基于个性化网络标志物的药物推荐方法研究

刘文斌; 吴倩; 杜玉改; 方刚; 石晓龙; 许鹏

doi:10.11999/JEIT190837

基于个性化网络标志物的药物推荐方法研究

doi: 10.11999/JEIT190837

刘文斌^{1, 2},
吴倩¹,
杜玉改¹,
方刚²,
石晓龙²,
许鹏^{2, 3, ,}

1.
温州大学计算机与人工智能学院温州 325035
2.
广州大学计算科技研究院广州 510006
3.
黔南民族师范学院计算机与信息学院都匀 558000

基金项目: 国家重点研发计划(2019YFA0706402)，国家自然科学基金(61572367, 61573017, 61972107, 61972109)

详细信息

作者简介:
刘文斌：男，1969年生，教授，研究方向为生物信息学

吴倩：女，1994年生，硕士，研究方向为生物信息学

杜玉改：女，1993年生，硕士，研究方向为生物信息学

方刚：男，1969年生，教授，研究方向为生物信息学

石晓龙：男，1975年生，教授，研究方向为生物信息学

许鹏：男，1986年生，博士后，研究方向为生物信息学

通讯作者:
许鹏　gdxupeng@gzhu.edu.cn

中图分类号: TP301
计量
- 文章访问数: 2465
- HTML全文浏览量: 922
- PDF下载量: 251
- 被引次数: 0
出版历程
- 收稿日期: 2019-10-29
- 修回日期: 2020-01-20
- 网络出版日期: 2020-02-27
- 刊出日期: 2020-06-22

Drug Recommendation Based on Individual Specific Biomarkers

Wenbin LIU^{1, 2},
Qian WU¹,
Yugai DU¹,
Gang FANG²,
Xiaolong SHI²,
Peng XU^{2, 3
, ,}

1.
College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325035, China
2.
Institute of Computing Science and Technology, Guangzhou University, Guangzhou 510006, China
3.
School of Computer Science of Information Technology, Qiannan Normal University for Nationalities, Duyun 558000, China

Funds: The National Key R&D Program of China (2019YFA0706402), The National Natural Science Foundation of China (61572367, 61573017, 61972107, 61972109)

摘要

摘要: 基于个性化标志物的药物推荐研究，有助于实现个性化用药及推动精准医疗的发展。该文利用基因表达谱数据及蛋白质网络信息，基于基因2维高斯分布方法筛选出个性化网络标志物。进而综合考虑靶基因的重要性和药物的副作用，提出了一种计算药物对个性化标志物影响权重的方法。将该方法应用于肺腺癌、肾透明细胞癌和子宫内膜癌数据集，通过启发式搜索方法，得到每个疾病样本重要药物推荐列表。结果表明，推荐的药物列表在同种癌症不同样本中既存在一致性，也表现出很大的差异性，如药物种类及药物排序差异，这说明个性化药物在疾病治疗中的重要性及必要性。通过从药物数据库中搜索药物组合对疾病治疗的影响作用表明，该文方法筛选得到的许多药物组合对具体疾病治疗具有积极影响，这进一步证明该文基于个性化网络标志物的药物推荐方法的准确性。该文的研究将有效促进精准化医疗的发展。
- 精准医疗 /
- 个性化标志物 /
- 网络标志物 /
- 药物推荐
Abstract: Drug recommendation research based on personalized markers can help to achieve personalized medicine and promote the development of precision medicine. In this paper, a method for calculating the weight of drugs on personalized markers is proposed, which first uses gene expression profile data and protein network information to filter out personalized network markers based on gene two-dimensional Gaussian distribution and then uses the importance degree of genes and the drugs side effect data to calculate the weight of drugs. This method is applied to lung adenocarcinoma, kidney renal clear cell carcinoma and uterine corpus endometrial carcinoma. Through the iterative process, a list of important drug recommendations for each disease sample is got. The results show that there are some differences in the recommended drug list and the ordering importance of drugs in different cases of the same kind of cancer, which indicates the importance and necessity of personalized drugs in the treatment of diseases. By querying the relationship between drugs from the drug database, many of the drug combinations screened by this method have a positive effect on the treatment of specific diseases, which further proves the accuracy of the drug recommendation methods based on personalized network markers. This study will effectively promote the development of precision medicine.
- Precision medicine /
- Personalized biomarkers /
- Network biomarkers /
- Drug recommendation

