应用机器学习方法构建药物分子解离速率常数的预测模型

doi:10.3866/PKU.WHXB201907006

物理化学学报 >> 2020, Vol. 36 >> Issue (1): 1907006.doi: 10.3866/PKU.WHXB201907006

所属专题：庆祝唐有祺院士百岁华诞特刊

应用机器学习方法构建药物分子解离速率常数的预测模型

苏敏仪^1,²,刘慧思³,林海霞^3,*(),王任小^1,^2,*()

¹ 中国科学院上海有机化学研究所, 生命有机化学国家重点实验室, 上海 200032
² 中国科学院大学，北京 100049
³ 上海大学理学院化学系，上海 200444

收稿日期:2019-07-01 录用日期:2019-08-30 发布日期:2019-09-03
通讯作者: 林海霞,王任小 E-mail:haixialin@staff.shu.edu.cn;wangrx@mail.sioc.ac.cn
基金资助:
中国科技部重点研发项目(2016YFA0502302);国家自然科学基金(81725022);国家自然科学基金(81430083);国家自然科学基金(21661162003);国家自然科学基金(21673276);国家自然科学基金(21472227);国家自然科学基金(21472226);中国科学院先导项目(XDB20000000)

Machine-Learning Model for Predicting the Rate Constant of ProteinLigand Dissociation

Minyi Su^1,²,Huisi Liu³,Haixia Lin^3,*(),Renxiao Wang^1,^2,*()

¹ State Key Laboratory of Bioorganic and Natural Products Chemistry, Shanghai Institute of Organic Chemistry, Chinese Academy of Sciences, Shanghai 200032, P. R. China
² University of Chinese Academy of Sciences, Beijing 100049, P. R. China
³ Department of Chemistry, College of Sciences, Shanghai University, Shanghai 200444, P. R. China

Received:2019-07-01 Accepted:2019-08-30 Published:2019-09-03
Contact: Haixia Lin,Renxiao Wang E-mail:haixialin@staff.shu.edu.cn;wangrx@mail.sioc.ac.cn
Supported by:
the National Key Research Program of Ministry of Science and Technology of China(2016YFA0502302);National Natural Science Foundation of China(81725022);National Natural Science Foundation of China(81430083);National Natural Science Foundation of China(21661162003);National Natural Science Foundation of China(21673276);National Natural Science Foundation of China(21472227);National Natural Science Foundation of China(21472226);Strategic Priority Research Program of Chinese Academy of Sciences(XDB20000000)

摘要/Abstract

摘要：

越来越多的研究表明：药物分子与靶标分子的结合动力学性质与其在体内的药效有很强的相关性。因此，以改善结合动力学性质为导向的分子设计为药物研发提供了新的思路。本工作的研究目标在于得出预测药物分子解离速率常数(k_off)的通用型定量结构-动力学关系(QSKR)模型。我们从文献中收集了406个配体分子的解离速率常数实验值，采用分子模拟方法构建了所有配体与靶蛋白复合物的三维结构模型。然后基于蛋白-配体原子对描述符，采用随机森林算法来构建预测配体分子解离速率常数的QSKR模型。通过探索不同条件(如距离区间，划分区间宽度和特征选择标准)下产生的描述符集合对模型预测精度的影响，确定当采用距离阈值为15 Å、划分区间宽度为3 Å、特征选择方差水平为2时得到的QSKR模型为最优，在两个独立测试集上获得良好的预测精度(相关系数为0.62)。本工作对预测药物分子解离速率常数这一关键科学问题进行了有益的探索，可为后续研究提供思路。

关键词: 解离速率常数, 配体结合动力学, 随机森林模型, 蛋白-配体相互作用, 基于结构的药物设计

Abstract:

An increasing number of recent studies have shown that the binding kinetics of a drug molecule to its target correlates strongly with its efficacy in vivo. Therefore, ligand optimization oriented to improved binding kinetics provides new ideas for rational drug design. Currently, ligand binding kinetics is modeled mainly through extensive molecular dynamics simulations, which limits its application to real-world problems. The present study aimed at obtaining a general-purpose quantitative structure-kinetics relationship (QSKR) model for predicting the dissociation rate constant (k_off) of a ligand based on its complex structure. This type of model is expected to be suitable for high-throughput tasks in structure-based drug design. We collected the experimentally measured k_off values for 406 ligand molecules from literature, and then constructed a three-dimensional structural model for each protein-ligand complex through molecular modeling. A training set was compiled using 60% of those complexes while the remaining 40% were assigned to two test sets. Based on distance-dependent protein-ligand atom pair descriptors, a random forest algorithm was adopted to derive a QSKR model. Various random forest models were then generated based on the descriptor sets obtained under different conditions, such as distance cutoff, bin width, and feature selection criteria. The cross-validation results of those models were then examined. It was observed that the optimal model was obtained when the distance cutoff was 15 Å (1 Å = 0.1 nm), the bin width was 3 Å, and feature selection variance level was 2. The final QSKR model produced correlation coefficients around 0.62 on the two independent test sets. This level of accuracy is at least comparable to that of the predictive models described in literature, which are typically computationally much more expensive. Our study attempts to address the issue of predicting k_off values in drug design. We hope that it can provide inspiration for further studies by other researchers.

