我要使用tidyverse / dplyr命令创建几列
1）一列count，对唯一个人的数量进行滚动计数，直到至少已选择和个独立个人为止> lastObsG==1和lastObsGE==1（即已到达基因的末端）。一旦count超过30个人，计数应重新设置。
2）group列，指示每组〜30个人的组号。
根据突变位置对个体进行排序。
作为最小的工作示例，下面提供了我的数据集和创建变量lastObsG和lastObsGE的代码。我还提供了前40行的输出，其中包括多余的列以及应在其中显示的值。
编辑
根据@Alexis的评论，我的意思是，只要最后一个观察结果满足lastObsG==1和lastObsGE==1，每个组至少应包含30个人。从样本输出中可以看出，第1组中有4个重复的个体，因此应该对33个独特的个体中的37个观察值进行分组。
代码
library(dplyr)
df %>%
group_by(gene) %>%
mutate(lastObsFlagG = as.integer(row_number() == n())) %>%
group_by(gene,exon) %>%
mutate(lastObsFlagGE = as.integer(row_number() == n())) %>%
data.frame()
示例输出
ID gene exon mutation lastObsFlagG lastObsFlagGE count group
1 TCGA-AN-A046 OR4F5 E1 69767 1 1 1 1
2 TCGA-A2-A0CP SAMD11 E2 925952 1 1 2 1
3 TCGA-A8-A08H NOC2L E5 956126 0 1 3 1
4 TCGA-GM-A2DM NOC2L E4 956911 0 0 4 1
5 TCGA-GM-A2DM NOC2L E4 956912 1 1 4 1
6 TCGA-D8-A1XM KLHL17 E3 961658 0 1 5 1
7 TCGA-BH-A18G KLHL17 E5 962441 0 1 6 1
8 TCGA-3C-AALI KLHL17 E8 963353 0 1 7 1
9 TCGA-AC-A62Y KLHL17 E9 964004 1 1 8 1
10 TCGA-AR-A2LE PLEKHN1 E1 966556 0 1 9 1
11 TCGA-E2-A14N PLEKHN1 E5 970728 0 1 10 1
12 TCGA-AO-A0J4 PLEKHN1 E12 973506 1 1 11 1
13 TCGA-D8-A1J9 HES4 E3 999551 1 1 12 1
14 TCGA-EW-A1PH ISG15 E2 1014276 1 1 13 1
15 TCGA-A2-A0T0 AGRN E2 1022338 0 1 14 1
16 TCGA-GM-A2DD AGRN E3 1035303 0 1 15 1
17 TCGA-5L-AAT1 AGRN E4 1040690 0 1 16 1
18 TCGA-OL-A5RW AGRN E8 1043314 0 1 17 1
19 TCGA-D8-A27M AGRN E25 1049355 0 1 18 1
20 TCGA-AR-A1AI AGRN E29 1050430 0 1 19 1
21 TCGA-5L-AAT0 AGRN E36 1055374 0 0 20 1
22 TCGA-5L-AAT0 AGRN E36 1055376 0 0 20 1
23 TCGA-C8-A8HP AGRN E36 1055442 1 1 21 1
24 TCGA-A7-A4SD TTLL10 E13 1184971 1 1 22 1
25 TCGA-BH-A1F0 SDF4 E4 1223283 0 0 23 1
26 TCGA-AO-A128 SDF4 E4 1223330 0 1 24 1
27 TCGA-E9-A1R0 SDF4 E2 1228592 1 1 25 1
28 TCGA-A2-A04P UBE2J2 E7 1255246 0 0 26 1
29 TCGA-C8-A274 UBE2J2 E7 1255342 1 1 27 1
30 TCGA-5L-AAT1 SCNN1D E1 1281422 0 1 27 1
31 TCGA-AO-A128 SCNN1D E6 1287116 0 1 27 1
32 TCGA-E2-A15R SCNN1D E7 1287596 0 1 28 1
33 TCGA-AC-A62V SCNN1D E11 1290543 1 1 29 1
34 TCGA-BH-A18V ACAP3 E22 1294187 0 1 30 1
35 TCGA-A7-A6VX ACAP3 E6 1300640 0 1 31 1
36 TCGA-GM-A2DB ACAP3 E3 1303170 0 0 32 1
37 TCGA-EW-A1IY ACAP3 E3 1303176 1 1 33 1
38 TCGA-D8-A1XQ CPSF3L E9 1313879 0 0 5 2
