A GPU-Based Implementation of the Firefly Algorithm for Variable Selection in Multivariate Calibration Problems

Several variable selection algorithms in multivariate calibration can be accelerated using Graphics Processing Units (GPU). Among these algorithms, the Firefly Algorithm (FA) is a recent proposed metaheuristic that may be used for variable selection. This paper presents a GPU-based FA (FA-MLR) with multiobjective formulation for variable selection in multivariate calibration problems and compares it with some traditional sequential algorithms in the literature. The advantage of the proposed implementation is demonstrated in an example involving a relatively large number of variables. The results showed that the FA-MLR, in comparison with the traditional algorithms is a more suitable choice and a relevant contribution for the variable selection problem. Additionally, the results also demonstrated that the FA-MLR performed in a GPU can be five times faster than its sequential implementation.     

Evaluation of a Learning-based Deformable Registration Method on Abdominal CT Images

BackgroundReliable image comparisons, based on fast and accurate deformable registration methods, are recognized as key steps in the diagnosis and follow-up of cancer as well as for radiation therapy planning or surgery. In the particular case of abdominal images, the images to compare often differ widely from each other due to organ deformation, patient motion, movements of gastrointestinal tract or breathing. As a consequence, there is a need for registration methods that can cope with both local and global large and highly non-linear deformations.MethodDeformable registration of medical images traditionally relies on the iterative minimization of a cost function involving a large number of parameters. For complex deformations and large datasets, this process is computationally very demanding, leading to processing times that are incompatible with the clinical routine workflow. Moreover, the highly non-convex nature of these optimization problems leads to a high risk of convergence toward local minima. Recently, deep learning approaches using Convolutional Neural Networks (CNN) have led to major breakthroughs by providing computationally fast unsupervised methods for the registration of 2D and 3D images within seconds. Among all the proposed approaches, the VoxelMorph learning-based framework pioneered to learn in an unsupervised way the complex mapping, parameterized using a CNN, between every couple of 2D or 3D pairs of images and the corresponding deformation field by minimizing a standard intensity-based similarity metrics over the whole learning database. Voxelmorph has so far only been evaluated on brain images. The present study proposes to evaluate this method in the context of inter-subject registration of abdominal CT images, which present a greater challenge in terms of registration than brain images, due to greater anatomical variability and significant organ deformations.ResultsThe performances of VoxelMorph were compared with the current top-performing non-learning-based deformable registration method “Symmetric Normalization” (SyN), implemented in ANTs, on two representative databases: LiTS and 3D-IRCADb-01. Three different experiments were carried out on 2D or 3D data, the atlas-based or pairwise registration, using two different similarity metrics, namely (MSE and CC). Accuracy of the registration was measured by the Dice score, which quantifies the volume overlap for the selected anatomical region.All the three experiments exhibit that the two deformable registration methods significantly outperform the affine registration and that VoxelMorph accuracy is comparable or even better than the reference non-learning based registration method ANTs (SyN), with a drastically reduced computation time.ConclusionBy substituting a time consuming optimization problem, VoxelMorph has made an outstanding achievement in learning-based registration algorithm, where a registration function is trained and thus, able to perform deformable registration almost accurately on abdominal images, while reducing the computation time from minutes to seconds and from seconds to milliseconds in comparison to ANTs (SyN) on a CPU.     

