计算机科学技术学报 ›› 2021,Vol. 36 ›› Issue (2): 261-275.doi: 10.1007/s11390-021-0866-2

所属专题： Emerging Areas

• • 上一篇    下一篇

基于多相似性度量融合的合成致死基因对预测

Lian-Lian Wu1,2,?, Yu-Qi Wen2,?, Xiao-Xi Yang2,3, Bo-Wei Yan2, Song He2,*, and Xiao-Chen Bo1,2,*   

  1. 1 Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300072, China;
    2 Department of Biotechnology, Beijing Institute of Radiation Medicine, Beijing 100850, China;
    3 Experimental Center, Beijing Friendship Hospital, Capital Medical University, Beijing 100850, China
  • 收稿日期:2020-08-03 修回日期:2021-02-28 出版日期:2021-03-05 发布日期:2021-04-01
  • 通讯作者: Song He, Xiao-Chen Bo E-mail:hes1224@163.com;boxc@bmi.ac.cn
  • 作者简介:Lian-Lian Wu is a Master student in Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin. She majors in biomedical engineering. Her research interests include bioinformatics, machine learning and deep learning.

Synthetic Lethal Interactions Prediction Based on Multiple Similarity Measures Fusion

Lian-Lian Wu1,2,?, Yu-Qi Wen2,?, Xiao-Xi Yang2,3, Bo-Wei Yan2, Song He2,*, and Xiao-Chen Bo1,2,*        

  1. 1 Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300072, China;
    2 Department of Biotechnology, Beijing Institute of Radiation Medicine, Beijing 100850, China;
    3 Experimental Center, Beijing Friendship Hospital, Capital Medical University, Beijing 100850, China
  • Received:2020-08-03 Revised:2021-02-28 Online:2021-03-05 Published:2021-04-01
  • Contact: Song He, Xiao-Chen Bo E-mail:hes1224@163.com;boxc@bmi.ac.cn
  • About author:Lian-Lian Wu is a Master student in Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin. She majors in biomedical engineering. Her research interests include bioinformatics, machine learning and deep learning.

PDF (PC)

45

补充材料

1

研究背景（context）：合成致死（Synthetic Lethality）是指两个非致死基因同时失活导致细胞死亡的现象，我们称这两个基因为合成致死基因对。在癌症治疗中，用药物靶向致癌基因的合成致死配对基因可以选择性地杀死癌细胞，而不危害正常细胞。这样的治疗策略有望实现更有效、毒性更低的个性化癌症治疗。因此，寻找有效的合成致死基因对对抗癌药物研究具有十分重要的意义。
目的（Objective）：我们的研究目的是通过使用计算方法识别出具有合成致死效应的基因对。目前已有的识别合成致死基因对的方法主要依靠高通量筛选。但基因组合的数量随着涉及的基因数量的增加呈指数增长，并随着癌症类型的增加而不断扩大。考虑到基因组合数量的庞大，通过高通量筛选测试所有可能的基因组合并不可行。因此，设计有效地探索基因组合空间并发现有效合成致死基因对的计算预测方法被迫切需要。
方法（Method）：我们提出了一种预测合成致死基因对的新方法，首先我们计算出基因之间基于基因表达谱、蛋白质序列、蛋白质-蛋白质相互作用网络、共通路信息和基因本体论的相似性分数。接下来，我们应用了SNF算法融合上述7种基因之间的相似性度量。第三，我们计算基因对之间的相似性度量。最后，我们应用k最近邻算法实现了基因对之间基于相似性的分类任务。
结果（Result&Findings）：经过与其他预测方法的性能对比后，我们发现我们的基于相似性的分类方法具有更好的预测性能，AUROC值达到了0.85。我们进一步分析了各数据类型的贡献度，发现在使用的7种相似性度量中，基于蛋白质序列的相似性特征贡献度最高。应用我们提出的方法预测新的合成致死基因对，我们发现RAS系列基因在训练集和预测结果中具有最多的合成致死配对基因。
结论（Conclusions）：我们融合了合成致死基因对的7种相似性度量，实现了基于相似性的分类任务，结果表明基于相似性的方法大大提高了模型的分类性能。我们进一步发现RAS基因的合成致死配对基因有可能成为癌症靶向治疗中的关键靶点，靶向RAS合成致死配对基因的药物有可能具有很大的抗癌潜力。使用该方法进行预测后，我们通过两个抗癌相关实例证明了预测结果的有效性。接下来我们还将进一步研究加入更多维度的属性信息、开发具有更高性能的计算模型以进一步实现对合成致死基因对的准确预测。

