基于分子描述符和机器学习方法预测和虚拟筛选乳腺癌靶向蛋白HEC1抑制剂

doi:10.3866/PKU.WHXB201507301

物理化学学报 >> 2015, Vol. 31 >> Issue (9): 1795-1802.doi: 10.3866/PKU.WHXB201507301

基于分子描述符和机器学习方法预测和虚拟筛选乳腺癌靶向蛋白HEC1抑制剂

何冰^1,²,罗勇¹,李秉轲²,薛英^1,³,余洛汀¹(),邱小龙^4,⁵,杨登贵⁴

¹ 四川大学华西医院生物治疗国家重点实验室,肿瘤中心及生物治疗协同创新中心,成都610041
² 成都师范学院化学与生命科学学院,成都611130
³ 四川大学化学学院,成都610064
⁴ 江苏兆邦生物医药研究院有限公司,江苏南通226000
⁵ 江苏海门慧聚药业有限公司,江苏海门226123

收稿日期:2015-04-02 发布日期:2015-09-06

Predicting and Virtually Screening Breast Cancer Targeting Protein HEC1 Inhibitors by Molecular Descriptors and Machine Learning Methods

Bing. HE^1,²,Yong. LUO¹,Bing-Ke. LI²,Ying. XUE^1,³,Luo-Ting. YU¹(),Xiao-Long. QIU^4,⁵,Teng-Kuei. YANG⁴

¹ State Key Laboratory of Biotherapy and Cancer Center, West China Hospital, Sichuan University, and Collaborative Innovation Center for Biotherapy, Chengdu 610041, P. R. China
² College of Chemistry and Life Science, Chengdu Normal University, Chengdu 611130, P. R. China
³ College of Chemistry, Sichuan University, Chengdu 610064, P. R. China
⁴ Zhaobang Bio-Med. Institute Co., Ltd., Nantong 226000, Jiangsu Province, P. R. China
⁵ Wisdom Pharmaceutical Co., Ltd., Haimen 226123, Jiangsu Province, P. R. China

Received:2015-04-02 Published:2015-09-06

摘要/Abstract

摘要：

HEC1(癌症高表达蛋白)是纺锤体检查点控制、着丝粒功能、细胞存活的关键的有丝分裂调节器,与原发性乳腺癌的不良预后有关.筛选具有高亲和力的HEC1新型抑制剂对探索乳腺癌的靶向治疗具有重要意义.本文从结构多样性的化合物库中筛选HEC1抑制剂.通过对分子描述符的特征筛选,采用支持向量机(SVM)和随机森林(RF)方法分别对HEC1抑制剂和非抑制剂建立了分类模型.经对比, RF模型显示了更好的预测精度.我们采用RF模型对HEC1抑制剂进行了虚拟筛选,从“in-house”实体库筛选得到2个潜在的HEC1抑制剂分子.随后对筛出的化合物进行了体外活性实验,发现对乳腺癌细胞株MDA-MB-468和MDA-MB-231均有一定程度的抗肿瘤活性.研究结果表明,机器学习方法对于设计和虚拟筛选HEC1抑制剂有良好的效果.

关键词: HEC1, 选择性抑制剂, 机器学习方法, 支持向量机, 随机森林, 虚拟筛选

Abstract:

Highly expressed in cancer 1 (HEC1) is a conserved mitotic regulator that is critical for spindle checkpoint control, kinetochore functionality, and cell survival. Overexpression of HEC1 has been detected in a variety of human cancers, and it is linked to poor prognosis of primary breast cancers. Thus, it is important to screen novel inhibitors with high affinity for HEC1. Machine learning (ML) methods were exhibiting good pharmacodynamics, and toxicity. In this work, two ML methods, support vector machines (SVMs) and random forests (RFs), were used to develop a classification method for searching inhibitors and non-inhibitors of HEC1 from the chemical library of structural diversity by screening characteristics of molecular descriptors. Both ML methods achieved promising prediction accuracies, and the RF model showed better performance. We performed virtual screening of HEC1 inhibitors by the RF model from an in-house database to screen potential HEC1 inhibitors. Two novel potential candidates were found. In vitro experiments of the two compounds showed that both had a certain degree of antitumor activity for the MDA-MB-468 and MDA-MB-231 breast cancer cell lines. Our study shows that ML methods are promising to design and virtually screen inhibitors of HEC1.

