以下是我正在使用的数据的示例数据框。对于熟悉遗传数据格式的人来说,它基本上是一个修改过的VCF文件。如果不是,基本上每行包含基因组中可能存在变体的位置的信息。
samp <- structure(list(Chrom = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L), .Label = "chr12", class = "factor"),
Pos = c(8613204L, 8613412L, 8614238L, 8614506L, 8614652L,
8614669L, 8614768L, 8614951L, 8614986L, 8615225L, 8615809L,
8616149L, 8616392L), Ref = structure(c(1L, 1L, 4L, 3L, 3L,
3L, 2L, 3L, 2L, 4L, 2L, 4L, 3L), .Label = c("A", "C", "G",
"T"), class = "factor"), Alt = structure(c(3L, 2L, 2L, 1L,
1L, 1L, 3L, 1L, 1L, 3L, 4L, 2L, 4L), .Label = c("A", "C",
"G", "T"), class = "factor"), Info = c("AC=3913;AF=0.78135;AN=5008;NS=2504;DP=-128;EAS_AF=0.9921;AMR_AF=0.8357;AFR_AF=0.5779;EUR_AF=0.7366;SAS_AF=0.8466;AA=G|||;CSQ=G|ENSG00000205846|ENST00000382073|Transcript|intron_variant||||||||1||||||;GENCODE=ENST00000382073;FUNSEQ=0.1881",
"AC=4051;AF=0.808906;AN=5008;NS=2504;DP=-128;EAS_AF=0.9921;AMR_AF=0.8444;AFR_AF=0.6725;EUR_AF=0.7366;SAS_AF=0.8538;AA=C|||;CSQ=C|ENSG00000205846|ENST00000382073|Transcript|intron_variant||||||||1||||||;GENCODE=ENST00000382073;FUNSEQ=0.1881",
"AC=4021;AF=0.802915;AN=5008;NS=2504;DP=-128;EAS_AF=0.9921;AMR_AF=0.8415;AFR_AF=0.6558;EUR_AF=0.7376;SAS_AF=0.8466;AA=T|||;CSQ=C|ENSG00000205846|ENST00000382073|Transcript|intron_variant||||||||1||||||;GENCODE=ENST00000382073;FUNSEQ=0.7997",
"AC=3990;AF=0.796725;AN=5008;NS=2504;DP=-128;EAS_AF=0.9921;AMR_AF=0.8386;AFR_AF=0.6339;EUR_AF=0.7376;SAS_AF=0.8466;AA=A|||;CSQ=A|ENSG00000205846|ENST00000382073|Transcript|intron_variant||||||||1||||||;GENCODE=ENST00000382073;FUNSEQ=0.1881",
"AC=4069;AF=0.8125;AN=5008;NS=2504;DP=17188;EAS_AF=0.9921;AMR_AF=0.8487;AFR_AF=0.6528;EUR_AF=0.7714;SAS_AF=0.8599;AA=A|||;CSQ=A|ENSG00000205846|ENST00000382073|Transcript|intron_variant||||||||1||||||;GENCODE=ENST00000382073;FUNSEQ=0.0029",
"AC=4044;AF=0.807508;AN=5008;NS=2504;DP=-128;EAS_AF=0.9911;AMR_AF=0.8458;AFR_AF=0.6362;EUR_AF=0.7714;SAS_AF=0.8599;AA=G|||;CSQ=A|ENSG00000205846|ENST00000382073|Transcript|intron_variant||||||||1||||||;GENCODE=ENST00000382073;FUNSEQ=0.0029",
NA, NA, "AC=3795;AF=0.757788;AN=5008;NS=2504;DP=-128;EAS_AF=0.9653;AMR_AF=0.7954;AFR_AF=0.5651;EUR_AF=0.7167;SAS_AF=0.82;AA=c|||;CSQ=A|ENSG00000205846|ENST00000382073|Transcript|intron_variant||||||||1||||||;GENCODE=ENST00000382073;FUNSEQ=0.0029",
NA, "AC=4053;AF=0.809305;AN=5008;NS=2504;DP=-128;EAS_AF=0.9921;AMR_AF=0.8458;AFR_AF=0.6362;EUR_AF=0.7724;SAS_AF=0.8671;AA=C|||;CSQ=T|ENSG00000205846|ENST00000382073|Transcript|intron_variant||||||||1||||||;GENCODE=ENST00000382073;FUNSEQ=0.0029",