关键词: 合成致死, 相似性度量融合, k最近邻, 多维度数据

Abstract: The synthetic lethality (SL) relationship arises when a combination of deficiencies in two genes leads to cell death, whereas a deficiency in either one of the two genes does not. The survival of the mutant tumor cells depends on the SL partners of the mutant gene, thereby the cancer cells could be selectively killed by inhibiting the SL partners of the oncogenic genes but normal cells could not. Therefore, there is an urgent need to develop more efficient computational methods of SL pairs identification for cancer targeted therapy. In this paper, we propose a new approach based on similarity fusion to predict SL pairs. Multiple types of gene similarity measures are integrated and k-nearest neighbors algorithm (k-NN) is applied to achieve the similarity-based classification task between gene pairs. As a similarity-based method, our method demonstrated excellent performance in multiple experiments. Besides the effectiveness of our method, the ease of use and expansibility can also make our method more widely used in practice.

Key words: synthetic lethality, similarity measures fusion, k-nearest neighbor, multi-dimensional data

[1] Hartwell L H, Szankasi P, Roberts C J et al. Integrating genetic approaches into the discovery of anticancer drugs. Science, 1997, 278(5340):1064-1068. DOI:10.1126/science.278.5340.1064.
[2] Boone C, Bussey H, Andrews B J. Exploring genetic interactions and networks with yeast. Nature Reviews Genetics, 2007, 8(6):437-449. DOI:10.1038/nrg2085.
[3] Chan D A, Giaccia A J. Harnessing synthetic lethal interactions in anticancer drug discovery. Nature Reviews Drug Discovery, 2011, 10(5):351-364. DOI:10.1038/nrd3374.
[4] Deng X, Das S, Valdez K et al. SL-BioDP:Multi-cancer interactive tool for prediction of synthetic lethality and response to cancer treatment. Cancers (Basel), 2019, 11(11):Article No. 1682. DOI:10.3390/cancers11111682.
[5] McLornan D P, List A, Mufti G J. Applying synthetic lethality for the selective targeting of cancer. New England Journal of Medicine, 2014, 371(18):1725-1735. DOI:10.1056/NEJMra1407390.
[6] Bryant H E, Schultz N, Thomas H D et al. Specific killing of BRCA2-deficient tumours with inhibitors of poly(ADPribose) polymerase. Nature, 2007, 434(7035):913-917. DOI:10.1038/nature03443.
[7] Downward J. Targeting RAS signalling pathways in cancer therapy. Nature Reviews Cancer, 2003, 3(1):11-22. DOI:10.1038/nrc969.
[8] Fong P C, Boss D S, Yap T A et al. Inhibition of poly(ADPribose) polymerase in tumors from BRCA mutation carriers. New England Journal of Medicine, 2009, 361(2):123-134. DOI:10.1056/NEJMoa0900212.
[9] Jackson S P, Bartek J. The DNA-damage response in human biology and disease. Nature, 2009, 461(7267):1071-1078. DOI:10.1038/nature08467.
[10] Lee J S, Das A, Auslander N et al. Harnessing synthetic lethality to predict the response to cancer treatment. Nature Communications, 2018, 9(1):Article No. 2546. DOI:10.1038/s41467-018-04647-1.
[11] Simons A, Dafni N, Dotan I. Establishment of a chemical synthetic lethality screen in cultured human cells. Genome Research, 2001, 11(2):266-273. DOI:10.1101/gr.154201.
