Quantifying the kinetic paths of flexible biomolecular recognition

Biomolecular recognition often involves large conformational changes, sometimes even local unfolding. The identification of kinetic pathways has become a central issue in understanding the nature of binding. A new approach is proposed here to study the dynamics of this binding-folding process through the establishment of a path-integral framework on the underlying energy landscape. The dominant kinetic paths of binding and folding can be determined and quantified. The significant coupling between the binding and folding of biomolecules often exists in many important cellular processes. In this case, the corresponding kinetic paths of binding are shown to be intimately correlated with those of folding and the dynamics becomes quite cooperative. This implies that binding and folding happen concurrently. When the coupling between binding and folding is weak (strong), the kinetic process usually starts with significant folding (binding) first, with the binding (folding) later proceeding to the end. The kinetic rate can be obtained through the contributions from the dominant paths. The rate is shown to have a bell-shaped dependence on temperature in the concentration-saturated regime consistent with experiment. The changes of the kinetics that occur upon changing the parameters of the underlying binding-folding energy landscape are studied.

Generalized Langevin equation: An efficient approach to nonequilibrium molecular dynamics of open systems

The generalized Langevin equation (GLE) has been recently suggested to simulate the time evolution of classical solid and molecular systems when considering general nonequilibrium processes. In this approach, a part of the whole system (an open system), which interacts and exchanges energy with its dissipative environment, is studied. Because the GLE is derived by projecting out exactly the harmonic environment, the coupling to it is realistic, while the equations of motion are non-Markovian. Although the GLE formalism has already found promising applications, e. g., in nanotribology and as a powerful thermostat for equilibration in classical molecular dynamics simulations, efficient algorithms to solve the GLE for realistic memory kernels are highly nontrivial, especially if the memory kernels decay nonexponentially. This is due to the fact that one has to generate a colored noise and take account of the memory effects in a consistent manner. In this paper, we present a simple, yet efficient, algorithm for solving the GLE for practical memory kernels and we demonstrate its capability for the exactly solvable case of a harmonic oscillator coupled to a Debye bath.

Co-Exploration of NLA Kernels and Specification of Compute Elements in Distributed Memory CGRAs

Coarse Grained Reconfigurable Architectures (CGRA) are emerging as embedded application processing units in computing platforms for Exascale computing. Such CGRAs are distributed memory multi- core compute elements on a chip that communicate over a Network-on-chip (NoC). Numerical Linear Algebra (NLA) kernels are key to several high performance computing applications. In this paper we propose a systematic methodology to obtain the specification of Compute Elements (CE) for such CGRAs. We analyze block Matrix Multiplication and block LU Decomposition algorithms in the context of a CGRA, and obtain theoretical bounds on communication requirements, and memory sizes for a CE. Support for high performance custom computations common to NLA kernels are met through custom function units (CFUs) in the CEs. We present results to justify the merits of such CFUs.

Automatic FPGA Synthesis of Memory Intensive C-based Kernels

Realising high performance image and signal processing
applications on modern FPGA presents a challenging implementation problem due to the large data frames streaming through these systems. Specifically, to meet the high bandwidth and data storage demands of these applications, complex hierarchical memory architectures must be manually specified
at the Register Transfer Level (RTL). Automated approaches which convert high-level operation descriptions, for instance in the form of C programs, to an FPGA architecture, are unable to automatically realise such architectures. This paper
presents a solution to this problem. It presents a compiler to automatically derive such memory architectures from a C program. By transforming the input C program to a unique dataflow modelling dialect, known as Valved Dataflow (VDF), a mapping and synthesis approach developed for this dialect can
be exploited to automatically create high performance image and video processing architectures. Memory intensive C kernels for Motion Estimation (CIF Frames at 30 fps), Matrix Multiplication (128x128 @ 500 iter/sec) and Sobel Edge Detection (720p @ 30 fps), which are unrealisable by current state-of-the-art C-based synthesis tools, are automatically derived from a C description of the algorithm.