HTML全文

图 1 癌症个性化网络标志物获取流程

下载: 全尺寸图片幻灯片

图 2 3种癌症中药物靶基因数量与药物副作用数量之间的散点图

下载: 全尺寸图片幻灯片

图 3 3种癌症中考虑药物副作用和不考虑药物副作用时药物的排名

下载: 全尺寸图片幻灯片

图 4 3类癌症得到的候选药物集合在各个样本中的具体分布

下载: 全尺寸图片幻灯片

图 5 DrugBank数据库中具有协同作用的药物对在各个样本中的分布情况

下载: 全尺寸图片幻灯片

表 1 3种癌症数据集统计信息

癌症类型	样本数量(正常/癌症)
LUAD	609(95/514)
KIRC	602(72/530)
UCEC	578(35/543)

下载: 导出CSV

表 2 启发式搜索的迭代过程

个性化药物推荐算法
输入：物集合$D = \{ d_1,d_2, ··· ,{d_n}\} $;
个性化标志物集合$T = \{ t_1,t_2, ··· ,t_m\} $;
输出：个性化药物推荐列表 (Personalized Drug, PD);
(1) Initialization: Set $k = 1$;
(2) DO
(3) for $i = 1,2, ··· ,n$
(4) Compute $S\left( {{d_i}} \right)$;
(5) EndFor
(6) If S(d_i) is the maximum among all drugs in $D$ then
(7) ${\rm{PD}}\left( k \right) = {d_i}$;
(8) $k = k + 1$;
(9) EndIf
(10) Update $D$: Delete d_i from $D$;
(11) Update $T$: Delete all targets of ${d_i}$ from $T$;
(12) WHILE Max(targets number of each drug in $D$)>=6

下载: 导出CSV

参考文献(25)

SIEGEL R L, MILLER K D, and JEMAL A. Cancer statistics, 2016[J]. CA: A Cancer Journal for Clinicians, 2016, 66(1): 7–30. doi: 10.3322/caac.21332

TORRE L A, BRAY F, SIEGEL R L, et al. Global cancer statistics, 2012[J]. CA: A Cancer Journal for Clinicians, 2015, 65(2): 87–108. doi: 10.3322/caac.21262

WANG Hongwei, SUN Qiang, ZHAO Wenyuan, et al. Individual-level analysis of differential expression of genes and pathways for personalized medicine[J]. Bioinformatics, 2015, 31(1): 62–68. doi: 10.1093/bioinformatics/btu522

LIU Xiaoping, WANG Yuetong, JI Hongbin, et al. Personalized characterization of diseases using sample-specific networks[J]. Nucleic Acids Research, 2016, 44(22): e164. doi: 10.1093/nar/gkw772

ZHANG Wanwei, ZENG Tao, and CHEN Luonan. EdgeMarker: Identifying differentially correlated molecule pairs as edge-biomarkers[J]. Journal of Theoretical Biology, 2014, 362: 35–43. doi: 10.1016/j.jtbi.2014.05.041

YU Xiangtian, ZHANG Jingsong, SUN Shaoyan, et al. Individual-specific edge-network analysis for disease prediction[J]. Nucleic Acids Research, 2017, 45(20): e170. doi: 10.1093/nar/gkx787

PERLMAN L, GOTTLIEB A, ATIAS N, et al. Combining drug and gene similarity measures for drug-target elucidation[J]. Journal of Computational Biology, 2011, 18(2): 133–145. doi: 10.1089/cmb.2010.0213

WANG Wenhui, YANG Sen, and LI Jing. Drug Target Predictions Based on Heterogeneous Graph Inference[M]. ALTMAN R B, DUNKER A K, HUNTER L, et al. Biocomputing 2013. Hawaii, USA: World Scientific, 2013: 53-64 doi: 10.1142/9789814447973_0006.

ZONG Nansu, KIM H, NGO V, et al. Deep mining heterogeneous networks of biomedical linked data to predict novel drug-target associations[J]. Bioinformatics, 2017, 33(15): 2337–2344. doi: 10.1093/bioinformatics/btx160

SU Junjie, YOON B J, and DOUGHERTY E R. Accurate and reliable cancer classification based on probabilistic inference of pathway activity[J]. PLoS One, 2009, 4(12): e8161. doi: 10.1371/journal.pone.0008161

TOMCZAK K, CZERWIŃSKA P, and WIZNEROWICZ M. The Cancer Genome Atlas (TCGA): An immeasurable source of knowledge[J]. Contemporary Oncology (Poznan, Poland) , 2015, 19(1A): A68–A77. doi: 10.5114/wo.2014.47136

