CN118166108A - 检测肺结节良恶性的甲基化标志物、评估模型及应用 - Google Patents
检测肺结节良恶性的甲基化标志物、评估模型及应用 Download PDFInfo
- Publication number
- CN118166108A CN118166108A CN202410599937.9A CN202410599937A CN118166108A CN 118166108 A CN118166108 A CN 118166108A CN 202410599937 A CN202410599937 A CN 202410599937A CN 118166108 A CN118166108 A CN 118166108A
- Authority
- CN
- China
- Prior art keywords
- chr1
- chr2
- chr7
- chr19
- chr5
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000011987 methylation Effects 0.000 title claims abstract description 76
- 238000007069 methylation reaction Methods 0.000 title claims abstract description 76
- 230000003211 malignant effect Effects 0.000 title claims abstract description 75
- 206010056342 Pulmonary mass Diseases 0.000 title claims abstract description 57
- 238000013210 evaluation model Methods 0.000 title claims abstract description 16
- 239000003550 marker Substances 0.000 title claims abstract description 14
- 101100495925 Schizosaccharomyces pombe (strain 972 / ATCC 24843) chr3 gene Proteins 0.000 claims description 115
- 238000012549 training Methods 0.000 claims description 47
- 230000008901 benefit Effects 0.000 claims description 35
- 238000012360 testing method Methods 0.000 claims description 31
- 238000012163 sequencing technique Methods 0.000 claims description 21
- 206010058467 Lung neoplasm malignant Diseases 0.000 claims description 17
- 201000005202 lung cancer Diseases 0.000 claims description 17
- 208000020816 lung neoplasm Diseases 0.000 claims description 17
- 239000000047 product Substances 0.000 claims description 15
- 238000002790 cross-validation Methods 0.000 claims description 13
- 210000002569 neuron Anatomy 0.000 claims description 12
- 230000000694 effects Effects 0.000 claims description 11
- 238000011282 treatment Methods 0.000 claims description 11
- 238000000034 method Methods 0.000 claims description 10
- 108091029430 CpG site Proteins 0.000 claims description 9
- 238000013211 curve analysis Methods 0.000 claims description 9
- 239000012634 fragment Substances 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- LSNNMFCWUKXFEE-UHFFFAOYSA-M Bisulfite Chemical compound OS([O-])=O LSNNMFCWUKXFEE-UHFFFAOYSA-M 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 5
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- GUAHPAJOXVYFON-ZETCQYMHSA-N (8S)-8-amino-7-oxononanoic acid zwitterion Chemical compound C[C@H](N)C(=O)CCCCCC(O)=O GUAHPAJOXVYFON-ZETCQYMHSA-N 0.000 claims description 3
- 230000003321 amplification Effects 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 210000000349 chromosome Anatomy 0.000 claims description 3
- 239000012084 conversion product Substances 0.000 claims description 3
- 230000030609 dephosphorylation Effects 0.000 claims description 3
- 238000006209 dephosphorylation reaction Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 238000000746 purification Methods 0.000 claims description 3
- 238000011002 quantification Methods 0.000 claims description 3
- 239000000758 substrate Substances 0.000 claims description 3
- 238000003786 synthesis reaction Methods 0.000 claims description 3
- 239000012264 purified product Substances 0.000 claims description 2
- 238000002360 preparation method Methods 0.000 claims 1
- 239000000523 sample Substances 0.000 description 20
- 230000006870 function Effects 0.000 description 9
- 206010028980 Neoplasm Diseases 0.000 description 8
- 230000035945 sensitivity Effects 0.000 description 8
- 206010054107 Nodule Diseases 0.000 description 7
- 238000010276 construction Methods 0.000 description 7
- 238000001514 detection method Methods 0.000 description 7
- 201000011510 cancer Diseases 0.000 description 5
- 230000036210 malignancy Effects 0.000 description 4
- 230000004083 survival effect Effects 0.000 description 4
- 239000000090 biomarker Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000007170 pathology Effects 0.000 description 2
- 230000002980 postoperative effect Effects 0.000 description 2
- 108090000623 proteins and genes Proteins 0.000 description 2
- 230000008685 targeting Effects 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 108020004414 DNA Proteins 0.000 description 1
- 230000007067 DNA methylation Effects 0.000 description 1
- 101001117509 Homo sapiens Prostaglandin E2 receptor EP4 subtype Proteins 0.000 description 1
- 101000703741 Homo sapiens Short stature homeobox protein 2 Proteins 0.000 description 1
- 208000019693 Lung disease Diseases 0.000 description 1
- 102100024450 Prostaglandin E2 receptor EP4 subtype Human genes 0.000 description 1
- 235000014443 Pyrus communis Nutrition 0.000 description 1
- -1 RASSF1A Proteins 0.000 description 1
- 102100031976 Short stature homeobox protein 2 Human genes 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000002591 computed tomography Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 102000054766 genetic haplotypes Human genes 0.000 description 1
- 238000011528 liquid biopsy Methods 0.000 description 1
- 238000012164 methylation sequencing Methods 0.000 description 1
- 231100000590 oncogenic Toxicity 0.000 description 1
- 230000002246 oncogenic effect Effects 0.000 description 1
- 239000013610 patient sample Substances 0.000 description 1
- 210000005259 peripheral blood Anatomy 0.000 description 1
- 239000011886 peripheral blood Substances 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 230000002685 pulmonary effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011269 treatment regimen Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Landscapes
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
检测肺结节良恶性的甲基化标志物、评估模型及应用,本发明通过收集肺结节良性样本和恶性样本,分为训练集和测试集,提取训练集样本的cfDNA,构建甲基化靶向测序文库,并进行测序,对序列进行甲基化转化处理、数据比对,计算甲基化分值,对训练集样本数据进行特征矩阵构建,获得评估模型,用测试集样本数据验证模型的效果,因此能够区分良性和恶性的肺结节,从而实现肺结节无创精准辨析的目的。
Description
技术领域
本发明涉及生物医药检测的技术领域,尤其涉及一种检测肺结节良恶性的甲基化标志物,这种检测肺结节良恶性的甲基化标志物的评估模型,以及该检测肺结节良恶性的甲基化标志物在肺癌早筛中的应用。
背景技术
肺癌是世界上最常见的癌症之一,也是致癌死亡的主要原因之一。肺癌5年生存率低于20%,晚期患者仅6%,而IA期则达到85%。因此,肺癌早期检测是提高肺癌生存率的重要手段。尽管低剂量计算机断层扫描(LDCT)已经广泛应用于肺癌早筛,但其区分恶性和良性结节方面仍存在挑战性。有研究通过LDCT筛查高危人群,发现24.2%的参与者出现肺结节,但96.4%为良性,如果不能准确区分良恶性肺结节,可能导致过度治疗。
近年来,液体活检作为一种有效的无创检测方法,可用来检测肺结节良恶性。研究表明,特定DNA甲基化模式的改变可以作为早期肿瘤的生物标志。而外周血中游离DNA(cfDNA)的甲基化已经被开发出来作为肺癌早筛的标志物。一些基因如RASSF1A,PTGER4,SHOX2的甲基化,已被确定为区分肺癌和良性肺疾病潜在的生物标志物。最近研究开发一种基于PCR的cfDNA甲基化检测方法,能有效区分癌症和正常样本,以及良性疾病。然而,这些基于血液的cfDNA甲基化检测方法尚未在临床实践中广泛应用。目前临床上还没有广泛接受的检测方法用于鉴别肺结节良恶性。
发明内容
为克服现有技术的缺陷,本发明要解决的技术问题是提供了一种检测肺结节良恶性的甲基化标志物,其能够区分良性和恶性的肺结节,从而实现肺结节无创精准辨析的目的。
本发明的技术方案是:一种检测肺结节良恶性的甲基化标志物,其按照染色体号:起始位置:终止位置的形式表示为以下的一种或多种:chr1:933461:933661、chr1:3663636:3663836、chr1:6508884:6509216、chr1:44873719:44873992、chr1:45252250:45252450、chr1:47910604:47910804、chr1:110612484:110612811、chr1:121260989:121261197、chr1:170630461:170630661、chr1:170630779:170630979、chr1:200004695:200004895、chr1:201709024:201709286、chr1:205411615:205411981、chr1:224804424:224804624、chr1:235098930:235099329、chr1:246952449:246952649、chr1:247590046:247590246、chr10:8094136:8094336、chr10:13771226:13771426、chr10:17271282:17271482、chr10:31446731:31446960、chr10:90342715:90342915、chr10:94822235:94822435、chr10:94834720:94834941、chr10:123923943:123924143、chr10:134862367:134862608、chr11:420350:420632、chr11:44325796:44325997、chr11:60620057:60620257、chr11:71954948:71955148、chr11:112834110:112834416、chr12:2282090:2282290、chr12:56123713:56123969、chr12:58013516:58013716、chr12:58021334:58021534、chr12:111404033:111404233、chr12:114846856:114847056、chr12:115124911:115125191、chr12:117798974:117799174、chr12:131418421:131418662、chr13:53389452:53389724、chr13:112726305:112726505、chr14:92040784:92040984、chr14:105830716:105830916、chr14:105933578:105934099、chr14:105940490:105940690、chr15:27113277:27113477、chr15:41218552:41218752、chr15:45670805:45671005、chr16:1037548:1037773、chr16:70771579:70771798、chr16:73097098:73097298、chr17:4802704:4803018、chr17:46669698:46669912、chr17:48546661:48546861、chr17:59481932:59482132、chr17:59564663:59565040、chr17:70112878:70113078、chr17:77721969:77722169、chr17:79952445:79952705、chr17:80745056:80745446、chr18:19746190:19746390、chr18:56940384:56940584、chr19:1769662:1769862、chr19:2278515:2278790、chr19:2790947:2791147、chr19:4713626:4713906、chr19:13125272:13125472、chr19:17008293:17008493、chr19:30713626:30713826、chr19:30716857:30717057、chr19:36389819:36390152、chr19:41317070:41317270、chr19:46974860:46975063、chr19:48918862:48919062、chr2:264146:264484、chr2:45228238:45228463、chr2:114034391:114034591、chr2:115919417:115919617、chr2:131721743:131721943、chr2:176994745:176995040、chr2:177016992:177017370、chr2:177024578:177024778、chr2:177029433:177029647、chr2:177030134:177030449、chr20:590590:590790、chr20:61318785:61319012、chr20:62053