本文選題：藥物活性　切入點(diǎn)：計(jì)算機(jī)輔助算法　出處：《新疆大學(xué)》2017年碩士論文

【摘要】：隨著世界經(jīng)濟(jì)的高速發(fā)展,基于生物活性分子的藥效研究也不斷進(jìn)步。目前,采用組合藥理分析、高通量篩選技術(shù)、數(shù)理統(tǒng)計(jì)分析等多種技術(shù),為藥物活性的內(nèi)在屬性研究開啟了新的征程。但是,由于藥物分子自身高緯度、高復(fù)雜度的特性,將各類技術(shù)轉(zhuǎn)化為實(shí)際操作依舊十分艱難,成為科研過(guò)程中的瓶頸。因此,從海量的藥理數(shù)據(jù)中,及時(shí)有效的確定活性分子,成為科研工作者迫在眉睫的任務(wù)。為了迅速找到該問(wèn)題的解決方法,科研人員選用計(jì)算機(jī)作為藥物發(fā)現(xiàn)的輔助工具,較大程度上,計(jì)算機(jī)的使用為科研工作者的工作進(jìn)程起到了一定的推動(dòng)作用。然而,針對(duì)藥物活性分子研究,現(xiàn)有的大多數(shù)科研工作者僅選用某一類計(jì)算方法對(duì)其進(jìn)行探討,這種研究方式在一定程度上約束了藥物活性分子的檢測(cè)范圍,對(duì)于藥物的及時(shí)發(fā)現(xiàn)也不利。在實(shí)際檢測(cè)過(guò)程中,無(wú)標(biāo)簽數(shù)據(jù)較有標(biāo)簽數(shù)據(jù)容易獲得。因此,根據(jù)樣本屬性,本文采用兩類計(jì)算機(jī)輔助算法(淺層機(jī)器學(xué)習(xí)和深層機(jī)器學(xué)習(xí))進(jìn)行藥物活性分子研究,淺層機(jī)器學(xué)習(xí)選用有監(jiān)督算法(Supervised algorithm)和半監(jiān)督算法(Semi-supervised algorithm),深層機(jī)器學(xué)習(xí)選用無(wú)監(jiān)督算法(Unsupervised algorithm)。有監(jiān)督算法中,支持向量機(jī)(Support Vector Machine,SVM)和人工神經(jīng)網(wǎng)絡(luò)(Artificial Neural Network,ANN)較為常見。半監(jiān)督算法中,半監(jiān)督支持向量機(jī)(Semi-supervised support vector machine,S4VM)和代價(jià)安全性半監(jiān)督支持向量機(jī)(Cost security semi-supervised support vector machine,CS4VM)較有代表性。無(wú)監(jiān)督算法中,棧式自編碼(Stacked AutoEncoder,SAE)和深度信念網(wǎng)絡(luò)(Deep Belief Network,DBN)較為杰出。針對(duì)研究目的,本文將此六種方法進(jìn)行合理分配,分別對(duì)三類藥物活性分子(PLK1PBD、SMAD3、IL-1B)進(jìn)行深入探究。由于藥物活性分子結(jié)構(gòu)繁雜,選用化學(xué)計(jì)量學(xué)軟件MOE對(duì)其進(jìn)行精密計(jì)算,分別獲得其2D及3D分子描述符,通過(guò)上述兩類算法進(jìn)行藥物活性分子識(shí)別,實(shí)驗(yàn)結(jié)果表明,在相同條件下,基于深度學(xué)習(xí)的無(wú)監(jiān)督算法更容易提取活性分子的深層信息,較其它算法而言,其精確度、敏感度、特異度及命中率等指標(biāo)皆具有明顯優(yōu)勢(shì)。
[Abstract]:With the rapid development of the world economy, the research on bioactive molecules has been improved.At present, combinatorial pharmacological analysis, high-throughput screening technology, mathematical statistical analysis and other techniques have opened up a new journey for the study of intrinsic properties of drug activity.However, due to the characteristics of high latitude and high complexity of drug molecules, it is still very difficult to convert all kinds of technologies into practical operation, and become the bottleneck in the research process.Therefore, from the massive pharmacological data, it becomes an urgent task for researchers to identify active molecules in a timely and effective manner.In order to find the solution to the problem quickly, the researchers choose the computer as the auxiliary tool of drug discovery. To a large extent, the use of the computer has played a certain role in promoting the work process of the researchers.However, for the study of drug active molecules, most existing researchers only choose one kind of calculation method to discuss it, this kind of research method restricts the detection range of drug active molecules to some extent.It is also unfavorable to the timely discovery of drugs.In the actual detection process, the untagged data is easier to obtain than the labeled data.Therefore, according to the sample properties, two kinds of computer-aided algorithms (shallow machine learning and deep machine learning) are used to study the active molecules of drugs.The supervised algorithm and semi-supervised algorithm are selected for shallow machine learning and unsupervised algorithm for deep machine learning.Among supervised algorithms, support Vector Machine (SVM) and artificial Neural Network (Ann) are more common.Semi-supervised support vector machine (semi-supervised support vector machine) and cost security semi-supervised support vector machine (CS4VM) are more representative in semi-supervised security semi-supervised support vector machine than semi-supervised support vector machine (semi-supervised support vector machine) and cost security semi-supervised support vector machine (CS4VM).Among the unsupervised algorithms, stackable AutoEncoding (SAE) and Deep Belief Network (DBN) are outstanding.For the purpose of this study, the six methods were divided into three kinds of drug active molecule, PLK1 PBD1, SMAD3, IL-1B, respectively.Because of the complexity of the active molecular structure, the 2D and 3D molecular descriptors are obtained by using the chemometrics software MOE. The experimental results show that the two algorithms are used to recognize the active molecules.Under the same conditions, the unsupervised algorithm based on deep learning is easier to extract the deep information of active molecules, and its accuracy, sensitivity, specificity and hit rate have obvious advantages over other algorithms.
【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】：2017
【分類號(hào)】：R91;TP181

