BACKGROUND: Multiple genetic factors and their interactive effects are speculated to contribute to complex diseases. Detecting such genetic interactive effects, i.e., epistatic interactions, however, remains a significant challenge in large-scale association studies. RESULTS: We have developed a new method, named SNPInterForest, for identifying epistatic interactions by extending an ensemble learning technique called random forest. Random forest is a predictive method that has been proposed for use in discovering single-nucleotide polymorphisms (SNPs), which are most predictive of the disease status in association studies. However, it is less sensitive to SNPs with little marginal effect. Furthermore, it does not natively exhibit information on interaction patterns of susceptibility SNPs. We extended the random forest framework to overcome the above limitations by means of (i) modifying the construction of the random forest and (ii) implementing a procedure for extracting interaction patterns from the constructed random forest. The performance of the proposed method was evaluated by simulated data under a wide spectrum of disease models. SNPInterForest performed very well in successfully identifying pure epistatic interactions with high precision and was still more than capable of concurrently identifying multiple interactions under the existence of genetic heterogeneity. It was also performed on real GWAS data of rheumatoid arthritis from the Wellcome Trust Case Control Consortium (WTCCC), and novel potential interactions were reported. CONCLUSIONS: SNPInterForest, offering an efficient means to detect epistatic interactions without statistical analyses, is promising for practical use as a way to reveal the epistatic interactions involved in common complex diseases.

IP networks have evolved into a global and commercial communication infrastructure so that traffic requiring quality of service (QoS) is introduced in addition to best effort traffic. Consequently, network providers need to manage their network resource based on service level agreement (SLA). Conventional distributed routing is not suitable for such SLA based resource management. We propose a QoS control architecture, which provides optimal resource assignment to SLA based traffic applying centralized resource management. We also propose an algorithm to determine QoS control based on resource requests.

Traffic engineering aims to optimize the utilization of existing network resources for load balance and failure recovery, and these are to be accomplished in a scalable fashion. This paper proposes a traffic engineering scheme using multiple multipoint-to-point (m-t-p) label switched paths (LSP) which can reduce the number of LSP and required labels in links. The scheme consists of m-t-p LSP creation and flow assignment. Routes are first selected, and m-t-p LSP are designed to include them. The m-t-p LSP design problem is formulated as a 0-1 integer programming problem. The flow assignment problem is formulated as a mixed integer programming problem in which maximum link load, i.e., maximum congestion, is minimized. Numerical comparisons with the conventional point-to-point LSP approach show that the m-t-p LSP approach can reduce the number of required LSP and labels. Moreover, numerical comparisons with conventional shortest path fast-based flow assignment show that our flow assignment scheme can reduce maximum link load.

This paper proposes the guided restoration algorithm starting at different timing (GRA-DT) which is a scaleable self-healing algorithm that takes into account the buffer size required for the self-healing OAM cells arriving at an ATM crossconnect. In the guided restoration algorithm (GRA) all self-healing processes are started just after VP-AIS cells are detected. Thus if many VPs are affected by failures, a lot of self-healing OAM cells are transmitted during a short period of time. To avoid losing such cells, ATM crossconnects must be equipped with a large size buffer to store the self-healing OAM cells waiting for processing. To reduce the buffer size, we propose the GRA-DT with which self-healing processes are started at different timing for different VPs. This scheme has the effect of dispersing self-healing OAM cell transmission in time. Thus the number of self-healing OAM cells waiting in a buffer decreases and the buffer size can be smaller. This can be achieved by a simple alternation of GRA that adds information on starting timing to one of the VP terminating nodes. The result obtained in evaluating GRA-DT in some lattice networks shows that the number of self-healing OAM cells is about 55-86% of that for GRA in the case of double link failures. In addition, GRA-DT effectively reduces the redundant link resource reservation, and thus the restoration ratio was increased by 20% for the 36 node network in the event of node failures.