011:62053327、chr20:62854302:62854579、chr21:45328459:45328682、chr22:19753961:19754161、chr22:22005999:22006199、chr22:22862794:22862994、chr22:22862846:22863046、chr22:29704450:29704650、chr22:46403741:46403941、chr22:50718628:50718828、chr3:5137616:5137816、chr3:46940237:46940437、chr3:48699053:48699253、chr3:69230395:69230599、chr3:157823001:157823300、chr3:170303686:170303888、chr3:181443236:181443436、chr3:194118929:194119129、chr3:196387720:196387920、chr4:1015769:1016117、chr4:1016350:1016717、chr4:1399902:1400261、chr4:144621462:144621662、chr4:183369409:183369609、chr5:2007790:2007990、chr5:16179948:16180148、chr5:37840176:37840376、chr5:92939735:92939935、chr5:139076623:139076941、chr5:139525754:139525954、chr5:140864704:140864904、chr5:140871317:140871517、chr5:140871596:140871805、chr5:178016519:178016719、chr5:178016963:178017163、chr6:2903381:2903581、chr6:26240701:26240901、chr6:38683053:38683380、chr6:137244436:137244636、chr6:137244902:137245102、chr6:166580183:166580476、chr7:19152085:19152381、chr7:27157175:27157375、chr7:27291262:27291557、chr7:54612256:54612456、chr7:87229732:87230069、chr7:93519986:93520213、chr7:96650220:96650420、chr7:100091203:100091483、chr8:20375580:20375780、chr8:22438141:22438341、chr8:22457092:22457292、chr8:55379155:55379355、chr8:61788861:61789200、chr8:67874783:67874983、chr8:99952076:99952276、chr8:99960396:99960596、chr8:104512705:104512905、chr9:14346823:14347137、chr9:36986533:36986733、chr9:71788607:71788807、chr9:110187518:110187718、chr9:127265715:127265915、chr9:141013967:141014167。
一种检测肺结节良恶性的甲基化标志物的评估模型,包括以下步骤:
(1)收集肺结节良性样本和恶性样本,分为训练集和测试集;
(2)提取训练集样本的cfDNA,构建甲基化靶向测序文库,并进行测序;
(3)对序列进行甲基化转化处理、数据比对,计算甲基化分值;
(4)对训练集样本数据进行特征矩阵构建,获得评估模型;
(5)用测试集样本数据验证模型的效果。
本发明通过收集肺结节良性样本和恶性样本,分为训练集和测试集,提取训练集样本的cfDNA,构建甲基化靶向测序文库,并进行测序,对序列进行甲基化转化处理、数据比对,计算甲基化分值,对训练集样本数据进行特征矩阵构建,获得评估模型,用测试集样本数据验证模型的效果,因此能够区分良性和恶性的肺结节,从而实现肺结节无创精准辨析的目的。
还提供了另一种检测肺结节良恶性的甲基化标志物的评估模型,包括以下步骤:
(I)训练集队列样本被随机分成五组,用于后续进行5折交叉验证,使用深度神经网络模型鉴别肺结节良恶性,模型包括:一个输入层,包含神经元数量与输入特征相同;输入层后接三个隐藏层,分别包含32、16、8个神经元;最后连接一个包含2个神经元的输出层;在输入层前设计一个批量归一化层;除输出层使用Sigmoid函数外,其他层都采用ReLU激活函数;模型采用Adam优化器和交叉熵损失函数进行训练,使用Keras构建这些模型,模型使用5折交叉验证方法,每次在训练样本80%样本上进行训练,在剩下20%样本进行验证;预测测试集样本时,5个交叉验证分类器预测分数的平均值作为最终预测结果;
(II)最终训练好的肺结节良恶性鉴别模型在训练集和测试集中获得受试者工作特征曲线下面积值AUC;
(III)模型决策曲线分析:为评估模型的潜在临床效用,采用决策曲线分析来评估模型决策净受益,对于不同的阈值,模型分数超过阈值的样本标记为干预对象,而得分低于阈值的样本则保持未处理;通过将真阳性样本的受益与假阳性的损益进行加权,计算出每个阈值下模型的净受益,对于表示无治疗的曲线净受益设为0,对于治疗所有患者的曲线,净益与y轴相交,相交值为对应恶性样本比例,当模型的净益在广泛范围内持续超过两个极端曲线的净益时,表明选择的阈值范围相对较为安全。
还提供了检测肺结节良恶性的甲基化标志物的评估模型在制备肺癌早筛产品中的应用。
附图说明
图1为本发明中计算甲基化分值的一个实施例的流程图。
图2为本发明一实施例中,良恶性鉴别深度学习模型结构。
图3为本发明一实施例中,模型在训练集测试集中的ROC曲线。
图4为本发明一实施例中,在测试集中模型的决策曲线分析图。该图显示模型在一系列阈值(x轴)上与对所有参与者进行干预(Treat all)或不进行干预(Treat none)相比的净受益。横坐标是判断恶性的风险阈值,纵坐标为不同阈值对应的临床净受益。
图5为良恶性鉴别模型在不同年龄(A)和性别(B)中的得分情况。
图6为基于随机选择甲基化标志物子集,构建模型ROC曲线。(A) 800个甲基化特征构建的模型效果;(B) 500个甲基化特征构建的模型效果;(C) 200个甲基化特征构建的模型效果。
图7为本发明的检测肺结节良恶性的甲基化标志物的评估模型。
具体实施方式
一种检测肺结节良恶性的甲基化标志物,其按照染色体号:起始位置:终止位置的形式表示为以下的一种或多种:chr1:933461:933661、chr1:3663636:3663836、chr1:6508884:6509216、chr1:44873719:44873992、chr1:45252250:45252450、chr1:47910604:47910804、chr1:110612484:110612811、chr1:121260989:121261197、chr1:170630461:170630661、chr1:170630779:170630979、chr1:200004695:200004895、chr1:201709024:201709286、chr1:205411615:205411981、chr1:224804424:224804624、chr1:235098930:235099329、chr1:246952449:246952649、chr1:247590046:247590246、chr10:8094136:8094336、chr10:13771226:13771426、chr10:17271282:17271482、chr10:31446731:31446960、chr10:90342715:90342915、chr10:94822235:94822435、chr10:94834720:94834941、chr10:123923943:123924143、chr10:134862367:134862608、chr11:420350:420632、chr11:44325796:44325997、chr11:60620057:60620257、chr11:71954948:71955148、chr11:112834110:112834416、chr12:2282090:2282290、chr12:56123713:56123969、chr12:58013516:58013716、chr12:58021334:58021534、chr12:111404033:111404233、chr12:114846856:114847056、chr12:115124911:115125191、chr12:117798974:117799174、chr12:131418421:131418662、chr13:53389452:53389724、chr13:112726305:112726505、chr14:92040784:92040984、chr14:105830716:105830916、chr14:105933578:105934099、chr14:105940490:105940690、chr15:27113277:27113477、chr15:41218552:41218752、chr15:45670805:45671005、chr16:1037548:1037773、chr16:70771579:70771798、chr16:73097098:73097298、chr17:4802704:4803018、chr17:46669698:46669912、chr17:48546661:48546861、chr17:59481932:59482132、chr17:59564663:59565040、chr17:70112878:70113078、chr17:77721969:77722169、chr17:79952445:79952705、chr17:80745056:80745446、chr18:19746190:19746390、chr18:56940384:56940584、chr19:1769662:1769862、chr19:2278515:2278790、chr19:2790947:2791147、chr19:4713626:4713906、chr19:13125272:13125472、chr19:17008293:17008493、chr19:30713626:30713826、chr19:30716857:30717057、chr19:36389819:36390152、chr19:41317070:41317270、chr19:46974860:46975063、chr19:48918862:48919062、chr2:264146:264484、chr2:45228238:45228463、chr2:114034391:114034591、chr2:115919417:115919617、chr2:131721743:131721943、chr2:176994745:176995040、chr2:177016992:177017370、chr2:177024578:177024778、chr2:177029433:177029647、chr2:177030134:177030449、chr20:590590:590790、chr20:61318785:61319012、chr20:62053011:62053327、chr20:62854302:62854579、chr21:45328459:45328682、chr22:19753961:19754161、chr22:22005999:22006199、chr22:22862794:22862994、chr22:22862846:22863046、chr22:29704450:29704650、chr22:46403741:46403941、chr22:50718628:50718828、chr3:5137616:5137816、chr3:46940237:46940437、chr3:48699053:48699253、chr3:69230395:69230599、chr3:157823001:157823300、chr3:170303686:170303888、chr3:181443236:181443436、chr3:194118929:194119129、chr3:196387720:196387920、chr4:1015769:1016117、chr4:1016350:1016717、chr4:1399902:1400261、chr4:144621462:144621662、chr4:183369409:183369609、chr5:2007790:2007990、chr5:16179948:16180148、chr5:37840176:37840376、chr5:92939735:92939935、chr5:139076623:139076941、chr5:139525754:139525954、chr5:140864704:140864904、chr5:140871317:140871517、chr5:140871596:140871805、chr5:178016519:178016719、chr5:178016963:178017163、chr6:2903381:2903581、chr6:26240701:26240901、chr6:38683053:38683380、chr6:137244436:137244636、chr6:137244902:137245102、chr6:166580183:166580476、chr7:19152085:19152381、chr7:27157175:27157375、chr7:27291262:27291557、chr7:54612256:54612456、chr7:87229732:87230069、chr7:93519986:93520213、chr7:96650220:96650420、chr7:100091203:100091483、chr8:20375580:20375780、chr8:22438141:22438341、chr8:22457092:22457292、chr8:55379155:55379355、chr8:61788861:61789200、chr8:67874783:67874983、chr8:99952076:99952276、chr8:99960396:99960596、chr8:104512705:104512905、chr9:14346823:14347137、chr9:36986533:36986733、chr9:71788607:71788807、chr9:110187518:110187718、chr9:127265715:127265915、chr9:141013967:141014167。这些是检测肺结节良恶性的重要甲基化标志物。申请人经过大量的试验和长时间的思考,获得了所有与检测肺结节良恶性相关的甲基化标志物,包括:chr1:933461:933661、chr1:969322:969629、chr1:1095763:1095986、chr1:1244934:1245214、chr1:1986153:1986353、chr1:2143942:2144142、chr1:2162026:2162290、chr1:2375506:2375706、chr1:2478439:2478810、chr1:2537360:2537650、chr1:2705949:2706149、chr1:2825194:2825394、chr1:2825531:2825731、chr1:2978722:2978922、chr1:2979017:2979217、chr1:2984449:2984656、chr1:3155250:3155539、chr1:3310104:3310358、chr1:3310195:3310395、chr1:3310706:3310940、chr1:3331940:3332307、chr1:3567381:3567648、chr1:3663636:3663836、chr1:6269251:6269591、chr1:6508884:6509216、chr1:7728844:7729044、chr1:8137321:8137521、chr1:10813808:10814072、chr1:11107039:11107343、chr1:12227353:12227740、chr1:15672425:15672625、chr1:20669702:20670104、chr1:21616360:21616664、chr1:25256338:25256538、chr1:27189993:27190207、chr1:27687058:27687449、chr1:27732201:27732413、chr1:29586580:29586780、chr1:32180083:32180341、chr1:32252185:32252487、chr1:41486014:41486250、chr1:43251115:43251315、chr1:43390402:43390670、chr1:44031322:44031663、chr1:44873030:44873230、chr1:44873719:44873992、chr1:44874546:44874746、chr1:44883311:44883638、chr1:45251902:45252102、chr1:45252250:45252450、chr1:47691404:47691604、chr1:47691646:47691993、chr1:47696833:47697033、chr1:47698162:47698362、chr1:47910604:47910804、chr1:50513701:50513948、chr1:50882097:50882297、chr1:50884300:50884500、chr1:50884547:50884747、chr1:50884757:50885087、chr1:50885363:50885563、chr1:50886858:50887058、chr1:50887188:50887447、chr1:52879413:52879613、chr1:61520321:61520632、chr1:62660635:62660835、chr1:63785343:63785664、chr1:63785890:63786090、chr1:63788723:63788923、chr1:63789808:63790008、chr1:63795753:63795966、chr1:66258438:66258638、chr1:66258752:66259270、chr1:67218167:67218438、chr1:77332988:77333298、chr1:78511631:78512031、chr1:91182896:91183268、chr1:91185256:91185556、chr1:98511032:98511232、chr1:108507266:108507466、chr1:108507595:108507795、chr1:108508007:108508250、chr1:110334699:110334899、chr1:110610804:110611103、chr1:110611583:110611783、chr1:110611972:110612252、chr1:110612484:110612811、chr1:110612988:110613188、chr1:111217716:111217916、chr1:119522323:119522523、chr1:119527250:119527450