Impact of deformable registration methods for prediction of recurrence free survival response to neoadjuvant chemotherapy in breast cancer: Results from the ISPY 1/ACRIN 6657 trial

PurposeImage registration plays a vital role in spatially aligning multiple MRI scans for better longitudinal assessment of tumor morphological features. The objective was to evaluate the effect of registration accuracy of six established deformable registration methods(ANTs, DRAMMS, ART, NiftyReg, SSD-FFD, and NMI-FFD) on the predictive value of extracted radiomic features when modeling recurrence-free-survival(RFS) for women after neoadjuvant chemotherapy(NAC) for locally advanced breast cancer.Methods130 women had DCE-MRI scans available from the first two visits in the ISPY1/ACRIN-6657 cohort. We calculated the transformation field from each of the different deformable registration methods, and used it to compute voxel-wise parametric-response-maps(PRM) for established four kinetic features.104-radiomic features were computed from each PRM map to characterize intra-tumor heterogeneity. We evaluated performance for RFS using Cox-regression, C-statistic, and Kaplan-Meier(KM) plots.ResultsA baseline model(F1:Age, Race, and Hormone-receptor-status) had a 0.54 C-statistic, and model F2(baseline + functional-tumor-volume at early treatment visit(FTV₂)) had 0.63. The F2+ANTs had the highest C-statistic(0.72) with the smallest landmark differences(5.40±4.40mm) as compared to other models. The KM curve for model F2 gave p=0.004 for separation between women above and below the median hazard compared to the model F1(p=0.31). A models augmented with radiomic features, also achieved significant KM curve separation(p<0.001) except the F2+ART model.ConclusionIncorporating image registration in quantifying changes in tumor heterogeneity during NAC can improve prediction of RFS. Radiomic features of PRM maps derived from warping the DCE-MRI kinetic maps using ANTs registration method further improved the early prediction of RFS as compared to other methods.     

FastGCN: A GPU Accelerated Tool for Fast Gene Co-Expression Networks

Gene co-expression networks comprise one type of valuable biological networks. Many methods and tools have been published to construct gene co-expression networks; however, most of these tools and methods are inconvenient and time consuming for large datasets. We have developed a user-friendly, accelerated and optimized tool for constructing gene co-expression networks that can fully harness the parallel nature of GPU (Graphic Processing Unit) architectures. Genetic entropies were exploited to filter out genes with no or small expression changes in the raw data preprocessing step. Pearson correlation coefficients were then calculated. After that, we normalized these coefficients and employed the False Discovery Rate to control the multiple tests. At last, modules identification was conducted to construct the co-expression networks. All of these calculations were implemented on a GPU. We also compressed the coefficient matrix to save space. We compared the performance of the GPU implementation with those of multi-core CPU implementations with 16 CPU threads, single-thread C/C++ implementation and single-thread R implementation. Our results show that GPU implementation largely outperforms single-thread C/C++ implementation and single-thread R implementation, and GPU implementation outperforms multi-core CPU implementation when the number of genes increases. With the test dataset containing 16,000 genes and 590 individuals, we can achieve greater than 63 times the speed using a GPU implementation compared with a single-thread R implementation when 50 percent of genes were filtered out and about 80 times the speed when no genes were filtered out.     

GPU-accelerated molecular dynamics simulation of solid covalent crystals

Graphics processing unit (GPU) is becoming a powerful computational tool in science and engineering. In this paper, different from previous molecular dynamics (MD) simulation with pair potentials and many-body potentials, two MD simulation algorithms implemented on a single GPU are presented to describe a special category of many-body potentials – bond order potentials used frequently in solid covalent materials, such as the Tersoff potentials for silicon crystals. The simulation results reveal that the performance of GPU implementations is apparently superior to their CPU counterpart. Furthermore, the proposed algorithms are generalised, transferable and scalable, and can be extended to the simulations with general many-body interactions such as Stillinger–Weber potential and so on.     

Performance evaluation of image processing algorithms on the GPU

The graphics processing unit (GPU), which originally was used exclusively for visualization purposes, has evolved into an extremely powerful co-processor. In the meanwhile, through the development of elaborate interfaces, the GPU can be used to process data and deal with computationally intensive applications. The speed-up factors attained compared to the central processing unit (CPU) are dependent on the particular application, as the GPU architecture gives the best performance for algorithms that exhibit high data parallelism and high arithmetic intensity. Here, we evaluate the performance of the GPU on a number of common algorithms used for three-dimensional image processing. The algorithms were developed on a new software platform called "CUDA", which allows a direct translation from C code to the GPU. The implemented algorithms include spatial transformations, real-space and Fourier operations, as well as pattern recognition procedures, reconstruction algorithms and classification procedures. In our implementation, the direct porting of C code in the GPU achieves typical acceleration values in the order of 10-20 times compared to a state-of-the-art conventional processor, but they vary depending on the type of the algorithm. The gained speed-up comes with no additional costs, since the software runs on the GPU of the graphics card of common workstations.     

