BioHackathon 2010 was the third in a series of meetings hosted by the Database Center for Life Sciences (DBCLS) in Tokyo, Japan. The overall goal of the BioHackathon series is to improve the quality and accessibility of life science research data on the Web by bringing together representatives from public databases, analytical tool providers, and cyber-infrastructure researchers to jointly tackle important challenges in the area of in silico biological research.

Interest in research involving health-medical information analysis based on artificial intelligence, especially for deep learning techniques, has recently been increasing. Most of the research in this field has been focused on searching for new knowledge for predicting and diagnosing disease by revealing the relation between disease and various information features of data. These features are extracted by analyzing various clinical pathology data, such as EHR (electronic health records), and academic literature using the techniques of data analysis, natural language processing, etc. However, still needed are more research and interest in applying the latest advanced artificial intelligence-based data analysis technique to bio-signal data, which are continuous physiological records, such as EEG (electroencephalography) and ECG (electrocardiogram). Unlike the other types of data, applying deep learning to bio-signal data, which is in the form of time series of real numbers, has many issues that need to be resolved in preprocessing, learning, and analysis. Such issues include leaving feature selection, learning parts that are black boxes, difficulties in recognizing and identifying effective features, high computational complexities, etc. In this paper, to solve these issues, we provide an encoding-based Wave2vec time series classifier model, which combines signal-processing and deep learning-based natural language processing techniques. To demonstrate its advantages, we provide the results of three experiments conducted with EEG data of the University of California Irvine, which are a real-world benchmark bio-signal dataset. After converting the bio-signals (in the form of waves), which are a real number time series, into a sequence of symbols or a sequence of wavelet patterns that are converted into symbols, through encoding, the proposed model vectorizes the symbols by learning the sequence using deep learning-based natural language processing. The models of each class can be constructed through learning from the vectorized wavelet patterns and training data. The implemented models can be used for prediction and diagnosis of diseases by classifying the new data. The proposed method enhanced data readability and intuition of feature selection and learning processes by converting the time series of real number data into sequences of symbols. In addition, it facilitates intuitive and easy recognition, and identification of influential patterns. Furthermore, real-time large-capacity data analysis is facilitated, which is essential in the development of real-time analysis diagnosis systems, by drastically reducing the complexity of calculation without deterioration of analysis performance by data simplification through the encoding process.

The issue of public health in Korea has attracted significant attention given the aging of the country’s population, which has created many types of social problems. The approach proposed in this article aims to address dementia, one of the most significant symptoms of aging and a public health care issue in Korea. The Korean National Health Insurance Service Senior Cohort Database contains personal medical data of every citizen in Korea. There are many different medical history patterns between individuals with dementia and normal controls. The approach used in this study involved examination of personal medical history features from personal disease history, sociodemographic data, and personal health examinations to develop a prediction model. The prediction model used a support-vector machine learning technique to perform a 10-fold cross-validation analysis. The experimental results demonstrated promising performance (80.9% F-measure). The proposed approach supported the significant influence of personal medical history features during an optimal observation period. It is anticipated that a biomedical “big data”-based disease prediction model may assist the diagnosis of any disease more correctly.

The interaction between biological researchers and the bioinformatics tools they use is still hampered by incomplete interoperability between such tools. To ensure interoperability initiatives are effectively deployed, end-user applications need to be aware of, and support, best practices and standards. Here, we report on an initiative in which software developers and genome biologists came together to explore and raise awareness of these issues: BioHackathon 2009. Developers in attendance came from diverse backgrounds, with experts in Web services, workflow tools, text mining and visualization. Genome biologists provided expertise and exemplar data from the domains of sequence and pathway analysis and glyco-informatics. One goal of the meeting was to evaluate the ability to address real world use cases in these domains using the tools that the developers represented. This resulted in i) a workflow to annotate 100,000 sequences from an invertebrate species; ii) an integrated system for analysis of the transcription factor binding sites (TFBSs) enriched based on differential gene expression data obtained from a microarray experiment; iii) a workflow to enumerate putative physical protein interactions among enzymes in a metabolic pathway using protein structure data; iv) a workflow to analyze glyco-gene-related diseases by searching for human homologs of glyco-genes in other species, such as fruit flies, and retrieving their phenotype-annotated SNPs. Beyond deriving prototype solutions for each use-case, a second major purpose of the BioHackathon was to highlight areas of insufficiency. We discuss the issues raised by our exploration of the problem/solution space, concluding that there are still problems with the way Web services are modeled and annotated, including: i) the absence of several useful data or analysis functions in the Web service "space"; ii) the lack of documentation of methods; iii) lack of compliance with the SOAP/WSDL specification among and between various programming-language libraries; and iv) incompatibility between various bioinformatics data formats. Although it was still difficult to solve real world problems posed to the developers by the biological researchers in attendance because of these problems, we note the promise of addressing these issues within a semantic framework.

Dementia is a cognitive impairment that poses a global threat. Current dementia treatments slow the progression of the disease. The timing of starting such treatment markedly affects the effectiveness of the treatment. Some experts mentioned that the optimal timing for starting the currently available treatment in order to delay progression to dementia is the mild cognitive impairment stage, which is the prior stage of dementia. However, medical records are typically only available at a later stage, i.e., from the early or middle stage of dementia. In order to address this limitation, this study developed a model using national health information data from 5 years prior, to predict dementia development 5 years in the future. The Senior Cohort Database, comprising 550,000 samples, were used for model development. The F-measure of the model predicting dementia development after a 5-year incubation period was 77.38%. Models for a 1- and 3-year incubation period were also developed for comparative analysis of dementia risk factors. The three models had some risk factors in common, but also had unique risk factors, depending on the stage. For the common risk factors, a difference in disease severity was confirmed. These findings indicate that the diagnostic criteria and treatment strategy for dementia should differ depending on the timing. Furthermore, since the results of this study present new dementia risk factors that have not been reported previously, this study may also contribute to identification of new dementia risk factors.

With the global trend toward an aging population, the increasing number of dementia patients and elderly living alone has emerged as a serious social issue in South Korea. The assessment of activities of daily living (ADL) is essential for diagnosing dementia. However, since the assessment is based on the ADL questionnaire, it relies on subjective judgment and lacks objectivity. Seven healthy seniors and six with early-stage dementia participated in the study to obtain ADL data. The derived ADL features were generated by smart home sensors. Statistical methods and machine learning techniques were employed to develop a model for auto-classifying the normal controls and early-stage dementia patients. The proposed approach verified the developed model as an objective ADL evaluation tool for the diagnosis of dementia. A random forest algorithm was used to compare a personalized model and a non-personalized model. The comparison result verified that the accuracy (91.20%) of the personalized model was higher than that (84.54%) of the non-personalized model. This indicates that the cognitive ability-based personalization showed encouraging performance in the classification of normal control and early-stage dementia and it is expected that the findings of this study will serve as important basic data for the objective diagnosis of dementia.