、chr1:119530493:119530714、chr1:119532788:119532988、chr1:119535692:119535892、chr1:119543191:119543547、chr1:119549342:119549542、chr1:121260989:121261197、chr1:145395625:145395980、chr1:145562922:145563122、chr1:146551463:146551747、chr1:150254960:150255160、chr1:151693837:151694148、chr1:151811354:151811554、chr1:151811702:151811902、chr1:154475045:154475245、chr1:155035356:155035581、chr1:155043384:155043584、chr1:156215548:156215837、chr1:156405314:156405514、chr1:156406417:156406629、chr1:156611838:156612099、chr1:158151044:158151244、chr1:165324051:165324251、chr1:165346030:165346230、chr1:169396540:169396740、chr1:170630461:170630661、chr1:170630779:170630979、chr1:180202481:180202846、chr1:180203521:180203721、chr1:180204074:180204274、chr1:180904506:180904814、chr1:181287519:181287719、chr1:181287751:181287951、chr1:182583982:182584185、chr1:182584200:182584400、chr1:197882498:197882698、chr1:200004695:200004895、chr1:200009817:200010017、chr1:201709024:201709286、chr1:203045120:203045320、chr1:203598665:203598961、chr1:205411615:205411981、chr1:209974618:209974838、chr1:212838794:212838994、chr1:213124588:213124788、chr1:214153199:214153399、chr1:221050383:221050583、chr1:223936731:223936939、chr1:224804256:224804456、chr1:224804424:224804624、chr1:226924813:226925063、chr1:228195223:228195423、chr1:228195495:228195695、chr1:228558810:228559010、chr1:229568009:229568209、chr1:234845168:234845486、chr1:235098930:235099329、chr1:235813721:235813921、chr1:237205224:237205424、chr1:237205513:237205713、chr1:237205919:237206212、chr1:237206116:237206316、chr1:237206150:237206350、chr1:240161230:240161455、chr1:246952449:246952649、chr1:247590046:247590246、chr1:248020555:248020755、chr1:248020790:248021176、chr10:518081:518444、chr10:5567439:5567728、chr10:7449719:7449919、chr10:8093384:8093681、chr10:8094136:8094336、chr10:8097474:8097837、chr10:13771226:13771426、chr10:15761473:15761673、chr10:15761861:15762061、chr10:16562233:16562433、chr10:16562599:16562852、chr10:17271221:17271421、chr10:17271223:17271423、chr10:17271282:17271482、chr10:22542122:22542322、chr10:22634278:22634478、chr10:22634363:22634563、chr10:23480625:23480825、chr10:23481046:23481246、chr10:28034653:28034853、chr10:31446731:31446960、chr10:35929070:35929334、chr10:50817643:50818011、chr10:57390986:57391186、chr10:60272746:60273033、chr10:72200092:72200377、chr10:72996144:72996424、chr10:74069147:74069510、chr10:83544020:83544240、chr10:83634420:83634620、chr10:88296342:88296594、chr10:90342715:90342915、chr10:90342997:90343386、chr10:94822235:94822435、chr10:94822554:94822754、chr10:94828207:94828407、chr10:94834720:94834941、chr10:99790636:99790963、chr10:102497304:102497504、chr10:102883272:102883472、chr10:102883646:102883846、chr10:102895034:102895234、chr10:102900241:102900441、chr10:103044097:103044410、chr10:103536237:103536559、chr10:105036590:105036794、chr10:105037376:105037644、chr10:106028818:106029018、chr10:106401281:106401481、chr10:108924091:108924291、chr10:108924362:108924562、chr10:109674543:109674895、chr10:110672177:110672377、chr10:113943613:113943813、chr10:118030662:118030862、chr10:118030868:118031151、chr10:118892523:118892723、chr10:118899862:118900105、chr10:119000909:119001109、chr10:119296259:119296529、chr10:119443747:119443947、chr10:122708383:122708583、chr10:123922994:123923299、chr10:123923943:123924143、chr10:124896740:124897020、chr10:124905504:124905704、chr10:125650986:125651186、chr10:126135997:126136197、chr10:129534694:129534894、chr10:129535471:129535681、chr10:130084908:130085108、chr10:131757287:131757512、chr10:131758415:131758615、chr10:131767964:131768242、chr10:131769770:131769970、chr10:131770965:131771313、chr10:133110348:133110620、chr10:133110769:133110969、chr10:133795737:133795937、chr10:133795950:133796150、chr10:133951870:133952070、chr10:134016194:134016408、chr10:134120624:134120824、chr10:134499767:134499983、chr10:134527175:134527410、chr10:134597777:134597977、chr10:134597986:134598186、chr10:134600680:134600880、chr10:134734173:134734395、chr10:134862367:134862608、chr10:134977904:134978104、chr10:135044363:135044603、chr10:135090209:135090425、chr10:135139477:135139677、chr11:420350:420632、chr11:626966:627383、chr11:636862:637062、chr11:637442:637727、chr11:1331807:1332007、chr11:1486503:1486703、chr11:1955139:1955372、chr11:2181981:2182295、chr11:2226052:2226252、chr11:2292332:2292651、chr11:2465329:2465529、chr11:11600237:11600617、chr11:13030834:13031059、chr11:13031102:13031302、chr11:15136317:15136669、chr11:17497417:17497617、chr11:17741892:17742092、chr11:20618486:20618686、chr11:31820260:31820460、chr11:31826962:31827162、chr11:31837411:31837611、chr11:31839396:31839726、chr11:31841612:31841916、chr11:31848632:31848877、chr11:43602922:43603140、chr11:44325796:44325997、chr11:44326290:44326490、chr11:46259307:46259674、chr11:47209002:47209202、chr11:58672824:58673024、chr11:60620057:60620257、chr11:62311321:62311598、chr11:63687058:63687258、chr11:64333172:64333372、chr11:65405657:65405857、chr11:66623737:66623937、chr11:66624180:66624380、chr11:67351177:67351436、chr11:68622069:68622269、chr11:69258178:69258378、chr11:69517830:69518030、chr11:71954948:71955148、chr11:73371736:73371944、chr11:74879677:74879877、chr11:75917528:75917998、chr11:76750646:76750846、chr11:94134563:94134763、chr11:112834110:112834416、chr11:123066361:123066731、chr11:123947017:123947283、chr11:124761342:124761580、chr11:125036402:125036602、chr11:125774078:125774278、chr11:130060469:130060669、chr11:131780628:131780828、chr11:131780892:131781092、chr11:132813724:132813924、chr11:132952609:132952916、chr11:134202140:134202340、chr11:134281635:134281835、chr12:2282090:2282290、chr12:3309482:3309682、chr12:4274033:4274474、chr12:6643463:6643663、chr12:6643622:6643822、chr12:20522486:20522765、chr12:22487698:22487898、chr12:25056205:25056405、chr12:25101899:25102155、chr12:28127911:28128111、chr12:30354393:30354624、chr12:33592314:33592514、chr12:33592774:33592974、chr12:39299500:39299726、chr12:43945939:43946139、chr12:47224975:47225175、chr12:49392100:49392300、chr12:49392225:49392425、chr12:50297535:50297964、chr12:52311647:52311991、chr12:52401109:52401309、chr12:54321625:54321825、chr12:54345506:54345851、chr12:56123713:56123969、chr12:57529619:57529819、chr12:58013516:58013716、chr12:58021334:58021534、chr12:58021577:58021823、chr12:58025689:58025889、chr12:58131193:58131393、chr12:62584894:62585094、chr12:62585025:62585225、chr12:63544037:63544348、chr12:63544441:63544641、chr12:65218302:65218502、chr12:66275938:66276138、chr12:75728444:75728656、chr12:81101927:81102127、chr12:95941955:95942157、chr12:98897228:98897428、chr12:99288553:99288753、chr12:108169315:108169605、chr12:109996613:109997009、chr12:111404033:111404233、chr12:111471918:111472118、chr12:111472097:111472297、chr12:111472100:111472300、chr12:111664589:111664851、chr12:111725319:111725697、chr12:113515300:113515540、chr12:113541913:113542113、chr12:113901298:113901498、chr12:113902107:113902307、chr12:113917423:113917666、chr12:114162628:114162828、chr12:114840811:114841011、chr12:114841096:114841296、chr12:114846856:114847056、chr12:114886396:114886596、chr12:115109913:115110164、chr12:115111826:115112463、chr12:115124911:115125191、chr12:117798974:117799174、chr12:122277643:122277843、chr12:123634864:123635131、chr12:125007806:125008144、chr12:125223350:125223550、chr12:125498898:125499098、chr12:127630638:127630838、chr12:129338496:129338838、chr12:131303645:131303958、chr12:131418421:131418662、chr12:133029845:133030045、chr12:133030159:133030359、chr12:133481530:133481730、chr12:133485245:133485445、chr13:21520235:21520435、chr13:24844736:24844936、chr13:25320071:25320271、chr13:25320388:25320588、chr13:28503001:28503238、chr13:32605445:32605645、chr13:36045177:36045385、chr13:36049724:36050122、chr13:36729096:36729334、chr13:37005557:37005757、chr13:37005935:37006328、chr13:46961383:46961583、chr13:49794987:49795187、chr13:49795241:49795441、chr13:51417486:51417774、chr13:53313042:53313242、chr13:53313416:53313616、chr13:53389452:53389724、chr13:53420547:53420945、chr13:53421052:53421252、chr13:58206778:58207128、chr13:79175946:79176146、chr13:79177322:79177722、chr13:96294369:96294576、chr13:100621183:100621383、chr13:100621473:100621673、chr13:100624022:100624302、chr13:100641708:100641908、chr13:100649543:100649743、chr13:102568764:102568964、chr13:109147964:109148164、chr13:111127887:111128087、chr13:111277395:111277690、chr13:112707892:112708602、chr13:112711391:112711603、chr13:112717213:112717438、chr13:112721382:112721582、chr13:112726305:112726505、chr13:112758741:112758954、chr13:112759950:112760185、chr13:113350703:113351027、chr13:114214669:114214869、chr14:23291034:23291346、chr14:24804138:24804360、chr14:24836024:24836224、chr14:29234949:29235282、chr14:29254362:29254704、chr14:33402227:33402534、chr14:36986598:36986864、chr14:37050242:37050511、chr14:37058072:37058272、chr14:37116