本文選題：分子對(duì)接 + 遺傳算法��； 參考：《大連理工大學(xué)》2014年博士論文

【摘要】：藥物分子設(shè)計(jì)作為一種新的藥物研究方法和手段,已經(jīng)取得了很多理論與實(shí)際的研究發(fā)現(xiàn)。隨著用于解釋生物大分子的結(jié)構(gòu)和功能的理論的不斷發(fā)展和成熟,藥物分子設(shè)計(jì)的理論和方法也在不斷的深化與發(fā)展。計(jì)算機(jī)輔助藥物設(shè)計(jì)是將藥物分子設(shè)計(jì)與飛速發(fā)展的計(jì)算機(jī)技術(shù)相結(jié)合的一個(gè)新的交叉研究領(lǐng)域,有效地推動(dòng)了藥物分子設(shè)計(jì)的進(jìn)一步發(fā)展。目前,計(jì)算機(jī)輔助藥物設(shè)計(jì)已經(jīng)成為進(jìn)行新藥探索的一種實(shí)用手段,可有效的降低藥品的研究費(fèi)用。分子對(duì)接方法是使用計(jì)算機(jī)技術(shù)來(lái)模擬配體與受體的相互作用與結(jié)合過(guò)程,是計(jì)算機(jī)輔助藥物設(shè)計(jì)中非常重要和實(shí)用的一種研究方法。 云計(jì)算是并行計(jì)算、分布式計(jì)算和網(wǎng)格計(jì)算的進(jìn)一步整合和發(fā)展,是一種深度基于互聯(lián)網(wǎng)的計(jì)算方式。通過(guò)云計(jì)算技術(shù),可以把原來(lái)只能在本地使用的軟件和服務(wù)擴(kuò)展到互聯(lián)網(wǎng)上,極大的方便了用戶的使用。CUDA (Compute Unified Device Architecture)一種通用的并行計(jì)算架構(gòu),該架構(gòu)使價(jià)格相對(duì)低廉的GPU (Graphic Processing Unit)也可以進(jìn)行復(fù)雜的科學(xué)計(jì)算等工作。鑒于諸多的優(yōu)勢(shì),云計(jì)算和CUDA并行計(jì)算都已成為目前的研究熱點(diǎn)問(wèn)題。 本文的主要研究?jī)?nèi)容包括： (1)提出了一種使用k均值聚類方法劃分殘基集團(tuán)和基于知識(shí)打分方法KScore的藥物分子對(duì)接算法。對(duì)受體活性位點(diǎn)處的殘基使用k均值聚類方法進(jìn)行基團(tuán)劃分,通過(guò)對(duì)這些基團(tuán)的運(yùn)動(dòng)考察來(lái)近似反映受體分子發(fā)生的柔性構(gòu)象變化。使用KScore評(píng)分方法對(duì)構(gòu)象的結(jié)合情況進(jìn)行評(píng)分,使用信息熵遺傳算法對(duì)優(yōu)化模型進(jìn)行迭代求解。仿真數(shù)值實(shí)驗(yàn)的結(jié)果表明,此方法對(duì)于測(cè)試集的平均對(duì)接時(shí)間較短,相比于其他流行對(duì)接方法而言其計(jì)算速度最快,并且其對(duì)接精度也相對(duì)較好。 (2)提出了一種基于多種評(píng)分函數(shù)的自適應(yīng)藥物分子對(duì)接算法。算法的評(píng)分函數(shù)選用基于力場(chǎng)、基于經(jīng)驗(yàn)(抽取疏水和熵變)和基于知識(shí)作為評(píng)分貢獻(xiàn)項(xiàng),建立自適應(yīng)對(duì)接優(yōu)化模型對(duì)問(wèn)題進(jìn)行優(yōu)化描述,使用信息熵多種群遺傳算法對(duì)優(yōu)化模型進(jìn)行求解。此方法對(duì)多種打分貢獻(xiàn)項(xiàng)進(jìn)行自適應(yīng)地綜合評(píng)定,其評(píng)價(jià)結(jié)果更為準(zhǔn)確和全面,同時(shí)避免了對(duì)訓(xùn)練集的過(guò)度依賴。對(duì)比于其他主流軟件和方法而言,此方法對(duì)于測(cè)試集的測(cè)試結(jié)果的平均RMSD值非常小,在參評(píng)的對(duì)接方法中為精度最優(yōu)方法。 (3)對(duì)于信息熵多種群遺傳算法和分子對(duì)接中的受體評(píng)分網(wǎng)格生成算法需要較多計(jì)算時(shí)間的問(wèn)題,提出了基于CUDA架構(gòu)基礎(chǔ)的并行算法。實(shí)現(xiàn)了信息熵遺傳算法的遺傳算子、懲罰函數(shù)和空間收縮因子等的并行計(jì)算。充分分析和挖掘受體評(píng)分網(wǎng)格算法的并行因素,結(jié)合GPU計(jì)算特點(diǎn),進(jìn)而提出了受體評(píng)分網(wǎng)格生成并行算法。實(shí)驗(yàn)結(jié)果表明,并行優(yōu)化后的算法對(duì)比原算法具有較高的計(jì)算效率。 (4)為了有效整合計(jì)算生物學(xué)應(yīng)用,提高軟硬件資源的利用率和有效降低資源的使用難度,在基于前期網(wǎng)格相關(guān)工作的基礎(chǔ)上,構(gòu)建了面向服務(wù)的計(jì)算生物學(xué)云社區(qū)平臺(tái)。針對(duì)本平臺(tái)服務(wù)對(duì)象和自身資源特點(diǎn)等情況,提出了四層云框架結(jié)構(gòu)并應(yīng)用于云平臺(tái)的建設(shè)。整合了課題組相關(guān)科研成果(包括本文相關(guān)成果),在進(jìn)行資源虛擬化和應(yīng)用服務(wù)化之上,以互聯(lián)網(wǎng)方式對(duì)用戶提供便捷而高效的使用平臺(tái)。用戶可在平臺(tái)上進(jìn)行包括分子對(duì)接和虛擬篩選等計(jì)算生物學(xué)相關(guān)工作,還可根據(jù)特定需求進(jìn)行相關(guān)應(yīng)用的流程化組織等。
[Abstract]:As a new drug research method and method , drug molecule design has been found . With the development and maturation of the theory of molecular design and function , the theory and method of drug molecule design have been deepening and developing . Computer - aided drug design has become a practical means to study drug molecule design . Computer - aided drug design has become a practical means to study drug molecule design .

