اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدParallel multi-objective algorithms for the molecular docking problem
97
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Molecular docking is an essential tool for drug design. It helps the scientist to rapidly know if two molecules, respectively called ligand and receptor, can be combined together to obtain a stable complex. We propose a new multi-objective model combining an energy term and a surface term to gain such complexes. The aim of our model is to provide complexes with a low energy and low surface. This model has been validated with two multi-objective genetic algorithms on instances from the literature dedicated to the docking benchmarking.
قيم البحث
اقرأ أيضاً
Principal component analysis (PCA) is a key statistical technique for multivariate data analysis. For large data sets the common approach to PCA computation is based on the standard NIPALS-PCA algorithm, which unfortunately suffers from loss of ortho
gonality, and therefore its applicability is usually limited to the estimation of the first few components. Here we present an algorithm based on Gram-Schmidt orthogonalization (called GS-PCA), which eliminates this shortcoming of NIPALS-PCA. Also, we discuss the GPU (Graphics Processing Unit) parallel implementation of both NIPALS-PCA and GS-PCA algorithms. The numerical results show that the GPU parallel optimize
We study emph{parallel} online algorithms: For some fixed integer $k$, a collective of $k$ parallel processes that perform online decisions on the same sequence of events forms a $k$-emph{copy algorithm}. For any given time and input sequence, th
e overall performance is determined by the best of the $k$ individual total results. Problems of this type have been considered for online makespan minimization; they are also related to optimization with emph{advice} on future events, i.e., a number of bits available in advance. We develop textsc{Predictive Harmonic}$_3$ (PH3), a relatively simple family of $k$-copy algorithms for the online Bin Packing Problem, whose joint competitive factor converges to 1.5 for increasing $k$. In particular, we show that $k=6$ suffices to guarantee a factor of $1.5714$ for PH3, which is better than $1.57829$, the performance of the best known 1-copy algorithm textsc{Advanced Harmonic}, while $k=11$ suffices to achieve a factor of $1.5406$, beating the known lower bound of $1.54278$ for a single online algorithm. In the context of online optimization with advice, our approach implies that 4 bits suffice to achieve a factor better than this bound of $1.54278$, which is considerably less than the previous bound of 15 bits.
The crux of molecular property prediction is to generate meaningful representations of the molecules. One promising route is to exploit the molecular graph structure through Graph Neural Networks (GNNs). It is well known that both atoms and bonds sig
nificantly affect the chemical properties of a molecule, so an expressive model shall be able to exploit both node (atom) and edge (bond) information simultaneously. Guided by this observation, we present Multi-View Graph Neural Network (MV-GNN), a multi-view message passing architecture to enable more accurate predictions of molecular properties. In MV-GNN, we introduce a shared self-attentive readout component and disagreement loss to stabilize the training process. This readout component also renders the whole architecture interpretable. We further boost the expressive power of MV-GNN by proposing a cross-dependent message passing scheme that enhances information communication of the two views, which results in the MV-GNN^cross variant. Lastly, we theoretically justify the expressiveness of the two proposed models in terms of distinguishing non-isomorphism graphs. Extensive experiments demonstrate that MV-GNN models achieve remarkably superior performance over the state-of-the-art models on a variety of challenging benchmarks. Meanwhile, visualization results of the node importance are consistent with prior knowledge, which confirms the interpretability power of MV-GNN models.
This paper introduces a new method of partitioning the solution space of a multi-objective optimisation problem for parallel processing, called Efficient Projection Partitioning. This method projects solutions down into a single dimension, greatly re
ducing the cost of partitioning the search space. We test EPP on a variety of randomly generated multi-objective combinatorial optimisation problems. The results are compared with the state of the art in parallel partitioning, and we show that in all scenarios tested, our new algorithm performs significantly better. Our proposed method allows the generation of non-dominated sets of larger problems with more decision variables or objective functions through the use of highly parallel computational infrastructure. Source code is provided to allow others to utilise, build upon and improve the algorithm
Exactly solving multi-objective integer programming (MOIP) problems is often a very time consuming process, especially for large and complex problems. Parallel computing has the potential to significantly reduce the time taken to solve such problems,
but only if suitable algorithms are used. The first of our new algorithms follows a simple technique that demonstrates impressive performance for its design. We then go on to introduce new theory for developing more efficient parallel algorithms. The theory utilises elements of the symmetric group to apply a permutation to the objective functions to assign different workloads, and applies to algorithms that order the objective functions lexicographically. As a result, information and updated bounds can be shared in real time, creating a synergy between threads. We design and implement two algorithms that take advantage of such theory. To properly analyse the running time of our three algorithms, we compare them against two existing algorithms from the literature, and against using multiple threads within our chosen IP solver, CPLEX. This survey of six different parallel algorithms, the first of its kind, demonstrates the advantages of parallel computing. Across all problem types tested, our new algorithms are on par with existing algorithms on smaller cases and massively outperform the competition on larger cases. These new algorithms, and freely available implementations, allows the investigation of complex MOIP problems with four or more objectives.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