133:37116488、chr14:37126634:37126834、chr14:37126878:37127078、chr14:37127797:37128181、chr14:38061327:38061706、chr14:38724555:38724973、chr14:38725201:38725401、chr14:48144205:48144405、chr14:51027707:51028060、chr14:51561291:51561602、chr14:52735129:52735329、chr14:55243006:55243206、chr14:57264908:57265108、chr14:57265398:57265598、chr14:57275744:57275944、chr14:57283271:57283615、chr14:58332601:58332828、chr14:60952593:60952793、chr14:60976665:60976952、chr14:61104459:61104820、chr14:61108866:61109085、chr14:61109427:61109627、chr14:64687310:64687528、chr14:74706677:74706973、chr14:74707177:74707377、chr14:74707284:74707484、chr14:85999636:85999949、chr14:92040784:92040984、chr14:92790215:92790472、chr14:93154029:93154229、chr14:93389444:93389644、chr14:95239409:95239609、chr14:96342976:96343182、chr14:97499586:97500105、chr14:99712183:99712446、chr14:101649759:101649959、chr14:102050405:102050641、chr14:102172384:102172584、chr14:103389423:103389623、chr14:103655787:103656071、chr14:104710881:104711152、chr14:105102434:105102644、chr14:105714973:105715224、chr14:105830716:105830916、chr14:105933578:105934099、chr14:105940100:105940394、chr14:105940490:105940690、chr15:27112682:27113006、chr15:27113022:27113222、chr15:27113277:27113477、chr15:28342180:28342415、chr15:28352819:28353149、chr15:29395897:29396097、chr15:31598590:31598819、chr15:33010426:33010626、chr15:34786666:34786866、chr15:34786976:34787337、chr15:37180302:37180610、chr15:41210238:41210638、chr15:41218213:41218413、chr15:41218552:41218752、chr15:41793866:41794364、chr15:45408827:45409161、chr15:45427262:45427462、chr15:45427503:45427782、chr15:45670347:45670547、chr15:45670675:45670875、chr15:45670805:45671005、chr15:48937628:48937828、chr15:53083387:53083587、chr15:53087384:53087584、chr15:53097858:53098215、chr15:58357928:58358128、chr15:60689364:60689617、chr15:60690643:60690843、chr15:65116254:65116454、chr15:66914593:66914793、chr15:68114350:68114550、chr15:68118965:68119313、chr15:68120727:68120927、chr15:68121381:68121679、chr15:68121923:68122316、chr15:76635120:76635744、chr15:79381756:79382075、chr15:79383162:79383362、chr15:82532806:82533006、chr15:83316205:83316540、chr15:83776418:83776618、chr15:83776646:83776846、chr15:83952160:83952360、chr15:84748632:84748891、chr15:89922183:89922438、chr15:89952386:89952646、chr15:96909441:96909641、chr15:101513581:101513781、chr16:230343:230641、chr16:630128:630451、chr16:671268:671498、chr16:1037548:1037773、chr16:1202353:1202553、chr16:1206396:1206596、chr16:1838506:1838845、chr16:2041825:2042025、chr16:2085778:2086156、chr16:3016878:3017078、chr16:3079744:3080098、chr16:3139015:3139246、chr16:3211457:3211740、chr16:4253135:4253487、chr16:4717986:4718215、chr16:5167459:5167659、chr16:11326998:11327245、chr16:12355072:12355272、chr16:16244174:16244374、chr16:22824667:22824867、chr16:22825689:22825889、chr16:22825962:22826162、chr16:23847490:23847690、chr16:23847868:23848068、chr16:27378732:27378932、chr16:28984534:28984734、chr16:30566925:30567182、chr16:31473538:31473738、chr16:31473848:31474048、chr16:31580122:31580353、chr16:33964856:33965077、chr16:49312035:49312235、chr16:50715367:50715567、chr16:51168473:51168843、chr16:51184518:51184792、chr16:51185940:51186330、chr16:51190057:51190257、chr16:54966149:54966349、chr16:55365211:55365411、chr16:56672392:56672592、chr16:57025884:57026193、chr16:57654378:57654578、chr16:58497281:58497481、chr16:67197725:67197925、chr16:67919979:67920237、chr16:68676499:68676699、chr16:69348736:69348936、chr16:70771579:70771798、chr16:73097098:73097298、chr16:82660460:82660774、chr16:86544838:86545038、chr16:86612373:86612573、chr16:87943150:87943350、chr16:88769930:88770130、chr17:554407:554607、chr17:755288:755610、chr17:1174438:1174713、chr17:4802704:4803018、chr17:4853831:4854082、chr17:5001038:5001304、chr17:6616981:6617228、chr17:7287513:7287763、chr17:8906693:8906985、chr17:9066057:9066257、chr17:11143843:11144043、chr17:18538073:18538578、chr17:21300616:21300930、chr17:26696281:26696563、chr17:26699200:26699407、chr17:26903975:26904175、chr17:27332412:27332612、chr17:32908642:32908945、chr17:32961877:32962200、chr17:35165517:35165717、chr17:35292148:35292348、chr17:35293755:35293955、chr17:35299796:35300027、chr17:36102570:36102770、chr17:36103189:36103389、chr17:36715800:36716000、chr17:36735154:36735354、chr17:37321640:37321840、chr17:38347693:38347893、chr17:41477161:41477361、chr17:41832759:41832959、chr17:42733631:42733831、chr17:43037283:43037636、chr17:43037642:43037842、chr17:44896776:44896976、chr17:46507488:46507777、chr17:46619020:46619220、chr17:46621663:46621863、chr17:46655755:46655955、chr17:46659176:46659376、chr17:46669698:46669912、chr17:46673881:46674081、chr17:46711176:46711496、chr17:46796372:46796572、chr17:46796653:46796853、chr17:46832411:46832611、chr17:48041381:48041581、chr17:48042487:48042687、chr17:48050277:48050483、chr17:48546406:48546645、chr17:48546661:48546861、chr17:59478234:59478566、chr17:59481932:59482132、chr17:59482195:59482395、chr17:59482763:59482963、chr17:59529176:59529588、chr17:59532118:59532318、chr17:59564663:59565040、chr17:61512776:61512976、chr17:70112878:70113078、chr17:73073838:73074038、chr17:73607909:73608115、chr17:73639752:73639995、chr17:75369060:75369260、chr17:75369368:75370149、chr17:75370344:75370592、chr17:76138689:76138889、chr17:76228159:76228359、chr17:76526519:76526719、chr17:76929754:76929954、chr17:76991129:76991518、chr17:77721969:77722169、chr17:79315110:79315329、chr17:79411994:79412194、chr17:79481479:79481679、chr17:79482394:79482623、chr17:79952445:79952705、chr17:79961771:79962117、chr17:80535225:80535425、chr17:80745056:80745446、chr17:80846736:80847133、chr17:80970910:80971203、chr18:904550:904750、chr18:908993:909193、chr18:5543429:5543629、chr18:5629858:5630191、chr18:5891157:5891357、chr18:11148957:11149157、chr18:12911106:12911306、chr18:19746190:19746390、chr18:19780648:19781005、chr18:22930394:22930594、chr18:24130840:24131164、chr18:25757438:25757752、chr18:31158804:31159004、chr18:31159160:31159360、chr18:44336540:44336814、chr18:49867020:49867262、chr18:53447617:53447817、chr18:55095185:55095385、chr18:55862585:55862951、chr18:56940384:56940584、chr18:60263492:60263692、chr18:61143773:61143973、chr18:70534025:70534322、chr18:70535336:70535536、chr18:74818217:74818417、chr18:74961722:74961922、chr18:74962213:74962413、chr18:76150778:76150991、chr18:76739171:76739371、chr18:76739663:76739863、chr18:77159233:77159590、chr18:77256428:77256628、chr18:77548012:77548347、chr19:660388:660761、chr19:752407:752607、chr19:1769662:1769862、chr19:1857160:1857360、chr19:2252104:2252327、chr19:2278515:2278790、chr19:2290432:2290681、chr19:2302770:2303146、chr19:2790947:2791147、chr19:3688030:3688230、chr19:4059528:4059746、chr19:4713626:4713906、chr19:4912069:4912269、chr19:6740734:6741161、chr19:6741171:6741371、chr19:8657592:8657792、chr19:9473648:9473848、chr19:10398151:10398351、chr19:10403253:10403585、chr19:10404550:10405159、chr19:10406957:10407312、chr19:10625017:10625241、chr19:10823485:10823947、chr19:10824035:10824235、chr19:11449921:11450271、chr19:12978686:12978886、chr19:13123065:13123265、chr19:13123416:13123616、chr19:13124920:13125120、chr19:13125272:13125472、chr19:13209774:13209974、chr19:13616861:13617166、chr19:13983963:13984163、chr19:15344061:15344322、chr19:15580341:15580719、chr19:15695359:15695719、chr19:16511819:16512143、chr19:17007265:17007465、chr19:17007540:17007740、chr19:17008293:17008493、chr19:18209946:18210205、chr19:18714539:18714739、chr19:19650947:19651147、chr19:24270437:24270637、chr19:29284293:29284545、chr19:30016976:30017176、chr19:30017043:30017243、chr19:30713626:30713826、chr19:30713685:30713885、chr19:30716857:30717057、chr19:30866047:30866331、chr19:31842371:31842571、chr19:31842771:31842971、chr19:36389819:36390152、chr19:36523307:36523522、chr19:36523795:36523995、chr19:37824779:37824979、chr19:37957790:37957990、chr19:38755091:38755291、chr19:38973896:38974096、chr19:38974211:38974411、chr19:39056164:39056455、chr19:39306255:39306455、chr19:39603141:39603386、chr19:39755552:39755772、chr19:39993574:39993774、chr19:41317070:41317270、chr19:41641405:41641605、chr19:42407508:42407708、chr19:42407740:42407940、chr19:42703843:42704124、chr19:43271257:43271457、chr19:45574933:45575279、chr19:45656232:45656457、chr19:46974860:46975063、chr19:46996738:46996938、chr19:47614089:47614369、chr19:48000283:48000596、chr19:48918862:48919062、chr19:48946974:48947213、chr19:49133468:49133668、chr19:50815759:50815995、chr19:51228577:51228777、chr19:52223029:52223229、chr19:54485549:54485769、chr19:55593132:55593428、chr19:55593530:55593730、chr19:55598552:55598752、chr19:56988933:56989133、chr19:57587704:57588086、chr19:58095530:58095874、chr2:264146:264484、chr2:468096:468607、chr2:469568:469933、chr2:2725269:2725469、chr2:3723146:3723346、chr2:3723904:3724104、chr2:3978819:3979113、chr2:5836034:5836335、chr2:5836489:5836689、chr2:7148520:7148