High performance hybrid functional Petri net simulations of biological pathway models on CUDA

Hybrid functional Petri nets are a wide-spread tool for representing and simulating biological models. Due to their potential of providing virtual drug testing environments, biological simulations have a growing impact on pharmaceutical research. Continuous research advancements in biology and medicine lead to exponentially increasing simulation times, thus raising the demand for performance accelerations by efficient and inexpensive parallel computation solutions. Recent developments in the field of general-purpose computation on graphics processing units (GPGPU) enabled the scientific community to port a variety of compute intensive algorithms onto the graphics processing unit (GPU). This work presents the first scheme for mapping biological hybrid functional Petri net models, which can handle both discrete and continuous entities, onto compute unified device architecture (CUDA) enabled GPUs. GPU accelerated simulations are observed to run up to 18 times faster than sequential implementations. Simulating the cell boundary formation by Delta-Notch signaling on a CUDA enabled GPU results in a speedup of approximately 7x for a model containing 1,600 cells.     

Elucidating ANTs in worms using genomic and bioinformatic tools — Biotechnological prospects?

Adenine nucleotide translocators (ANTs) belong to the mitochondrial carrier family (MCF) of proteins. ATP production and consumption are tightly linked to ANTs, the kinetics of which have been proposed to play a key regulatory role in mitochondrial oxidative phosphorylation. ANTs are also recognized as a central component of the mitochondrial permeability transition pore associated with apoptosis. Although ANTs have been investigated in a range of vertebrates, including human, mouse and cattle, and invertebrates, such as Drosophila melanogaster (vinegar fly), Saccharomyces cerevisiae (yeast) and Caenorhabditis elegans (free-living nematode), there has been a void of information on these molecules for parasitic nematodes of socio-economic importance. Exploring ANTs in nematodes has the potential lead to a better understanding of their fundamental roles in key biological pathways and might provide an avenue for the identification of targets for the rational design of nematocidal drugs. In the present article, we describe the discovery of an ANT from Haemonchus contortus (one of the most economically important parasitic nematodes of sheep and goats), conduct a comparative analysis of key ANTs and their genes (particularly ant-1.1) in nematodes and other organisms, predict the functional roles utilizing a combined genomic-bioinformatic approach and propose ANTs and associated molecules as possible drug targets, with the potential for biotechnological outcomes.     

Anthracyclines and their metabolism in human liver microsomes and the participation of the new microsomal carbonyl reductase