Cloud computing is a further integration and development of parallel computing , distributed computing and grid computing . It is a deep - depth Internet - based computing approach . With cloud computing technology , software and services that can only be used locally can be extended to the Internet , which makes users more convenient to use . The architecture enables the relatively inexpensive GPU ( Graphic Processing Unit ) to perform complex scientific calculations .

The main research contents of this paper include :

( 1 ) A molecular docking algorithm using k - means clustering method to divide residue group and knowledge - based scoring method KScore is proposed . The residue of receptor active site is divided into groups by using k - means clustering method .

( 2 ) The self - adaptive drug molecular docking algorithm based on a plurality of scoring functions is proposed . The scoring function of the algorithm is based on the force field , based on experience ( extraction of hydrophobic and entropy change ) and knowledge as the score contribution term , and the optimization model is solved by using the information entropy multi - group genetic algorithm . The method has a more accurate and comprehensive evaluation result , and meanwhile avoids the over - dependence on the training set . Compared with other mainstream software and methods , the method has very small average RMSD value for the test result of the test set , and the method is the optimal method in the docking method of the evaluation .

( 3 ) To solve the problem of multiple computing time , the parallel algorithm of genetic operator , penalty function and space contraction factor of the information entropy genetic algorithm is proposed . The parallel factors of genetic operator , penalty function and space contraction factor of the information entropy genetic algorithm are realized . The parallel factors of the algorithm of the receptor scoring grid are analyzed and the parallel algorithm of the receptor scoring grid is fully analyzed . The experimental results show that the parallel algorithm has higher computational efficiency compared with the original algorithm .

( 4 ) In order to effectively integrate the computational biology application , improve the utilization rate of the software and hardware resources and effectively reduce the use difficulty of the resources , a four - layer cloud framework structure is constructed and applied to the construction of the cloud platform based on the related work of the previous grid .
【學(xué)位授予單位】：大連理工大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2014
【分類號(hào)】：TP18;TP393.09

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李純蓮,王希誠(chéng),趙金城,武金瑛;一種基于信息熵的多種群遺傳算法[J];大連理工大學(xué)學(xué)報(bào);2004年04期

2 康玲;李洪林;王希誠(chéng);;一種考慮蛋白質(zhì)柔性的分子對(duì)接方法[J];大連理工大學(xué)學(xué)報(bào);2008年02期

3 楊梅;李志民;曹大勇;;CUDA架構(gòu)下大規(guī)模稠密線性方程組的并行求解[J];計(jì)算機(jī)工程與應(yīng)用;2011年32期

4 李伯虎;張霖;王時(shí)龍;陶飛;曹軍威;姜曉丹;宋曉;柴旭東;;云制造——面向服務(wù)的網(wǎng)絡(luò)化制造新模式[J];計(jì)算機(jī)集成制造系統(tǒng);2010年01期

5 李祖華;張軍;王永劍;于坤千;;DDGrid:一種大規(guī)模藥物虛擬篩選網(wǎng)格[J];計(jì)算機(jī)工程與科學(xué);2009年S1期

6 黃江波;付志紅;;基于自適應(yīng)遺傳算法函數(shù)優(yōu)化與仿真[J];計(jì)算機(jī)仿真;2011年05期

7 張超群;鄭建國(guó);錢潔;;遺傳算法編碼方案比較[J];計(jì)算機(jī)應(yīng)用研究;2011年03期

8 馬永杰;云文霞;;遺傳算法研究進(jìn)展[J];計(jì)算機(jī)應(yīng)用研究;2012年04期

9 王瑞琪;張承慧;李珂;;基于改進(jìn)混沌優(yōu)化的多目標(biāo)遺傳算法[J];控制與決策;2011年09期

10 Huan WANG;Ping LIU;Hao XIE;;An empirical molecular docking study of a di-iron binding protein with iron ions[J];Journal of Zhejiang University-Science C(Computers & Electronics);2013年02期

，

本文編號(hào)：2087230