本文關(guān)鍵詞：大數(shù)據(jù)環(huán)境下化合物類藥性與活性預(yù)測(cè)研究　出處：《新疆大學(xué)》2016年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 海量數(shù)據(jù) 機(jī)器學(xué)習(xí) 深度學(xué)習(xí) 類藥性 活性預(yù)測(cè)

【摘要】：在藥物研發(fā)過(guò)程中,需要通過(guò)從海量化合物數(shù)據(jù)庫(kù)中篩選出質(zhì)量較高的藥物先導(dǎo)物來(lái)實(shí)現(xiàn)藥物設(shè)計(jì)成功效率的增加,因此,類藥性的概念應(yīng)運(yùn)而生,藥化學(xué)家們通過(guò)這一概念對(duì)分子結(jié)構(gòu)特征和性質(zhì)進(jìn)行研究,并總結(jié)出了類藥性預(yù)測(cè)指標(biāo)。另外,化合物的構(gòu)造活性關(guān)系研究也是藥物設(shè)計(jì)的重要方式之一,在發(fā)現(xiàn)和研究新的藥物的過(guò)程中,研究化合物活性與研究化合物類藥性同樣重要。在大多傳統(tǒng)的化合物活性研究中,通過(guò)動(dòng)物活體測(cè)驗(yàn)和檢測(cè)方式對(duì)化合物的藥物活性進(jìn)行測(cè)定,在海量化合物數(shù)據(jù)環(huán)境下無(wú)疑要耗費(fèi)大量時(shí)間及成本。而現(xiàn)代化合物活性研究對(duì)未知化合物的活性預(yù)測(cè)是通過(guò)使用數(shù)學(xué)方法建立定量構(gòu)效關(guān)系模型來(lái)實(shí)現(xiàn)的。隨著計(jì)算機(jī)數(shù)據(jù)挖掘技術(shù)的不斷發(fā)展,機(jī)器學(xué)習(xí)成為了計(jì)算機(jī)科學(xué)領(lǐng)域的一個(gè)活躍的研究方法,科學(xué)家們應(yīng)用機(jī)器學(xué)習(xí)方法提高藥物活性預(yù)測(cè)效率。然而,大多數(shù)已有研究方法使用的都是淺層機(jī)器學(xué)習(xí)算法,面對(duì)已知樣本和計(jì)算單元受到限制的情況下,其對(duì)復(fù)雜問(wèn)題的泛化能力難以滿足要求,無(wú)法學(xué)習(xí)更有用的特征。并且這些研究樣本數(shù)據(jù)量普遍較小,準(zhǔn)確率較低,在當(dāng)今海量化合物數(shù)據(jù)環(huán)境下實(shí)用性較差。本文以海量化合物數(shù)據(jù)為對(duì)象,結(jié)合深度學(xué)習(xí)方法,建立了海量化合物類藥性及藥物活性預(yù)測(cè)模型,具體內(nèi)容包括以下兩個(gè)部分:(1)海量化合物類藥性預(yù)測(cè)模型。第一部分結(jié)合化合物數(shù)據(jù)結(jié)構(gòu),為實(shí)現(xiàn)海量化合物類藥性的快速預(yù)測(cè)建立了分布式計(jì)算模型,并在此模型基礎(chǔ)上,根據(jù)類藥性評(píng)價(jià)規(guī)則快速高效地篩選出具有類藥性的化合物。模型使用了基于分治策略的分段哈希算法,并設(shè)計(jì)了連續(xù)屬性離散化方法,針對(duì)不適于用哈希檢索的連續(xù)數(shù)值型數(shù)據(jù)進(jìn)行離散化處理。(2)海量化合物藥物活性預(yù)測(cè)模型。第二部分對(duì)淺層機(jī)器學(xué)習(xí)方法和深度機(jī)器學(xué)習(xí)方法進(jìn)行介紹,并介紹它們的特點(diǎn)。然后以分子描述符為特征,分別使用不同的學(xué)習(xí)方法建立了海量化合物的藥物活性預(yù)測(cè)模型并對(duì)兩種學(xué)習(xí)方法進(jìn)行對(duì)比。實(shí)驗(yàn)結(jié)果表明,本文采用的深度學(xué)習(xí)模型適用于海量化合物類藥性及藥物活性預(yù)測(cè),可快速有效地篩選類藥化合物并預(yù)測(cè)其藥物活性。模型具有穩(wěn)定的可擴(kuò)展性和高效性,其正確性也得到了體現(xiàn)。
[Abstract]:In the process of drug development, it is necessary to select the high-quality drug precursors from the mass database of compounds to increase the efficiency of drug design. Therefore, the concept of drug-like came into being. Pharmacologists have studied the molecular structure and properties through this concept, and summarized the predictors of drug-like properties. In addition, the study of structure-activity relationship of compounds is also one of the important ways of drug design. In the discovery and research of new drugs, the study of the activity of compounds is just as important as the study of the properties of compounds, in most traditional studies of the activity of compounds. The drug activity of the compound was determined by animal living test and detection. In the environment of mass compound data, there is no doubt that it will cost a lot of time and cost, but the activity prediction of unknown compounds in modern compound activity research is realized by using mathematical method to establish quantitative structure-activity relationship model. With the development of computer data mining technology. Machine learning has become an active research method in the field of computer science. Scientists use machine learning to improve the efficiency of drug activity prediction. Most of the existing research methods use shallow machine learning algorithms. When the known samples and computing units are limited, its generalization ability to complex problems is difficult to meet the requirements. We can not learn more useful features. And these research sample data is generally small, the accuracy is low, and the practicability is poor in today's mass compound data environment. This paper takes the massive compound data as the object. Combined with the method of deep learning, the prediction model of drug properties and drug activity of massive compounds was established. The main contents are as follows: 1) the following two parts: 1) the prediction model of mass chemical properties. The first part establishes a distributed computing model for fast prediction of large amounts of chemical compounds by combining the data structure of compounds. On the basis of this model, we quickly and efficiently screen out the compounds with similar properties according to the evaluation rules of similar properties. The model uses a partition-and-conquer strategy based subsection hash algorithm, and designs a continuous attribute discretization method. A mass drug activity prediction model for continuous numerical data which is not suitable for hash retrieval is presented. In the second part, the shallow machine learning method and depth machine learning method are introduced. Then using different learning methods to establish the drug activity prediction model of massive compounds and compare the two learning methods. The depth learning model used in this paper is suitable for the prediction of drug properties and drug activity of a large number of compounds. It can quickly and effectively screen and predict the drug activity of drug like compounds. The model has stable expansibility and high efficiency. Its correctness has also been reflected.
【學(xué)位授予單位】：新疆大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP311.13;R91