39 TCGA-5L-AAT1 CPSF3L E9 1313888 0 1 6 2
40 TCGA-C8-A26Y CPSF3L E7 1314919 0 1 7 2
数据集
"ID" "gene" "exon" "mutation"
"TCGA-AN-A046" "OR4F5" "E1" 69767
"TCGA-A2-A0CP" "SAMD11" "E2" 925952
"TCGA-A8-A08H" "NOC2L" "E5" 956126
"TCGA-GM-A2DM" "NOC2L" "E4" 956911
"TCGA-GM-A2DM" "NOC2L" "E4" 956912
"TCGA-D8-A1XM" "KLHL17" "E3" 961658
"TCGA-BH-A18G" "KLHL17" "E5" 962441
"TCGA-3C-AALI" "KLHL17" "E8" 963353
"TCGA-AC-A62Y" "KLHL17" "E9" 964004
"TCGA-AR-A2LE" "PLEKHN1" "E1" 966556
"TCGA-E2-A14N" "PLEKHN1" "E5" 970728
"TCGA-AO-A0J4" "PLEKHN1" "E12" 973506
"TCGA-D8-A1J9" "HES4" "E3" 999551
"TCGA-EW-A1PH" "ISG15" "E2" 1014276
"TCGA-A2-A0T0" "AGRN" "E2" 1022338
"TCGA-GM-A2DD" "AGRN" "E3" 1035303
"TCGA-5L-AAT1" "AGRN" "E4" 1040690
"TCGA-OL-A5RW" "AGRN" "E8" 1043314
"TCGA-D8-A27M" "AGRN" "E25" 1049355
"TCGA-AR-A1AI" "AGRN" "E29" 1050430
"TCGA-5L-AAT0" "AGRN" "E36" 1055374
"TCGA-5L-AAT0" "AGRN" "E36" 1055376
"TCGA-C8-A8HP" "AGRN" "E36" 1055442
"TCGA-A7-A4SD" "TTLL10" "E13" 1184971
"TCGA-BH-A1F0" "SDF4" "E4" 1223283
"TCGA-AO-A128" "SDF4" "E4" 1223330
"TCGA-E9-A1R0" "SDF4" "E2" 1228592
"TCGA-A2-A04P" "UBE2J2" "E7" 1255246
"TCGA-C8-A274" "UBE2J2" "E7" 1255342
"TCGA-5L-AAT1" "SCNN1D" "E1" 1281422
"TCGA-AO-A128" "SCNN1D" "E6" 1287116
"TCGA-E2-A15R" "SCNN1D" "E7" 1287596
"TCGA-AC-A62V" "SCNN1D" "E11" 1290543
"TCGA-BH-A18V" "ACAP3" "E22" 1294187
"TCGA-A7-A6VX" "ACAP3" "E6" 1300640
"TCGA-GM-A2DB" "ACAP3" "E3" 1303170
"TCGA-EW-A1IY" "ACAP3" "E3" 1303176
"TCGA-D8-A1XQ" "CPSF3L" "E9" 1313879
"TCGA-5L-AAT1" "CPSF3L" "E9" 1313888
"TCGA-C8-A26Y" "CPSF3L" "E7" 1314919
"TCGA-D8-A1XK" "CPSF3L" "E2" 1321057
"TCGA-AO-A128" "TAS1R3" "E2" 1331863
"TCGA-A8-A07P" "TAS1R3" "E6" 1334323
"TCGA-A7-A0DA" "DVL1" "E14" 1338066
"TCGA-C8-A8HQ" "DVL1" "E10" 1339589
"TCGA-BH-A18T" "DVL1" "E8" 1340130
"TCGA-C8-A12V" "MXRA8" "E6" 1354445
"TCGA-C8-A3M8" "AURKAIP1" "E2" 1374747
"TCGA-BH-A0B6" "CCNL2" "E11" 1387308
"TCGA-A8-A09Z" "CCNL2" "E4" 1395413
"TCGA-AC-A23H" "MRPL20" "E4" 1402084
"TCGA-BH-A1FU" "MRPL20" "E4" 1402116
"TCGA-BH-A0W4" "MRPL20" "E4" 1402194
"TCGA-AR-A1AH" "MRPL20" "E4" 1402205
"TCGA-A8-A06Q" "ANKRD65" "E1" 1420868
"TCGA-AC-A8OQ" "ATAD3C" "E1" 1450566
"TCGA-A2-A25A" "ATAD3C" "E11" 1462661
"TCGA-AR-A5QQ" "ATAD3B" "E7" 1482563