[12] Barbie D A, Tamayo P, Boehm J S et al. Systematic RNA interference reveals that oncogenic KRAS-driven cancers require TBK1. Nature, 2009, 462(7269):108-112. DOI:10.1038/nature08460.
[13] Steckel M, Molina-Arcas M, Weigelt B et al. Determination of synthetic lethal interactions in KRAS oncogenedependent cancer cells reveals novel therapeutic targeting strategies. Cell Research, 2012, 22(8):1227-1245. DOI:10.1038/cr.2012.82.
[14] Han K, Jeng E E, Hess G T et al. Synergistic drug combinations for cancer identified in a CRISPR screen for pairwise genetic interactions. Nature Biotechnology, 2017, 35(5):463-474. DOI:10.1038/nbt.3834.
[15] Du D, Roguev A, Gordon D E et al. Genetic interaction mapping in mammalian cells using CRISPR interference. Nature Methods, 2017, 14(6):577-580. DOI:10.1038/nmeth.4286.
[16] Bleicher K H, Böhm H J, Müller K et al. Hit and lead generation:Beyond high-throughput screening. Nature Reviews Drug Discovery, 2003, 2(5):369-378. DOI:10.1038/nrd1086.
[17] Bajorath J. Integration of virtual and high-throughput screening. Nature Reviews Drug Discovery, 2002, 1(11):882-894. DOI:10.1038/nrd941.
[18] Guo J, Liu H, Zheng J. SynLethDB:Synthetic lethality database toward discovery of selective and sensitive anticancer drug targets. Nucleic Acids Res., 2016, 44(D1):D1011-D1017. DOI:10.1093/nar/gkv1108.
[19] Lu X, Kensche P R, Huynen M A et al. Genome evolution predicts genetic interactions in protein complexes and reveals cancer drug targets. Nature Communications, 2013, 4:Article No. 2124. DOI:10.1038/ncomms3124.
[20] Srivas R, Shen J P, Yang C C et al. A network of conserved synthetic lethal interactions for exploration of precision cancer therapy. Molecular Cell, 2016, 63(3):514-525. DOI:10.1016/j.molcel.2016.06.022.
[21] Kim J W, Botvinnik O B, Abudayyeh O et al. Characterizing genomic alterations in cancer by complementary functional associations. Nature Biotechnology, 2016, 34(5):539-546. DOI:10.1038/nbt.3527.
[22] Cho H, Berger B, Peng J. Compact integration of multinetwork topology for functional analysis of genes. Cell Systems, 2016, 3(6):540-548. DOI:10.1016/j.cels.2016.10.017.
[23] Jerby-Arnon L, Pfetzer N, Waldman Y et al. Predicting cancer-specific vulnerability via data-driven detection of synthetic lethality. Cell, 2014, 158(5):1199-1209. DOI:10.1016/j.cell.2014.07.027.
[24] Wan F, Li S, Tian T et al. EXP2SL:A machine learning framework for cell-line-specific synthetic lethality prediction. Frontiers in Pharmacology, 2020, 11:Article No. 112. DOI:10.3389/fphar.2020.00112.
[25] Liany H, Jeyasekharan A, Rajan V. Predicting synthetic lethal interactions using heterogeneous data sources. Bioinformatics, 2020, 36(7):2209-2216. DOI:10.1093/bioinformatics/btz893.
[26] Li P, Huang C, Fu Y et al. Large-scale exploration and analysis of drug combinations. Bioinformatics, 2015, 31(12):2007-2016. DOI:10.1093/bioinformatics/btv080.
[27] Menche J, Sharma A, Kitsak M et al. Uncovering diseasedisease relationships through the incomplete interactome. Science, 2015, 347(6224):Article No. 1257601. DOI:10.1126/science.1257601.
[28] Duan Q, Flynn C, Niepel M et al. LINCS Canvas Browser:Interactive web app to query, browse and interrogate LINCS L1000 gene expression signatures. Nucleic Acids Research, 2014, 42(W1):W449-W460. DOI:10.1093/nar/gku476.