Key words: HEC1, Selective inhibitor, Machine learning method, Support vector machine, Random forest, Virtual screening

点击下载补充材料PDF格式文件

何冰,罗勇,李秉轲,薛英,余洛汀,邱小龙,杨登贵. 基于分子描述符和机器学习方法预测和虚拟筛选乳腺癌靶向蛋白HEC1抑制剂[J]. 物理化学学报, 2015, 31(9): 1795-1802.

Bing. HE,Yong. LUO,Bing-Ke. LI,Ying. XUE,Luo-Ting. YU,Xiao-Long. QIU,Teng-Kuei. YANG. Predicting and Virtually Screening Breast Cancer Targeting Protein HEC1 Inhibitors by Molecular Descriptors and Machine Learning Methods[J]. Acta Phys. -Chim. Sin., 2015, 31(9): 1795-1802.

链接本文: https://www.whxb.pku.edu.cn/CN/10.3866/PKU.WHXB201507301

https://www.whxb.pku.edu.cn/CN/Y2015/V31/I9/1795

参考文献

1	Gan S. J. ; Wang Q. ; Zhu L. M. ; Xie H. ; Ding X. F. Basic & Clin. Med 2015, 35 (1), 134.
1	甘绍举; 王青; 朱丽敏; 谢浩; 丁先锋. 基础医学与临床, 2015, 35 (1), 134.
2	Chen Y. ; Riley D. J. ; Chen P. L. ; Lee W. H. Mol. Cell Biol 1997, 17 (10), 6049.
3	Du X. L. ; Wang M. R. Acta Acad. Med. Sin 2007, 29 (1), 137.
3	杜小莉; 王明荣. 中国医学科学院学报, 2007, 29 (1), 137.
4	Hu C. M. ; Zhu J. ; Guo X. E. ; Chen W. ; Qiu X. L. ; Ngo B. ; Chien R. ; Wang Y. V. ; Tsai C. Y. ; Wu G. ; Kim Y. ; Lopez R. ; Chamberlin A. R. ; Lee E. H. ; Lee W. H. Oncogene 2015, 34, 1220.
5	Huang L. Y. ; Chang C. C. ; Lee Y. S. ; Chang J. M. ; Huang J. J. ; Chuang S. H. ; Kao K. J. ; Lau G. M. ; Tsai P. Y. ; Liu C. W. ; Lin H. S. ; Lau J. Y. Mol. Cancer Ther 2014, 13 (6), 1419.
6	Lee Y. S. ; Chuang S. H. ; Huang L. Y. ; Lai C. L. ; Lin Y. H. ; Yang J. Y. ; Liu C. W. ; Yang S. C. ; Lin H. S. ; Chang C. C. ; Lai J. Y. ; Jian P. S. ; Lam K. ; Chang J. M. ; Lau J. Y. ; Huang J.J. J.Med. Chem 2014, 57 (10), 4098.
7	Wu G. ; Qiu X. L. ; Zhou L. ; Zhu J. ; Chamberlin R. ; Lau J. ; Chen P. L. ; Lee W. H. Cancer Res 2008, 68 (20), 8393.
8	Qiu X. L. ; Li G. ; Wu G. ; Zhu J. ; Zhou L. ; Chen P. L. ; Chamberlin A. R. ; Lee W.H. J.Med. Chem 2009, 52 (6), 1757.
9	Chen Y. ; Riley D. J. ; Zheng L. ; Chen P. L. ; Lee W. H. J.Biol. Chem 2002, 277 (51), 49408.
10	Diaz-Rodríguez E. ; Sotillo R. ; Schvartzman J. M. ; Benezra R. Proc. Natl. Acad. Sci. U. S. A 2008, 105 (43), 16719.
11	Ferretti C. ; Totta P. ; Fiore M. ; Mattiuzzo M. ; Schillaci T. ; Ricordye R. ; Di Leonardo A. ; Degrassi F. Cell Cycle 2010, 9 (20), 4174.
12	Wei R. ; Ngo B. ; Wu G. ; Lee W. H. Mol. Biol. Cell 2011, 22 (19), 3584.
13	Xue Y. ; Li H. ; Ung C. ; Yap C. ; Chen Y. Chem. Res. Toxicol 2006, 19, 1030.