"TCGA-AO-A1KS" "ATAD3B" "E12" 1487900
"TCGA-AO-A124" "ATAD3B" "E15" 1490662
"TCGA-A7-A56D" "ATAD3B" "E16" 1495857
"TCGA-D8-A27N" "ATAD3B" "E16" 1495961
"TCGA-AR-A2LH" "ATAD3A" "E5" 1518929
"TCGA-EW-A1OY" "ATAD3A" "E12" 1525277
"TCGA-AO-A128" "ATAD3A" "E16" 1533987
"TCGA-BH-A1FM" "SSU72" "E3" 1544993
"TCGA-C8-A12Y" "MIB2" "E4" 1623874
"TCGA-AC-A23H" "MIB2" "E7" 1625321
"TCGA-B6-A0RV" "MIB2" "E10" 1626960
"TCGA-E2-A1LG" "MIB2" "E19" 1629667
"TCGA-C8-A1HI" "SLC35E2B" "E8" 1668398
"TCGA-A2-A0CR" "SLC35E2B" "E8" 1668406
"TCGA-PL-A8LZ" "SLC35E2B" "E7" 1669727
"TCGA-C8-A3M7" "CDK11A" "E17" 1703847
"TCGA-D8-A1JP" "CDK11A" "E17" 1703884
"TCGA-C8-A1HK" "CDK11A" "E17" 1703915
"TCGA-D8-A27G" "CDK11A" "E15" 1704265
"TCGA-5L-AAT1" "CDK11A" "E13" 1705003
"TCGA-D8-A1JE" "CDK11A" "E11" 1707419
"TCGA-BH-A18P" "CDK11A" "E5" 1716352
"TCGA-D8-A27G" "CDK11A" "E5" 1716387
"TCGA-EW-A6SD" "CDK11A" "E5" 1716477
"TCGA-BH-A0W4" "CDK11A" "E3" 1721601
"TCGA-AN-A049" "CDK11A" "E3" 1721603
"TCGA-D8-A1XK" "SLC35E2" "E3" 1739030
"TCGA-LL-A5YM" "SLC35E2" "E1" 1745772
"TCGA-A7-A26H" "NADK" "E5" 1756596
"TCGA-AO-A128" "GNB1" "E5" 1815804
"TCGA-A2-A3Y0" "CALML6" "E4" 1916819
"TCGA-AR-A0U3" "CALML6" "E4" 1916828
"TCGA-AR-A5QQ" "GABRD" "E3" 2025399
"TCGA-A2-A0CP" "PRKCZ" "E8" 2148880
"TCGA-A2-A3Y0" "PRKCZ" "E13" 2172304
"TCGA-E2-A15E" "PRKCZ" "E13" 2172364
"TCGA-BH-A18N" "C1orf86" "E2" 2194056
"TCGA-OL-A5D6" "SKI" "E1" 2229410
"TCGA-BH-A2L8" "SKI" "E3" 2303317
"TCGA-D8-A4Z1" "SKI" "E5" 2304504
"TCGA-BH-A0B6" "SKI" "E5" 2304579
"TCGA-GM-A2D9" "MORN1" "E14" 2321445
"TCGA-AR-A0TR" "MORN1" "E12" 2336532
"TCGA-BH-A18G" "MORN1" "E8" 2372498
"TCGA-AN-A0FV" "MORN1" "E8" 2372505
"TCGA-AN-A0FV" "MORN1" "E8" 2372506
"TCGA-BH-A0HF" "MORN1" "E8" 2372521
"TCGA-E2-A1IG" "MORN1" "E8" 2372562
"TCGA-AQ-A04J" "MORN1" "E7" 2374471
"TCGA-BH-A1F5" "MORN1" "E4" 2387496
"TCGA-A8-A09Z" "MORN1" "E3" 2388258
"TCGA-BH-A0HA" "MORN1" "E3" 2388291
"TCGA-B6-A0IA" "RER1" "E2" 2397118
"TCGA-E2-A10C" "PEX10" "E3" 2408786
"TCGA-AC-A3HN" "PLCH2" "E1" 2476493
"TCGA-AC-A8OP" "PLCH2" "E3" 2479760
"TCGA-A2-A0YK" "PLCH2" "E5" 2484610
"TCGA-B6-A0IK" "PLCH2" "E11" 2491251
"TCGA-C8-A135" "PLCH2" "E18" 2498827
"TCGA-E2-A15E" "PLCH2" "E19" 2499127