720、chr2:8314701:8314901、chr2:10444997:10445197、chr2:11622388:11622588、chr2:19556022:19556222、chr2:19556785:19556985、chr2:24300144:24300422、chr2:25499956:25500156、chr2:27529689:27529890、chr2:30453572:30453772、chr2:31805766:31805966、chr2:39187516:39187716、chr2:44058865:44059175、chr2:44065704:44065904、chr2:45028929:45029292、chr2:45155938:45156214、chr2:45156730:45157036、chr2:45159797:45160173、chr2:45169759:45169959、chr2:45171681:45171953、chr2:45227849:45228049、chr2:45228238:45228463、chr2:45232498:45232698、chr2:45240689:45240889、chr2:47270844:47271044、chr2:50574443:50574739、chr2:63275030:63275230、chr2:63280893:63281093、chr2:63283019:63283219、chr2:63285937:63286137、chr2:63286154:63286354、chr2:66666356:66666556、chr2:66666644:66667043、chr2:66808644:66808938、chr2:71115853:71116209、chr2:71134457:71134682、chr2:72365494:72365694、chr2:72371208:72371433、chr2:73147428:73147715、chr2:73429973:73430173、chr2:73430006:73430206、chr2:74726373:74726801、chr2:74731340:74731602、chr2:74742517:74742717、chr2:74743044:74743244、chr2:80529783:80530040、chr2:85395652:85395907、chr2:85811643:85811843、chr2:87017367:87017662、chr2:89064624:89064824、chr2:97427786:97428040、chr2:98963053:98963318、chr2:105458976:105459176、chr2:105459323:105459523、chr2:105459667:105460135、chr2:105461064:105461264、chr2:105470452:105470736、chr2:105472158:105472358、chr2:105480351:105480659、chr2:106681853:106682053、chr2:106682020:106682220、chr2:106682111:106682311、chr2:106959197:106959397、chr2:111875067:111875325、chr2:111875427:111875627、chr2:111876734:111876934、chr2:111876902:111877102、chr2:113931508:113931708、chr2:114034391:114034591、chr2:114034788:114034988、chr2:115919236:115919436、chr2:115919417:115919617、chr2:118981858:118982058、chr2:119916114:119916314、chr2:127863675:127864070、chr2:128180759:128180959、chr2:131721743:131721943、chr2:131792198:131792398、chr2:144694552:144694789、chr2:144695022:144695331、chr2:154334730:154334930、chr2:154727984:154728184、chr2:162283575:162283775、chr2:162930273:162930473、chr2:162930518:162930718、chr2:171572971:171573171、chr2:171679667:171679867、chr2:175191863:175192152、chr2:175199560:175199798、chr2:175200574:175200802、chr2:175202176:175202376、chr2:175202377:175202577、chr2:175208640:175208840、chr2:176936260:176936480、chr2:176945337:176945719、chr2:176947852:176948127、chr2:176956558:176956758、chr2:176964760:176964960、chr2:176969332:176969532、chr2:176979559:176979759、chr2:176981004:176981204、chr2:176987322:176987856、chr2:176987885:176988085、chr2:176988018:176988218、chr2:176994745:176995040、chr2:177016992:177017370、chr2:177017395:177017595、chr2:177024578:177024778、chr2:177025034:177025300、chr2:177029433:177029647、chr2:177030134:177030449、chr2:177043062:177043477、chr2:177053268:177053486、chr2:182322169:182322369、chr2:187466570:187466770、chr2:193059391:193059591、chr2:198650929:198651129、chr2:198651308:198651659、chr2:200327248:200327458、chr2:208988921:208989121、chr2:216877796:216878063、chr2:219736309:219736509、chr2:220299707:220299907、chr2:220313289:220313489、chr2:220361478:220361678、chr2:223161693:223162062、chr2:223170505:223170837、chr2:233352617:233352817、chr2:233368258:233368458、chr2:233792902:233793102、chr2:237068303:237068577、chr2:238864855:238865085、chr2:239755167:239755412、chr2:240270422:240270792、chr2:241760027:241760227、chr2:242743413:242743779、chr2:242799431:242799631、chr2:242801904:242802104、chr20:590590:590790、chr20:2780950:2781341、chr20:3220575:3220775、chr20:3653171:3653565、chr20:3758843:3759043、chr20:5297043:5297281、chr20:12805752:12805952、chr20:13200627:13200827、chr20:19667703:19667903、chr20:21081978:21082178、chr20:21377133:21377333、chr20:21502359:21502559、chr20:21503176:21503376、chr20:22562763:22562963、chr20:24598883:24599203、chr20:25061988:25062188、chr20:25062301:25062670、chr20:37274870:37275238、chr20:37435527:37435727、chr20:39319279:39319664、chr20:41818310:41818510、chr20:43331809:43332099、chr20:43727203:43727553、chr20:55202107:55202685、chr20:55205965:55206356、chr20:55500358:55500677、chr20:57875309:57875527、chr20:59827678:59827907、chr20:59828849:59829088、chr20:60010496:60010769、chr20:60175249:60175597、chr20:60428269:60428538、chr20:60447728:60447992、chr20:60791925:60792239、chr20:61088625:61088827、chr20:61304694:61304954、chr20:61318785:61319012、chr20:61340295:61340495、chr20:61606676:61606962、chr20:61636379:61636600、chr20:61808594:61808794、chr20:61809027:61809383、chr20:61809586:61809786、chr20:61951525:61951758、chr20:62046355:62046589、chr20:62053011:62053327、chr20:62172835:62173192、chr20:62330559:62330808、chr20:62366275:62366475、chr20:62690146:62690346、chr20:62854302:62854579、chr21:19617713:19617923、chr21:27945326:27945526、chr21:32931314:32931514、chr21:34443217:34443417、chr21:38065524:38065724、chr21:38068425:38068680、chr21:38068692:38068892、chr21:38069664:38069864、chr21:38069978:38070273、chr21:38073231:38073431、chr21:38073554:38073754、chr21:38076779:38076979、chr21:38077466:38077686、chr21:38079753:38079988、chr21:38080417:38080617、chr21:38081264:38081620、chr21:38082591:38082909、chr21:38120397:38120597、chr21:38378347:38378547、chr21:45328459:45328682、chr21:47518807:47519007、chr22:17082401:17082618、chr22:19512066:19512266、chr22:19753961:19754161、chr22:20267817:20268017、chr22:22005999:22006199、chr22:22006209:22006409、chr22:22006617:22006817、chr22:22862794:22862994、chr22:22862846:22863046、chr22:29704450:29704650、chr22:36861325:36861709、chr22:37464853:37465053、chr22:40081744:40082016、chr22:40390957:40391252、chr22:41445005:41445210、chr22:42470491:42470829、chr22:46368000:46368200、chr22:46403741:46403941、chr22:46839718:46839928、chr22:46921614:46921814、chr22:47458284:47458484、chr22:50016146:50016378、chr22:50496720:50497081、chr22:50644509:50644818、chr22:50718628:50718828、chr22:50987176:50987479、chr3:5137616:5137816、chr3:9178082:9178352、chr3:9904400:9904673、chr3:11178463:11178663、chr3:11178892:11179092、chr3:13323366:13323566、chr3:17522515:17522715、chr3:33260347:33260547、chr3:38035519:38035753、chr3:38036014:38036227、chr3:38080591:38080791、chr3:38080707:38080907、chr3:44063476:44063676、chr3:44102254:44102454、chr3:46940237:46940437、chr3:48699021:48699221、chr3:48699053:48699253、chr3:49459532:49459732、chr3:49756830:49757030、chr3:49756883:49757083、chr3:50377975:50378564、chr3:52864771:52864971、chr3:52865018:52865236、chr3:66002678:66003019、chr3:69230395:69230599、chr3:120169805:120170005、chr3:120169838:120170038、chr3:122296568:122296915、chr3:123167022:123167222、chr3:124860388:124860588、chr3:124860723:124861087、chr3:128211041:128211241、chr3:128241488:128241789、chr3:129693363:129693563、chr3:129693578:129693796、chr3:129693800:129694000、chr3:129694374:129694634、chr3:133393342:133393542、chr3:137483825:137484025、chr3:138658504:138658704、chr3:138658952:138659152、chr3:138679277:138679477、chr3:142839765:142840048、chr3:147109862:147110062、chr3:147110112:147110359、chr3:147111605:147111805、chr3:147128111:147128311、chr3:147128332:147128532、chr3:147131073:147131275、chr3:147136741:147137009、chr3:147137118:147137476、chr3:157812179:157812593、chr3:157821224:157821424、chr3:157823001:157823300、chr3:157824756:157824956、chr3:157825025:157825225、chr3:170137183:170137383、chr3:170303686:170303888、chr3:171175903:171176215、chr3:172166628:172166828、chr3:179754913:179755264、chr3:181441375:181441582、chr3:181443236:181443436、chr3:181444089:181444289、chr3:183543540:183543740、chr3:184099455:184099694、chr3:184301379:184301579、chr3:184301691:184301908、chr3:184322086:184322286、chr3:185973717:185973917、chr3:185973998:185974198、chr3:186490337:186490537、chr3:192125834:192126034、chr3:192126117:192126324、chr3:192126754:192127145、chr3:193776050:193776250、chr3:194118612:194118812、chr3:194118768:194118968、chr3:194118929:194119129、chr3:195555690:195555890、chr3:195599735:195600027、chr3:196387720:196387920、chr3:196756019:196756219、chr3:197121414:197121632、chr3:197281747:197282044、chr3:197282524:197282724、chr3:197282711:197282911、chr3:197639716:197639916、chr4:107673:107873、chr4:569626:569868、chr4:1015769:1016117、chr4:1016350:1016717、chr4:1161184:1161538、chr4:1398511:1398772、chr4:1399902:1400261、chr4:2042204:2042481、chr4:3201486:3201720、chr4:3447856:3448097、chr4:4731999:4732199、chr4:5710006:5710312、chr4:5713119:5713344、chr4:8859842:8860042、chr4:8859947:8860147、chr4:8863209:8863409、chr4:10020751:10020951、chr4:13543558:13543849、chr4:13544023:13544223、chr4:13544253:13544453、chr4:13545285:13545485、chr4:13545661:13545861、chr4:24801688:24801888、chr4:37246660:37246908、chr4:39448374:39448574、chr4:41869202:41869525、chr4:41882099:41882458、chr4:44449557:44449757、chr4:48485417:48485821、chr4:48492345:48492545、chr4:54959962:54960162、chr4:54975862:54976223、chr4:55098080:55098369、chr4:57521292:57521580、chr4:57521683:57521883、chr4:57521737:57521937、chr4:57521812:57522