南-北方汉族人、韩国人和日本人遗传划分机器学习模型优化方案

doi:10.16288/j.yczz.22-073

遗传 ›› 2022, Vol. 44 ›› Issue (11): 1028-1043.doi: 10.16288/j.yczz.22-073

南-北方汉族人、韩国人和日本人遗传划分机器学习模型优化方案

孔永强¹(), 刘金凯¹, 顾佳琪², 徐景怡¹, 郑雨诺², 魏以梁²(), 伍少远^1,²()

1. 天津医科大学基础医学院生物化学与分子生物学系，天津市表观遗传学重点实验室，天津 300070
2. 江苏师范大学，江苏省系统发育与比较基因组学重点实验室，徐州 221116

收稿日期:2022-05-03 修回日期:2022-07-13 出版日期:2022-11-20 发布日期:2022-08-11
通讯作者: 魏以梁,伍少远 E-mail:kongyongqiang@tmu.edu.cn;weiyiliang.2013@tsinghua.org.cn;shaoyuan5@gmail.com
作者简介:孔永强，在读硕士研究生，专业方向：生物学。E-mail: kongyongqiang@tmu.edu.cn
基金资助:
法医遗传学公安部重点实验室开放课题(2020FGKFKT01);江苏省研究生科研与实践创新计划项目任务书(KYCX20_2286);江苏省研究生科研与实践创新计划项目任务书(KYCX21_2597)

Optimization scheme of machine learning model for genetic division between northern Han, southern Han, Korean and Japanese

Yongqiang Kong¹(), Jinkai Liu¹, Jiaqi Gu², Jingyi Xu¹, Yunuo Zheng², Yiliang Wei²(), Shaoyuan Wu^1,²()

1. Key Laboratory of Tianjin for Epigenetics, Department of Biochemistry and Molecular Biology, School of Basic Medical Sciences, Tianjin Medical University, Tianjin 300070, China
2. Key Laboratory of Phylogeny and Comparative Genomics of Jiangsu Province, Jiangsu Normal University, Xuzhou 221116, China

Received:2022-05-03 Revised:2022-07-13 Online:2022-11-20 Published:2022-08-11
Contact: Wei Yiliang,Wu Shaoyuan E-mail:kongyongqiang@tmu.edu.cn;weiyiliang.2013@tsinghua.org.cn;shaoyuan5@gmail.com
Supported by:
Supported by the Key Laboratory of Forensic Genetics of China No(2020FGKFKT01);the Graduate Research and Practice Innovation Program of Jiangsu Normal University Nos(KYCX20_2286);the Graduate Research and Practice Innovation Program of Jiangsu Normal University Nos(KYCX21_2597)

摘要/Abstract

摘要：

中国汉族人、韩国人和日本人作为东亚主体人群，其中中国汉族人呈现由北向南的梯度混合，在遗传结构上存在不同程度的差异。为实现对中国南-北方汉族人、韩国人和日本人的高分辨率遗传划分，本研究收集和分析了文献报道和实验室前期数据筛选出的1185个东亚人群祖先信息性SNPs (ancestry informative SNPs, AISNPs)，应用softmax与随机森林两种机器学习算法构建族群遗传划分模型，然后利用系统发育树、STRUCTURE和主成分分析方法进一步评估不同模型AISNPs位点组合的族群分类效果，最终筛选出234-AISNP的最优组合，softmax模型准确率为92%，实现了南方汉族人、北方汉族人、韩国人和日本人的高精度区分。本研究测试的两种机器学习算法模型为近距离人群的高分辨率划分提供了重要参考，可作为法医DNA族群推断体系位点开发的重要工具。

关键词: 法医遗传学, 祖先信息位点, 机器学习, 东亚人群, 南北方汉族

Abstract:

Han Chinese, Korean and Japanese are the main populations of East Asia, and Han Chinese presents a gradient admixture from north to south. There are differences among the East Asian populations in genetic structure. To achieve fine-scale genetic classification of southern (S-) and northern (N-) Han Chinese, Korean and Japanese individuals in this study, we collected and analyzed 1185 ancestry informative SNPs (AISNPs) from previous literature reports and our laboratory findings. First, two machine learning algorithms, softmax and randomForest, were used to build genetic classification models. Then, phylogenetic tree, STRUCTURE and principal component analysis were used to evaluate the performance of classification for different AISNP panels. The 234-AISNP panel achieved a fine-scale differentiation among the target populations in four classification schemes. The accuracy of the softmax model was 92%, which realized the accurate classification of the S-Han, N-Han, Korean and Japanese individuals. The two machine learning models tested in this study provided important references for the high-resolution discrimination of close-range populations and will be useful tools to optimize marker panels for developing forensic DNA ancestry inference systems.

Key words: forensic genetics, ancestry informative SNPs, machine learning, East Asia, S-Han and N-Han

孔永强, 刘金凯, 顾佳琪, 徐景怡, 郑雨诺, 魏以梁, 伍少远. 南-北方汉族人、韩国人和日本人遗传划分机器学习模型优化方案[J]. 遗传, 2022, 44(11): 1028-1043.

Yongqiang Kong, Jinkai Liu, Jiaqi Gu, Jingyi Xu, Yunuo Zheng, Yiliang Wei, Shaoyuan Wu. Optimization scheme of machine learning model for genetic division between northern Han, southern Han, Korean and Japanese[J]. Hereditas(Beijing), 2022, 44(11): 1028-1043.