"TCGA-PE-A5DE" "PLCH2" "E22" 2504427
"TCGA-LD-A74U" "PANK4" "E16" 2510680
"TCGA-S3-AA10" "PANK4" "E15" 2511386
"TCGA-C8-A1HM" "PANK4" "E10" 2515609
"TCGA-AC-A23H" "PANK4" "E7" 2519284
"TCGA-BH-A18N" "PANK4" "E4" 2520820
"TCGA-BH-A0HF" "PANK4" "E4" 2520821
"TCGA-BH-A0HF" "PANK4" "E3" 2521173
"TCGA-5L-AAT1" "PANK4" "E3" 2521297
"TCGA-B6-A0RN" "PANK4" "E2" 2521747
"TCGA-5L-AAT1" "PANK4" "E1" 2526579
"TCGA-C8-A12V" "TNFRSF14" "E3" 2558349
"TCGA-OL-A66P" "TNFRSF14" "E6" 2561704
"TCGA-A2-A25F" "TNFRSF14" "E6" 2561714
"TCGA-AC-A23H" "TNFRSF14" "E8" 2563296
"TCGA-A7-A6VV" "MMEL1" "E20" 2592868
"TCGA-D8-A1J8" "MMEL1" "E20" 2592908
"TCGA-A2-A0EU" "MMEL1" "E15" 2596056
"TCGA-AR-A1AJ" "MMEL1" "E11" 2603941
"TCGA-E2-A572" "MMEL1" "E10" 2604271
"TCGA-EW-A1J5" "MMEL1" "E10" 2604275
"TCGA-E2-A574" "MMEL1" "E9" 2605620
"TCGA-AC-A23H" "MMEL1" "E5" 2609733
"TCGA-B6-A0IA" "MMEL1" "E5" 2609757
"TCGA-AN-A0XS" "ACTRT2" "E1" 3021531
"TCGA-E9-A1RC" "ACTRT2" "E1" 3022445
"TCGA-AC-A6IW" "ACTRT2" "E1" 3022597
"TCGA-A2-A4S3" "ACTRT2" "E1" 3022696
"TCGA-A2-A0EX" "PRDM16" "E4" 3385231
"TCGA-B6-A0WZ" "PRDM16" "E5" 3396498
"TCGA-E9-A22E" "PRDM16" "E6" 3402898
"TCGA-BH-A8FZ" "PRDM16" "E9" 3411750
"TCGA-BH-A0HF" "PRDM16" "E9" 3412534
"TCGA-A8-A09V" "PRDM16" "E15" 3431074
"TCGA-5L-AAT1" "ARHGEF16" "E2" 3463558
"TCGA-AR-A1AI" "ARHGEF16" "E4" 3467276
"TCGA-E9-A1R4" "ARHGEF16" "E13" 3479535
"TCGA-AC-A5XS" "MEGF6" "E37" 3490581
"TCGA-AC-A23H" "MEGF6" "E7" 3514608
"TCGA-A2-A0SY" "MEGF6" "E2" 3602584
"TCGA-AC-A23H" "TPRG1L" "E2" 3625459
"TCGA-AR-A1AS" "WRAP73" "E1" 3649987
"TCGA-BH-A0DX" "TP73" "E2" 3682353
"TCGA-A1-A0SF" "TP73" "E3" 3683095
"TCGA-5L-AAT1" "TP73" "E3" 3683125
"TCGA-A8-A095" "TP73" "E4" 3707673
"TCGA-BH-A0HA" "TP73" "E8" 3727733
"TCGA-E9-A1R5" "CCDC27" "E1" 3752488
"TCGA-BH-A0C0" "CCDC27" "E3" 3755474
"TCGA-GM-A5PV" "CCDC27" "E6" 3762664
"TCGA-A2-A3Y0" "CCDC27" "E9" 3766586
"TCGA-BH-A1F6" "LRRC47" "E7" 3781140
"TCGA-B6-A0WZ" "LRRC47" "E7" 3781267
"TCGA-BH-A0B6" "LRRC47" "E2" 3787022
"TCGA-AR-A2LE" "CEP104" "E19" 3823467
"TCGA-A2-A0EN" "CEP104" "E12" 3833888
"TCGA-A8-A09Z" "CEP104" "E11" 3835070
"TCGA-AC-A4ZE" "DFFB" "E7" 3883608
"TCGA-AR-A1AH" "C1orf174" "E4" 3890056
"TCGA-BH-A18G" "AJAP1" "E2" 4711920