[29] The UniProt Consortium. UniProt:A hub for protein information. Nucleic Acids Research, 2015, 43(D1):D204-D212. DOI:10.1093/nar/gku989.
[30] Davis A P, Grondin C J, Johnson R J et al. The comparative toxicogenomics database:Update 2019. Nucleic Acids Research, 2019, 47(D1):D948-D954. DOI:10.1093/nar/gky868.
[31] Subramanian A, Tamayo P, Mootha V K et al. Gene set enrichment analysis:A knowledge-based approach for interpreting genome-wide expression profiles. Proceedings of the National Academy of Sciences of the United States of America, 2005, 102(43):15545-15550. DOI:0.1073/pnas.0506580102.
[32] Iorio F, Tagliaferri R, Di Bernardo D. Identifying network of drug mode of action by gene expression profiling. Journal of Computational Biology, 2009, 16(2):241-251. DOI:10.1089/cmb.2008.10TT.
[33] Smith T F, Waterman M S. Identification of common molecular subsequences. Journal of Molecular Biology, 1981, 147(1):195-197. DOI:10.1016/0022-2836(81)90087-5.
[34] Perlman L, Gottlieb A, Atias N et al. Combining drug and gene similarity measures for drug-target elucidation. Journal of Computational Biology, 2011, 18(2):133-145. DOI:10.1089/cmb.2010.0213.
[35] Yu G, Li F, Qin Y et al. GOSemSim:An R package for measuring semantic similarity among GO terms and gene products. Bioinformatics, 2010, 26(7):976-978. DOI:10.1093/bioinformatics/btq064.
[36] Wang J Z, Du Z, Payattakool R et al. A new method to measure the semantic similarity of GO terms. Bioinformatics, 2007, 23(10):1274-1281. DOI:10.1093/bioinformatics/btm087.
[37] Wang B, Mezlini A, Demir F et al. Similarity network fusion for aggregating data types on a genomic scale. Nature Methods, 2014, 11(3):333-337. DOI:10.1038/nmeth.2810.
[38] Altman N S. An introduction to kernel and nearestneighbor nonparametric regression. The American Statistician, 1992, 46(3):175-185. DOI:10.1080/00031305.1992.10475879.
[39] He S, He H, Xu W. ICM:A web server for integrated clustering of multi-dimensional biomedical data. Nucleic Acids Research, 2016, 44(W1):W154-W159. DOI:10.1093/nar/gkw378.
[40] Hoadley K A, Yau C, Wolf D M et al. Multiplatform analysis of 12 cancer types reveals molecular classification within and across tissues of origin. Cell, 2014, 158(4):929-944. DOI:10.1016/j.cell.2014.06.049.
[41] Ma T, Zhang A. Affinity network fusion and semisupervised learning for cancer patient clustering. Methods, 2018, 145:16-24. DOI:10.1016/j.ymeth.2018.05.020.
[42] Tipping M E, Bishop C M. Probabilistic principal component analysis. Journal of the Royal Statistical Society, Series B, 1999, 21(3):611-622. DOI:10.1111/1467-9868.00196.
[43] Pedregosa F, Varoquaux G, Gramfort A et al. Scikit-learn:Machine learning in Python. Journal of Machine learning Research, 2011, 12:2825-2830.
[44] Moore A R, Rosenberg S C, McCormick F et al. RAStargeted therapies:Is the undruggable drugged? Nature Reviews Drug Discovery, 2020, 19(8):533-552. DOI:10.1038/s41573-020-0068-6.
[45] Wishart D S, Feunang Y D, Guo A C et al. DrugBank 5.0:A major update to the DrugBank database for 2018. Nucleic Acids Research, 2018, 46(D1):D1074-D1082. DOI:10.1093/nar/gkx1037.
[46] Costa-Cabral S, Brough R, Konde A et al. CDK1 is a synthetic lethal target for KRAS mutant tumours. PLoS ONE, 2016, 11(2):Article No. e0149099. DOI:10.1371/journal.pone.0149099.