201、chr4:57522402:57522652、chr4:62068300:62068500、chr4:74864213:74864573、chr4:81952235:81952435、chr4:85418299:85418499、chr4:85418610:85418919、chr4:107956865:107957065、chr4:111536301:111536501、chr4:111542016:111542306、chr4:123747706:123747906、chr4:134071901:134072171、chr4:134073075:134073281、chr4:140656442:140656642、chr4:144621462:144621662、chr4:147559211:147559411、chr4:147559993:147560193、chr4:154709519:154709799、chr4:155664066:155664266、chr4:169799403:169799603、chr4:172734845:172735045、chr4:174450302:174450626、chr4:174450783:174450983、chr4:183369409:183369609、chr4:190940255:190940455、chr5:473035:473235、chr5:508551:508751、chr5:1005137:1005337、chr5:1139821:1140202、chr5:1291139:1291339、chr5:1295328:1295528、chr5:1875838:1876195、chr5:1876269:1876469、chr5:1877854:1878054、chr5:1878170:1878370、chr5:1882887:1883087、chr5:1887435:1887635、chr5:2007790:2007990、chr5:2754887:2755087、chr5:3596560:3596842、chr5:3599720:3599934、chr5:3600530:3600795、chr5:3600840:3601126、chr5:3602378:3602578、chr5:3606438:3606670、chr5:5139775:5140028、chr5:7395528:7395728、chr5:7850161:7850361、chr5:11385354:11385752、chr5:16179948:16180148、chr5:16180218:16180418、chr5:32712668:32712868、chr5:37834783:37835164、chr5:37840176:37840376、chr5:40680915:40681115、chr5:40681817:40682017、chr5:54516317:54516748、chr5:54519320:54519520、chr5:59189846:59190046、chr5:72526093:72526489、chr5:72528198:72528506、chr5:72677368:72677764、chr5:72732462:72732662、chr5:76249591:76249791、chr5:77268570:77268770、chr5:80256758:80256958、chr5:92906255:92906617、chr5:92939735:92939935、chr5:112073279:112073728、chr5:115151371:115151724、chr5:115152406:115152637、chr5:115265921:115266121、chr5:122431121:122431321、chr5:132161430:132161630、chr5:134364359:134364559、chr5:134374689:134374889、chr5:134825822:134826085、chr5:134870613:134870990、chr5:134871359:134871593、chr5:137610046:137610246、chr5:137610325:137610586、chr5:138729977:138730177、chr5:139047806:139048006、chr5:139076623:139076941、chr5:139077081:139077281、chr5:139227564:139227764、chr5:139227959:139228159、chr5:139525754:139525954、chr5:140306322:140306522、chr5:140306438:140306666、chr5:140800889:140801089、chr5:140864413:140864613、chr5:140864704:140864904、chr5:140871317:140871517、chr5:140871596:140871805、chr5:140892824:140893033、chr5:145725689:145725889、chr5:168253313:168253513、chr5:169805839:169806039、chr5:170736445:170736645、chr5:170736667:170736867、chr5:170737114:170737430、chr5:170742525:170742728、chr5:172177213:172177413、chr5:172659554:172659918、chr5:175085103:175085467、chr5:175792886:175793131、chr5:176024114:176024314、chr5:176278450:176278652、chr5:176829529:176829796、chr5:176830310:176830677、chr5:176830914:176831114、chr5:177411431:177411827、chr5:178003891:178004091、chr5:178016519:178016719、chr5:178016963:178017163、chr5:178421448:178421697、chr5:178421987:178422187、chr5:178770944:178771144、chr5:180100746:180100975、chr5:180486527:180486727、chr6:391439:391639、chr6:391738:391938、chr6:391996:392345、chr6:392722:392922、chr6:393080:393280、chr6:1080845:1081160、chr6:1378941:1379141、chr6:1384272:1384610、chr6:1393206:1393469、chr6:1614911:1615144、chr6:1620178:1620569、chr6:1625055:1625255、chr6:1625294:1625494、chr6:2903381:2903581、chr6:3053594:3053794、chr6:6003896:6004283、chr6:6724534:6724734、chr6:7142421:7142621、chr6:10381956:10382156、chr6:10382247:10382447、chr6:10398459:10398659、chr6:10417560:10417760、chr6:10421345:10421545、chr6:10425984:10426373、chr6:11044435:11044635、chr6:19691753:19691953、chr6:19691998:19692198、chr6:25726972:25727172、chr6:25726976:25727176、chr6:26240701:26240901、chr6:26614581:26614781、chr6:28956573:28956773、chr6:29943274:29943548、chr6:30095659:30095859、chr6:30139864:30140064、chr6:31794591:31794960、chr6:31830341:31830541、chr6:31830468:31830668、chr6:31830667:31830867、chr6:31830678:31830878、chr6:31830923:31831123、chr6:31915034:31915355、chr6:35454222:35454562、chr6:38683053:38683380、chr6:41606328:41606528、chr6:43044256:43044549、chr6:43970712:43970912、chr6:45631459:45631659、chr6:50818154:50818354、chr6:53213585:53213785、chr6:56716287:56716518、chr6:73331227:73331529、chr6:73332056:73332325、chr6:80656891:80657091、chr6:85476110:85476310、chr6:85476974:85477296、chr6:99291616:99291816、chr6:99295870:99296149、chr6:100050801:100051143、chr6:100895021:100895221、chr6:100905428:100905673、chr6:105584422:105584622、chr6:105584524:105584724、chr6:106429583:106429783、chr6:106547117:106547340、chr6:108353111:108353501、chr6:108440609:108440859、chr6:108488634:108488917、chr6:108490998:108491321、chr6:108495586:108495940、chr6:118229139:118229400、chr6:125283715:125283915、chr6:133562461:133562661、chr6:134210963:134211163、chr6:137244436:137244636、chr6:137244902:137245102、chr6:137814694:137814894、chr6:142410001:142410201、chr6:150285273:150285473、chr6:150285715:150285915、chr6:152623048:152623248、chr6:152623335:152623535、chr6:154360602:154360817、chr6:160500387:160500620、chr6:160500917:160501117、chr6:160769603:160769864、chr6:163818059:163818259、chr6:166580183:166580476、chr6:166582802:166583088、chr6:166970625:166970825、chr6:167544878:167545117、chr7:391421:391621、chr7:853051:853251、chr7:966059:966259、chr7:1275110:1275310、chr7:1275496:1275696、chr7:1387486:1387767、chr7:2237966:2238356、chr7:2545233:2545433、chr7:4848607:4848995、chr7:4859554:4859825、chr7:6545818:6546018、chr7:6560118:6560318、chr7:6560383:6560583、chr7:6703799:6704025、chr7:8482114:8482413、chr7:10516254:10516562、chr7:19145945:19146145、chr7:19152085:19152381、chr7:19156506:19156764、chr7:20823981:20824181、chr7:21582970:21583352、chr7:24323230:24323430、chr7:24323597:24323836、chr7:24323937:24324310、chr7:26416199:26416400、chr7:27157175:27157375、chr7:27191701:27191901、chr7:27204459:27204659、chr7:27204968:27205168、chr7:27206030:27206230、chr7:27213867:27214119、chr7:27225030:27225230、chr7:27225312:27225538、chr7:27244589:27244789、chr7:27252672:27252872、chr7:27260117:27260462、chr7:27286084:27286380、chr7:27291262:27291557、chr7:28998040:28998368、chr7:29605610:29605810、chr7:29605867:29606083、chr7:30721539:30721739、chr7:30721998:30722198、chr7:30722316:30722516、chr7:35293630:35293958、chr7:35297071:35297271、chr7:35297370:35297570、chr7:35301095:35301411、chr7:35494447:35494647、chr7:37487651:37487851、chr7:37488184:37488384、chr7:37488376:37488576、chr7:42267684:42267940、chr7:43152215:43152415、chr7:44185174:44185374、chr7:45438663:45438984、chr7:49813454:49813654、chr7:49814916:49815116、chr7:49815508:49815708、chr7:50343949:50344149、chr7:50344442:50344642、chr7:54612253:54612453、chr7:54612256:54612456、chr7:64030126:64030403、chr7:64349425:64349625、chr7:64349788:64349988、chr7:64349912:64350112、chr7:67016160:67016360、chr7:67935878:67936078、chr7:70111531:70111731、chr7:70596191:70596436、chr7:70596972:70597239、chr7:70597944:70598290、chr7:71801989:71802189、chr7:73407894:73408161、chr7:84816240:84816440、chr7:87229732:87230069、chr7:87848176:87848376、chr7:93519986:93520213、chr7:96622040:96622409、chr7:96650220:96650420、chr7:96650624:96650824、chr7:97361415:97361615、chr7:97361699:97361899、chr7:100075176:100075453、chr7:100091203:100091483、chr7:100318439:100318639、chr7:100660590:100660790、chr7:107499318:107499518、chr7:113723311:113723551、chr7:116963383:116963583、chr7:121950595:121950907、chr7:127176970:127177170、chr7:127672113:127672313、chr7:127744150:127744731、chr7:128337485:128337748、chr7:128430732:128430960、chr7:134143728:134144119、chr7:137531918:137532187、chr7:139168541:139168844、chr7:139208240:139208520、chr7:140340353:140340553、chr7:145813731:145813931、chr7:145813955:145814155、chr7:149917105:149917305、chr7:150069026:150069233、chr7:150069569:150069875、chr7:151478298:151478548、chr7:152622494:152622712、chr7:152622815:152623286、chr7:153584765:153585074、chr7:153585316:153585516、chr7:155164914:155165222、chr7:155167506:155167719、chr7:155258993:155259193、chr7:155260929:155261194、chr7:155302221:155302618、chr7:156029367:156029567、chr7:156797100:156797300、chr7:157372332:157372649、chr7:157477681:157477881、chr7:157478267:157478467、chr7:157481309:157481509、chr7:157481934:157482234、chr7:157486000:157486283、chr7:157670084:157670284、chr7:157744228:157744428、chr7:157794583:157794783、chr7:158030636:158030992、chr7:158936544:158936744、chr7:158937005:158937205、chr7:158937490:158937706、chr7:158937984:158938184、chr8:429523:429830、chr8:686927:687127、chr8:687377:687577、chr8:3549446:3549646、chr8:4849899:4850110、chr8:10588811:10589173、chr8:16884512:16884816、chr8:20375580:20375780、chr8:21647523:21647723、chr8:22438141:22438341、chr8:22457092:22457292、chr8:22876154:22876354、chr8:23020937:23021137、chr8:23564023:23564306、chr8:23564051:23564251、chr8:24772344:24772544、chr8:25907762:25907962、chr8:27183182:27183555、chr8:37655479:37655700、chr8:41424527:41424742、chr8:41753645:41753845、chr8:49292322:49292522、chr8:55366344:55366577、chr8:55366749:55366