Scalable Feature Selection Applications for Genome-Wide Association Studies of Complex Diseases

Personalized medicine will revolutionize our capabilities to combat disease. Working toward this goal, a fundamental task is the deciphering of geneticvariants that are predictive of complex diseases. Modern studies, in the formof genome-wide association studies (GWAS) have afforded researchers with the opportunity to reveal new genotype-phenotype relationships through the extensive scanning of genetic variants. These studies typically contain over half a million genetic features for thousands of individuals. Examining this with methods other than univariate statistics is a challenging task requiring advanced algorithms that are scalable to the genome-wide level. In the future, next-generation sequencing studies (NGS) will contain an even larger number of common and rare variants. Machine learning-based feature selection algorithms have been shown to have the ability to effectively create predictive models for various genotype-phenotype relationships. This work explores the problem of selecting genetic variant subsets that are the most predictive of complex disease phenotypes through various feature selection methodologies, including filter, wrapper and embedded algorithms. The examined machine learning algorithms were demonstrated to not only be effective at predicting the disease phenotypes, but also doing so efficiently through the use of computational shortcuts. While much of the work was able to be run on high-end desktops, some work was further extended so that it could be implemented on parallel computers helping to assure that they will also scale to the NGS data sets. Further, these studies analyzed the relationships between various feature selection methods and demonstrated the need for careful testing when selecting an algorithm. It was shown that there is no universally optimal algorithm for variant selection in GWAS, but rather methodologies need to be selected based on the desired outcome, such as the number of features to be included in the prediction model. It was also demonstrated that without proper model validation, for example using nested cross-validation, the models can result in overly-optimistic prediction accuracies and decreased generalization ability. It is through the implementation and application of machine learning methods that one can extract predictive genotype–phenotype relationships and biological insights from genetic data sets.

Model-based testing of software systems : functionality and performance

Software is a key component in many of our devices and products that we use every day. Most customers demand not only that their devices should function as expected but also that the software should be of high quality, reliable, fault tolerant, efficient, etc. In short, it is not enough that a calculator gives the correct result of a calculation, we want the result instantly, in the right form, with minimal use of battery, etc. One of the key aspects for succeeding in today's industry is delivering high quality. In most software development projects, high-quality software is achieved by rigorous testing and good quality assurance practices. However, today, customers are asking for these high quality software products at an ever-increasing pace. This leaves the companies with less time for development. Software testing is an expensive activity, because it requires much manual work. Testing, debugging, and verification are estimated to consume 50 to 75 per cent of the total development cost of complex software projects. Further, the most expensive software defects are those which have to be fixed after the product is released. One of the main challenges in software development is reducing the associated cost and time of software testing without sacrificing the quality of the developed software. It is often not enough to only demonstrate that a piece of software is functioning correctly. Usually, many other aspects of the software, such as performance, security, scalability, usability, etc., need also to be verified. Testing these aspects of the software is traditionally referred to as nonfunctional testing. One of the major challenges with non-functional testing is that it is usually carried out at the end of the software development process when most of the functionality is implemented. This is due to the fact that non-functional aspects, such as performance or security, apply to the software as a whole. In this thesis, we study the use of model-based testing. We present approaches to automatically generate tests from behavioral models for solving some of these challenges. We show that model-based testing is not only applicable to functional testing but also to non-functional testing. In its simplest form, performance testing is performed by executing multiple test sequences at once while observing the software in terms of responsiveness and stability, rather than the output. The main contribution of the thesis is a coherent model-based testing approach for testing functional and performance related issues in software systems. We show how we go from system models, expressed in the Unified Modeling Language, to test cases and back to models again. The system requirements are traced throughout the entire testing process. Requirements traceability facilitates finding faults in the design and implementation of the software. In the research field of model-based testing, many new proposed approaches suffer from poor or the lack of tool support. Therefore, the second contribution of this thesis is proper tool support for the proposed approach that is integrated with leading industry tools. We o er independent tools, tools that are integrated with other industry leading tools, and complete tool-chains when necessary. Many model-based testing approaches proposed by the research community suffer from poor empirical validation in an industrial context. In order to demonstrate the applicability of our proposed approach, we apply our research to several systems, including industrial ones.

Spectrally Tuned Lanthanide Photoluminescence for Point-of-Care Testing

Point-of-care (POC) –diagnostics is a field with rapidly growing market share. As these applications become more widely used, there is an increasing pressure to improve their performance to match the one of a central laboratory tests. Lanthanide luminescence has been widely utilized in diagnostics because of the numerous advantages gained by the utilization of time-resolved or anti-Stokes detection. So far the use of lanthanide labels in POC has been scarce due to limitations set by the instrumentation required for their detection and the shortcomings, e.g. low brightness, of these labels. Along with the advances in the research of lanthanide luminescence, and in the field of semiconductors, these materials are becoming a feasible alternative for the signal generation also in the future POC assays. The aim of this thesis was to explore ways of utilizing time-resolved detection or anti-Stokes detection in POC applications. The long-lived fluorescence for the time-resolved measurement can be produced with lanthanide chelates. The ultraviolet (UV) excitation required by these chelates is cumbersome to produce with POC compatible fluorescence readers. In this thesis the use of a novel light-harvesting ligand was studied. This molecule can be used to excite Eu(III)-ions at wavelengths extending up to visible part of the spectrum. An enhancement solution based on this ligand showed a good performance in a proof-of-concept -bioaffinity assay and produced a bright signal upon 365 nm excitation thanks to the high molar absorptivity of the chelate. These features are crucial when developing miniaturized readers for the time-resolved detection of fluorescence. Upconverting phosphors (UCPs) were studied as an internal light source in glucose-sensing dry chemistry test strips and ways of utilizing their various emission wavelengths and near-infrared excitation were explored. The use of nanosized NaYF :Yb3+,Tm3+-particles enabled the replacement of an external UV-light source with a NIR-laser and gave an additional degree of freedom in the optical setup of the detector instrument. The new method enabled a blood glucose measurement with results comparable to a current standard method of measuring reflectance. Microsized visible emitting UCPs were used in a similar manner, but with a broad absorbing indicator compound filtering the excitation and emission wavelengths of the UCP. This approach resulted in a novel way of benefitting from the non-linear relationship between the excitation power and emission intensity of the UCPs, and enabled the amplification of the signal response from the indicator dye.

