Yaohang Li

GPU-accelerated differential evolutionary Markov Chain Monte Carlo method for multi-objective optimization over continuous space

In this paper, the attractive features of evolutionary algorithm and Markov Chain Monte Carlo are combined into a new Differential Evolutionary Markov Chain Monte Carlo (DE-MCMC) method for multi-objective optimization problems with continuous variables. The DE-MCMC evolves a population of Markov chains through differential evolution (DE) toward a diversified set of solutions at the Pareto optimal front in the multi-objective function space. The computational results show the effectiveness of the DE-MCMC algorithm in a variety of standardized test functions as well as a protein loop structure sampling application. Moreover, the DE-MCMC algorithm can efficiently take advantage of the massive-parallel, many-core architecture, where its implementation on GPU can achieve speedup of 14~35.

Context-Based Features Enhance Protein Secondary Structure Prediction Accuracy

We report a new approach of using statistical context-based scores as encoded features to train neural networks to achieve secondary structure prediction accuracy improvement. The context-based scores are pseudo-potentials derived by evaluating statistical, high-order inter-residue interactions, which estimate the favorability of a residue adopting certain secondary structure conformation within its amino acid environment. Encoding these context-based scores as important training and prediction features provides a way to address a long-standing difficulty in neural network-based secondary structure predictions of taking interdependency among secondary structures of neighboring residues into account. Our computational results have shown that the context-based scores are effective features to enhance the prediction accuracy of secondary structure predictions. An overall 7-fold cross-validated Q3 accuracy of 82.74% and Segment Overlap Accuracy (SOV) accuracy of 86.25% are achieved on a set of more than 7987 protein chains with, at most, 25% sequence identity. The Q3 prediction accuracy on benchmarks of CB513, Manesh215, Carugo338, as well as CASP9 protein chains is higher than popularly used secondary structure prediction servers, including Psipred, Profphd, Jpred, Porter (ab initio), and Netsurf. More significant improvement is observed in the SOV accuracy, where more than 4% enhancement is observed, compared to the server with the best SOV accuracy. A Q8 accuracy of >70% (71.5%) is also found in eight-state secondary structure prediction. The majority of the Q3 accuracy improvement is contributed from correctly identifying β-sheets and α-helices. When the context-based scores are incorporated, there are 15.5% more residues predicted with >90% confidence. These high-confidence predictions usually have a rather high accuracy (averagely ~95%). The three- and eight-state prediction servers (SCORPION) implementing our methods are available online.

Template-based C8-SCORPION: a protein 8-state secondary structure prediction method using structural information and context-based features

BackgroundSecondary structures prediction of proteins is important to many protein structure modeling applications. Correct prediction of secondary structures can significantly reduce the degrees of freedom in protein tertiary structure modeling and therefore reduces the difficulty of obtaining high resolution 3D models.MethodsIn this work, we investigate a template-based approach to enhance 8-state secondary structure prediction accuracy. We construct structural templates from known protein structures with certain sequence similarity. The structural templates are then incorporated as features with sequence and evolutionary information to train two-stage neural networks. In case of structural templates absence, heuristic structural information is incorporated instead.ResultsAfter applying the template-based 8-state secondary structure prediction method, the 7-fold cross-validated Q8 accuracy is 78.85%. Even templates from structures with only 20%~30% sequence similarity can help improve the 8-state prediction accuracy. More importantly, when good templates are available, the prediction accuracy of less frequent secondary structures, such as 3-10 helices, turns, and bends, are highly improved, which are useful for practical applications.ConclusionsOur computational results show that the templates containing structural information are effective features to enhance 8-state secondary structure predictions. Our prediction algorithm is implemented on a web server named C8-SCORPION available at: http://hpcr.cs.odu.edu/c8scorpion.

Dinosolve: a protein disulfide bonding prediction server using context-based features to enhance prediction accuracy.