"TCGA-BH-A1F2" "AJAP1" "E3" 4769894
"TCGA-AC-A23H" "AJAP1" "E4" 4772372
"TCGA-C8-A12L" "AJAP1" "E4" 4772486
"TCGA-AC-A23H" "NPHP4" "E28" 5864419
"TCGA-BH-A1FD" "NPHP4" "E28" 5864478
"TCGA-EW-A1IZ" "NPHP4" "E27" 5865131
"TCGA-EW-A1J5" "NPHP4" "E27" 5865172
"TCGA-A2-A04P" "NPHP4" "E26" 5866378
"TCGA-D8-A1XZ" "NPHP4" "E24" 5867849
"TCGA-4H-AAAK" "NPHP4" "E20" 5877217
"TCGA-D8-A1JD" "NPHP4" "E19" 5880178
"TCGA-GM-A2D9" "NPHP4" "E17" 5890905
"TCGA-E2-A1LA" "NPHP4" "E17" 5890987
"TCGA-D8-A1J8" "NPHP4" "E17" 5891009
"TCGA-E2-A1B4" "NPHP4" "E16" 5904787
"TCGA-EW-A1P3" "NPHP4" "E13" 5907125
"TCGA-BH-A0EE" "NPHP4" "E12" 5909177
"TCGA-A2-A0ER" "NPHP4" "E11" 5927714
"TCGA-BH-A0HF" "NPHP4" "E11" 5927761
"TCGA-AO-A128" "NPHP4" "E9" 5947174
"TCGA-AC-A23H" "NPHP4" "E4" 5969131
"TCGA-AC-A23H" "NPHP4" "E2" 5986185
答案 0 :(得分：1)
如果无论顺序如何，唯一身份个体的数量必须> = 30， 那么我认为这应该起作用：
library(magrittr)
compute_counts <- function(ID, gene_ends) {
ids <- as.integer(ID)
seen_ids <- numeric()
count <- 0L
adjust_count <- function(id, gene_end) {
if (!(id %in% seen_ids)) {
seen_ids <<- sort(c(seen_ids, id)) # sort strictly not needed
count <<- count + 1L
}
if (gene_end && length(seen_ids) >= 30L) {
count <- count # copy enclosed value locally
seen_ids <<- numeric()
count <<- 0L
}
count
}
unlist(Map(adjust_count, ids, gene_ends))
}
out <- df %>%
mutate(num_unique = compute_counts(ID, lastObsFlagG & lastObsFlagGE),
group = cumsum(c(-1L, diff(num_unique)) < 0L)) %T>%
View
此版本（考虑原始帖子）基于dipetkov的回答，
它使用一个带有关闭功能的辅助函数，当基因结束并且满足adjustment条件时，该函数将更新封闭的count。
library(magrittr)
compute_counts <- function(ID, gene_ends) {
rle <- rle(as.integer(ID))
ids <- unlist(Map(rep, 1L:length(rle$values), each = rle$lengths))
adjustment <- 0L
adjust_count <- function(id, gene_end) {
count <- id - adjustment
if (gene_end && count >= 30L) {
adjustment <<- id
}
count
}
unlist(Map(adjust_count, ids, gene_ends))
}
out <- df %>%
mutate(count = compute_counts(ID, lastObsFlagG & lastObsFlagGE),
group = cumsum(count == 1L)) %T>%
View
答案 1 :(得分：1)
此解决方案使用purrr::accumulate而不是循环。 （实际上，accumulate2是因为有两个条件来决定何时切换到新组：个体ID和基因指示器的开始。）
library("tidyverse")
# Helper function which expresses the switch condition
switch_group <- function(acc, individual, gene_starts) {