949、chr8:55370383:55370609、chr8:55370701:55370901、chr8:55371779:55371979、chr8:55379155:55379355、chr8:55379910:55380110、chr8:55382662:55382862、chr8:57069546:57069746、chr8:57069819:57070019、chr8:57358434:57358672、chr8:57358854:57359054、chr8:61788861:61789200、chr8:65282197:65282431、chr8:65493661:65493861、chr8:67873708:67873908、chr8:67874783:67874983、chr8:69243166:69243493、chr8:69243680:69243962、chr8:70946907:70947107、chr8:70981921:70982121、chr8:70982810:70983191、chr8:70983528:70983793、chr8:70984167:70984544、chr8:72756154:72756354、chr8:72917538:72917738、chr8:80803510:80803710、chr8:86350778:86350978、chr8:92607079:92607414、chr8:97157461:97157847、chr8:97170347:97170653、chr8:97171974:97172174、chr8:97506340:97506540、chr8:99951835:99952035、chr8:99952076:99952276、chr8:99952536:99952797、chr8:99960396:99960596、chr8:99986572:99986772、chr8:99986831:99987031、chr8:101118382:101118582、chr8:101661784:101661984、chr8:104153124:104153364、chr8:104512705:104512905、chr8:105235524:105235724、chr8:105479044:105479244、chr8:116679728:116679928、chr8:120684496:120684696、chr8:124173191:124173417、chr8:127569252:127569452、chr8:128750778:128751098、chr8:129103499:129103699、chr8:132052200:132052576、chr8:132053071:132053271、chr8:132054575:132054776、chr8:140715944:140716144、chr8:141231103:141231303、chr8:142428149:142428349、chr8:143541276:143541476、chr8:143613404:143613604、chr8:143613755:143613955、chr8:143694277:143694673、chr8:143956598:143956798、chr8:145048031:145048231、chr8:145105489:145105984、chr8:145106299:145106499、chr8:145106620:145106820、chr9:117804:118004、chr9:841555:841878、chr9:1042644:1042844、chr9:2157701:2157901、chr9:3181252:3181452、chr9:13323124:13323324、chr9:14346823:14347137、chr9:19788555:19788755、chr9:19789033:19789233、chr9:21974601:21974801、chr9:34623748:34623952、chr9:36986533:36986733、chr9:68413067:68413267、chr9:71788607:71788807、chr9:71788926:71789126、chr9:79637962:79638162、chr9:80262750:80263114、chr9:96711549:96711871、chr9:97369640:97369840、chr9:97807408:97807608、chr9:97807618:97807818、chr9:98789698:98790082、chr9:99482113:99482344、chr9:100616444:100616644、chr9:110187518:110187718、chr9:110228416:110228616、chr9:111929248:111929602、chr9:113800938:113801238、chr9:122918680:122918880、chr9:124461377:124461663、chr9:126348875:126349266、chr9:126774925:126775125、chr9:126776181:126776455、chr9:126778194:126778644、chr9:126780941:126781141、chr9:127257997:127258338、chr9:127265715:127265915、chr9:129377423:129377776、chr9:129387197:129387429、chr9:129445386:129445586、chr9:131012698:131012898、chr9:132382275:132382649、chr9:135462468:135462668、chr9:137028497:137028697、chr9:137028843:137029043、chr9:139393876:139394111、chr9:140051215:140051415、chr9:140683687:140683969、chr9:141013967:141014167、chrX:8698966:8699166。
如图7所示,一种检测肺结节良恶性的甲基化标志物的评估模型,包括以下步骤:
(1)收集肺结节良性样本和恶性样本,分为训练集和测试集;
(2)提取训练集样本的cfDNA,构建甲基化靶向测序文库,并进行测序;
(3)对序列进行甲基化转化处理、数据比对,计算甲基化分值;
(4)对训练集样本数据进行特征矩阵构建,获得评估模型;
(5)用测试集样本数据验证模型的效果。
本发明通过收集肺结节良性样本和恶性样本,分为训练集和测试集,提取训练集样本的cfDNA,构建甲基化靶向测序文库,并进行测序,对序列进行甲基化转化处理、数据比对,计算甲基化分值,对训练集样本数据进行特征矩阵构建,获得评估模型,用测试集样本数据验证模型的效果,因此能够区分良性和恶性的肺结节,从而实现肺结节无创精准辨析的目的。
优选地,所述步骤(2)中,使用MethylTitan方法构建甲基化靶向测序文库,包括以下分步骤:
(2.1)根据生产商的操作指南,使用Methylcode亚硫酸氢盐转化试剂盒对 cfDNA进行亚硫酸氢盐转化;
(2.2)转化产物经去磷酸化后,连接到具有UMI 的通用接头上;
(2.3)连接产物作为模板进行第二链合成,合成产物经纯化后,作为模板使用PCR技术和专用引物panel进行一轮半靶向扩增;
(2.4)PCR产物纯化后作为底物进行第二轮 PCR,以添加样本特异性条形码和全长测序接头,纯化后的第二轮PCR产物为测序文库。
优选地,所述步骤(2)中,测序包括:使用KAPA 文库定量试剂盒KK4844对文库进行定量,并在Illumina NextSeq 500/550测序仪上以双端150 个碱基模式进行测序,每个样本至少需要4M reads。
优选地,所述步骤(3)中使用pear软件包合并来源于潜在相同片段的双端reads,以选择高质量的原始 cfDNA 片段;使用trim_galore软件包切除片段末端的接头序列,然后从每条read中提取UMI;经过上述处理的reads被比对到 CT 和 GA 转换后的人类基因组参考序列上,经 UMI 去重后,获得reads中各CpG位点甲基化信号。
优选地,所述步骤(3)中,为减少随机因素的干扰,排除原始panel中10个CpG位点数少于3的区域,剩余1646个甲基化区域进行后续分析,计算甲基化分值,包括以下分步骤:
(3.1)每个靶点区域read编码:该区域内的每条read都被转化为一个向量,其长度等于CpG位点的数量;甲基化位点编码为2,非甲基化位点编码为1,未覆盖位点编码为0;
(3.2)每个靶点区域的read建模:在每个靶点区域,基于read编码向量训练结节良恶性模型,计算出read来源肺癌的概率;
(3.3)统计区域特征:对于每个样本的每个靶点区域,将概率数值分箱为14组,从0到1,统计每个组中的read数量和频率,以及该区域的read总数,得到一个长度为29的向量作为该区域特征;
(3.4)区域建模:对于每个靶点区域训练良恶性打分模型,评估区域来源于肺癌的概率,作为区域甲基化特征分值。
还提供了另一种检测肺结节良恶性的甲基化标志物的评估模型,包括以下步骤:
(I)训练集队列样本被随机分成五组,用于后续进行5折交叉验证,使用深度神经网络模型鉴别肺结节良恶性,模型包括:一个输入层,包含神经元数量与输入特征相同;输入层后接三个隐藏层,分别包含32、16、8个神经元;最后连接一个包含2个神经元的输出层;在输入层前设计一个批量归一化层;除输出层使用Sigmoid函数外,其他层都采用ReLU激活函数;模型采用Adam优化器和交叉熵损失函数进行训练,使用Keras构建这些模型,模型使用5折交叉验证方法,每次在训练样本80%样本上进行训练,在剩下20%样本进行验证;预测测试集样本时,5个交叉验证分类器预测分数的平均值作为最终预测结果;
(II)最终训练好的肺结节良恶性鉴别模型在训练集和测试集中获得受试者工作特征曲线下面积值AUC;
(III)模型决策曲线分析:为评估模型的潜在临床效用,采用决策曲线分析来评估模型决策净受益,对于不同的阈值,模型分数超过阈值的样本标记为干预对象,而得分低于阈值的样本则保持未处理;通过将真阳性样本的受益与假阳性的损益进行加权,计算出每个阈值下模型的净受益,对于表示无治疗的曲线净受益设为0,对于治疗所有患者的曲线,净益与y轴相交,相交值为对应恶性样本比例,当模型的净益在广泛范围内持续超过两个极端曲线的净益时,表明选择的阈值范围相对较为安全。
还提供了检测肺结节良恶性的甲基化标志物的评估模型在制备肺癌早筛产品中的应用。
下面对本发明的具体实施例做详细说明。
1、甲基化测序文库构建和甲基化单倍型
MethylTitan方法构建甲基化靶向测序文库,首先根据生产商的操作指南,使用Methylcode亚硫酸氢盐转化试剂盒(ThermoFisher,MECOV50) 对 cfDNA 进行亚硫酸氢盐转化。转化产物经去磷酸化后,连接到具有UMI 的通用接头上。连接产物作为模板进行第二链合成。合成产物经纯化后,作为模板使用PCR技术和专用引物panel进行一轮半靶向扩增。PCR产物纯化后作为底物进行第二轮 PCR,以添加样本特异性条形码和全长测序接头。纯化后的第二轮PCR产物即为测序文库。使用KAPA 文库定量试剂盒(KK4844) 对文库进行定量,并在 Illumina NextSeq 500/550测序仪上以双端150 个碱基模式进行测序,每个样本至少需要4M reads。
使用pear软件包(版本0.9.6)合并来源于潜在相同片段的双端reads,以选择高质量的原始 cfDNA 片段。使用trim_galore软件包(版本0.4.0)切除片段末端的接头序列,然后从每条read中提取UMI。经过上述处理的reads被比对到 CT 和 GA 转换后的人类基因组参考序列(版本hg19)上,经 UMI 去重后的可获得reads中各CpG位点甲基化信号。
2、甲基化分值计算
为减少随机因素的干扰,排除原始panel中10个CpG位点数少于3的区域,剩余1646个甲基化区域进行后续分析。区域甲基化特征分值(MMS)包括如下步骤(参见图1):1)每个靶点区域read编码:该区域内的每条read都被转化为一个向量,其长度等于CpG位点的数量。甲基化位点编码为2,非甲基化位点编码为1,未覆盖位点编码为0;2)每个靶点区域的read建模:在每个靶点区域,基于read编码向量训练结节良恶性模型,可计算出read来源肺癌的概率;3)统计区域特征:对于每个样本的每个靶点区域,将概率数值分箱为14组(从0到1),统计每个组中的read数量和频率,以及该区域的read总数,得到一个长度为29的向量作为该区域特征;4)区域建模:对于每个靶点区域训练良恶性打分模型,可以评估区域来源于肺癌的概率,即是区域甲基化特征分值。
实施例1 肺结节良恶性模型构建
1)入组样本:前瞻性从多个中心入组419例5-30mm的肺结节患者样本,包含211恶性肺结节样本和208例良性肺结节样本。恶性样本均由术后病理确认,良性样本由术后病理或者专家综合评估确认。所有样本分为训练集和独立测试集(参见图2)。训练集包括162个良性结节和162个恶性结节,其性别和年龄完全匹配。测试集包含46个良性和49个恶性样本。恶性样本主要为早期癌症(0期-Ⅰ期),具体信息见表1。
表1
2)构建模型:首先训练集队列样本被随机分成五组,用于后续进行5折交叉验证(注意后续模型训练中该分组保持一致,不做变更)。使用深度神经网络模型鉴别肺结节良恶性。模型包括一个输入层,包含神经元数量与输入特征相同。输入层后接三个隐藏层,分别包含32、16、8个神经元。最后连接一个包含2个神经元的输出层。在输入层前设计一个批量归一化层(参见图2)。除最后输出层使用Sigmoid函数外,其他层都采用ReLU激活函数。模型采用Adam优化器和交叉熵损失函数进行训练,使用Keras(版本2.4.3)构建这些模型。模型使用5折交叉验证方法,每次在训练样本80%样本上进行训练,在剩下20%样本进行验证。预测测试集样本时,5个交叉验证分类器预测分数的平均值作为最终预测结果。
3)良恶性鉴别模型效果:最终训练好的肺结节良恶性鉴别模型在训练集和测试集中获得较高的受试者工作特征曲线下面积值(area under the receiver operatingcharacteristic curve,简称AUC),分别为0.824(95%置信区间,0.789-0.860)和0.799(0.72-0.869) (参见图3)。当选取阈值为0.514时,训练集达到0.667(0.59-0.736)的敏感度和0.802(0.732-0.859)的特异性,而测试集的敏感度和特异性分别为0.776(0.634-0.874)和0.609(0.456-0.741)。
4)模型决策曲线分析:为评估模型的潜在临床效用,我们采用决策曲线分析(decision curve analysis,DCA)来评估模型决策净受益(net benifit)情况。对于不同的阈值,模型分数超过阈值的样本标记为干预对象,而得分低于阈值的样本则保持未处理。通过将真阳性样本的受益与假阳性的损益进行加权,可以计算出每个阈值下模型的净受益。对于表示无治疗的曲线净受益设为0。对于治疗所有患者的曲线,净益与y轴相交,相交值为对应恶性样本比例。当模型的净益在广泛范围内持续超过两个极端曲线的净益时,这表明我们选择的阈值范围相对较为安全。与治疗所有患者的策略相比,我们的综合模型在测试集中在阈值概率超过0.2时在预测恶性风险方面表现出更高的净益(参见图4)。在0.2和0.9之间的阈值范围内,模型相对于全治疗策略和无治疗策略,始终保持较高的净受益。上述结果表明,基于甲基化构建的良恶性鉴别模型有助于肺结节进行更好的诊疗决策。
5)协变量和对预测结果的影响:虽然训练集中平衡了年龄、性别人口学因素,但是测试集中良性结节患者平均年龄为48.5岁,恶性结节患者平均年龄59.5岁,差异显著(P<0.001)。为评估模型预测结果是否会受到年龄性别因素的影像,对不同年龄段(<60周岁、和>=60周岁组)和不同性别内的良性和恶性结节的预测结果进行比较。测试集中结果显示,各年龄组的良性结节患者,或者各年龄组的恶性结节患者模型预测分值无显著差异(图5A)。男性恶性结节和女性结节患者之间也无显著差异,仅男性良性结节和女性良性结节患者存在差异(图5B)。因此,构建的结节良恶性鉴别模型基本不受上述因素的影响,具有较好稳定性。
实施例2 减少靶点数量对模型性能的影响
为了验证模型对于靶点数量的鲁棒性,首先随机抽取800个甲基化标志物,同样采用五折交叉验证方法构建肺结节良恶性鉴别模型。基于这些甲基化标志物和影像特征构建模型结果显示(图6A),训练集中AUC为0.829(0.792-0.867),灵敏度、特异性分别是0.673(0.596-0.741),0.802(0.732-0.859)。该模型在测试集中同样得到验证,AUC、灵敏度和特异性分别是0.793(0.712-0.867),0.694(0.551-0.808),0.717(0.566-0.83)。
甚至进一步将甲基化标志物缩减到500个,然后采用相同的框架建立模型。在训练集上进行交叉验证结果显示(图6B),AUC、灵敏度和特异性分别是0.778(0.733-0.820),0.617(0.54-0.691),0.802(0.732-0.859)。在测试集上进行验证的AUC、灵敏度和特异性分别是0.779(0.694-0.848),0.592(0.449-0.727),0.783(0.642-0.884)。
最后随机将甲基化标志物缩减至200个,最后训练的模型在测试集、验证集AUC分别是0.772(0.730-0.813),0.773(0.691-0.851),见图6C。训练集灵敏度、特异性分别是0.574(0.497-0.648),0.802(0.732-0.859)。测试集灵敏度、特异性分别是0.551(0.387-0.665),0.761(0.62-0.865)。
以上结果表明,基于1646个甲基化随机抽取的某个子集,即使特征数量少于全体1/2(800个),或者少于1/3(500个),甚至少于1/7(200个),所建立的模型预测性能略低于基于全部特征建立的模型,但是在训练集和测试中同样能较好的预测肺结节恶性风险程度,这表明基于这些甲基化、蛋白质标志物以及影像特征构建模型具有较高地鲁棒性。
以上所述,仅是本发明的较佳实施例,并非对本发明作任何形式上的限制,凡是依据本发明的技术实质对以上实施例所作的任何简单修改、等同变化与修饰,均仍属本发明技术方案的保护范围。
Claims (10)