BackgroundDisulfide bonds play an important role in protein folding and structure stability. Accurately predicting disulfide bonds from protein sequences is important for modeling the structural and functional characteristics of many proteins.MethodsIn this work, we introduce an approach of enhancing disulfide bonding prediction accuracy by taking advantage of context-based features. We firstly derive the first-order and second-order mean-force potentials according to the amino acid environment around the cysteine residues from large number of cysteine samples. The mean-force potentials are integrated as context-based scores to estimate the favorability of a cysteine residue in disulfide bonding state as well as a cysteine pair in disulfide bond connectivity. These context-based scores are then incorporated as features together with other sequence and evolutionary information to train neural networks for disulfide bonding state prediction and connectivity prediction.ResultsThe 10-fold cross validated accuracy is 90.8% at residue-level and 85.6% at protein-level in classifying an individual cysteine residue as bonded or free, which is around 2% accuracy improvement. The average accuracy for disulfide bonding connectivity prediction is also improved, which yields overall sensitivity of 73.42% and specificity of 91.61%.ConclusionsOur computational results have shown that the context-based scores are effective features to enhance the prediction accuracies of both disulfide bonding state prediction and connectivity prediction. Our disulfide prediction algorithm is implemented on a web server named Dinosolve available at: http://hpcr.cs.odu.edu/dinosolve.

DEMCMC-GPU: An Efficient Multi-Objective Optimization Method with GPU Acceleration on the Fermi Architecture

In this paper, we present an efficient method implemented on Graphics Processing Unit (GPU), DEMCMC-GPU, for multi-objective continuous optimization problems. The DEMCMC-GPU kernel is the DEMCMC algorithm, which combines the attractive features of Differential Evolution (DE) and Markov Chain Monte Carlo (MCMC) to evolve a population of Markov chains toward a diversified set of solutions at the Pareto optimal front in the multi-objective search space. With parallel evolution of a population of Markov chains, the DEMCMC algorithm is a natural fit for the GPU architecture. The implementation of DEMCMC-GPU on the pre-Fermi architecture can lead to a ~25 speedup on a set of multi-objective benchmark function problems, compare to the CPU-only implementation of DEMCMC. By taking advantage of new cache mechanism in the emerging NVIDIA Fermi GPU architecture, efficient sorting algorithm on GPU, and efficient parallel pseudorandom number generators, the speedup of DEMCMC-GPU can be aggressively improved to ~100.

Accelerating knowledge-based energy evaluation in protein structure modeling with Graphics Processing Units

Evaluating the energy of a protein molecule is one of the most computationally costly operations in many protein structure modeling applications. In this paper, we present an efficient implementation of knowledge-based energy functions by taking advantage of the recent Graphics Processing Unit (GPU) architectures. We use DFIRE, a knowledge-based all-atom potential, as an example to demonstrate our GPU implementations on the latest NVIDIA Fermi architecture. A load balancing workload distribution scheme is designed to assign computations of pair-wise atom interactions to threads to achieve perfect or near-perfect load balancing in the symmetric N-body problem in DFIRE. Reorganizing atoms in the protein also improves the cache efficiency in Fermi GPU architecture, which is particularly effective for small proteins. Our DFIRE implementation on GPU (GPU-DFIRE) has exhibited a speedup of up to ~150 on NVIDIA Quadro FX3800M and ~250 on NVIDIA Tesla M2050 compared to the serial DFIRE implementation on CPU. Furthermore, we show that protein structure modeling applications, including a Monte Carlo sampling program and a local optimization program, can benefit from GPU-DFIRE with little programming modification but significant computational performance improvement.