图/表 9

表1

表2

表3

图1

表4

图2

图3

表5

234-AISNP组合的信息"

rs号	染色体	第37版序列位置	等位基因	F_st	I_n	rs号	染色体	第37版序列位置	等位基因	F_st	I_n
rs11119385	1	205317503	C/T	0.024	0.005	rs6478966	9	93716118	T/C	0.029	0.006
rs11161614	1	48334490	A/C	0.051	0.011	rs7022178	9	16806521	T/A/C	0.073	0.015
rs11164354	1	70295901	C/T	0.022	0.005	rs7032231	9	108878562	C/T	0.062	0.014
rs11805598	1	151830098	C/T	0.016	0.004	rs7038964	9	101776125	G/A	0.052	0.012
rs1371566	1	230137518	A/G	0.032	0.007	rs943327	9	101356091	C/G	0.015	0.003
rs1442502	1	165380623	G/A	0.032	0.007	rs998410	9	100556109	A/G/T	0.054	0.012
rs1564032	1	244136216	G/A	0.014	0.003	rs10900048	10	25401705	G/A	0.016	0.004
rs2430184	1	184795779	C/T	0.031	0.007	rs1341667	10	64415184	A/C/G	0.028	0.006
rs2488457	1	114377568	A/G	0.011	0.002	rs17121800	10	104320029	G/T	0.068	0.013
rs4414069	1	199244248	G/C/T	0.020	0.004	rs2295756	10	77504287	A/G	0.032	0.007
rs520605	1	166548317	G/A	0.013	0.003	rs4372441	10	127954919	G/A	0.053	0.012
rs6549596	1	31183486	C/T	0.022	0.005	rs4918000	10	21762267	A/G	0.044	0.010
rs723848	1	172862939	C/T	0.043	0.009	rs703989	10	44987921	T/A/C	0.017	0.004
rs929115	1	164459913	C/G/T	0.052	0.011	rs7909976	10	13914443	C/A/T	0.020	0.005
rs10929660	2	1985248	G/A	0.034	0.007	rs978605	10	94837743	C/T	0.031	0.008
rs12151767	2	193385209	A/G	0.055	0.012	rs10431079	11	101351383	G/A	0.053	0.011
rs12691557	2	124764392	C/T	0.013	0.003	rs10894034	11	116440011	T/C	0.010	0.002
rs13390103	2	142291181	T/A/C	0.019	0.004	rs11034709	11	19209050	T/C	0.079	0.015
rs1453054	2	171693639	C/G/T	0.020	0.004	rs11222851	11	129255618	C/T	0.024	0.005
rs16834705	2	187743228	T/G	0.034	0.008	rs11223550	11	131832284	G/T	0.046	0.010
rs16850913	2	137349278	G/A	0.069	0.016	rs11224765	11	99884272	A/G	0.063	0.013
rs2042020	2	5702577	C/T	0.031	0.007	rs12574415	11	68091265	C/T	0.024	0.005
rs2194757	2	10529961	A/C/G	0.011	0.003	rs1566734	11	18281916	C/T	0.019	0.004
rs4254643	2	231582797	T/C	0.024	0.007	rs174583	11	48145375	A/C	0.039	0.008
rs4611596	2	130255181	A/G	0.024	0.005	rs1794072	11	38428289	A/G	0.019	0.004
rs4675874	2	234858801	G/A	0.013	0.003	rs1835298	11	109322914	C/G	0.017	0.004
rs6436971	2	198274929	G/A	0.066	0.015	rs4491175	11	61303803	C/G/T	0.053	0.012
rs6717406	2	166421763	A/G	0.037	0.010	rs4578397	11	116440678	A/G	0.071	0.014
rs7569376	2	48955683	A/G	0.022	0.005	rs4938285	11	112057620	G/A	0.043	0.009
rs7630111	2	191344132	C/T	0.040	0.009	rs659366	11	69462910	G/A	0.016	0.004
rs11128125	3	61814273	G/T	0.040	0.008	rs7117447	11	101310590	C/T	0.082	0.017
rs1225051	3	49971514	C/A/G/T	0.012	0.003	rs713278	11	133532372	A/G	0.048	0.011
rs12488690	3	149344615	C/A	0.048	0.012	rs741245	11	133547942	T/A/G	0.023	0.005
rs1488485	3	1454063	C/T	0.027	0.006	rs770576	11	90956214	T/A/C	0.053	0.011
rs1613215	3	74954560	A/C/T	0.039	0.009	rs10858883	12	41753811	C/G/T	0.037	0.008
rs16862627	3	69389614	T/A/C/G	0.013	0.003	rs11104947	12	69906287	A/G/T	0.084	0.019
rs17008485	3	17194071	G/A	0.014	0.003	rs3217805	12	4227248	G/A	0.073	0.017
rs1709621	3	172389873	G/C	0.022	0.005	rs4533076	12	638166	C/T	0.045	0.010
rs17582830	3	114165901	C/A/T	0.018	0.004	rs9532080	12	88942980	G/A	0.052	0.012
rs4353835	3	11220006	C/A	0.070	0.013	rs9549212	12	128910954	A/C/T	0.038	0.009
rs4678169	3	94033744	G/C/T	0.030	0.007	rs10492574	13	90173515	A/C/G	0.055	0.012
rs6599390	3	181497374	G/A	0.025	0.005	rs11841589	13	46695350	T/C	0.087	0.016
rs9826148	3	100936248	C/A/G	0.039	0.009	rs11841652	13	43086351	A/G	0.011	0.002
rs9852677	3	32451697	C/A	0.028	0.006	rs11846710	13	73814891	G/T	0.052	0.011
rs9857773	3	138730737	C/T	0.042	0.009	rs12589835	13	108536028	C/T	0.031	0.007
rs9860483	3	130021945	G/A	0.081	0.016	rs1322944	13	41022093	C/T	0.048	0.011
rs9869826	3	45900369	G/A/T	0.015	0.003	rs1333099	13	53683163	A/G	0.053	0.011
rs1026975	4	99304600	A/G	0.025	0.006	rs1751034	13	47411985	A/G	0.019	0.004
rs11466640	4	38138661	C/T	0.026	0.006	rs452748	13	99683635	T/C	0.019	0.005
rs1522221	4	71229896	G/A/T	0.026	0.006	rs4941430	13	27534715	G/A	0.026	0.005
rs16997770	4	113971374	T/G	0.058	0.013	rs9513535	13	94969796	T/C	0.052	0.011
rs17016175	4	143373910	A/G/T	0.022	0.005	rs10132336	14	71262932	T/C	0.038	0.009
rs17239258	4	178295766	G/A/T	0.027	0.007	rs10134903	14	88682616	G/A	0.023	0.005
rs17579988	4	19044103	G/A	0.018	0.004	rs10139575	14	50481926	T/C	0.020	0.004
rs17583068	4	24728480	G/A	0.028	0.006	rs10483991	14	80242132	T/C/G	0.050	0.011
rs2035023	4	124693346	T/C	0.052	0.010	rs11159882	14	88006776	T/G	0.029	0.007
rs2622637	4	100335874	C/A	0.076	0.017	rs11625485	14	74869017	A/G/T	0.054	0.011