[47] Grem J L, Voeller D M, Geoffroy F et al. Determinants of trimetrexate lethality in human colon cancer cells. British Journal of Cancer, 1994, 70(6):1075-1084. DOI:10.1038/bjc.1994.451.
[48] Raimondi M V, Randazzo O, La Franca M et al. DHFR inhibitors:Reading the past for discovering novel anticancer agents. Molecules, 2019, 24(6):Article No. 1140. DOI:10.3390/molecules24061140.
[49] Gesto D S, Cerqueira N M, Fernandes P A et al. Gemcitabine:A critical nucleoside for cancer therapy. Current Medicinal Chemistry, 2012, 19(7):1076-1087. DOI:10.2174/092986712799320682.
[50] Shimasaki T, Ishigaki Y, Nakamura Y et al. Glycogen synthase kinase 3β inhibition sensitizes pancreatic cancer cells to gemcitabine. Journal of Gastroenterology, 2012, 47(3):321-333. DOI:10.1007/s00535-011-0484-9.
[51] Kunnumakkara A B, Sung B, Ravindran J et al. Zyflamend suppresses growth and sensitizes human pancreatic tumors to gemcitabine in an orthotopic mouse model through modulation of multiple targets. International Journal of Cancer, 2012, 131(3):E292-E303. DOI:10.1002/ijc.26442.
[52] Xia G, Wang H, Song Z et al. Gambogic acid sensitizes gemcitabine efficacy in pancreatic cancer by reducing the expression of ribonucleotide reductase subunit-M2(RRM2). Journal of Experimental & Clinical Cancer Research, 2017, 36(1):Article No. 107. DOI:10.1186/s13046-017-0579-0.
[53] Yoshida K, Toden S, Ravindranathan P et al. Curcumin sensitizes pancreatic cancer cells to gemcitabine by attenuating PRC2 subunit EZH2, and the lncRNA PVT1 expression. Carcinogenesis, 2017, 38(10):1036-1046. DOI:10.1093/carcin/bgx065.
[54] Ashworth A, Lord C J, Reis-Filho J S. Genetic interactions in cancer progression and treatment. Cell., 2011, 145(1):30-38. DOI:10.1016/j.cell.2011.03.020.
[55] Brough R, Frankum J R, Costa-Cabral S et al. Searching for synthetic lethality in cancer. Current Opinion in Genetics and Development, 2011, 21(1):34-41. DOI:10.1016/j.gde.2010.10.009.
[1] 章海达, 邢郅豪, 陈璐, 高云君. 无索引数据集上的度量全k最近邻查询[J]. , 2016, 31(6): 1194-1211.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] 潘启敬;. A Routing Algorithm with Candidate Shortest Path[J]. , 1986, 1(3): 33 -52 .
[2] 徐洁; 李庆南; 黄世泽; 徐江峰;. DFTSNA:A Distributed Fault-Tolerant Shipboard System[J]. , 1990, 5(2): 109 -116 .
[3] 王鼎兴; 郑纬民; 杜晓黎; 郭毅可;. On the Execution Mechanisms of Parallel Graph Reduction[J]. , 1990, 5(4): 333 -346 .
[4] 廖先湜; 刘旭峰; 金兰;. The THUDSOS Distributed Operating System[J]. , 1991, 6(3): 301 -305 .
[5] 李永成; 张钹;. A Topological Implementation for Motion Planning of a Robotic Arm[J]. , 1993, 8(1): 1 -10 .
[6] 金芝; 胡守仁;. SCKE:Combining Logic- with Object-Oriented Paradigm[J]. , 1993, 8(1): 38 -48 .
[7] 吴信东;. Inductive Learning[J]. , 1993, 8(2): 22 -36 .
[8] 陈意云;. Nonterminating Rewritings with Head Boundedness[J]. , 1993, 8(2): 66 -75 .
[9] 姜文彬;. A Method for Minimization Design of Two-Level Logic Networks Using Multiplexer Universal Logic Modules[J]. , 1994, 9(1): 92 -96 .
[10] 武继刚; 朱洪;. The Least Basic Operations on Heap and Improved Heapsort[J]. , 1994, 9(3): 261 -266 .
版权所有 © 《计算机科学技术学报》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持：support@magtech.com.cn
总访问量：