Key words: Dissociation rate constant, Ligand binding kinetics, Random forest model, Protein-ligand interaction, Structure-based drug design

MSC2000:

O641

苏敏仪,刘慧思,林海霞,王任小. 应用机器学习方法构建药物分子解离速率常数的预测模型[J]. 物理化学学报, 2020, 36(1): 1907006.

Minyi Su,Huisi Liu,Haixia Lin,Renxiao Wang. Machine-Learning Model for Predicting the Rate Constant of ProteinLigand Dissociation[J]. Acta Physico-Chimica Sinica, 2020, 36(1): 1907006.

图/表 10

图1

图2

图3

图4

图5

图6

表1

图7

表2

表3

参考文献 33

1	Copeland R. A. ; Pompliano D. L. ; Meek T. D. Nat. Rev. Drug Discov. 2006, 5, 730. doi: 10.1038/nrd2082
2	Tummino P. J. ; Copeland R. A. Biochemistry 2008, 47, 5481. doi: 10.1021/bi8002023
3	Schuetz D. A. ; Arnout de Witte W. E. ; Wong Y. C. ; Knasmueller B. ; Richter L. ; Kokh D. B. ; Sadiq S. K. ; Bosma R. ; Nederpelt I. ; Heitman L. H. ; et al Drug Discov. Today 2017, 22, 896. doi: 10.1016/j.drudis.2017.02.002
4	Pan A. C. ; Borhani D. W. ; Dror R. O. ; Shaw D. E. Drug Discov. Today 2013, 18, 667. doi: 10.1016/j.drudis.2013.02.007
5	Guo D. ; Mulder K. T. ; Ijzerman A. P. ; Heitman L. H. Br. J. Pharmacol. 2012, 166, 1846. doi: 10.1111/j.1476-5381.2012.01897.x
6	Folmer R. H. A. Drug Discov. Today 2018, 23, 12. doi: 10.1016/j.drudis.2017.07.016
7	Bruce N. J. ; Ganotra G. K. ; Kokh D. B. ; Sadiq S. K. ; Wade R. C. Curr. Opin. Struct. Biol. 2018, 49, 1. doi: 10.1016/j.sbi.2017.10.001
8	Qu S. J. ; Huang S. H. ; Pan X. C. ; Yang L. ; Mei H. J. Chem. Inf. Model. 2016, 56, 2061. doi: 10.1021/acs.jcim.6b00326
9	Ganotra G. K. ; Wade R. C. ACS Med. Chem. Lett. 2018, 9, 1134. doi: 10.1021/acsmedchemlett.8b00397
10	Liu Z.H ; Li Y. ; Han L. ; Li J. ; Liu J. ; Zhao Z. X. ; Nie W. ; Liu Y. C ; Wang R. X. Bioinformatics 2015, 31, 405. doi: 10.1093/bioinformatics/btu626
11	Li W. ; Godzik A. Bioinformatics 2006, 22, 1658. doi: 10.1093/bioinformatics/btl158
12	Fu L. ; Niu B. ; Zhu Z. ; Wu S. ; Li W. Bioinformatics 2012, 28, 3150. doi: 10.1093/bioinformatics/bts565
13	Royston J. P. Appl. Stat. 1982, 31, 115. doi: 10.2307/2347973
14	Royston J. P. Appl. Stat. 1982, 31, 176. doi: 10.2307/2347986
15	Rogers D. ; Hahn M. J. Chem. Inf. Model. 2010, 50, 742. doi: 10.1021/ci100050t
16	Bietz S. ; Urbaczek S. ; Schulz B. ; Rarey M. J. Cheminform. 2014, 6, 1. doi: 10.1186/1758-2946-6-12
17	Friesner R. A. ; Banks J. L. ; Murphy R. B. ; Halgren T. A. ; Klicic J. J. ; Mainz D. T. ; Repasky M. P. ; Knoll E. H. ; Shelley M. ; Perry J. K. ; et al J. Med. Chem. 2004, 47, 1739. doi: 10.1021/jm0306430