rs279845	4	46305733	T/C	0.013	0.003	rs1256520	14	57087118	A/C/G	0.049	0.011
rs2972336	4	143391299	A/G	0.032	0.007	rs12588061	14	40942142	C/G	0.042	0.010
rs3775539	4	84577025	T/C	0.039	0.009	rs174520	14	65737193	C/A	0.053	0.012
rs4865142	4	53278689	G/A	0.043	0.010	rs17823795	14	58343352	G/A	0.033	0.008
rs639617	4	178655568	C/T	0.030	0.006	rs4902391	14	65811537	T/C	0.045	0.010
rs7666030	4	956047	A/G	0.015	0.003	rs8005568	14	101151012	C/G/T	0.040	0.009
rs7676014	4	4346373	C/T	0.046	0.009	rs8015594	14	40865770	G/A	0.054	0.011
rs10058739	5	127677188	T/C	0.014	0.003	rs10459664	15	27940339	A/G	0.052	0.011
rs10806975	5	167397540	C/T	0.011	0.002	rs17822931	15	84586464	T/C	0.037	0.009
rs11745587	5	88188058	A/C/G	0.021	0.005	rs2313427	15	70123826	T/G	0.028	0.006
rs11959012	5	165711426	G/A	0.035	0.008	rs4486887	15	35064934	C/T	0.033	0.007
rs12654905	5	11984496	T/A/G	0.024	0.005	rs11639903	16	9222411	A/G	0.011	0.002
rs13160399	5	144030993	C/A/T	0.040	0.009	rs1420288	16	50677571	C/T	0.041	0.009
rs1422931	5	144074365	G/A	0.019	0.004	rs160539	16	63282080	A/G/T	0.036	0.008
rs1428150	5	89518433	A/C	0.040	0.008	rs2297514	16	89972345	T/C	0.026	0.006
rs1468722	5	143038150	G/A/C/T	0.013	0.003	rs2353686	16	63353953	C/G	0.032	0.008
rs17076328	5	169750158	G/T	0.013	0.003	rs4280278	16	29288634	T/C	0.047	0.010
rs17207681	5	132490807	A/G	0.051	0.012	rs6502840	16	82273372	G/A	0.042	0.009
rs17451739	5	142018424	T/G	0.056	0.013	rs8049660	16	86354605	T/C	0.043	0.009
rs17599827	5	65596821	T/C	0.059	0.014	rs8060207	16	54477881	T/C	0.039	0.009
rs17631488	5	18680420	A/T	0.072	0.014	rs16944149	17	8135061	T/C	0.025	0.006
rs2589787	5	11202649	C/A/T	0.035	0.008	rs16966855	17	26093315	T/C/G	0.010	0.002
rs304141	5	79020426	A/G	0.076	0.016	rs2068746	17	1243941	C/T	0.021	0.005
rs315808	5	167668843	C/T	0.066	0.013	rs2642066	17	58184540	T/C	0.067	0.014
rs4912933	5	132561277	G/A/C/T	0.028	0.006	rs9303660	17	28526475	T/C	0.021	0.005
rs6898653	5	110585627	C/T	0.045	0.009	rs9941426	17	75668619	C/A/G/T	0.044	0.010
rs11042911	6	33024654	A/C	0.036	0.007	rs11086012	18	76478188	A/G	0.015	0.003
rs1178148	6	138406328	C/A/T	0.039	0.009	rs1561201	18	1948608	A/C/G/T	0.014	0.003
rs12660882	6	108906200	C/T	0.015	0.003	rs17072984	18	57332158	T/G	0.048	0.011
rs1539348	6	63640369	C/T	0.011	0.002	rs1708698	18	28158452	C/A	0.014	0.003
rs210798	6	134423175	A/T	0.013	0.003	rs2278339	18	10029988	G/A/T	0.031	0.009
rs480631	6	130102959	C/T	0.024	0.005	rs2377962	18	455128	A/G	0.076	0.017
rs6924957	6	79659170	A/G	0.039	0.009	rs475235	18	9101722	G/T	0.042	0.009
rs761798	6	33047031	T/C	0.015	0.003	rs6117562	18	46454048	A/G/T	0.032	0.007
rs7740161	6	120775626	G/A	0.016	0.004	rs9964230	18	852562	G/A	0.022	0.005
rs258728	7	8859616	C/T	0.023	0.005	rs7268940	19	39206288	C/T	0.037	0.008
rs321967	7	66699784	T/C	0.017	0.004	rs8107011	19	10666112	G/A/T	0.030	0.007
rs3757419	7	55238464	T/A/G	0.032	0.007	rs16986850	20	39263421	C/A	0.033	0.008
rs3757425	7	125115418	A/G	0.034	0.007	rs16991180	20	2090118	C/A/T	0.055	0.012
rs3923736	7	81663275	C/A	0.050	0.011	rs17377643	20	23727145	C/T	0.052	0.011
rs4718412	7	66029429	C/T	0.060	0.013	rs2837352	20	12905188	T/A/C	0.023	0.005
rs6465469	7	81697666	A/C	0.011	0.002	rs6030932	20	41048928	T/C	0.051	0.011
rs7006443	7	155060730	A/C/G/T	0.041	0.012	rs6123723	20	12921966	T/C	0.047	0.012
rs7794745	7	141673345	C/G	0.012	0.003	rs760873	20	42146320	T/G	0.054	0.012
rs7802058	7	78314549	G/A/C	0.014	0.003	rs1524930	21	37999799	C/T	0.033	0.007
rs10504726	8	72774349	G/A	0.020	0.004	rs2330015	21	40287238	A/C/T	0.043	0.010
rs10957985	8	80568935	T/A/C	0.041	0.009	rs2836749	21	22447717	A/G	0.030	0.007
rs12676684	8	88289450	G/T	0.053	0.012	rs6000401	21	45246422	A/G	0.037	0.008
rs1517114	8	18258316	G/A/T	0.013	0.003	rs928844	21	23231832	C/T	0.055	0.012
rs1537523	8	119479124	G/C/T	0.026	0.007	rs12483769	22	47271217	T/C/G	0.047	0.009
rs2945733	8	10097398	G/A	0.044	0.010	rs131864	22	41537589	A/G	0.037	0.008
rs2976396	8	134615750	T/G	0.116	0.026	rs17002737	22	42280618	T/C	0.053	0.012
rs4922234	8	9712822	C/G/T	0.013	0.003	rs17129041	22	24825511	C/A/T	0.022	0.005
rs10521076	9	104423907	C/T	0.054	0.012	rs198464	22	49595560	C/T	0.028	0.006
rs10991718	9	89140339	G/A	0.025	0.006	rs2269658	22	42241372	G/A/T	0.038	0.008
rs12006467	9	29780195	G/A	0.071	0.014	rs229562	22	22536956	C/T	0.056	0.012
rs12351269	9	3430684	T/C	0.037	0.008	rs4820428	22	37149336	C/T	0.029	0.008
rs1875174	9	136079463	C/T	0.025	0.005	rs5770018	22	48282309	G/A/C	0.014	0.003
rs1981500	9	117032448	T/C	0.028	0.007	rs6007756	22	37599065	G/T	0.030	0.007
rs2636864	9	92800165	G/C	0.038	0.008	rs860236	22	42605548	C/T	0.016	0.006