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 劉艾林,杜冠華;化合物類藥性預(yù)測(cè)方法的研究[J];中國(guó)藥學(xué)雜志;2003年09期

2 韓春艷;李燕;劉剛;;類藥性:預(yù)測(cè)與實(shí)踐[J];化學(xué)進(jìn)展;2008年09期

3 李光,孫龍川;試析花類藥性能特點(diǎn)[J];江西中醫(yī)藥;2000年03期

4 惲榴紅;新藥發(fā)現(xiàn)階段類藥性評(píng)選[J];國(guó)外醫(yī)學(xué).藥學(xué)分冊(cè);2003年04期

5 章承繼,李煒,仇綴百;化合物類藥性的虛擬判斷方法研究[J];中國(guó)藥學(xué)雜志;2004年09期

6 林海燕;;淺析魚(yú)類藥性能特點(diǎn)[J];黑龍江中醫(yī)藥;2006年02期

7 姚麗梅,李偉榮,孫龍川;淺析果類藥性能特點(diǎn)[J];江西中醫(yī)學(xué)院學(xué)報(bào);2001年01期

8 李淑雯;試析根類藥性能特點(diǎn)[J];江西中醫(yī)藥;2002年01期

9 林海燕;淺析海洋生物類藥性能特點(diǎn)[J];江西中醫(yī)藥;2003年04期

10 朱偉;吳釘紅;丘小惠;徐文;;治療慢性腎病中藥的計(jì)算機(jī)藥理學(xué)研究[J];中國(guó)中藥雜志;2010年23期

相關(guān)會(huì)議論文 前2條

1 田盛;李有勇;侯廷軍;;中草藥化合物類藥性的理論研究[A];中國(guó)化學(xué)會(huì)第28屆學(xué)術(shù)年會(huì)第14分會(huì)場(chǎng)摘要集[C];2012年

2 魏敏吉;;如何提高新藥研發(fā)過(guò)程中生物樣品分析速度和質(zhì)量[A];2010年中國(guó)藥學(xué)大會(huì)暨第十屆中國(guó)藥師周論文集[C];2010年

相關(guān)重要報(bào)紙文章 前3條

1 編譯 李勇;“化學(xué)騙子”做糊涂科學(xué)[N];醫(yī)藥經(jīng)濟(jì)報(bào);2014年

2 健康時(shí)報(bào)記者　 鄭帆影;肺癌化療后吃點(diǎn)甲魚(yú)[N];健康時(shí)報(bào);2006年

3 上海中醫(yī)藥大學(xué) 副教授 單寶枝;何謂中藥的“以毒攻毒”[N];家庭醫(yī)生報(bào);2004年

相關(guān)博士學(xué)位論文 前1條

1 田盛;基于中藥資源的計(jì)算機(jī)輔助藥物分子設(shè)計(jì)[D];蘇州大學(xué);2014年

相關(guān)碩士學(xué)位論文 前4條

1 閆奕霖;大數(shù)據(jù)環(huán)境下化合物類藥性與活性預(yù)測(cè)研究[D];新疆大學(xué);2016年

2 田盛;類藥性和生物利用度的理論預(yù)測(cè)研究[D];蘇州大學(xué);2011年

3 孔慶雅;類藥性質(zhì)研究：藥物關(guān)鍵理化性質(zhì)和結(jié)構(gòu)的統(tǒng)計(jì)與分析[D];華東理工大學(xué);2015年

4 崔海東;取代吡咯烷-2-甲腈衍生物的合成、分子對(duì)接及虛擬類藥性評(píng)估[D];廣東藥學(xué)院;2015年

，

本文編號(hào)：1440967