SZKLARCZYK D, MORRIS J H, COOK H, et al. The STRING database in 2017: Quality-controlled protein-protein association networks, made broadly accessible[J]. Nucleic Acids Research, 2017, 45(D1): D362–D368. doi: 10.1093/nar/gkw937

WISHART D S, FEUNANG Y D, GUO A C, et al. DrugBank 5.0: A major update to the DrugBank database for 2018[J]. Nucleic Acids Research, 2018, 46(D1): D1074–D1082. doi: 10.1093/nar/gkx1037

GRIFFITH M, GRIFFITH O L, COFFMAN A C, et al. DGIdb: Mining the druggable genome[J]. Nature Methods, 2013, 10(12): 1209–1210. doi: 10.1038/nmeth.2689

李玉博, 陈邈. 几乎完备高斯整数序列构造法[J]. 电子与信息学报, 2018, 40(7): 1752–1758. doi: 10.11999/JEIT170844

LI Yubo and CHEN Miao. Construction of nearly perfect gaussian integer sequences[J]. Journal of Electronics &Information Technology, 2018, 40(7): 1752–1758. doi: 10.11999/JEIT170844

陈曦, 张坤. 一种基于树增强朴素贝叶斯的分类器学习方法[J]. 电子与信息学报, 2019, 41(8): 2001–2008. doi: 10.11999/JEIT180886

CHEN Xi and ZHANG Kun. A classifier learning method based on tree-augmented naïve bayes[J]. Journal of Electronics &Information Technology, 2019, 41(8): 2001–2008. doi: 10.11999/JEIT180886

FANUCCHI M P, FOSSELLA F V, BELT R, et al. Randomized phase ii study of bortezomib alone and bortezomib in combination with docetaxel in previously treated advanced non-small-cell lung cancer[J]. Journal of Clinical Oncology, 2006, 24(31): 5025–5033. doi: 10.1200/JCO.2006.06.1853

DAVIES A M, RUEL C, LARA P N, et al. The proteasome inhibitor bortezomib in combination with gemcitabine and carboplatin in advanced non-small cell lung cancer: A california cancer consortium phase I study[J]. Journal of Thoracic Oncology, 2008, 3(1): 68–74. doi: 10.1097/JTO.0b013e31815e8b88

DAVIES A M, CHANSKY K, LARA Jr P N, et al. Bortezomib plus gemcitabine/carboplatin as first-line treatment of advanced non-small cell lung cancer: A phase II southwest oncology group study (S0339)[J]. Journal of Thoracic Oncology, 2009, 4(1): 87–92. doi: 10.1097/JTO.0b013e3181915052

KELLY K, CROWLEY J, BUNN PA, et al. Randomized phase III trial of paclitaxel plus carboplatin versus vinorelbine plus cisplatin in the treatment of patients with advanced non-small-cell lung cancer: A southwest oncology group trial[J]. Journal of Clinical Oncology, 2001, 19(13): 3210–3218. doi: 10.1200/JCO.2001.19.13.3210

SANDLER A, GRAY R, PERRY M C, et al. Paclitaxel-carboplatin alone or with bevacizumab for non-small-cell lung cancer[J]. New England Journal of Medicine, 2006, 355(24): 2542–2550. doi: 10.1056/NEJMoa061884

MCNAMARA M, SWEENEY C, ANTONARAKIS E S, et al. The evolving landscape of metastatic hormone-sensitive prostate cancer: A critical review of the evidence for adding docetaxel or abiraterone to androgen deprivation[J]. Prostate Cancer and Prostatic Diseases, 2018, 21(3): 306–318. doi: 10.1038/s41391-017-0014-9

ROBINET G, BARLESI F, FOURNEL P, et al. Second-line therapy with gefitinib in combination with docetaxel for advanced non-small cell lung cancer: A phase II randomized study[J]. Targeted Oncology, 2007, 2(2): 63–71. doi: 10.1007/s11523-007-0042-9

ANGELOPOULOU A, KOLOKITHAS-NTOUKAS A, FYTAS C, et al. Folic acid-functionalized, condensed magnetic nanoparticles for targeted delivery of doxorubicin to tumor cancer cells overexpressing the folate receptor[J]. ACS Omega, 2019, 4(26): 22214–22227. doi: 10.1021/acsomega.9b03594

TEDESCO-SILVA H, PASCUAL J, VIKLICKY O, et al. Safety of everolimus with reduced calcineurin inhibitor exposure in de novo kidney transplants: An analysis from the randomized TRANSFORM study[J]. Transplantation, 2019, 103(9): 1953–1963. doi: 10.1097/TP.0000000000002626

施引文献

资源附件(0)

访问统计