A load-balancing workload distribution scheme for three-body interaction computation on Graphics Processing Units (GPU)

Three-body effects play an important role for obtaining quantitatively high accuracy in a variety of molecular simulation applications. However, evaluation of three-body potentials is computationally costly, generally of O( N 3 ) where N is the number of particles in a system. In this paper, we present a load-balancing workload distribution scheme for calculating three-body interactions by taking advantage of the Graphics Processing Units (GPU) architectures. Perfect load-balancing is achieved if N is not divisible by 3 and nearly perfect load-balancing is obtained if N is divisible by 3. The workload distribution scheme is particularly suitable for the GPUs Single Instruction Multiple Threads (SIMT) architecture, where particles data accessed by threads can be coalesced into efficient memory transactions. We use two potential energy functions with three-body terms, the Axilrod-Teller potential and the Context-based Secondary Structure Potential, as examples to demonstrate the effectiveness of our workload distribution scheme. Load-balancing scheme for calculating three-body interactions on GPU.Perfect load-balancing is achieved if N is not divisible by 3.Nearly perfect load-balancing is obtained if N is divisible by 3.Parallel efficiency demonstrated in three-body potentials.

An implementation of block conjugate gradient algorithm on CPU-GPU processors

In this paper, we investigate the implementation of the Block Conjugate Gradient (BCG) algorithm on CPU-GPU processors. By analyzing the performance of various matrix operations in BCG, we identify the main performance bottleneck in constructing new search direction matrices. Replacing the QR decomposition by eigendecomposition of a small matrix remedies the problem by reducing the computational cost of generating orthogonal search directions. Moreover, a hybrid (offload) computing scheme is designed to enables the BCG implementation to handle linear systems with large, sparse coefficient matrices that cannot fit in the GPU memory. The hybrid scheme offloads matrix operations to GPU processors while helps hide the CPU-GPU memory transaction overhead. We compare the performance of our BCG implementation with the one on CPU with Intel Xeon Phi coprocessors using the automatic offload mode. With sufficient number of right hand sides, the CPU-GPU implementation of BCG can reach speedup of 2.61 over the CPU-only implementation, which is significantly higher than that of the CPU-Intel Xeon Phi implementation.

Reusing Random Walks in Monte Carlo Methods for Linear Systems

Abstract In this paper, we present an approach of reusing random walks in Monte Carlo methods for linear systems. The fundamental idea is, during the Monte Carlo sampling process, the random walks generated to estimate one unknown element can also be effectively reused to estimate the other unknowns in the solution vector. As a result, when the random walks are reused, a single random walk can contribute samples for estimations of multiple unknowns in the solution simultaneously while ensuring that the samples for the same unknown element are statistically independent. Consequently, the total number of random walk transition steps needed for estimating the overall solution vector is reduced, which improves the performance of the Monte Carlo algorithm. We apply this approach to the Monte Carlo algorithm in two linear algebra applications, including solving a system of linear equations and approximating the inversion of a matrix. Our computational results show that compared to the conventional implementations of Monte Carlo algorithms for linear systems without random walk reusing, our approach can significantly improve the performance of Monte Carlo sampling process by reducing the overall number of transition steps in random walks to obtain the entire solution within desired precision.

FLEXc: protein flexibility prediction using context-based statistics, predicted structural features, and sequence information.

BackgroundThe fluctuation of atoms around their average positions in protein structures provides important information regarding protein dynamics. This flexibility of protein structures is associated with various biological processes. Predicting flexibility of residues from protein sequences is significant for analyzing the dynamic properties of proteins which will be helpful in predicting their functions.ResultsIn this paper, an approach of improving the accuracy of protein flexibility prediction is introduced. A neural network method for predicting flexibility in 3 states is implemented. The method incorporates sequence and evolutionary information, context-based scores, predicted secondary structures and solvent accessibility, and amino acid properties. Context-based statistical scores are derived, using the mean-field potentials approach, for describing the different preferences of protein residues in flexibility states taking into consideration their amino acid context.The 7-fold cross validated accuracy reached 61xa0% when context-based scores and predicted structural states are incorporated in the training process of the flexibility predictor.ConclusionsIncorporating context-based statistical scores with predicted structural states are important features to improve the performance of predicting protein flexibility, as shown by our computational results. Our prediction method is implemented as web service called “FLEXc” and available online at: http://hpcr.cs.odu.edu/flexc.