14	Xue Y. ; Yap C. W. ; Sun L. Z. ; Cao Z. W. ; Wang J. ; Chen Y. Z. J.Chem. Inf. Comput. Sci 2004, 44, 1497.
15	Xue Y. ; Li Z. ; Yap C. W. ; Sun L. ; Chen X. ; Chen Y. Z. J.Chem. Inf. Comput. Sci 2004, 44, 1630.
16	Yang X. G. ; Chen D. ; Wang M. ; Xue Y. ; Chen Y. Z. J.Comput. Chem 2009, 30, 1202.
17	Yang X. G. ; Lv W. ; Chen Y. Z. ; Xue Y. J.Comput. Chem 2010, 31, 1249.
18	Lv W. ; Xue Y. Eur. J.Med. Chem 2010, 45, 1167.
19	Cong Y. ; Yang X. ; Lv W. ; Xue Y. J.Mol. Graph. Model 2009, 28, 236.
20	Luan F. ; Liu H. ; Ma W. ; Fan B. Eur. Med. Chem 2008, 43, 43.
21	Ung C. Y. ; Li H. ; Yap C. W. ; Chen Y. Z. Mol. Pharmacol 2007, 71, 158.
22	Li H. ; Ung C. ; Yap C. ; Xue Y. ; Li Z. ; Cao Z. ; Chen Y. Chem. Res. Toxicol 2005, 18, 1071.
23	Li B. K. ; Cong Y. ; Tian Z. Y. ; Xue Y. Acta Phys. -Chim. Sin 2014, 30 (1), 171.
23	李秉轲; 丛湧; 田之悦; 薛英. 物理化学学报, 2014, 30 (1), 171.
24	Huang, J. J.; Lau, J. Improved Modulators of HEC1 Activity and Methods. CN Patent 103038231.A, 2013-04-10. Huang, J. J., Lau, J. HEC1
24	活性调节剂及其方法:中国, CN103038231.A[P]. 2013-04-10.
25	Duda R. O. ; Hart P. E. Pattern Classification and Scene Analysis; John Wiley & Sons: Hoboken, New Jersey, USA 1973.
26	ChemDraw 7.0.1 ed.; CambridgeSoft Corporation, Cambridge: Massachusetts, USA, 2007.
27	Corina 3.4 edn.; Molecular Networks GmbH Computerchemie: Erlangen, Germany, 2006.
28	Burges C. J. Data Min. Knowl. Disc 1998, 2, 121.
29	Vapnik V. N. The Nature of Statistical Learning Theory; Springer: Berlin & Heidelberg, Germany 1995.
30	Doucet J. P. ; Barbault F. ; Xia H. ; Panaye A. ; Fan B. Curr. Comput-Aid. Drug 2007, 3, 263.
31	Svetnik V. ; Liaw A. ; Tong C. ; Culberson J. C. ; Sheridan R. P. ; Feuston B. P. J.Chem. Inf. Comput. Sci 2003, 43, 1947.
32	BreimanL. Mach. Learn 2001, 45, 4.
33	Khandelwal A. ; Krasowski M. D. ; Reschly E. J. ; Sinz M. W. ; Swaan P. W. ; Ekins S. Chem. Res. Toxicol 2008, 21, 1457.
34	Breiman, L. Out-of-bag Estimation, 1996, http://citeseerx.ist.psu.edu.sci-hub.org/viewdoc/download?doi=10.1.1.45.3712&rep=rep1&type=pdf (accessed Mar 15, 2015).
35	Breiman, L. Wald Lecture II, Looking inside the Black Box, 2005. http://www.stat.berkeley.edu/users/breiman (accessed Mar 15, 2015).
36	Breiman, L.; Cutler, A. Random Forests, Version 5.1, 2004. http://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm (accessed Mar 15, 2015).