Stability and predictive ability of beta

The purpose of this paper is to examine the stability and predictive abilities of the beta coefficients of individual equities in the Finnish stock market. As beta is widely used in several areas of finance, including risk management, asset pricing and performance evaluation among others, it is important to understand its characteristics and find out whether its estimates can be trusted and utilized.

TAKING ADVANTAGE OF THE LOCAL ADVANTAGE? - Investment value of the analyst local advantage in the Finnish stock market in 2006–2014

An investor can either conduct independent analysis or rely on the analyses of others. Stock analysts provide markets with expectations regarding particular securities. However, analysts have different capabilities and resources, of which investors are seldom cognizant. The local advantage refers to the advantage stemming from cultural or geographical proximity to securities analyzed. The research has confirmed that local agents are generally more accurate or produce excess returns. This thesis tests the investment value of the local advantage regarding Finnish stocks via target price data. The empirical section investigates the local advantage from several aspects. It is discovered that local analysts were more focused on certain sectors generally located close to consumer markets. Market reactions to target price revisions were generally insignificant with the exception to local positive target prices. Both local and foreign target prices were overly optimistic and exhibited signs of herding. Neither group could be identified as a leader or follower of new information. Additionally, foreign price change expectations were more in line with the quantitative models and ideas such as beta or return mean reversion. The locals were more accurate than foreign analysts in 5 out of 9 sectors and vice versa in one. These sectors were somewhat in line with coverage decisions and buttressed the idea of local advantage stemming from proximity to markets, not to headquarters. The accuracy advantage was dependent on sample years and on the measure used. Local analysts ranked magnitudes of price changes more accurately in optimistic and foreign analysts in pessimistic target prices. Directional accuracy of both groups was under 50% and target prices held no linear predictive power. Investment value of target prices were tested by forming mean-variance efficient portfolios. Parallel to differing accuracies in the levels of expectations foreign portfolio performed better when short sales were allowed and local better when disallowed. Both local and non-local portfolios performed worse than a passive index fund, albeit not statistically significantly. This was in line with previously reported low overall accuracy and different accuracy profiles. Refraining from estimating individual stock returns altogether produced statistically significantly higher Sharpe ratios compared to local or foreign portfolios. The proposed method of testing the investment value of target prices of different groups suffered from some inconsistencies. Nevertheless, these results are of interest to investors seeking the advice of security analysts.

TAKING ADVANTAGE OF THE LOCAL ADVANTAGE? - Investment value of the analyst local advantage in the Finnish stock market in 2006–2014

An investor can either conduct independent analysis or rely on the analyses of others. Stock analysts provide markets with expectations regarding particular securities. However, analysts have different capabilities and resources, of which investors are seldom cognizant. The local advantage refers to the advantage stemming from cultural or geographical proximity to securities analyzed. The research has confirmed that local agents are generally more accurate or produce excess returns. This thesis tests the investment value of the local advantage regarding Finnish stocks via target price data. The empirical section investigates the local advantage from several aspects. It is discovered that local analysts were more focused on certain sectors generally located close to consumer markets. Market reactions to target price revisions were generally insignificant with the exception to local positive target prices. Both local and foreign target prices were overly optimistic and exhibited signs of herding. Neither group could be identified as a leader or follower of new information. Additionally, foreign price change expectations were more in line with the quantitative models and ideas such as beta or return mean reversion. The locals were more accurate than foreign analysts in 5 out of 9 sectors and vice versa in one. These sectors were somewhat in line with coverage decisions and buttressed the idea of local advantage stemming from proximity to markets, not to headquarters. The accuracy advantage was dependent on sample years and on the measure used. Local analysts ranked magnitudes of price changes more accurately in optimistic and foreign analysts in pessimistic target prices. Directional accuracy of both groups was under 50% and target prices held no linear predictive power. Investment value of target prices were tested by forming mean-variance efficient portfolios. Parallel to differing accuracies in the levels of expectations foreign portfolio performed better when short sales were allowed and local better when disallowed. Both local and non-local portfolios performed worse than a passive index fund, albeit not statistically significantly. This was in line with previously reported low overall accuracy and different accuracy profiles. Refraining from estimating individual stock returns altogether produced statistically significantly higher Sharpe ratios compared to local or foreign portfolios. The proposed method of testing the investment value of target prices of different groups suffered from some inconsistencies. Nevertheless, these results are of interest to investors seeking the advice of security analysts.

Automated UI testing. WBCT, a computer-automated user test environment tool.

Today, the user experience and usability in software application are becoming a major design issue due to the adaptation of many processes using new technologies. Therefore, the study of the user experience and usability might be included in every software development project and, thus, they should be tested to get traceable results. As a result of different testing methods to evaluate the concepts, a non-expert on the topic might have doubts on which option he/she should opt for and how to interpret the outcomes of the process. This work aims to create a process to ease the whole testing methodology based on the process created by Seffah et al. and a supporting software tool to follow the procedure of these testing methods for the user experience and usability.