表5

图4

参考文献 65

[1]	Phillips C. Forensic genetic analysis of bio-geographical ancestry. Forensic Sci Int Genet, 2015, 18: 49-65. doi: 10.1016/j.fsigen.2015.05.012
[2]	Tishkoff SA, Kidd KK. Implications of biogeography of human populations for 'race' and medicine. Nat Genet, 2004, 36(< W>11 Suppl): S21-S27. doi: 10.1038/ng1438
[3]	Marchini J, Cardon LR, Phillips MS, Donnelly P. The effects of human population structure on large genetic association studies. Nat Genet, 2004, 36(5): 512-517. pmid: 15052271
[4]	Paschou P, Lewis J, Javed A, Drineas P. Ancestry informative markers for fine-scale individual assignment to worldwide populations. J Med Genet, 2010, 47(12): 835-847. doi: 10.1136/jmg.2010.078212
[5]	Phillips C, Salas A, Sánchez JJ, Fondevila M, Gómez-Tato A, Alvarez-Dios J, Calaza M, de Cal MC, Ballard D, Lareu MV, Carracedo A. Inferring ancestral origin using a single multiplex assay of ancestry-informative marker SNPs. Forensic Sci Int Genet, 2007, 1(3-4): 273-280. doi: 10.1016/j.fsigen.2007.06.008
[6]	Kidd KK, Speed WC, Pakstis AJ, Furtado MR, Fang RX, Madbouly A, Maiers M, Middha M, Friedlaender FR, Kidd JR. Progress toward an efficient panel of SNPs for ancestry inference. Forensic Sci Int Genet, 2014, 10: 23-32. doi: 10.1016/j.fsigen.2014.01.002
[7]	Jiang L, Sun QF, Ma Q, Zhao WT, Liu J, Zhao L, Ji AQ, Li CX. Optimization and validation of analysis method based on 27-plex SNP panel for ancestry inference. Hereditas (Beijing), 2017, 39(2): 166-173.
	江丽, 孙启凡, 马泉, 赵雯婷, 刘京, 赵蕾, 季安全, 李彩霞. 27-plex SNP 种族推断方法的优化及验证. 遗传, 2017, 39(2): 166-173.
[8]	Qin PF, Li ZQ, Jin WF, Lu DS, Lou HY, Shen JW, Jin L, Shi YY, Xu SH. A panel of ancestry informative markers to estimate and correct potential effects of population stratification in Han Chinese. Eur J Hum Genet, 2014, 22(2): 248-253. doi: 10.1038/ejhg.2013.111 pmid: 23714748
[9]	Wang YC, Lu DS, Chung YJ, Xu SH. Genetic structure, divergence and admixture of Han Chinese, Japanese and Korean populations. Hereditas, 2018, 155: 19. doi: 10.1186/s41065-018-0057-5 pmid: 29636655
[10]	Shi CM, Liu Q, Zhao SL, Chen H. Ancestry informative SNP panels for discriminating the major East Asian populations: Han Chinese, Japanese and Korean. Ann Hum Genet, 2019, 83(5): 348-354. doi: 10.1111/ahg.12320
[11]	Wang CC, Yeh HY, Popov AN, Zhang HQ, Matsumura H, Sirak K, Cheronet O, Kovalev A, Rohland N, Kim AM, Mallick S, Bernardos R, Tumen D, Zhao J, Liu YC, Liu JY, Mah M, Wang K, Zhang Z, Adamski N, Broomandkhoshbacht N, Callan K, Candilio F, Carlson KSD, Culleton BJ, Eccles L, Freilich S, Keating D, Lawson AM, Mandl K, Michel M, Oppenheimer J, Özdoğan KT, Stewardson K, Wen SQ, Yan S, Zalzala F, Chuang R, Huang CJ, Looh H, Shiung CC, Nikitin YG, Tabarev AV, Tishkin AA, Lin S, Sun ZY, Wu XM, Yang TL, Hu X, Chen L, Du H, Bayarsaikhan J, Mijiddorj E, Erdenebaatar D, Iderkhangai TO, Myagmar E, Kanzawa-Kiriyama H, Nishino M, Shinoda KI, Shubina OA, Guo J, Cai WW, Deng QY, Kang LL, Li D, Li DW, Lin RM, Nini, Shrestha R, Wang LX, Wei LW, Xie GM, Yao HB, Zhang MF, He GL, Yang XM, Hu R, Robbeets M, Schiffels S, Kennett DJ, Jin L, Li H, Krause J, Pinhasi R, Reich D. Genomic insights into the formation of human populations in East Asia. Nature, 2021, 591(7850): 413-419. doi: 10.1038/s41586-021-03336-2
[12]	Jung JY, Kang PW, Kim E, Chacon D, Beck D, McNevin D. Ancestry informative markers (AIMs) for Korean and other East Asian and South East Asian populations. Int J Legal Med, 2019, 133(6): 1711-1719. doi: 10.1007/s00414-019-02129-7 pmid: 31388795
[13]	Okada Y, Momozawa Y, Sakaue S, Kanai M, Ishigaki K, Akiyama M, Kishikawa T, Arai Y, Sasaki T, Kosaki K, Suematsu M, Matsuda K, Yamamoto K, Kubo M, Hirose N, Kamatani Y. Deep whole-genome sequencing reveals recent selection signatures linked to evolution and disease risk of Japanese. Nat Commun, 2018, 9(1): 1631. doi: 10.1038/s41467-018-03274-0 pmid: 29691385
[14]	Akiyama M, Okada Y, Kanai M, Takahashi A, Momozawa Y, Ikeda M, Iwata N, Ikegawa S, Hirata M, Matsuda K, Iwasaki M, Yamaji T, Sawada N, Hachiya T, Tanno K, Shimizu A, Hozawa A, Minegishi N, Tsugane S, Yamamoto M, Kubo M, Kamatani Y. Genome-wide association study identifies 112 new loci for body mass index in the Japanese population. Nat Genet, 2017, 49(10): 1458-1467. doi: 10.1038/ng.3951 pmid: 28892062
