CAMPAIGN: an open-source library of GPU-accelerated data clustering algorithms

Semiglobal Sequence Alignment with Gaps Using GPU

In this paper, we consider the pair-wise semiglobal sequence alignment problem with gaps, which is motivated by the re-sequencing problem that requires to assemble short reads sequences into a genome sequence by referring to a reference sequence. The problem has been studied before for single gap and bounded number of gaps. For single gap, there is a GPU-based algorithm proposed (Barton et al., 2015). In our work, we propose a GPU-based algorithm for the bounded number of gaps case, called GPUGapsMis. We implement the algorithm and compare the performance with the CPU-based algorithm, called CPUGapsMis. The algorithm has two distinct stages: the alignment phase, and the backtrack phase. We investigate several different approaches, in order to determine the most favorable for this problem, by means of a Hybrid model or a wholly-GPU based model, as well as the alignment of single text sequences or multiple text sequences on the GPU at a time. We show that the alignment phase of the algorithm is a good candidate for parallelization, with peak speedup of 11 times. We show that although the backtracking phase is sequential, it is more beneficial to perform it on the GPU, as opposed to returning to the CPU and performing there. When performing both phases on the GPU, GPUGapsMis achieves a peak speedup of 10.4 times against CPUGapsMis. Our data parallel GPU algorithm achieves results which are an improvement on those of an existing GPU data parallel implementation (Ojiaku, 2014).

Efficient visibility-driven medical image visualisation via adaptive binned visibility histogram

'Visibility' is a fundamental optical property that represents the observable, by users, proportion of the voxels in a volume during interactive volume rendering. The manipulation of this 'visibility' improves the volume rendering processes; for instance by ensuring the visibility of regions of interest (ROIs) or by guiding the identification of an optimal rendering view-point. The construction of visibility histograms (VHs), which represent the distribution of all the visibility of all voxels in the rendered volume, enables users to explore the volume with real-time feedback about occlusion patterns among spatially related structures during volume rendering manipulations. Volume rendered medical images have been a primary beneficiary of VH given the need to ensure that specific ROIs are visible relative to the surrounding structures, e.g. the visualisation of tumours that may otherwise be occluded by neighbouring structures. VH construction and its subsequent manipulations, however, are computationally expensive due to the histogram binning of the visibilities. This limits the real-time application of VH to medical images that have large intensity ranges and volume dimensions and require a large number of histogram bins. In this study, we introduce an efficient adaptive binned visibility histogram (AB-VH) in which a smaller number of histogram bins are used to represent the visibility distribution of the full VH. We adaptively bin medical images by using a cluster analysis algorithm that groups the voxels according to their intensity similarities into a smaller subset of bins while preserving the distribution of the intensity range of the original images. We increase efficiency by exploiting the parallel computation and multiple render targets (MRT) extension of the modern graphical processing units (GPUs) and this enables efficient computation of the histogram. We show the application of our method to single-modality computed tomography (CT), magnetic resonance (MR) imaging and multi-modality positron emission tomography-CT (PET-CT). In our experiments, the AB-VH markedly improved the computational efficiency for the VH construction and thus improved the subsequent VH-driven volume manipulations. This efficiency was achieved without major degradation in the VH visually and numerical differences between the AB-VH and its full-bin counterpart. We applied several variants of the K-means clustering algorithm with varying Ks (the number of clusters) and found that higher values of K resulted in better performance at a lower computational gain. The AB-VH also had an improved performance when compared to the conventional method of down-sampling of the histogram bins (equal binning) for volume rendering visualisation.

GPUDePiCt: A Parallel Implementation of a Clustering Algorithm for Computing Degenerate Primers on Graphics Processing Units

In order to make multiple copies of a target sequence in the laboratory, the technique of Polymerase Chain Reaction (PCR) requires the design of "primers", which are short fragments of nucleotides complementary to the flanking regions of the target sequence. If the same primer is to amplify multiple closely related target sequences, then it is necessary to make the primers "degenerate", which would allow it to hybridize to target sequences with a limited amount of variability that may have been caused by mutations. However, the PCR technique can only allow a limited amount of degeneracy, and therefore the design of degenerate primers requires the identification of reasonably well-conserved regions in the input sequences. We take an existing algorithm for designing degenerate primers that is based on clustering and parallelize it in a web-accessible software package GPUDePiCt, using a shared memory model and the computing power of Graphics Processing Units (GPUs). We test our implementation on large sets of aligned sequences from the human genome and show a multi-fold speedup for clustering using our hybrid GPU/CPU implementation over a pure CPU approach for these sequences, which consist of more than 7,500 nucleotides. We also demonstrate that this speedup is consistent over larger numbers and longer lengths of aligned sequences.

Discovering epistasis in large scale genetic association studies by exploiting graphics cards

Despite the enormous investments made in collecting DNA samples and generating germline variation data across thousands of individuals in modern genome-wide association studies (GWAS), progress has been frustratingly slow in explaining much of the heritability in common disease. Today's paradigm of testing independent hypotheses on each single nucleotide polymorphism (SNP) marker is unlikely to adequately reflect the complex biological processes in disease risk. Alternatively, modeling risk as an ensemble of SNPs that act in concert in a pathway, and/or interact non-additively on log risk for example, may be a more sensible way to approach gene mapping in modern studies. Implementing such analyzes genome-wide can quickly become intractable due to the fact that even modest size SNP panels on modern genotype arrays (500k markers) pose a combinatorial nightmare, require tens of billions of models to be tested for evidence of interaction. In this article, we provide an in-depth analysis of programs that have been developed to explicitly overcome these enormous computational barriers through the use of processors on graphics cards known as Graphics Processing Units (GPU). We include tutorials on GPU technology, which will convey why they are growing in appeal with today's numerical scientists. One obvious advantage is the impressive density of microprocessor cores that are available on only a single GPU. Whereas high end servers feature up to 24 Intel or AMD CPU cores, the latest GPU offerings from nVidia feature over 2600 cores. Each compute node may be outfitted with up to 4 GPU devices. Success on GPUs varies across problems. However, epistasis screens fare well due to the high degree of parallelism exposed in these problems. Papers that we review routinely report GPU speedups of over two orders of magnitude (>100x) over standard CPU implementations.

A fast parallel clustering algorithm for molecular simulation trajectories

We implemented a GPU-powered parallel k-centers algorithm to perform clustering on the conformations of molecular dynamics (MD) simulations. The algorithm is up to two orders of magnitude faster than the CPU implementation. We tested our algorithm on four protein MD simulation datasets ranging from the small Alanine Dipeptide to a 370-residue Maltose Binding Protein (MBP). It is capable of grouping 250,000 conformations of the MBP into 4000 clusters within 40 seconds. To achieve this, we effectively parallelized the code on the GPU and utilize the triangle inequality of metric spaces. Furthermore, the algorithm's running time is linear with respect to the number of cluster centers. In addition, we found the triangle inequality to be less effective in higher dimensions and provide a mathematical rationale. Finally, using Alanine Dipeptide as an example, we show a strong correlation between cluster populations resulting from the k-centers algorithm and the underlying density. © 2012 Wiley Periodicals, Inc.