Constructive Synthesis of Memory-Intensive Accelerators for FPGA From Nested Loop Kernels

Field-programmable gate arrays are ideal hosts to custom accelerators for signal, image, and data processing but de- mand manual register transfer level design if high performance and low cost are desired. High-level synthesis reduces this design burden but requires manual design of complex on-chip and off-chip memory architectures, a major limitation in applications such as video processing. This paper presents an approach to resolve this shortcoming. A constructive process is described that can derive such accelerators, including on- and off-chip memory storage from a C description such that a user-defined throughput constraint is met. By employing a novel statement-oriented approach, dataflow intermediate models are derived and used to support simple ap- proaches for on-/off-chip buffer partitioning, derivation of custom on-chip memory hierarchies and architecture transformation to ensure user-defined throughput constraints are met with minimum cost. When applied to accelerators for full search motion estima- tion, matrix multiplication, Sobel edge detection, and fast Fourier transform, it is shown how real-time performance up to an order of magnitude in advance of existing commercial HLS tools is enabled whilst including all requisite memory infrastructure. Further, op- timizations are presented that reduce the on-chip buffer capacity and physical resource cost by up to 96% and 75%, respectively, whilst maintaining real-time performance.

CUDA-for-clusters: a system for efficient execution of CUDA kernels on multi-core clusters

Rapid advancements in multi-core processor architectures coupled with low-cost, low-latency, high-bandwidth interconnects have made clusters of multi-core machines a common computing resource. Unfortunately, writing good parallel programs that efficiently utilize all the resources in such a cluster is still a major challenge. Various programming languages have been proposed as a solution to this problem, but are yet to be adopted widely to run performance-critical code mainly due to the relatively immature software framework and the effort involved in re-writing existing code in the new language. In this paper, we motivate and describe our initial study in exploring CUDA as a programming language for a cluster of multi-cores. We develop CUDA-For-Clusters (CFC), a framework that transparently orchestrates execution of CUDA kernels on a cluster of multi-core machines. The well-structured nature of a CUDA kernel, the growing popularity, support and stability of the CUDA software stack collectively make CUDA a good candidate to be considered as a programming language for a cluster. CFC uses a mixture of source-to-source compiler transformations, a work distribution runtime and a light-weight software distributed shared memory to manage parallel executions. Initial results on running several standard CUDA benchmark programs achieve impressive speedups of up to 7.5X on a cluster with 8 nodes, thereby opening up an interesting direction of research for further investigation.

Use of shared memory in the context of embedded multi-core processors: exploration of the technology and its limits

Modern embedded systems embrace many-core shared-memory designs. Due to constrained power and area budgets, most of them feature software-managed scratchpad memories instead of data caches to increase the data locality. It is therefore programmers’ responsibility to explicitly manage the memory transfers, and this make programming these platform cumbersome. Moreover, complex modern applications must be adequately parallelized before they can the parallel potential of the platform into actual performance. To support this, programming languages were proposed, which work at a high level of abstraction, and rely on a runtime whose cost hinders performance, especially in embedded systems, where resources and power budget are constrained. This dissertation explores the applicability of the shared-memory paradigm on modern many-core systems, focusing on the ease-of-programming. It focuses on OpenMP, the de-facto standard for shared memory programming. In a first part, the cost of algorithms for synchronization and data partitioning are analyzed, and they are adapted to modern embedded many-cores. Then, the original design of an OpenMP runtime library is presented, which supports complex forms of parallelism such as multi-level and irregular parallelism. In the second part of the thesis, the focus is on heterogeneous systems, where hardware accelerators are coupled to (many-)cores to implement key functional kernels with orders-of-magnitude of speedup and energy efficiency compared to the “pure software” version. However, three main issues rise, namely i) platform design complexity, ii) architectural scalability and iii) programmability. To tackle them, a template for a generic hardware processing unit (HWPU) is proposed, which share the memory banks with cores, and the template for a scalable architecture is shown, which integrates them through the shared-memory system. Then, a full software stack and toolchain are developed to support platform design and to let programmers exploiting the accelerators of the platform. The OpenMP frontend is extended to interact with it.