[15]	Liu SY, Huang SJ, Chen F, Zhao LJ, Yuan YY, Francis SS, Fang L, Li ZL, Lin L, Liu R, Zhang Y, Xu HX, Li SK, Zhou YW, Davies RW, Liu Q, Walters RG, Lin K, Ju J, Korneliussen T, Yang MA, Fu QM, Wang J, Zhou LJ, Krogh A, Zhang HY, Wang W, Chen ZM, Cai ZM, Yin Y, Yang HM, Mao M, Shendure J, Wang J, Albrechtsen A, Jin X, Nielsen R, Xu X. Genomic analyses from non-invasive prenatal testing reveal genetic associations, patterns of viral infections, and Chinese population history. Cell, 2018, 175(2): 347-359. doi: S0092-8674(18)31032-8 pmid: 30290141
[16]	Xu SH, Yin XY, Li SL, Jin WF, Lou HY, Yang L, Gong XH, Wang HY, Shen YP, Pan XD, He YG, Yang YJ, Wang Y, Fu WQ, An Y, Wang JC, Tan JZ, Qian J, Chen XL, Zhang X, Sun YF, Zhang XJ, Wu BL, Jin L. Genomic dissection of population substructure of Han Chinese and its implication in association studies. Am J Hum Genet, 2009, 85(6): 762-774. doi: 10.1016/j.ajhg.2009.10.015
[17]	Jeon S, Bhak Y, Choi Y, Jeon Y, Kim S, Jang J, Jang J, Blazyte A, Kim C, Kim Y, Shim J, Kim N, Kim YJ, Park SG, Kim J, Cho YS, Park Y, Kim HM, Kim BC, Park NH, Shin ES, Kim BC, Bolser D, Manica A, Edwards JS, Church G, Lee S, Bhak J. Korean genome project: 1094 Korean personal genomes with clinical information. Sci Adv, 2020, 6(22): eaaz7835. doi: 10.1126/sciadv.aaz7835
[18]	Cao YN, Li L, Xu M, Feng ZM, Sun XH, Lu JL, Xu Y, Du PN, Wang TG, Hu RY, Ye Z, Shi LX, Tang XL, Yan L, Gao ZN, Chen G, Zhang YF, Chen LL, Ning G, Bi YF, Wang WQ, Consortium C. The ChinaMAP analytics of deep whole genome sequences in 10,588 individuals. Cell Res, 2020, 30(9): 717-731. doi: 10.1038/s41422-020-0322-9 pmid: 32355288
[19]	Jinam TA, Kanzawa-Kiriyama H, Inoue I, Tokunaga K, Omoto K, Saitou N. Unique characteristics of the Ainu population in Northern Japan. J Hum Genet, 2015, 60(10): 565-571. doi: 10.1038/jhg.2015.79 pmid: 26178428
[20]	Kim JJ, Verdu P, Pakstis AJ, Speed WC, Kidd JR, Kidd KK. Use of autosomal loci for clustering individuals and populations of East Asian origin. Hum Genet, 2005, 117(6): 511-519. doi: 10.1007/s00439-005-1334-8
[21]	Clarke L, Fairley S, Zheng-Bradley X, Streeter I, Perry E, Lowy E, Tassé A-M, and Flicek P. The international genome sample resource (IGSR): a worldwide collection of genome variation incorporating the 1000 genomes project data. Nucleic Acids Res, 2016, 45(1): 854-859.
[22]	Zhang WQ, Meehan J, Su ZQ, Ng HW, Shu M, Luo H, Ge WG, Perkins R, Tong WD, Hong HX. Whole genome sequencing of 35 individuals provides insights into the genetic architecture of Korean population. BMC Bioinformatics, 2014, 15(11): 6-18. doi: 10.1186/1471-2105-15-6
[23]	Byrska-Bishop M, Evani US, Zhao XF, Basile AO, Abel HJ, Regier AA, Corvelo A, Clarke WE, Musunuri R, Nagulapalli K, Fairley S, Runnels A, Winterkorn L, Lowy E, Flicek P, Germer S, Brand H, Hall IM, Talkowski ME, Narzisi G, Zody MC, The Human Genome Structural Variation Consortium. High coverage whole genome sequencing of the expanded 1000 Genomes Project cohort including 602 trios. bioRxiv, 2021, doi: 10.1101/2021.02.06.430068. doi: 10.1101/2021.02.06.430068
[24]	Bergström A, McCarthy SA, Hui RY, Almarri MA, Ayub Q, Danecek P, Chen Y, Felkel S, Hallast P, Kamm J, Blanché H, Deleuze JF, Cann H, Mallick S, Reich D, Sandhu MS, Skoglund P, Scally A, Xue YL, Durbin R, Tyler-Smith C. Insights into human genetic variation and population history from 929 diverse genomes. Science, 2020, 367(6484): eaay5012. doi: 10.1126/science.aay5012
[25]	Mallick S, Li H, Lipson M, Mathieson I, Gymrek M, Racimo F, Zhao MY, Chennagiri N, Nordenfelt S, Tandon A, Skoglund P, Lazaridis I, Sankararaman S, Fu QM, Rohland N, Renaud G, Erlich Y, Willems T, Gallo C, Spence JP, Song YS, Poletti G, Balloux F, van Driem G, de Knijff P, Romero IG, Jha AR, Behar DM, Bravi CM, Capelli C, Hervig T, Moreno-Estrada A, Posukh OL, Balanovska E, Balanovsky O, Karachanak-Yankova S, Sahakyan H, Toncheva D, Yepiskoposyan L, Tyler-Smith C, Xue YL, Abdullah MS, Ruiz-Linares A, Beall CM, Di Rienzo A, Jeong C, Starikovskaya EB, Metspalu E, Parik J, Villems R, Henn BM, Hodoglugil U, Mahley R, Sajantila A, Stamatoyannopoulos G, Wee JTS, Khusainova R, Khusnutdinova E, Litvinov S, Ayodo G, Comas D, Hammer MF, Kivisild T, Klitz W, Winkler CA, Labuda D, Bamshad M, Jorde LB, Tishkoff SA, Watkins WS, Metspalu M, Dryomov S, Sukernik R, Singh L, Thangaraj K, Pääbo S, Kelso J, Patterson N, Reich D. The Simons genome diversity project: 300 genomes from 142 diverse populations. Nature, 2016, 538(7624): 201-206.