if ((individual - acc) > 30 && gene_starts == TRUE) individual else acc
}
df %>%
mutate(
# Generate run-length type individual id's
individual = data.table::rleid(ID),
# Detect the start of a new gene (when its name is different from the previous gene)
gene_starts = gene != lag(gene, default = "")) %>%
# Detect when to switch to a new group
mutate(switch = accumulate2(individual, gene_starts[-1], switch_group) %>% unlist()) %>%
# The rest just restarts the counter and group id as required
mutate(count = individual - switch + 1,
group = data.table::rleid(switch)) %>%
print(n = 75)
#> # A tibble: 200 x 9
#> ID gene exon mutation id starts switch count group
#> <fct> <chr> <fct> <int> <int> <lgl> <int> <dbl> <int>
#> 1 TCGA-AN-A046 OR4F5 E1 69767 1 TRUE 1 1 1
#> 2 TCGA-A2-A0CP SAMD11 E2 925952 2 TRUE 1 2 1
#> 3 TCGA-A8-A08H NOC2L E5 956126 3 TRUE 1 3 1
#> 4 TCGA-GM-A2DM NOC2L E4 956911 4 FALSE 1 4 1
#> 5 TCGA-GM-A2DM NOC2L E4 956912 4 FALSE 1 4 1
#> 6 TCGA-D8-A1XM KLHL17 E3 961658 5 TRUE 1 5 1
#> 7 TCGA-BH-A18G KLHL17 E5 962441 6 FALSE 1 6 1
#> 8 TCGA-3C-AALI KLHL17 E8 963353 7 FALSE 1 7 1
#> 9 TCGA-AC-A62Y KLHL17 E9 964004 8 FALSE 1 8 1
#> 10 TCGA-AR-A2LE PLEKHN1 E1 966556 9 TRUE 1 9 1
#> 11 TCGA-E2-A14N PLEKHN1 E5 970728 10 FALSE 1 10 1
#> 12 TCGA-AO-A0J4 PLEKHN1 E12 973506 11 FALSE 1 11 1
#> 13 TCGA-D8-A1J9 HES4 E3 999551 12 TRUE 1 12 1
#> 14 TCGA-EW-A1PH ISG15 E2 1014276 13 TRUE 1 13 1
#> 15 TCGA-A2-A0T0 AGRN E2 1022338 14 TRUE 1 14 1
#> 16 TCGA-GM-A2DD AGRN E3 1035303 15 FALSE 1 15 1
#> 17 TCGA-5L-AAT1 AGRN E4 1040690 16 FALSE 1 16 1
#> 18 TCGA-OL-A5RW AGRN E8 1043314 17 FALSE 1 17 1
#> 19 TCGA-D8-A27M AGRN E25 1049355 18 FALSE 1 18 1
#> 20 TCGA-AR-A1AI AGRN E29 1050430 19 FALSE 1 19 1
#> 21 TCGA-5L-AAT0 AGRN E36 1055374 20 FALSE 1 20 1
#> 22 TCGA-5L-AAT0 AGRN E36 1055376 20 FALSE 1 20 1
#> 23 TCGA-C8-A8HP AGRN E36 1055442 21 FALSE 1 21 1
#> 24 TCGA-A7-A4SD TTLL10 E13 1184971 22 TRUE 1 22 1
#> 25 TCGA-BH-A1F0 SDF4 E4 1223283 23 TRUE 1 23 1
#> 26 TCGA-AO-A128 SDF4 E4 1223330 24 FALSE 1 24 1
#> 27 TCGA-E9-A1R0 SDF4 E2 1228592 25 FALSE 1 25 1
#> 28 TCGA-A2-A04P UBE2J2 E7 1255246 26 TRUE 1 26 1
#> 29 TCGA-C8-A274 UBE2J2 E7 1255342 27 FALSE 1 27 1