1.检测肺结节良恶性的甲基化标志物,其特征在于:其按照染色体号:起始位置:终止位置的形式表示为以下的一种或多种:chr1:933461:933661、chr1:3663636:3663836、chr1:6508884:6509216、chr1:44873719:44873992、chr1:45252250:45252450、chr1:47910604:47910804、chr1:110612484:110612811、chr1:121260989:121261197、chr1:170630461:170630661、chr1:170630779:170630979、chr1:200004695:200004895、chr1:201709024:201709286、chr1:205411615:205411981、chr1:224804424:224804624、chr1:235098930:235099329、chr1:246952449:246952649、chr1:247590046:247590246、chr10:8094136:8094336、chr10:13771226:13771426、chr10:17271282:17271482、chr10:31446731:31446960、chr10:90342715:90342915、chr10:94822235:94822435、chr10:94834720:94834941、chr10:123923943:123924143、chr10:134862367:134862608、chr11:420350:420632、chr11:44325796:44325997、chr11:60620057:60620257、chr11:71954948:71955148、chr11:112834110:112834416、chr12:2282090:2282290、chr12:56123713:56123969、chr12:58013516:58013716、chr12:58021334:58021534、chr12:111404033:111404233、chr12:114846856:114847056、chr12:115124911:115125191、chr12:117798974:117799174、chr12:131418421:131418662、chr13:53389452:53389724、chr13:112726305:112726505、chr14:92040784:92040984、chr14:105830716:105830916、chr14:105933578:105934099、chr14:105940490:105940690、chr15:27113277:27113477、chr15:41218552:41218752、chr15:45670805:45671005、chr16:1037548:1037773、chr16:70771579:70771798、chr16:73097098:73097298、chr17:4802704:4803018、chr17:46669698:46669912、chr17:48546661:48546861、chr17:59481932:59482132、chr17:59564663:59565040、chr17:70112878:70113078、chr17:77721969:77722169、chr17:79952445:79952705、chr17:80745056:80745446、chr18:19746190:19746390、chr18:56940384:56940584、chr19:1769662:1769862、chr19:2278515:2278790、chr19:2790947:2791147、chr19:4713626:4713906、chr19:13125272:13125472、chr19:17008293:17008493、chr19:30713626:30713826、chr19:30716857:30717057、chr19:36389819:36390152、chr19:41317070:41317270、chr19:46974860:46975063、chr19:48918862:48919062、chr2:264146:264484、chr2:45228238:45228463、chr2:114034391:114034591、chr2:115919417:115919617、chr2:131721743:131721943、chr2:176994745:176995040、chr2:177016992:177017370、chr2:177024578:177024778、chr2:177029433:177029647、chr2:177030134:177030449、chr20:590590:590790、chr20:61318785:61319012、chr20:62053011:62053327、chr20:62854302:62854579、chr21:45328459:45328682、chr22:19753961:19754161、chr22:22005999:22006199、chr22:22862794:22862994、chr22:22862846:22863046、chr22:29704450:29704650、chr22:46403741:46403941、chr22:50718628:50718828、chr3:5137616:5137816、chr3:46940237:46940437、chr3:48699053:48699253、chr3:69230395:69230599、chr3:157823001:157823300、chr3:170303686:170303888、chr3:181443236:181443436、chr3:194118929:194119129、chr3:196387720:196387920、chr4:1015769:1016117、chr4:1016350:1016717、chr4:1399902:1400261、chr4:144621462:144621662、chr4:183369409:183369609、chr5:2007790:2007990、chr5:16179948:16180148、chr5:37840176:37840376、chr5:92939735:92939935、chr5:139076623:139076941、chr5:139525754:139525954、chr5:140864704:140864904、chr5:140871317:140871517、chr5:140871596:140871805、chr5:178016519:178016719、chr5:178016963:178017163、chr6:2903381:2903581、chr6:26240701:26240901、chr6:38683053:38683380、chr6:137244436:137244636、chr6:137244902:137245102、chr6:166580183:166580476、chr7:19152085:19152381、chr7:27157175:27157375、chr7:27291262:27291557、chr7:54612256:54612456、chr7:87229732:87230069、chr7:93519986:93520213、chr7:96650220:96650420、chr7:100091203:100091483、chr8:20375580:20375780、chr8:22438141:22438341、chr8:22457092:22457292、chr8:55379155:55379355、chr8:61788861:61789200、chr8:67874783:67874983、chr8:99952076:99952276、chr8:99960396:99960596、chr8:104512705:104512905、chr9:14346823:14347137、chr9:36986533:36986733、chr9:71788607:71788807、chr9:110187518:110187718、chr9:127265715:127265915、chr9:141013967:141014167。
2.根据权利要求1所述的检测肺结节良恶性的甲基化标志物的评估模型,其特征在于:其包括以下步骤:
(1)收集肺结节良性样本和恶性样本,分为训练集和测试集;
(2)提取样本的cfDNA,构建甲基化靶向测序文库,并进行测序;
(3)对序列进行甲基化转化处理、数据比对,计算甲基化分值;
(4)对训练集样本数据进行特征矩阵构建,获得评估模型;
(5)用测试集样本数据验证模型的效果。
3.根据权利要求2所述的检测肺结节良恶性的甲基化标志物的评估模型,其特征在于:所述步骤(2)中,使用MethylTitan方法构建甲基化靶向测序文库,包括以下分步骤:
(2.1)根据生产商的操作指南,使用Methylcode亚硫酸氢盐转化试剂盒对 cfDNA 进行亚硫酸氢盐转化;
(2.2)转化产物经去磷酸化后,连接到具有UMI 的通用接头上;
(2.3)连接产物作为模板进行第二链合成,合成产物经纯化后,作为模板使用PCR技术和专用引物panel进行一轮半靶向扩增;
(2.4)PCR产物纯化后作为底物进行第二轮 PCR,以添加样本特异性条形码和全长测序接头,纯化后的第二轮PCR产物为测序文库。
4.根据权利要求3所述的检测肺结节良恶性的甲基化标志物的评估模型,其特征在于:所述步骤(2)中,测序包括:使用KAPA 文库定量试剂盒KK4844对文库进行定量,并在Illumina NextSeq 500/550测序仪上以双端150 个碱基模式进行测序,每个样本至少需要4M reads。
5.根据权利要求4所述的检测肺结节良恶性的甲基化标志物的评估模型,其特征在于:所述步骤(3)中使用pear软件包合并来源于潜在相同片段的双端reads,以选择高质量的原始 cfDNA 片段;使用trim_galore软件包切除片段末端的接头序列,然后从每条read中提取UMI;经过上述处理的reads被比对到 CT 和 GA 转换后的人类基因组参考序列上,经UMI 去重后,获得reads中各CpG位点甲基化信号。
6.根据权利要求5所述的检测肺结节良恶性的甲基化标志物的评估模型,其特征在于:所述步骤(3)中,为减少随机因素的干扰,排除原始panel中10个CpG位点数少于3的区域,剩余1646个甲基化区域进行后续分析,计算甲基化分值,包括以下分步骤:
(3.1)每个靶点区域read编码:该区域内的每条read都被转化为一个向量,其长度等于CpG位点的数量;甲基化位点编码为2,非甲基化位点编码为1,未覆盖位点编码为0;
(3.2)每个靶点区域的read建模:在每个靶点区域,基于read编码向量训练结节良恶性模型,计算出read来源肺癌的概率;
(3.3)统计区域特征:对于每个样本的每个靶点区域,将概率数值分箱为14组,从0到1,统计每个组中的read数量和频率,以及该区域的read总数,得到一个长度为29的向量作为该区域特征;
(3.4)区域建模:对于每个靶点区域训练良恶性打分模型,评估区域来源于肺癌的概率,作为区域甲基化特征分值。
7.根据权利要求1所述的检测肺结节良恶性的甲基化标志物的评估模型,其特征在于:其包括如下步骤:
(I)训练集队列样本被随机分成五组,用于后续进行5折交叉验证,使用深度神经网络模型鉴别肺结节良恶性,模型包括:一个输入层,包含神经元数量与输入特征相同;输入层后接三个隐藏层,分别包含32、16、8个神经元;最后连接一个包含2个神经元的输出层;在输入层前设计一个批量归一化层;除输出层使用Sigmoid函数外,其他层都采用ReLU激活函数;模型采用Adam优化器和交叉熵损失函数进行训练,使用Keras构建这些模型,模型使用5折交叉验证方法,每次在训练样本80%样本上进行训练,在剩下20%样本进行验证;预测测试集样本时,5个交叉验证分类器预测分数的平均值作为最终预测结果;
(II)最终训练好的肺结节良恶性鉴别模型在训练集和测试集中获得受试者工作特征曲线下面积值AUC;
(III)模型决策曲线分析:为评估模型的潜在临床效用,采用决策曲线分析来评估模型决策净受益,对于不同的阈值,模型分数超过阈值的样本标记为干预对象,而得分低于阈值的样本则保持未处理;通过将真阳性样本的受益与假阳性的损益进行加权,计算出每个阈值下模型的净受益,对于表示无治疗的曲线净受益设为0,对于治疗所有患者的曲线,净益与y轴相交,相交值为对应恶性样本比例,当模型的净益在广泛范围内持续超过两个极端曲线的净益时,表明选择的阈值范围相对较为安全。
8.根据权利要求7所述的检测肺结节良恶性的甲基化标志物的评估模型,其特征在于:将年龄、性别作为协变量,分析对预测结果的影响。
9.根据权利要求7所述的检测肺结节良恶性的甲基化标志物的评估模型,其特征在于:减少靶点数量,分析对模型性能的影响。
10.根据权利要求2或7所述的检测肺结节良恶性的甲基化标志物的评估模型在制备肺癌早筛产品中的应用。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410599937.9A CN118166108A (zh) | 2024-05-15 | 2024-05-15 | 检测肺结节良恶性的甲基化标志物、评估模型及应用 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410599937.9A CN118166108A (zh) | 2024-05-15 | 2024-05-15 | 检测肺结节良恶性的甲基化标志物、评估模型及应用 |
Publications (1)
Publication Number | Publication Date |
---|---|
CN118166108A true CN118166108A (zh) | 2024-06-11 |
Family
ID=91359231
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410599937.9A Pending CN118166108A (zh) | 2024-05-15 | 2024-05-15 | 检测肺结节良恶性的甲基化标志物、评估模型及应用 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118166108A (zh) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112080555A (zh) * | 2019-06-14 | 2020-12-15 | 上海鹍远健康科技有限公司 | Dna甲基化检测试剂盒及检测方法 |
WO2022161076A1 (zh) * | 2021-01-27 | 2022-08-04 | 广州市基准医疗有限责任公司 | 用于肺结节良恶性检测的甲基化标记物或其组合及应用 |
CN116356021A (zh) * | 2023-02-28 | 2023-06-30 | 复旦大学附属中山医院 | 基于cfDNA靶向甲基化测序多维度特征的常见消化系统癌症早检技术 |
CN116804218A (zh) * | 2022-03-16 | 2023-09-26 | 江苏鹍远生物科技股份有限公司 | 用于检测肺结节良恶性的甲基化标志物及其应用 |
CN117133439A (zh) * | 2023-05-26 | 2023-11-28 | 福建省妇幼保健院 | 一种卵巢恶性和交界性肿瘤诊断模型构建方法 |
US20240084393A1 (en) * | 2020-12-17 | 2024-03-14 | Anchordx Medical Co., Ltd. | Dna methelation molecular markers for identifying benignity or malignancy of lung nodule and applications of the same |
-
2024
- 2024-05-15 CN CN202410599937.9A patent/CN118166108A/zh active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112080555A (zh) * | 2019-06-14 | 2020-12-15 | 上海鹍远健康科技有限公司 | Dna甲基化检测试剂盒及检测方法 |
US20240084393A1 (en) * | 2020-12-17 | 2024-03-14 | Anchordx Medical Co., Ltd. | Dna methelation molecular markers for identifying benignity or malignancy of lung nodule and applications of the same |
WO2022161076A1 (zh) * | 2021-01-27 | 2022-08-04 | 广州市基准医疗有限责任公司 | 用于肺结节良恶性检测的甲基化标记物或其组合及应用 |
CN116804218A (zh) * | 2022-03-16 | 2023-09-26 | 江苏鹍远生物科技股份有限公司 | 用于检测肺结节良恶性的甲基化标志物及其应用 |
CN116356021A (zh) * | 2023-02-28 | 2023-06-30 | 复旦大学附属中山医院 | 基于cfDNA靶向甲基化测序多维度特征的常见消化系统癌症早检技术 |
CN117133439A (zh) * | 2023-05-26 | 2023-11-28 | 福建省妇幼保健院 | 一种卵巢恶性和交界性肿瘤诊断模型构建方法 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113257350B (zh) | 基于液体活检的ctDNA突变程度分析方法和装置、ctDNA性能分析装置 | |
JP2021072774A (ja) | 染色体相互作用の部位を用いた検出法 | |
CN111128299B (zh) | 一种结直肠癌预后显著相关ceRNA调控网络的构建方法 | |
CN112086129B (zh) | 预测肿瘤组织cfDNA的方法及系统 | |
CN113838533B (zh) | 一种癌症检测模型及其构建方法和试剂盒 | |
CN109830264B (zh) | 肿瘤患者基于甲基化位点进行分类的方法 | |
CN112941180A (zh) | 一组肺癌dna甲基化分子标志物及其在制备用于肺癌早期诊断试剂盒中的应用 | |
CN111276252A (zh) | 一种肿瘤良恶性鉴别模型的构建方法及装置 | |
CN115087745A (zh) | 无细胞样品中的双末端dna片段类型及其用途 | |
CN115820860A (zh) | 基于增强子甲基化差异的非小细胞肺癌标志物筛选方法及其标志物和应用 | |
CN116356021A (zh) | 基于cfDNA靶向甲基化测序多维度特征的常见消化系统癌症早检技术 | |
CN111676291A (zh) | 一种用于肺癌患病风险评估的miRNA标志物 | |
CN118166108A (zh) | 检测肺结节良恶性的甲基化标志物、评估模型及应用 | |
CN116805509A (zh) | 结直肠癌免疫治疗预测标志物的构建方法及应用 | |
CN115976209A (zh) | 一种肺癌预测模型的训练方法以及预测装置和应用 | |
CN110819700A (zh) | 一种构建肺部小结节计算机辅助检测模型的方法 | |
WO2018209704A1 (zh) | 基于dna测序数据的样本来源检测方法、装置和存储介质 | |
CN114045337A (zh) | 基于肠道微生物的胆管癌非侵入性标志物筛选、分析方法及应用 | |
EP3635138B1 (en) | Method for analysing cell-free nucleic acids | |
CN111172285A (zh) | 用于胰腺癌早期诊断和/或预后监测的miRNA组及其应用 | |
Li et al. | Development and validation of a five-immune gene pair signature in endometrial carcinoma | |
CN111996255B (zh) | 结直肠恶性息肉的诊断标记物及其用途 | |
CN111094594A (zh) | 产生复数候选探针和鉴定哺乳动物中细胞类型的方法 | |
AU2004290440A1 (en) | Method to predict upper aerodigestive tract cancer | |
CN116790755A (zh) | 一种神经胶质瘤检测的标志物及其应用 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination |