs at lower temperatures. This method can be effective to grow SWNTs at lower temperature. Furnace temperature, methane flow, productivity of CNTs and the diameter distributions of CNTs were considered in the process of CNTs synthesis. The lowest synthesis temperature of CNTs grown from ferritin nanoparticles was 700°C. In the future, it is possible to apply this method to grow CNTs on electronic devices at the lower temperature.

Biomarker identification of hepatocellular carcinoma using a methodical literature mining strategy

Abstract Hepatocellular carcinoma (HCC), one of the most common causes of cancer-related deaths, carries a 5-year survival rate of 18%, underscoring the need for robust biomarkers. In spite of the increased availability of HCC related literatures, many of the promising biomarkers reported have not been validated for clinical use. To narrow down the wide range of possible biomarkers for further clinical validation, bioinformaticians need to sort them out using information provided in published works. Biomedical text mining is an automated way to obtain information of interest within the massive collection of biomedical knowledge, thus enabling extraction of data for biomarkers associated with certain diseases. This method can significantly reduce both the time and effort spent on studying important maladies such as liver diseases. Herein, we report a text mining-aided curation pipeline to identify potential biomarkers for liver cancer. The curation pipeline integrates PubMed E-Utilities to collect abstracts from PubMed and recognize several types of named entities by machine learning-based and pattern-based methods. Genes/proteins from evidential sentences were classified as candidate biomarkers using a convolutional neural network. Lastly, extracted biomarkers were ranked depending on several criteria, such as the frequency of keywords and articles and the journal impact factor, and then integrated into a meaningful list for bioinformaticians. Based on the developed pipeline, we constructed MarkerHub, which contains 2128 candidate biomarkers extracted from PubMed publications from 2008 to 2017. Database URL: http://markerhub.iis.sinica.edu.tw

Combining Multiple Classifiers Using Global Ranking for ReachOut.com Post Triage.

In this paper, we present our methods for the 2016 CLPPsych shared task. We extracted and selected eight features from the corpus consisting of posts from ReachOut.com including the information of the post’s source board, numbers of kudos and views, post time, ranks of the authors, unigram of the body and subject, frequency of the used emotion icons, and the topic model features. Two support vector machine models were trained with the extracted features. A baseline system was also developed, which uses the calculated log likelihood ratio (LLR) for each token to rank a post. Finally, the prediction results of the above three systems were integrated by using a global ranking algorithm with the weighted Borda-fuse (WBF) model and the linear combination model. The best Fscore achieved by our systems is 0.3 which is based on the global ranking method with WBF.