#> 30 TCGA-5L-AAT1 SCNN1D E1 1281422 28 TRUE 1 28 1
#> 31 TCGA-AO-A128 SCNN1D E6 1287116 29 FALSE 1 29 1
#> 32 TCGA-E2-A15R SCNN1D E7 1287596 30 FALSE 1 30 1
#> 33 TCGA-AC-A62V SCNN1D E11 1290543 31 FALSE 1 31 1
#> 34 TCGA-BH-A18V ACAP3 E22 1294187 32 TRUE 32 1 2
#> 35 TCGA-A7-A6VX ACAP3 E6 1300640 33 FALSE 32 2 2
#> 36 TCGA-GM-A2DB ACAP3 E3 1303170 34 FALSE 32 3 2
#> 37 TCGA-EW-A1IY ACAP3 E3 1303176 35 FALSE 32 4 2
#> 38 TCGA-D8-A1XQ CPSF3L E9 1313879 36 TRUE 32 5 2
#> 39 TCGA-5L-AAT1 CPSF3L E9 1313888 37 FALSE 32 6 2
#> 40 TCGA-C8-A26Y CPSF3L E7 1314919 38 FALSE 32 7 2
#> 41 TCGA-D8-A1XK CPSF3L E2 1321057 39 FALSE 32 8 2
#> 42 TCGA-AO-A128 TAS1R3 E2 1331863 40 TRUE 32 9 2
#> 43 TCGA-A8-A07P TAS1R3 E6 1334323 41 FALSE 32 10 2
#> 44 TCGA-A7-A0DA DVL1 E14 1338066 42 TRUE 32 11 2
#> 45 TCGA-C8-A8HQ DVL1 E10 1339589 43 FALSE 32 12 2
#> 46 TCGA-BH-A18T DVL1 E8 1340130 44 FALSE 32 13 2
#> 47 TCGA-C8-A12V MXRA8 E6 1354445 45 TRUE 32 14 2
#> 48 TCGA-C8-A3M8 AURKAIP1 E2 1374747 46 TRUE 32 15 2
#> 49 TCGA-BH-A0B6 CCNL2 E11 1387308 47 TRUE 32 16 2
#> 50 TCGA-A8-A09Z CCNL2 E4 1395413 48 FALSE 32 17 2
#> 51 TCGA-AC-A23H MRPL20 E4 1402084 49 TRUE 32 18 2
#> 52 TCGA-BH-A1FU MRPL20 E4 1402116 50 FALSE 32 19 2
#> 53 TCGA-BH-A0W4 MRPL20 E4 1402194 51 FALSE 32 20 2
#> 54 TCGA-AR-A1AH MRPL20 E4 1402205 52 FALSE 32 21 2
#> 55 TCGA-A8-A06Q ANKRD65 E1 1420868 53 TRUE 32 22 2
#> 56 TCGA-AC-A8OQ ATAD3C E1 1450566 54 TRUE 32 23 2
#> 57 TCGA-A2-A25A ATAD3C E11 1462661 55 FALSE 32 24 2
#> 58 TCGA-AR-A5QQ ATAD3B E7 1482563 56 TRUE 32 25 2
#> 59 TCGA-AO-A1KS ATAD3B E12 1487900 57 FALSE 32 26 2
#> 60 TCGA-AO-A124 ATAD3B E15 1490662 58 FALSE 32 27 2
#> 61 TCGA-A7-A56D ATAD3B E16 1495857 59 FALSE 32 28 2
#> 62 TCGA-D8-A27N ATAD3B E16 1495961 60 FALSE 32 29 2
#> 63 TCGA-AR-A2LH ATAD3A E5 1518929 61 TRUE 32 30 2
#> 64 TCGA-EW-A1OY ATAD3A E12 1525277 62 FALSE 32 31 2
#> 65 TCGA-AO-A128 ATAD3A E16 1533987 63 FALSE 32 32 2
#> 66 TCGA-BH-A1FM SSU72 E3 1544993 64 TRUE 64 1 3
#> 67 TCGA-C8-A12Y MIB2 E4 1623874 65 TRUE 64 2 3
#> 68 TCGA-AC-A23H MIB2 E7 1625321 66 FALSE 64 3 3
#> 69 TCGA-B6-A0RV MIB2 E10 1626960 67 FALSE 64 4 3
#> 70 TCGA-E2-A1LG MIB2 E19 1629667 68 FALSE 64 5 3
由reprex package（v0.2.1）于2019-03-23创建