Learning with Kernels on Graphs: DAG-based kernels, data streams and RNA function prediction.

In many application domains data can be naturally represented as graphs. When the application of analytical solutions for a given problem is unfeasible, machine learning techniques could be a viable way to solve the problem. Classical machine learning techniques are defined for data represented in a vectorial form. Recently some of them have been extended to deal directly with structured data. Among those techniques, kernel methods have shown promising results both from the computational complexity and the predictive performance point of view. Kernel methods allow to avoid an explicit mapping in a vectorial form relying on kernel functions, which informally are functions calculating a similarity measure between two entities. However, the definition of good kernels for graphs is a challenging problem because of the difficulty to find a good tradeoff between computational complexity and expressiveness. Another problem we face is learning on data streams, where a potentially unbounded sequence of data is generated by some sources. There are three main contributions in this thesis. The first contribution is the definition of a new family of kernels for graphs based on Directed Acyclic Graphs (DAGs). We analyzed two kernels from this family, achieving state-of-the-art results from both the computational and the classification point of view on real-world datasets. The second contribution consists in making the application of learning algorithms for streams of graphs feasible. Moreover,we defined a principled way for the memory management. The third contribution is the application of machine learning techniques for structured data to non-coding RNA function prediction. In this setting, the secondary structure is thought to carry relevant information. However, existing methods considering the secondary structure have prohibitively high computational complexity. We propose to apply kernel methods on this domain, obtaining state-of-the-art results.

Attention and memory bias for body image and health related information using an Emotional Stroop task in a non-clinical sample

It has been proposed that body image disturbance is a form of cognitive bias wherein schemas for self-relevant information guide the selective processing of appearancerelated information in the environment. This threatening information receives disproportionately more attention and memory, as measured by an Emotional Stroop and incidental recall task. The aim of this thesis was to expand the literature on cognitive processing biases in non-clinical males and females by incorporating a number of significant methodological refinements. To achieve this aim, three phases of research were conducted. The initial two phases of research provided preliminary data to inform the development of the main study. Phase One was a qualitative exploration of body image concerns amongst males and females recruited through the general community and from a university. Seventeen participants (eight male; nine female) provided information on their body image and what factors they saw as positively and negatively impacting on their self evaluations. The importance of self esteem, mood, health and fitness, and recognition of the social ideal were identified as key themes. These themes were incorporated as psycho-social measures and Stroop word stimuli in subsequent phases of the research. Phase Two involved the selection and testing of stimuli to be used in the Emotional Stroop task. Six experimental categories of words were developed that reflected a broad range of health and body image concerns for males and females. These categories were high and low calorie food words, positive and negative appearance words, negative emotion words, and physical activity words. Phase Three addressed the central aim of the project by examining cognitive biases for body image information in empirically defined sub-groups. A National sample of males (N = 55) and females (N = 144), recruited from the general community and universities, completed an Emotional Stroop task, incidental memory test, and a collection of psycho-social questionnaires. Sub-groups of body image disturbance were sought using a cluster analysis, which identified three sub-groups in males (Normal, Dissatisfied, and Athletic) and four sub-groups in females (Normal, Health Conscious, Dissatisfied, and Symptomatic). No differences were noted between the groups in selective attention, although time taken to colour name the words was associated with some of the psycho-social variables. Memory biases found across the whole sample for negative emotion, low calorie food, and negative appearance words were interpreted as reflecting the current focus on health and stigma against being unattractive. Collectively these results have expanded our understanding of processing biases in the general community by demonstrating that the processing biases are found within non-clinical samples and that not all processing biases are associated with negative functionality

Situated case-based reasoning as a constructive memory model for design reasoning

This paper describes an extended case-based reasoning model that addresses the notion of situatedness in designing through constructive memory. The model is illustrated through an application for predicting the corrosion rate for a specific material on a specific building.

