MAESTRO--multi agent stability prediction upon point mutations.

BACKGROUND: Point mutations can have a strong impact on protein stability. A change in stability may subsequently lead to dysfunction and finally cause diseases. Moreover, protein engineering approaches aim to deliberately modify protein properties, where stability is a major constraint. In order to support basic research and protein design tasks, several computational tools for predicting the change in stability upon mutations have been developed. Comparative studies have shown the usefulness but also limitations of such programs. RESULTS: We aim to contribute a novel method for predicting changes in stability upon point mutation in proteins called MAESTRO. MAESTRO is structure based and distinguishes itself from similar approaches in the following points: (i) MAESTRO implements a multi-agent machine learning system. (ii) It also provides predicted free energy change (Δ ΔG) values and a corresponding prediction confidence estimation. (iii) It provides high throughput scanning for multi-point mutations where sites and types of mutation can be comprehensively controlled. (iv) Finally, the software provides a specific mode for the prediction of stabilizing disulfide bonds. The predictive power of MAESTRO for single point mutations and stabilizing disulfide bonds is comparable to similar methods. CONCLUSIONS: MAESTRO is a versatile tool in the field of stability change prediction upon point mutations. Executables for the Linux and Windows operating systems are freely available to non-commercial users from http://biwww.che.sbg.ac.at/MAESTRO.

Unstable Footwear Affects Magnitude and Structure of Variability in Postural Control.

This study evaluated the amount, and particularly, the structure of variability in postural control accompanying an unstable shoe (US) application. Mediolateral and anterior-posterior center of pressure signals plus electromyographic profiles of the tibialis anterior and gastrocnemius medialis were recorded in 29 asymptomatic men while wearing both US and flat shoes. Statistical analysis included common measures of dispersion as well as sample entropy and largest Lyapunov exponent estimates. Data were compared by two-way repeated-measures analysis of variance. Corresponding main effects of footwear revealed that, in contrast to the flat shoes condition, the US intervention consistently increased center of pressure and electromyographic net fluctuations and rendered the overall system less complex, as reflected by the lower sample entropy and higher Lyapunov exponent values observed throughout. Accordingly, employing US in stance should be functional concerning motor development; however, the greater sensitivity of US users to external perturbations must not be overlooked and warrants further investigation.

An entropy approach for evaluating adaptive motor learning processes while walking with unstable footwear.

This study evaluated the short- and long-term effects of unstable shoes (US) on the structure/shape of variability in gait. Therefore, sample entropy (SEn) values of centre of mass velocity (vCOM) signals in medio-lateral (ML), anterior-posterior (AP) and vertical (VT) direction were computed for 12 sport students during walking with US and flat shoes (FS) before and after a 10-week accommodation period. Statistical analysis included two-way repeated-measures ANOVA followed by post hoc tests where appropriate (α = 0.05). Most noteworthy, it was found that (1) when compared to FS, using US increased the predictability of vCOM time series, not necessarily always at pre-test, but especially at post-test since (2) the corresponding SEn values decreased for the US condition while remaining stable for the FS condition during the interval between laboratory visits, although (3) the related shoe-by-visit interaction effects were only significant for vCOMML data and not for vCOMAP nor for vCOMVT data. Accordingly, the path of adapting to US was characterised by a "decomplexification" of the motor system; however, the variable practice (i.e., training) loads accompanying such a footwear intervention were probably too small to further expand the overall flexibility capabilities of athletically active persons (in more real-life settings).

Sleep in patients with disorders of consciousness characterized by means of machine learning.

Sleep has been proposed to indicate preserved residual brain functioning in patients suffering from disorders of consciousness (DOC) after awakening from coma. However, a reliable characterization of sleep patterns in this clinical population continues to be challenging given severely altered brain oscillations, frequent and extended artifacts in clinical recordings and the absence of established staging criteria. In the present study, we try to address these issues and investigate the usefulness of a multivariate machine learning technique based on permutation entropy, a complexity measure. Specifically, we used long-term polysomnography (PSG), along with video recordings in day and night periods in a sample of 23 DOC; 12 patients were diagnosed as Unresponsive Wakefulness Syndrome (UWS) and 11 were diagnosed as Minimally Conscious State (MCS). Eight hour PSG recordings of healthy sleepers (N = 26) were additionally used for training and setting parameters of supervised and unsupervised model, respectively. In DOC, the supervised classification (wake, N1, N2, N3 or REM) was validated using simultaneous videos which identified periods with prolonged eye opening or eye closure.The supervised classification revealed that out of the 23 subjects, 11 patients (5 MCS and 6 UWS) yielded highly accurate classification with an average F1-score of 0.87 representing high overlap between the classifier predicting sleep (i.e. one of the 4 sleep stages) and closed eyes. Furthermore, the unsupervised approach revealed a more complex pattern of sleep-wake stages during the night period in the MCS group, as evidenced by the presence of several distinct clusters. In contrast, in UWS patients no such clustering was found. Altogether, we present a novel data-driven method, based on machine learning that can be used to gain new and unambiguous insights into sleep organization and residual brain functioning of patients with DOC.

Towards a framework for agent-based image analysis of remote-sensing data.

Object-based image analysis (OBIA) as a paradigm for analysing remotely sensed image data has in many cases led to spatially and thematically improved classification results in comparison to pixel-based approaches. Nevertheless, robust and transferable object-based solutions for automated image analysis capable of analysing sets of images or even large image archives without any human interaction are still rare. A major reason for this lack of robustness and transferability is the high complexity of image contents: Especially in very high resolution (VHR) remote-sensing data with varying imaging conditions or sensor characteristics, the variability of the objects' properties in these varying images is hardly predictable. The work described in this article builds on so-called rule sets. While earlier work has demonstrated that OBIA rule sets bear a high potential of transferability, they need to be adapted manually, or classification results need to be adjusted manually in a post-processing step. In order to automate these adaptation and adjustment procedures, we investigate the coupling, extension and integration of OBIA with the agent-based paradigm, which is exhaustively investigated in software engineering. The aims of such integration are (a) autonomously adapting rule sets and (b) image objects that can adopt and adjust themselves according to different imaging conditions and sensor characteristics. This article focuses on self-adapting image objects and therefore introduces a framework for agent-based image analysis (ABIA).