MOTIVATION: Whole-genome sequencing has revolutionized biosciences by providing tools for constructing complete DNA sequences of individuals. With entire genomes at hand, scientists can pinpoint DNA fragments responsible for oncogenesis and predict patient responses to cancer treatments. Machine learning plays a paramount role in this process. However, the sheer volume of whole-genome data makes it difficult to encode the characteristics of genomic variants as features for learning algorithms. RESULTS: In this article, we propose three feature extraction methods that facilitate classifier learning from sets of genomic variants. The core contributions of this work include: (i) strategies for determining features using variant length binning, clustering and density estimation; (ii) a programing library for automating distribution-based feature extraction in machine learning pipelines. The proposed methods have been validated on five real-world datasets using four different classification algorithms and a clustering approach. Experiments on genomes of 219 ovarian, 61 lung and 929 breast cancer patients show that the proposed approaches automatically identify genomic biomarkers associated with cancer subtypes and clinical response to oncological treatment. Finally, we show that the extracted features can be used alongside unsupervised learning methods to analyze genomic samples. AVAILABILITY AND IMPLEMENTATION: The source code of the presented algorithms and reproducible experimental scripts are available on Github at https://github.com/MNMdiagnostics/dbfe. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

This paper presents an overview of what Big Data can bring to the modern industry.Through following the history of contemporary Big Data frameworks the authors observe that the tools available have reached sufficient maturity so as to be usable in an industrial setting.The authors propose the concept of a system for collecting, organising, processing and analysing experimental data obtained from measurements with process tomography.Process tomography is used for noninvasive flow monitoring and data acquisition.The measurement data is collected, stored and processed to identify process regimes and process threats.Further general examples of solutions that aim to take advantage of the existence of such tools are presented as proof of viability of such approach.As the first step in the process of creating the proposed system, a scalable, distributed, containerisation-based cluster has been constructed, with consumer-grade hardware.

This paper investigates the potential of using an electromyographic gesture recognition armband as an everyday companion for operating mobile devices in awareness-requiring contexts and suggests the fields, in which further developments are advisable.The Myo armband from Thalmic Labs is a fully functional motion controller, based on gesture recognition through EMG muscle sensing.The device has been applied for audio control, and the usability and relevance of the gestural interaction have been examined.Participants were asked to operate on a recording while cycling, and a reference group performed similar task in leisure context.The gathered answers suggest decent potential of gestural interaction manner for environments requiring high visual attention, eg.driving or cycling.However, the current state of the solution acts in too sensitive way, as processing numerous misinterpreted gestures highly decreases the system's usability.Moreover, gestures employed are perceived as too apparent and intrusive for social interactions.

The subject of this paper is to compare two different modality multi-touch interactive surfaces based on both: user experience and results of measurements in order to examine how different properties influence usefulness, in specific, their fitness to act as a "coffee table".Tests were conducted on the Microsoft PixelSense (AKA Surface) and a Samsung touch screen overlay both 40+ inches diagonally.The study covers analysis of obtained measurements and summary of user experience collected over a number of summits and experiments.While tests for both devices returned very similar results, with the overlay more favorable, neither device could truly fit the tested use case due to their inconvenience, form factor and other issues.