Anthracyclines (ANTs) are widely used in the treatment of various forms of cancer. Although their usage contributes to an improvement in life expectancy, it is limited by severe adverse effects-acute and chronic cardiotoxicity. Several enzymes from both AKR and SDR superfamilies have been reported as participants in the reduction of ANTs. Nevertheless all of these are located in the cytosolic compartment. One microsomal reductase has been found to be involved in the metabolism of xenobiotics-11beta-HSD1, but no further information has been reported about its role in the metabolism of ANTs. The aim of this study is to bring new information about the biotransformation of doxorubicin (DOX), daunorubicin (DAUN) and idarubicin (IDA), not only in human liver microsomal fraction, but also by a novel human liver microsomal carbonyl reductase that has been purified by our group. The reduction of ANTs at C-13 position is regarded as the main pathway in the biotransformation of ANTs. However, our experiments with human liver microsomal fraction show different behaviour, especially when the concentration of ANTs in the incubation mixture is increased. Microsomal fraction was incubated with doxorubicin, daunorubicin and idarubicin. DOX was both reduced into doxorubicinol (DOXOL) and hydrolyzed into aglycone DOX and then subsequently reduced. The same behaviour was observed for the metabolism of DAUN and IDA. The activity of hydrolases definitely brings a new look to the entire metabolism of ANTs in microsomal fraction, as formed aglycones undergo reduction and compete for the binding site with the main ANTs. Moreover, as there are two competitive reducing reactions present for all three ANTs, kinetic values of direct reduction and the reduction of aglycone were calculated. These results were compared to previously published data for human liver cytosol. In addition, the participation of the newly determined human liver microsomal carbonyl reductase was studied. No reduction of DOX into DOXOL was detected. Nevertheless, the involvement in reduction of DAUN into DAUNOL as well as IDA into IDAOL was demonstrated. The kinetic values obtained were then compared with data which have already been reported for cytosolic ANTs reductases.     

An evaluation of multiple feed-forward networks on GPUs

The Graphics Processing Unit (GPU) originally designed for rendering graphics and which is difficult to program for other tasks, has since evolved into a device suitable for general-purpose computations. As a result graphics hardware has become progressively more attractive yielding unprecedented performance at a relatively low cost. Thus, it is the ideal candidate to accelerate a wide variety of data parallel tasks in many fields such as in Machine Learning (ML). As problems become more and more demanding, parallel implementations of learning algorithms are crucial for a useful application. In particular, the implementation of Neural Networks (NNs) in GPUs can significantly reduce the long training times during the learning process. In this paper we present a GPU parallel implementation of the Back-Propagation (BP) and Multiple Back-Propagation (MBP) algorithms, and describe the GPU kernels needed for this task. The results obtained on well-known benchmarks show faster training times and improved performances as compared to the implementation in traditional hardware, due to maximized floating-point throughput and memory bandwidth. Moreover, a preliminary GPU based Autonomous Training System (ATS) is developed which aims at automatically finding high-quality NNs-based solutions for a given problem.     

Rapid pedobarographic image registration based on contour curvature and optimization

Image registration, the process of optimally aligning homologous structures in multiple images, has recently been demonstrated to support automated pixel-level analysis of pedobarographic images and, subsequently, to extract unique and biomechanically relevant information from plantar pressure data. Recent registration methods have focused on robustness, with slow but globally powerful algorithms. In this paper, we present an alternative registration approach that affords both speed and accuracy, with the goal of making pedobarographic image registration more practical for near-real-time laboratory and clinical applications. The current algorithm first extracts centroid-based curvature trajectories from pressure image contours, and then optimally matches these curvature profiles using optimization based on dynamic programming. Special cases of disconnected images (that occur in high-arched subjects, for example) are dealt with by introducing an artificial spatially linear bridge between adjacent image clusters. Two registration algorithms were developed: a ‘geometric’ algorithm, which exclusively matched geometry, and a ‘hybrid’ algorithm, which performed subsequent pseudo-optimization. After testing the two algorithms on 30 control image pairs considered in a previous study, we found that, when compared with previously published results, the hybrid algorithm improved overlap ratio (p=0.010), but both current algorithms had slightly higher mean-squared error, assumedly because they did not consider pixel intensity. Nonetheless, both algorithms greatly improved the computational efficiency (25±8 and 53±9 ms per image pair for geometric and hybrid registrations, respectively). These results imply that registration-based pixel-level pressure image analyses can, eventually, be implemented for practical clinical purposes.     

GPU accelerated sequence alignment with traceback for GATK HaplotypeCaller

Background

Pairwise sequence alignment is widely used in many biological tools and applications. Existing GPU accelerated implementations mainly focus on calculating optimal alignment score and omit identifying the optimal alignment itself. In GATK HaplotypeCaller (HC), the semi-global pairwise sequence alignment with traceback has so far been difficult to accelerate effectively on GPUs.