[1]	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 - .
[2]	罗棋耀,王紫鋆,金宏威,刘振明,张亮仁. 分子对接打分修正及在内皮脂肪酶选择性抑制剂筛选中的应用[J]. 物理化学学报, 2016, 32(10): 2606 -2619 .
[3]	时静洁, 陈利平, 陈网桦. 基于迭代自组织数据分析算法与蚁群算法建立有机物黏度的QSPR模型[J]. 物理化学学报, 2014, 30(5): 803 -810 .
[4]	丁俊杰, 丁晓琴, 李大禹, 潘里, 陈冀胜. ω-芋螺毒素的定量构效关系与虚拟筛选[J]. 物理化学学报, 2014, 30(11): 2157 -2167 .
[5]	李秉轲, 丛湧, 田之悦, 薛英. 基于分子描述符和机器学习方法预测和虚拟筛选MMP-13对MMP-1的选择性抑制剂[J]. 物理化学学报, 2014, 30(1): 171 -182 .
[6]	许先进, 苏计国, 刘斌, 李春华, 谭建军, 张小轶, 陈慰祖, 王存新. 持久性有机污染物4,4’-DDE和CB-153的反向虚拟筛选[J]. 物理化学学报, 2013, 29(10): 2276 -2285 .
[7]	丛湧, 薛英. 基于机器学习方法的丙型肝炎病毒聚合酶NS5B非核苷抑制剂的定量构效关系研究[J]. 物理化学学报, 2013, 29(08): 1639 -1647 .
[8]	王志明, 韩娜, 袁哲明, 伍朝华. 基于岭回归和SVM的高维特征选择与肽QSAR建模[J]. 物理化学学报, 2013, 29(03): 498 -507 .
[9]	吕巍, 薛英, 孟庆伟. 基于机器学习方法的H1N1神经氨酸苷酶抑制剂的分类预测[J]. 物理化学学报, 2013, 29(01): 217 -223 .
[10]	时静洁, 陈利平, 陈网桦, 石宁, 杨惠, 徐伟. 基于启发式方法和支持向量机方法预测有机物的热导率[J]. 物理化学学报, 2012, 28(12): 2790 -2796 .
[11]	丁新强, 武治印, 金宏威, 刘振明. 药物发现中常用化合物库特征描述与对比分析[J]. 物理化学学报, 2012, 28(10): 2401 -2410 .
[12]	乔康, 曾凌晓, 金宏威, 刘振明, 张亮仁. 人类腺苷受体A₃亚型拮抗剂的构效关系分析[J]. 物理化学学报, 2012, 28(06): 1509 -1519 .
[13]	张庆友, 龙海林, 冯秀林, 索净洁, 张丹丹, 李静亚, 许力壮, 许禄. MOLMAP指数及其在变异性预测中的应用[J]. 物理化学学报, 2012, 28(03): 541 -546 .
[14]	代志军, 周玮, 袁哲明, . 基于支持向量机的高维特征非线性快速筛选与肽QSAR建模[J]. 物理化学学报, 2011, 27(07): 1654 -1660 .
[15]	吕巍, 薛英. 基于机器学习方法的丙型肝炎病毒非结构蛋白5B聚合酶抑制剂活性预测[J]. 物理化学学报, 2011, 27(06): 1407 -1416 .

基于分子描述符和机器学习方法预测和虚拟筛选乳腺癌靶向蛋白HEC1抑制剂

Predicting and Virtually Screening Breast Cancer Targeting Protein HEC1 Inhibitors by Molecular Descriptors and Machine Learning Methods

RichHTML

PDF

赞

可视化

摘要/Abstract

支持信息

引用本文

使用本文

参考文献

相关文章 15

Metrics

推荐阅读 0