Measuring episodic memory: A novel approach with an indefinite number of alternative forms

Both clinical practice and clinical research settings can require successive administrations of a memory test, particularly when following the trajectory of suspected memory decline in older adults. However, relatively few verbal episodic memory tests have alternative forms. We set out to create a broad based memory test to allow for the use of an essentially unlimited number of alternative forms. Four tasks for inclusion in such a test were developed. These tasks varied the requirement for recall as opposed to recognition, the need to form an association between unrelated words, and the need to discriminate the most recent list from earlier lists, all of which proved useful. A total of 115 participants completed the battery of tests and were used to show that the test could differentiate between older and younger adults; a sub-sample of 73 participants completed alternative forms of the tests to determine test-retest reliability and the amount of learning to learn.

Event-related potential (ERP) correlates of impaired visuospatial memory in schizophrenia

Previous studies have reported that patients with schizophrenia demonstrate impaired performance during working memory (WM) tasks. The current study aimed to determine whether WM impairments in schizophrenia are accompanied by reduced slow wave (SW) activity during on-line maintenance of mnemonic information. Event-related potentials were obtained from patients with schizophrenia and well controls as they performed a visuospatial delayed response task. On 50% of trials, a distractor stimulus was introduced during the delay. Compared with controls, patients with schizophrenia produced less SW memory negativity, particularly over the right hemisphere, together with reduced frontal enhancement of SW memory negativity in response to distraction. The results indicate that patients with schizophrenia generate less maintenance phase neuronal activity during WM performance, especially under conditions of distraction.

Working memory correlates of three symptom clusters in schizophrenia

Examined whether discrete working memory deficits underlie positive, negative and disorganised symptoms of schizophrenia. 52 outpatients (mean age 37.5 yrs) with schizophrenia were studied using items drawn from the Positive and Negative Syndrome Scale (PANSS). Linear regression and correlational analyses were conducted to examine whether symptom dimension scores were related to performance on several tests of working memory function. Severity of negative symptoms correlated with reduced production of words during a verbal fluency task, impaired ability to hold letter and number sequences on-line and manipulate them simultaneously, reduced performance during a dual task, and compromised visuospatial working memory under distraction-free conditions. Severity of disorganisation symptoms correlated with impaired visuospatial working memory under conditions of distraction, failure of inhibition during a verbal fluency task, perseverative responding on a test of set-shifting ability, and impaired ability to judge the veracity of simple declarative statements. The present study provides evidence that the positive, negative and disorganised symptom dimensions of the PANSS constitute independent clusters, associated with unique patterns of working memory impairment.

Eye-movements and visual imagery : a working memory approach to the treatment of post-traumatic stress disorder

It has been claimed that the symptoms of post-traumatic stress disorder (PTSD) can be ameliorated by eye-movement desensitization-reprocessing therapy (EMD-R), a procedure that involves the individual making saccadic eye-movements while imagining the traumatic event. We hypothesized that these eye-movements reduce the vividness of distressing images by disrupting the function of the visuospatial sketchpad (VSSP) of working memory, and that by doing so they reduce the intensity of the emotion associated with the image. This hypothesis was tested by asking non-PTSD participants to form images of neutral and negative pictures under dual task conditions. Their images were less vivid with concurrent eye-movements and with a concurrent spatial tapping task that did not involve eye-movements. In the first three experiments, these secondary tasks did not consistently affect participants' emotional responses to the images. However, Expt 4 used personal recollections as stimuli for the imagery task, and demonstrated a significant reduction in emotional response under the same dual task conditions. These results suggest that, if EMD-R works, it does so by reducing the vividness and emotiveness of traumatic images via the VSSP of working memory. Other visuospatial tasks may also be of therapeutic value.