[26]	Liu XY, Lu DS, Saw WY, Shaw PJ, Wangkumhang P, Ngamphiw C, Fucharoen S, Lert-Itthiporn W, Chin- Inmanu K, Chau TNB, Anders K, Kasturiratne A, de Silva HJ, Katsuya T, Kimura R, Nabika T, Ohkubo T, Tabara Y, Takeuchi F, Yamamoto K, Yokota M, Mamatyusupu D, Yang WJ, Chung YJ, Jin L, Hoh BP, Wickremasinghe AR, Ong RH, Khor CC, Dunstan SJ, Simmons C, Tongsima S, Suriyaphol P, Kato N, Xu SH, Teo YY. Characterising private and shared signatures of positive selection in 37 Asian populations. Eur J Hum Genet, 2017, 25(4): 499-508. doi: 10.1038/ejhg.2016.181 pmid: 28098149
[27]	Wen H, Wei YL, Guo XY, Sun CC, Xue SY, Liu J, Fan H, Jiang L. High-resolution SNP ancestry inference model and efficiency evaluation in three East Asian populations. Prog Biochem Biophys, 2021, 48(8): 973-981.
	文豪, 魏以梁, 郭晓媛, 孙昌春, 薛思瑶, 刘京, 范虹, 江丽. 东亚三族群SNP高分辨推断模型构建与效能评估. 生物化学与生物物理进展, 2021, 48(8): 973-981.
[28]	Guo XY, Sun CC, Xue SY, Zhao H, Jiang L, Li CX. 49AISNP: a study on the ancestry inference of the three ethnic groups in the north of East Asia. Hereditas (Beijing), 2021, 43(9): 880-889.
	郭晓媛, 孙昌春, 薛思瑶, 赵慧, 江丽, 李彩霞. 49AISNP:东亚北方三个族群遗传来源推断. 遗传, 2021, 43(9): 880-889.
[29]	Kim T, Seo HD, Hennighausen L, Lee D, Kang K. Octopus-toolkit: a workflow to automate mining of public epigenomic and transcriptomic next-generation sequencing data. Nucleic Acids Res, 2018, 46(9): 53-58. doi: 10.1093/nar/gky083 pmid: 29420797
[30]	1000 Genomes Project Consortium, Auton A, Brooks LD, Durbin RM, Garrison EP, Kang HM, Korbel JO, Marchini JL, McCarthy S, McVean GA, Abecasis GR. A global reference for human genetic variation. Nature, 2015, 526(7571): 68-74.
[31]	Sudmant PH, Rausch T, Gardner EJ, Handsaker RE, Abyzov A, Huddleston J, Zhang Y, Ye K, Jun G, Fritz MHY, Konkel MK, Malhotra A, Stütz AM, Shi XH, Casale FP, Chen JM, Hormozdiari F, Dayama G, Chen K, Malig M, Chaisson MJP, Walter K, Meiers S, Kashin S, Garrison E, Auton A, Lam HYK, Mu XJ, Alkan C, Antaki D, Bae T, Cerveira E, Chines P, Chong ZC, Clarke L, Dal E, Ding L, Emery S, Fan X, Gujral M, Kahveci F, Kidd JM, Kong Y, Lameijer EW, McCarthy S, Flicek P, Gibbs RA, Marth G, Mason CE, Menelaou A, Muzny DM, Nelson BJ, Noor A, Parrish NF, Pendleton M, Quitadamo A, Raeder B, Schadt EE, Romanovitch M, Schlattl A, Sebra R, Shabalin AA, Untergasser A, Walker JA, Wang M, Yu FL, Zhang C, Zhang J, Zheng-Bradley XQ, Zhou WD, Zichner T, Sebat J, Batzer MA, McCarroll SA, 1000 Genomes Project Consortium, Mills RE, Gerstein MB, Bashir A, Stegle O, Devine SE, Lee C, Eichler EE, Korbel JO. An integrated map of structural variation in 2,504 human genomes. Nature, 2015, 526(7571): 75-81. doi: 10.1038/nature15394
[32]	Korn JM, Kuruvilla FG, McCarroll SA, Wysoker A, Nemesh J, Cawley S, Hubbell E, Veitch J, Collins PJ, Darvishi K, Lee C, Nizzari MM, Gabriel SB, Purcell S, Daly MJ, Altshuler D. Integrated genotype calling and association analysis of SNPs, common copy number polymorphisms and rare CNVs. Nat Genet, 2008, 40(10): 1253-1260. doi: 10.1038/ng.237 pmid: 18776909
[33]	Van der Auwera GA, O'Connor BD. Genomics in the Cloud: Using Docker, GATK, and WDL in Terra. 2020: O'Reilly Media, Incorporated.
[34]	Meire M, Ballings M, Van den Poel D. imputeMissings: impute missing values in a predictive context. 2016.
[35]	Rustowicz R. Crop classification with multi-temporal satellite imagery. 2017.
[36]	Breiman L, Cutler A, Liaw A, Wiener M. Package ‘randomForest’. 2018.
[37]	Yu GC, Smith DK, Zhu HC, Guan Y, Lam TTY. ggtree: an R package for visualization and annotation of phylogenetic trees with their covariates and other associated data. Methods Ecol Evol, 2017, 8(1): 28-36. doi: 10.1111/2041-210X.12628
[38]	Hao W, Storey JD. Extending tests of Hardy-Weinberg equilibrium to structured populations. Genetics, 2019, 213(3): 759-770. doi: 10.1534/genetics.119.302370
[39]	Pritchard JK, Przeworski M. Linkage disequilibrium in humans: models and data. Am J Hum Genet, 2001, 69(1): 1-14. doi: 10.1086/321275
[40]	Barrett JC, Fry B, Maller J, Daly MJ. Haploview: analysis and visualization of LD and haplotype maps. Bioinformatics, 2005, 21(2): 263-265. pmid: 15297300
[41]	Armstrong RA. When to use the Bonferroni correction. Ophthalmic Physiol Opt, 2014, 34(5): 502-508. doi: 10.1111/opo.12131
[42]	Boca SM, Rosenberg NA. Mathematical properties of Fst between admixed populations and their parental source populations. Theor Popul Biol, 2011, 80(3): 208-216. doi: 10.1016/j.tpb.2011.05.003 pmid: 21640742