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 ;Editor Profile:Guest Editor of Special Issue on Targets and Anticancer Drug Research[J];Acta Pharmaceutica Sinica B;2017年01期

2 仝建波;占培;吳英紀(jì);;HIV-1逆轉(zhuǎn)錄酶抑制劑的3D-QSAR研究及分子設(shè)計(jì)[J];分析測(cè)試學(xué)報(bào);2016年11期

3 王存國(guó);;從高分子化學(xué)的一個(gè)趣味實(shí)驗(yàn)談如何培養(yǎng)學(xué)生的綜合實(shí)驗(yàn)?zāi)芰J];高分子通報(bào);2016年11期

4 馬彬廣;;蛋白折疊預(yù)測(cè)[J];科學(xué)通報(bào);2016年24期

5 吳宇強(qiáng);孫靜秋;崔穎;李靈芝;;黃酮類化合物醛糖脫氫酶抑制活性貝葉斯正則化反向傳播神經(jīng)網(wǎng)絡(luò)模型構(gòu)建[J];計(jì)算機(jī)與應(yīng)用化學(xué);2016年06期

6 盧宇源;安立佳;王健;;高分子黏彈性的經(jīng)典唯象模型[J];高分子學(xué)報(bào);2016年06期

7 高雙印;田生偉;禹龍;史新宇;;基于深度學(xué)習(xí)的PLK1 PBD活性預(yù)測(cè)[J];計(jì)算機(jī)應(yīng)用研究;2017年01期

8 曹小鳳;謝紅薇;安建成;郝曉燕;曹杰;;基于模糊理論的高血壓藥物療效預(yù)測(cè)模型研究[J];計(jì)算機(jī)應(yīng)用與軟件;2016年02期

9 盧騁;劉祥;唐延婷;徐永學(xué);仲威龍;孫濤;周紅剛;;基于酪氨酸磷酸酶(PTP1B)的Ⅱ型糖尿病藥物設(shè)計(jì)、合成和體外活性及毒性的初步評(píng)價(jià)[J];化學(xué)學(xué)報(bào);2016年02期

10 宗可昕;張晶;陳云雨;范卓文;司書毅;;PLK1 PBD靶向抗腫瘤抑制劑的篩選及活性研究[J];中國(guó)醫(yī)藥生物技術(shù);2016年01期

相關(guān)碩士學(xué)位論文 前2條

1 王曉茜;抗微生物肽和抗癌肽的特征信息提取及預(yù)測(cè)算法研究[D];內(nèi)蒙古農(nóng)業(yè)大學(xué);2014年

2 楊鵬;用貝葉斯網(wǎng)絡(luò)對(duì)蛋白質(zhì)LOOP結(jié)構(gòu)建模的研究[D];蘇州大學(xué);2011年

，

本文編號(hào)：1716150