18	Halgren T. A. ; Murphy R. B. ; Friesner R. A. ; Beard H. S. ; Frye L. L. ; Pollard W. T. ; Banks J. L. J. Med. Chem. 2004, 47, 1750. doi: 10.1021/jm030644s
19	Friesner R. A. ; Murphy R. B. ; Repasky M. P. ; Frye L. L. ; Greenwood J. R. ; Halgren T. A. ; Sanschagrin P. C. ; Mainz D. T. J. Med. Chem. 2006, 49, 6177. doi: 10.1021/jm051256o
20	Qiu D. ; Shenkin P. S. ; Hollinger F. P. ; Still W. C. J. Phys. Chem. A 1997, 101, 3005. doi: 10.1021/jp961992r
21	Case, D. A.; Babin, V.; Berryman, J. T.; Betz, R. M.; Cai, Q.; Cerutti, D. S.; Cheatham, T. E., Ⅲ; Darden, T. A.; Duke, R. E.; Gohlke, H.; Goetz, A. W.; et al. AMBER 2014; University of California: San Francisco, CA, USA, 2014.
22	Frisch, M. J.; Trucks, G. W.; Schlegel, H. B.; Scuseria, G. E.; Robb, M. A.; Cheeseman, J. R.; Scalmani, G.; Barone, V.; Petersson, G. A.; Nakatsuji, H.; et al. Gaussian 09, Revision A.02; Gaussian, Inc.: Wallingford, CT, USA, 2016.
23	Cieplak P. ; Cornell W. D. ; Bayly C. ; Kollman P. A. J. Comput. Chem. 1995, 16, 1357. doi: 10.1002/jcc.540161106
24	Maier J. A. ; Martinez C. ; Kasavajhala K. ; Wickstrom L. ; Hauser K. E. ; Simmerling C. J. Chem. Theory Comput. 2015, 11, 3696. doi: 10.1021/acs.jctc.5b00255
25	Wang J. ; Wolf R. M. ; Caldwell J. W. ; Kollman P. A. ; Case D. A. J. Comput. Chem. 2004, 25, 1157. doi: 10.1002/jcc.20035
26	Jorgensen W. L. ; Chandrasekhar J. ; Madura J. D. ; Impey R. W. ; Klein M. L. J. Chem. Phys. 1983, 79, 926. doi: 10.1063/1.445869
27	Ryckaert, J. P.; Ciccotti, G.; Berendsen, H. J. C. J. Chem. Phys. 1977, 23, 327. doi: 10.1.1.399.6868
28	Roe D. R. ; Cheatham T. E. Ⅲ. J. Chem. Theory Comput. 2013, 9, 3084. doi: 10.1021/ct400341p
29	Rudling A. ; Orro A. ; Carlsson J. J. Chem. Inf. Model. 2018, 58, 350. doi: 10.1021/acs.jcim.7b00520
30	Ballester P. J. ; Schreyer A. ; Blundell T. L. J. Chem. Inf. Model. 2014, 54, 944. doi: 10.1021/ci500091r
31	Pedregosa F. ; Varoquaux G. ; Gramfort A. ; Michel V. ; Thirion B. ; Grisel O. ; Blondel M. ; Prettenhofer P. ; Weiss R. ; Dubourg V. ; et al J. Mach. Learn. Res. 2011, 12, 2825.
32	Kennard R. W. ; Stone L. A. Technometrics 1969, 11, 137. doi: 10.1080/00401706.1969.10490666
33	Martin T. M. ; Harten P. ; Young D. M. ; Muratov E. N. ; Golbraikh A. ; Zhu H. ; Tropsha A. J. Chem. Inf. Model. 2012, 52, 2570. doi: 10.1021/ci300338w

Distance cutoff /Å	Bin width/Å ^a
6	1, 2, 3, 6
9	1, 3, 9
12	1, 2, 3, 4, 6, 12
15	1, 3, 5, 15

Bin width/Å	Bin width/Å	Feature selection variance level
Bin width/Å	Bin width/Å	0	1	2
6	1	0.548	0.507	0.393
	2	0.524	0.406	0.304
	3	0.509	0.484	0.546
	6	0.496	0.526	0.519
9	1	0.507	0.437	0.408
	3	0.563	0.576	0.447
	9	0.511	0.551	0.482
12	1	0.557	0.436	0.489
	2	0.562	0.416	0.568
	3	0.526	0.504	0.619
	4	0.553	0.501	0.363
	6	0.461	0.626	0.536
	12	0.425	0.356	0.604
15	1	0.317	0.604	0.487
	3	0.573	0.551	0.671
	5	0.417	0.574	0.585
	15	0.569	0.532	0.585

Data set	R		RMSE
Data set	Model 1	Reference model	Model 1	Reference model
internal validation set	0.671	0.436	1.03	1.18
external test set	0.623	0.252	1.06	1.06
HSP90 test set	0.625	0.375	0.85	0.98

[1]	刘苗苗, 王文娟, 郝秀萍, 董晓燕. Aβ40和hIAPP在溶液和表面的成核与交叉成核聚集行为[J]. 物理化学学报, 0, (): 2002024 -0 .
[2]	周蔚, 李运超, 范楼珍, 李晓宏. 硫黄素T与侧翼连接双链DNA的G-四链体高特异性作用[J]. 物理化学学报, 0, (): 2004017 -0 .
[3]	林锦亮, 张雅敏, 张浩力. 单分子器件中的新颖静电场效应[J]. 物理化学学报, 0, (): 2005010 -0 .
[4]	Zhang Chengcheng, Crisci Ralph, Chen Zhan. 原位探测防污高分子材料与液体界面的分子结构[J]. 物理化学学报, 2020, 36(10): 1910003 -0 .
[5]	杨亚梅, 伦会洁, 龙腊生, 孔祥建, 郑兰荪. 稀土-钛氧簇合物EuTi₆，EuTi₇和La₂Ti₁₄的可控合成[J]. 物理化学学报, 2020, 36(9): 1912007 -0 .
[6]	乔成芳,吕磊,许文风,夏正强,周春生,陈三平,高胜利. 三维无溶剂含能Ag-MOF的制备、热分解动力学及爆炸性能[J]. 物理化学学报, 2020, 36(6): 1905085 -0 .
[7]	王磊, 孙毯毯, 闫娜娜, 刘晓娜, 马超, 徐舒涛, 郭鹏, 田鹏, 刘中民. 不同结构导向剂合成不同硅含量SAPO-34分子筛的酸性质[J]. 物理化学学报, 0, (): 2003046 -0 .
[8]	李海霞,王纪伟,焦丽芳,陶占良,梁静. 碳包覆纳米SnSb合金作为高性能钠离子电池负极材料[J]. 物理化学学报, 2020, 36(5): 1904017 -0 .
[9]	纪毅, 梁力鑫, Changmiao Guo, 包信和, Tatyana Polenova, 侯广进. 固体核磁共振高速魔角旋转条件下对称性脉冲零量子同核重耦技术[J]. 物理化学学报, 2020, 36(4): 1905029 -0 .
[10]	刘小龙, 王强, 王超, 徐君, 邓风. Silicalite-1分子筛氢键诱导晶化机制的固体核磁共振研究[J]. 物理化学学报, 2020, 36(4): 1905035 -0 .
[11]	邓静,马涛,常自伟,赵伟静,杨俊. 基于固体核磁共振方法的蛋白质组装体三维结构解析[J]. 物理化学学报, 2020, 36(4): 1905019 -0 .
[12]	李玉红,吴新平,刘聪,王萌,宋本腾,郁桂云,杨刚,侯文华,龚学庆,彭路明. 部分还原二氧化钛的NMR和EPR研究[J]. 物理化学学报, 2020, 36(4): 1905021 -0 .
[13]	李超, 沈明, 胡炳文. 面向金属离子电池研究的固体核磁共振和电子顺磁共振方法[J]. 物理化学学报, 2020, 36(4): 1902019 -0 .
[14]	李诗涵,赵侦超,李世坤,邢友东,张维萍. DFT计算结合固体NMR研究富铝SSZ-13的铝分布和Brønsted酸性[J]. 物理化学学报, 2020, 36(4): 1903021 -0 .
[15]	石峰,胡丽丽,任进军,杨秋红. 固体核磁共振研究碱土金属磷硅酸盐玻璃的六配位硅结构[J]. 物理化学学报, 2020, 36(4): 1902018 -0 .

应用机器学习方法构建药物分子解离速率常数的预测模型

Machine-Learning Model for Predicting the Rate Constant of ProteinLigand Dissociation

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 33

相关文章 15

Metrics

本文评价

推荐阅读 0