[43]	Rosenberg NA, Li LM, Ward R, Pritchard JK. Informativeness of genetic markers for inference of ancestry. Am J Hum Genet, 2003, 73(6): 1402-1422. doi: 10.1086/380416
[44]	Hui SB, Wang WJ. Improvement of multi-variable's redundant attributes in classification algorithm of support vector machines. Computer Engineering and Design, 2006, 27(8): 1385-138.
	惠守博, 王文杰. 支持向量机分类算法中多元变量共线性问题的改进. 计算机工程与设计, 2006, 27(8): 1385- 1388.
[45]	Zhao YD, Liu R, Liu YL, Xiao F, Zhang Y. Multivariate logistic regression collinearity diagnosis analysis. Chinese Journal of Health Statistics, 2000, (5): 3-5.
	赵宇东, 刘嵘, 刘延龄, 肖峰, 张扬. 多元logistic回归的共线性分析. 中国卫生统计, 2000, (5): 3-5.
[46]	Wang L, Tong X, Sheng MW, Qin HD, Tang QS. Review of image classification based on softmax classifier in deep learning. Navigation and Control, 2019, 18(6): 1-9+47.
	万磊, 佟鑫, 盛明伟, 秦洪德, 唐松奇. Softmax分类器深度学习图像分类方法应用综述. 导航与控制, 2019, 18(6): 1-9+47.
[47]	Rigatti SJ. Random Forest. J Insur Med, 2017, 47(1): 31-39. doi: 10.17849/insm-47-01-31-39.1 pmid: 28836909
[48]	Heo J, Yoon JG, Park H, Kim YD, Nam HS, Heo JH. Machine learning-based model for prediction of outcomes in acute stroke. Stroke, 2019, 50(5): 1263-1265. doi: 10.1161/STROKEAHA.118.024293 pmid: 30890116
[49]	Che DS, Liu Q, Rasheed K, Tao XP. Decision tree and ensemble learning algorithms with their applications in bioinformatics. Adv Exp Med Biol, 2011, 696: 191-199. doi: 10.1007/978-1-4419-7046-6_19 pmid: 21431559
[50]	Connor CW. Artificial intelligence and machine learning in anesthesiology. Anesthesiology, 2019, 131(6): 1346-1359. doi: 10.1097/ALN.0000000000002694 pmid: 30973516
[51]	Pandis N. Linear regression. Am J Orthod Dentofacial Orthop, 2016, 149(3): 431-434. doi: 10.1016/j.ajodo.2015.11.019
[52]	LaValley MP. Logistic regression. Circulation, 2008, 117(18): 2395-2399. doi: 10.1161/CIRCULATIONAHA.106.682658 pmid: 18458181
[53]	Huang SJ, Cai NG, Pacheco PP, Narrandes S, Wang Y, Xu W. Applications of support vector machine (SVM) learning in cancer genomics. Cancer Genomics Proteomics, 2018, 15(1): 41-51.
[54]	Karalis G. Decision trees and applications. Adv Exp Med Biol, 2020, 1194: 239-242. doi: 10.1007/978-3-030-32622-7_21 pmid: 32468539
[55]	Hatwell J, Gaber MM, Atif Azad RM. Ada-WHIPS: explaining AdaBoost classification with applications in the health sciences. BMC Med Inform Decis Mak, 2020, 20(1): 250. doi: 10.1186/s12911-020-01201-2
[56]	Wen J, Xu Y, Li ZY, Ma ZL, Xu YR. Inter-class sparsity based discriminative least square regression. Neural Netw, 2018, 102: 36-47. doi: 10.1016/j.neunet.2018.02.002
[57]	Kloumann IM, Ugander J, Kleinberg J. Block models and personalized PageRank. Proc Natl Acad Sci USA, 2017, 114(1): 33-38. doi: 10.1073/pnas.1611275114
[58]	Jung Y, Hu JH. A k-fold averaging cross-validation procedure. J Nonparametr Stat, 2015, 27(2): 167-179. doi: 10.1080/10485252.2015.1010532
[59]	Liu J, Li S, Jiang L, Zhao L, Zhao WT, Feng L, Liu HB, Ji AQ, Li CX. DNA ancestry analyzer: an automatic program for ancestry inference of unknown individuals. Life Sci Res, 2018, 22(1): 3-7+41.
	刘京, 李盛, 江丽, 赵蕾, 赵雯婷, 丰蕾, 刘海渤, 季安全, 李彩霞. 对于未知来源个体进行族群推断的自动分析系统. 生命科学研究, 2018, 22(1): 3-7+41.
[60]	Ringnér M. What is principal component analysis? Nat Biotechnol, 2008, 26(3): 303-304. doi: 10.1038/nbt0308-303 pmid: 18327243
[61]	Pritchard JK, Stephens M, Donnelly P. Inference of population structure using multilocus genotype data. Genetics, 2000, 155(2): 945-959. doi: 10.1093/genetics/155.2.945
[62]	Cai LJ. The technical means of forensic material evidence identification in criminal investigation cases-DNA identification technology. Legality Vision, 2018, (34): 177.
	蔡立君. 刑侦案件中法医物证鉴定的技术手段——DNA鉴定技术. 法制博览, 2018, (34): 177.
[63]	Jiang L, Zhao L, Liu J, Zhao WT, Ma Q, Zhao H, Ji AQ, Li CX. DNA ancestry inference assisting to have a case solved. Forensic Science and Technology, 2019, 44(4): 371-373.
	江丽, 赵蕾, 刘京, 赵雯婷, 马泉, 赵慧, 季安全, 李彩霞. DNA供者族群推断技术在案件中的应用. 刑事技术, 2019, 44(4): 371-373.
[64]	Charilaou P, Battat R. Machine learning models and over-fitting considerations. World J Gastroenterol, 2022, 28(5): 605-607. doi: 10.3748/wjg.v28.i5.605
[65]	Dizaji KG, Chen W, Huang H. Deep large-scale multitask learning network for gene expression inference. J Comput Biol, 2021, 28(5): 485-500. doi: 10.1089/cmb.2020.0438 pmid: 34014778

编辑推荐

Metrics

www.chinagene.cn
备案号：京ICP备09063187号-4
总访问:,今日访问:,当前在线:

族群信息	族群简称	样本量	样本来源	参考文献
中国南方汉族人	CHS	105	千人基因组计划	[21]
中国北京汉族人	CHB	103	千人基因组计划	[21]
韩国人	KOR	91	韩国个人基因组计划	[22]
东京的日本人	JPT	104	千人基因组计划	[21]

族群信息	族群简称	样本量	样本来源	参考文献
中国南方汉族人	T_CHS	58	千人基因组计划(新增698)	[23]
中国北方汉族人	T_Northern Han	10	人类基因组多样性计划	[24]
韩国人	T_Korean	100	亚洲多样性计划	[26]
韩国人	T_Korean	2	西蒙斯基因组多样性计划	[25]
日本人	T_Japanese	27	人类基因组多样性计划	[24]
日本人	T_Japanese	2	西蒙斯基因组多样性计划	[25]

目标区分人群	样本量	参考来源
中国汉族人	461	Qin等(2014)^[8]、Xu等(2009)^[16]、Liu等(2018)^[15]、Cao等(2020)^[18]
韩国人	141	Jeon等(2020)^[17]
东亚人(韩国人)	100	Jung等(2019)^[12]
日本人	111	Aklyma等(2017)^[14]、Jinam等(2015)^[19]、Okada等(2018)^[13]
中国汉族人、韩国人和日本人	341	Shi等(2019)^[10]、Wang等(2018)^[9]
东亚人	8	Kim等(2005)^[20]
中国北方汉族人和日本人	23	本实验室^[27,28]

AISNP数	准确率(95%置信区间)		kappa系数
AISNP数	softmax	随机森林	softmax	随机森林
92	0.7538(0.6879~0.8119)	0.7337(0.6665~0.7937)	0.6339	0.6155
156	0.8844(0.8316~0.9253)	0.7889(0.7256~0.8435)	0.8156	0.6925
234	0.9196(0.8727~0.9533)	0.8342(0.7751~0.883)	0.8713	0.7554
326	0.9095(0.8608~0.9455)	0.7839(0.7202~0.839)	0.8532	0.6564
471	0.9146(0.8667~0.9494)	0.8241(0.764~0.8743)	0.8605	0.7285
534	0.9196(0.8727~0.9533)	0.7889(0.7256~0.8435)	0.8693	0.6778
661	0.4573(0.3867~0.5292)	0.8191(0.7585~0.87)	0.358	0.719
735	0.1457 (0.0998~0.2025)	0.9447(0.9032~0.9721)	0	0.914
829	0.4422(0.372~0.5141)	0.9146(0.8667~0.9494)	0.3022	0.8679
950	0.4824(0.4112~0.5542)	0.8693(0.8144~0.9128)	0.3651	0.7935
1128	0.4724(0.4014~0.5442)	0.8794(0.8259~0.9212)	0.3316	0.8076

南-北方汉族人、韩国人和日本人遗传划分机器学习模型优化方案

Optimization scheme of machine learning model for genetic division between northern Han, southern Han, Korean and Japanese

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 65

相关文章 11

编辑推荐

Metrics

[1]	郭晓媛, 孙昌春, 薛思瑶, 赵慧, 江丽, 李彩霞. 49AISNP：东亚北方三个族群遗传来源推断[J]. 遗传, 2021, 43(9): 880-889.
[2]	李茜, 王浩宇, 曹悦岩, 朱强, 舒潘寅, 侯婷芸, 王雨婷, 张霁. 微单倍型遗传标记的法医基因组学研究[J]. 遗传, 2021, 43(10): 962-971.
[3]	刘志勇, 乌日嘎, 李燃, 王蔷薇, 孙宏钰. 法医遗传学研究和鉴定中的伦理问题[J]. 遗传, 2021, 43(10): 994-1002.
[4]	胡雅丽, 戴睿, 刘永鑫, 张婧赢, 胡斌, 储成才, 袁怀波, 白洋. 水稻典型品种日本晴和IR24根系微生物组的解析[J]. 遗传, 2020, 42(5): 506-518.
[5]	刘杨, 孙昌春, 马咪, 王玲, 赵雯婷, 马泉, 季安全, 刘京, 李彩霞. 74-plex SNPs复合检测体系在中国人群中的族群推断研究[J]. 遗传, 2020, 42(3): 296-308.
[6]	张桂珊, 杨勇, 张灵敏, 戴宪华. 机器学习方法在CRISPR/Cas9系统中的应用[J]. 遗传, 2018, 40(9): 704-723.
[7]	赵学彤, 杨亚东, 渠鸿竹, 方向东. 组学时代下机器学习方法在临床决策支持中的应用[J]. 遗传, 2018, 40(9): 693-703.
[8]	彭哲也,唐紫珺,谢民主. 机器学习方法在基因交互作用探测中的研究进展[J]. 遗传, 2018, 40(3): 218-226.
[9]	田娇阳, 李玉春, 孔庆鹏, 张亚平. 遗传学视角下东亚人群的起源和演化[J]. 遗传, 2018, 40(10): 814-824.
[10]	江丽,孙启凡,马泉,赵雯婷,刘京,赵蕾,季安全,李彩霞. 27-plex SNP种族推断方法的优化及验证[J]. 遗传, 2017, 39(2): 166-173.
[11]	侯妍妍，应晓敏，李伍举. microRNA计算发现方法的研究进展[J]. 遗传, 2008, 30(6): 687-696.