Helsinki Institute for Information Technology

About: Helsinki Institute for Information Technology is a facility organization based out in Espoo, Finland. It is known for research contribution in the topics: Population & Bayesian network. The organization has 630 authors who have published 1962 publications receiving 63426 citations.

Machine learning approaches for drug combination therapies.

Abstract: Drug combination therapy is a promising strategy to treat complex diseases such as cancer and infectious diseases. However, current knowledge of drug combination therapies, especially in cancer patients, is limited because of adverse drug effects, toxicity and cell line heterogeneity. Screening new drug combinations requires substantial efforts since considering all possible combinations between drugs is infeasible and expensive. Therefore, building computational approaches, particularly machine learning methods, could provide an effective strategy to overcome drug resistance and improve therapeutic efficacy. In this review, we group the state-of-the-art machine learning approaches to analyze personalized drug combination therapies into three categories and discuss each method in each category. We also present a short description of relevant databases used as a benchmark in drug combination therapies and provide a list of well-known, publicly available interactive data analysis portals. We highlight the importance of data integration on the identification of drug combinations. Finally, we address the advantages of combining multiple data sources on drug combination analysis by showing an experimental comparison.

Distributed user authentication in wireless LANs

Abstract: An increasing number of mobile devices, including smartphones, use WLAN for accessing the Internet. Existing WLAN authentication mechanisms are either disruptive, such as presenting a captive web page prompting for password, or unreliable, enabling a malicious user to attack a part of operator's infrastructure. In this paper, we present a distributed authentication architecture for WLAN users providing instant network access without manual interactions. It supports terminal mobility across WLAN access points with the Host Identity Protocol (HIP), at the same time protecting the operator's infrastructure from external attacks. User data sent over a wireless link is protected by the IPsec ESP protocol. We present our architecture design and implementation experience on two OpenWrt WLAN access points, followed by measurement results of the working prototype. The system is being deployed into pilot use in the city-wide panOULU WLAN.

Association analysis for quantitative traits by data mining: QHPM.

Abstract: Previously, we have presented a data mining-based algorithmic approach to genetic association analysis, Haplotype Pattern Mining. We have now extended the approach with the possibility of analysing quantitative traits and utilising covariates. This is accomplished by using a linear model for measuring association. We present results with the extended version, QHPM, with simulated quantitative trait data. One data set was simulated with the population simulator package Populus, and another was obtained from GAW12. In the former, there were 2–3 underlying susceptibility genes for a trait, each with several ancestral disease mutations, and 1 or 2 environmental components. We show that QHPM is capable of finding the susceptibility loci, even when there is strong allelic heterogeneity and environmental effects in the disease models. The power of finding quantitative trait loci is dependent on the ascertainment scheme of the data: collecting the study subjects from both ends of the quantitative trait distribution is more effective than using unselected individuals or individuals ascertained based on disease status, but QHPM has good power to localize the genes even with unselected individuals. Comparison with quantitative trait TDT (QTDT) showed that QHPM has better localization accuracy when the gene effect is weak.

Visible - actionable - sustainable: sustainable interaction design in professional domains

Abstract: The growing body of sustainable HCI shows that new interfaces may increase awareness and motivate action for environmental impact. Most of this research has been aimed at consumer decision-making, leaving out many professional domains. This workshop broadens the scope of HCI research to consider new user groups including professional users, educators, designers and engineers, governments and NGO's. We propose a broad approach to sustainable HCI for emerging domains: visible - actionable - sustainable. In order to effect sustainable change, new interfaces need to make issues visible in order to promote actionable decisions towards socially and environmentally sustainable ends. These approaches can support sustainable decision-making in product design and a variety of sectors. This workshop will gather interdisciplinary case studies to help identify emerging domains of where sustainable interaction design could provide important social and environmental benefit. The expected outcome is the start of a pattern language for sustainability solutions to the most promising application domains. Patterns are named solutions to recurring problems with enough flexibility to be applied in new contexts. Pattern languages have been developed for architecture and urban planning, object-oriented programming, change management, HCI, and pedagogy. We choose to structure the workshop around the concepts and techniques of pattern languages because because they focus the attention of the community on creating and sharing expertise on what works in general and in a form and format that is useful to designers who are working on specific solutions for specific contexts. The workshop will consider submissions to inform a pattern language from a number of potential application domains for sustainable interaction design including professional users, education, food and drink, marketing and sales, governments, NGOs, designers and engineers.