Results

We first analyze the characteristics of the semi-global alignment with traceback in GATK HC and then propose a new algorithm that allows for retrieving the optimal alignment efficiently on GPUs. For the first stage, we choose intra-task parallelization model to calculate the position of the optimal alignment score and the backtracking matrix. Moreover, in the first stage, our GPU implementation also records the length of consecutive matches/mismatches in addition to lengths of consecutive insertions and deletions as in the CPU-based implementation. This helps efficiently retrieve the backtracking matrix to obtain the optimal alignment in the second stage.

Conclusions

Experimental results show that our alignment kernel with traceback is up to 80x and 14.14x faster than its CPU counterpart with synthetic datasets and real datasets, respectively. When integrated into GATK HC (alongside a GPU accelerated pair-HMMs forward kernel), the overall acceleration is 2.3x faster than the baseline GATK HC implementation, and 1.34x faster than the GATK HC implementation with the integrated GPU-based pair-HMMs forward algorithm. Although the methods proposed in this paper is to improve the performance of GATK HC, they can also be used in other pairwise alignments and applications.

     

A Hybrid CPU/GPU Pattern-Matching Algorithm for Deep Packet Inspection

The large quantities of data now being transferred via high-speed networks have made deep packet inspection indispensable for security purposes. Scalable and low-cost signature-based network intrusion detection systems have been developed for deep packet inspection for various software platforms. Traditional approaches that only involve central processing units (CPUs) are now considered inadequate in terms of inspection speed. Graphic processing units (GPUs) have superior parallel processing power, but transmission bottlenecks can reduce optimal GPU efficiency. In this paper we describe our proposal for a hybrid CPU/GPU pattern-matching algorithm (HPMA) that divides and distributes the packet-inspecting workload between a CPU and GPU. All packets are initially inspected by the CPU and filtered using a simple pre-filtering algorithm, and packets that might contain malicious content are sent to the GPU for further inspection. Test results indicate that in terms of random payload traffic, the matching speed of our proposed algorithm was 3.4 times and 2.7 times faster than those of the AC-CPU and AC-GPU algorithms, respectively. Further, HPMA achieved higher energy efficiency than the other tested algorithms.     

The role of adenine nucleotide translocators in regulation of oxidative phosphorylation in heart mitochondria

The regulative role of adenine nucleotide translocators (ANTs) in oxidative phosphorylation has been estimated by the titration of respiration of isolated rabbit heart mitochondria with carboxyatractyloside in the presence of a non-rate limiting creatine phosphokinase ADP-regenerating system. It has been established that the respiration rate is not controlled by ANTs in the two extreme states, state 3 and state 4. On the other hand, at an intermediate respiration rate (30-70% of the state 3 respiration, which roughly corresponds to that under physiological conditions) the ANT control coefficient had a value of 0.62-0.75. Thus, ANTs seem to play a key role in the regulation of oxidative phosphorylation.     

Anthranilate derivatives as TACE inhibitors: Docking based CoMFA and CoMSIA analyses

Anthranilic acid based derivatives (ANTs) have been identified as a novel class of potent tumor necrosis factor-α converting enzyme (TACE) inhibitors. A computational strategy based on molecular docking studies, followed by CoMFA and CoMSIA analyses has been performed to elucidate the atomic details of the TACE/ANT interactions and also to identify the most important features impacting TACE inhibitory activity of ANTs. The CoMSIA model resulted to be slightly more predictive than CoMFA model, and gave conventional r² 0.991, r_cv² 0.793, q² 0.777, SEE 0.050, F-value 655.610, and r_test² 0.871. The 3D-QSAR field contributions and the structural features of the TACE binding site showed a good correlation. These studies will be useful to design new TACE inhibitors with improved potency.     

