Performance of Nonlinear Finite-Difference Poisson-Boltzmann Solvers.
Performance of Nonlinear Finite-Difference Poisson-Boltzmann Solvers.
复制标题
DOI：
10.1021/ct900381r
复制
发表时间：
2010-01-12
影响因子：
5.5
通讯作者：
Luo, Ray
中科院分区：
文献类型：
--
作者：
Cai, Qin;Hsieh, Meng-Juei;Wang, Jun;Luo, Ray
我们实现并优化了七个有限差分求解器的全非线性Poisson-Boltzmann方程在生物分子的应用，包括四个松弛方法，共轭梯度法，和两个不精确牛顿方法。用大量的核酸和蛋白质对这七个求解器的性能进行了广泛的评估。值得注意的是我们分析中的不精确牛顿法。通过将不完全Cholesky共轭梯度和几何多重网格引入其内部线性循环，我们研究了线性求解器在其性能中的作用。我们定制和优化了两个线性求解器，以加快收敛速度。此外，我们还探索了优化逐次超松弛方法的策略，以减少其收敛失败，而不会牺牲太多的收敛速度。具体来说，我们试图自适应地改变松弛参数，并利用阻尼策略，从不精确牛顿法，以改善连续的超松弛方法。我们的分析表明，非线性方法伴随着一个功能的辅助策略，如共轭梯度法和不精确牛顿法，可以保证收敛的测试分子。特别是不精确牛顿法，当它与高效的线性求解器相结合时，表现出令人印象深刻的性能。
We implemented and optimized seven finite-difference solvers for the full nonlinear Poisson-Boltzmann equation in biomolecular applications, including four relaxation methods, one conjugate gradient method, and two inexact Newton methods. The performance of the seven solvers was extensively evaluated with a large number of nucleic acids and proteins. Worth noting is the inexact Newton method in our analysis. We investigated the role of linear solvers in its performance by incorporating the incomplete Cholesky conjugate gradient and the geometric multigrid into its inner linear loop. We tailored and optimized both linear solvers for faster convergence rate. In addition, we explored strategies to optimize the successive over-relaxation method to reduce its convergence failures without too much sacrifice in its convergence rate. Specifically we attempted to adaptively change the relaxation parameter and to utilize the damping strategy from the inexact Newton method to improve the successive over-relaxation method. Our analysis shows that the nonlinear methods accompanied with a functional-assisted strategy, such as the conjugate gradient method and the inexact Newton method, can guarantee convergence in the tested molecules. Especially the inexact Newton method exhibits impressive performance when it is combined with highly efficient linear solvers that are tailored for its special requirement.
登录
查看更多内容
DOI：
10.1137/0902035
发表时间：
1981-01-01
期刊：
SIAM JOURNAL ON SCIENTIFIC AND STATISTICAL COMPUTING
影响因子：
--
作者：
ALCOUFFE, RE;BRANDT, A;PAINTER, JW
通讯作者：
PAINTER, JW
影响因子：
3.1
作者：
EISENSTAT, SC;WALKER, HF
通讯作者：
WALKER, HF
影响因子：
2.9
作者：
Chen, Long;Holst, Michael J.;Xu, Jinchao
通讯作者：
Xu, Jinchao
影响因子：
3
作者：
HOLST, MJ;SAIED, F
通讯作者：
SAIED, F
影响因子：
2.9
作者：
JAYARAM, B;SHARP, KA;HONIG, B
通讯作者：
HONIG, B