Common intervals and sorting by reversals: a marriage of necessity

This paper revisits the problem of sorting by reversals with tools developed in the context of detecting common intervals. Mixing the two approaches yields new definitions and algorithms for the reversal distance computations, that apply directly on the original permutation. Traditional constructions such as recasting the signed permutation as a positive permutation, or traversing the overlap graph to analyze its connected components, are replaced by elementary definitions in terms of intervals of the permutation. This yields simple linear time algorithms that identify the essential features in a single pass over the permutation and use only simple data structures like arrays and stacks.     

Performance improvements for iterative electron tomography reconstruction using graphics processing units (GPUs)

Iterative reconstruction algorithms are becoming increasingly important in electron tomography of biological samples. These algorithms, however, impose major computational demands. Parallelization must be employed to maintain acceptable running times. Graphics Processing Units (GPUs) have been demonstrated to be highly cost-effective for carrying out these computations with a high degree of parallelism. In a recent paper by Xu et al. (2010), a GPU implementation strategy was presented that obtains a speedup of an order of magnitude over a previously proposed GPU-based electron tomography implementation. In this technical note, we demonstrate that by making alternative design decisions in the GPU implementation, an additional speedup can be obtained, again of an order of magnitude. By carefully considering memory access locality when dividing the workload among blocks of threads, the GPU’s cache is used more efficiently, making more effective use of the available memory bandwidth.     

The utility of deformable image registration for small artery visualisation in contrast-enhanced whole body MR angiography

PurposeAn investigation was carried out into the effect of three image registration techniques on the diagnostic image quality of contrast-enhanced magnetic resonance angiography (CE-MRA) images.MethodsWhole-body CE-MRA data from the lower legs of 27 patients recruited onto a study of asymptomatic atherosclerosis were processed using three deformable image registration algorithms. The resultant diagnostic image quality was evaluated qualitatively in a clinical evaluation by four expert observers, and quantitatively by measuring contrast-to-noise ratios and volumes of blood vessels, and assessing the techniques' ability to correct for varying degrees of motion.ResultsThe first registration algorithm (‘AIR’) introduced significant stenosis-mimicking artefacts into the blood vessels' appearance, observed both qualitatively (clinical evaluation) and quantitatively (vessel volume measurements). The two other algorithms (‘Slicer’ and ‘SEMI’), based on the normalised mutual information (NMI) concept and designed specifically to deal with variations in signal intensity as found in contrast-enhanced image data, did not suffer from this serious issue but were rather found to significantly improve the diagnostic image quality both qualitatively and quantitatively, and demonstrated a significantly improved ability to deal with the common problem of patient motion.ConclusionsThis work highlights both the significant benefits to be gained through the use of suitable registration algorithms and the deleterious effects of an inappropriate choice of algorithm for contrast-enhanced MRI data. The maximum benefit was found in the lower legs, where the small arterial vessel diameters and propensity for leg movement during image acquisitions posed considerable problems in making accurate diagnoses from the un-registered images.     

Parallel high-dimensional multi-objective feature selection for EEG classification with dynamic workload balancing on CPU–GPU architectures

Many bioinformatics applications that analyse large volumes of high-dimensional data comprise complex problems requiring metaheuristics approaches with different types of implicit parallelism. For example, although functional parallelism would be used to accelerate evolutionary algorithms, the fitness evaluation of the population could imply the computation of cost functions with data parallelism. This way, heterogeneous parallel architectures, including central processing unit (CPU) microprocessors with multiple superscalar cores and accelerators such as graphics processing units (GPUs) could be very useful. This paper aims to take advantage of such CPU–GPU heterogeneous architectures to accelerate electroencephalogram classification and feature selection problems by evolutionary multi-objective optimization, in the context of brain computing interface tasks. In this paper, we have used the OpenCL framework to develop parallel master-worker codes implementing an evolutionary multi-objective feature selection procedure in which the individuals of the population are dynamically distributed among the available CPU and GPU cores.