"AC=4076;AF=0.813898;AN=5008;NS=2504;DP=-128;EAS_AF=0.9921;AMR_AF=0.8473;AFR_AF=0.6528;EUR_AF=0.7724;SAS_AF=0.8671;AA=C|||;CSQ=C|ENSG00000205846|ENST00000382073|Transcript|intron_variant||||||||1||||||;GENCODE=ENST00000382073;FUNSEQ=0.0029",
"AC=4052;AF=0.809105;AN=5008;NS=2504;DP=-128;EAS_AF=0.9921;AMR_AF=0.8473;AFR_AF=0.6346;EUR_AF=0.7724;SAS_AF=0.8671;AA=T|||;CSQ=T|ENSG00000205846|ENST00000382073|Transcript|intron_variant||||||||1||||||;GENCODE=ENST00000382073;FUNSEQ=0.0029"
), TG_rs = c("rs10770739", "rs10770740", "rs4883148", "rs4883149",
"rs4883150", "rs4883151", NA, NA, "rs7303948", NA, "rs4242889",
"rs4883154", "rs4242890")), row.names = c(NA, -13L), .Names = c("Chrom",
"Pos", "Ref", "Alt", "Info", "TG_rs"), class = "data.frame")
我想要做的是从&#34;信息&#34;中提取值。柱。但是,此列中包含的信息对于每一行都不相同,并且不总是以相同的顺序出现。因此,我想使用模式匹配来获取我感兴趣的值。
我写了一个小函数来提取&#34;等位基因频率&#34; (AF)适用于各种超级人群&#34; (例如,AMR,AFR,EUR,SAS,EAS)包含在“信息”列中。
extractAF <- function(pop, vec) {
info <- unlist((strsplit(vec, ";", fixed=TRUE)))
AF <- as.numeric(unlist(strsplit((info[grep(pop, (unlist((strsplit(vec, ";", fixed=TRUE)))))]), "=", fixed=TRUE))[2])
return(AF)
}
这个功能需要两个参数:&#39; pop&#39;这是一个字符串,指定要提取的超级人口,以及&#39; vec&#39;它旨在获取我的数据框的Info列。
当通过单个向量时,该函数按预期工作:
extractAF("AFR_AF", samp[1,'Info'])
#[1] 0.5779
extractAF("AFR_AF", samp[5,'Info'])
#[1] 0.6528
但是,我希望对数据帧的每一行执行此操作,并创建一个包含数据的新列。当我使用dplyr的mutate函数时,我会得到一个具有相同值的列:
library("dplyr")
mutate(samp, AFR_AF = extractAF("AFR_AF", Info))
我读了一篇文章(我现在似乎无法找到,否则我会引用它),即mutate一次传递所有行,而不是我需要的逐行传递。
所以我根据这个post尝试了以下几种方式:
apply(samp[,'Info'], 1, function(x) extractAF("AFR_AF", x))
应用中出错(samp [,&#34; Info&#34;],1,function(x)extractAF(&#34; AMR_AF&#34;,x)): dim(X)必须具有正长度
samp[, extractAF("AMR_AF", Info), by = .I]
[.data.frame
中的错误(samp,,extractAF(&#34; AMR_AF&#34;,Info),by = .I):
未使用的参数(by = .I)
samp[, extractAF("AMR_AF", Info), by = 1:nrow(samp)]
Error in `[.data.frame`(samp, , extractAF("AMR_AF", Info), by = 1:nrow(samp)) :
unused argument (by = 1:nrow(samp))
#
更新
在下面的INFO列中包含NA和AF = 0的其他样本数据集:
结构(列表(CHROM = c(&#34; chr1&#34;,&#34; chr1&#34;,&#34; chr1&#34;,&#34; chr1&#34;,&#34; ; CHR1&#34 ;, &#34; chr1&#34;),POS = c(16090898L,16091074L,16091583L,16092212L, 16093560L,16093639L),ID = c(&#34; rs6429774&#34;,&#34; rs6429776&#34;,NA, &#34; rs74528955&#34;,&#34; rs904912&#34;,NA),REF = c(&#34; G&#34;,&#34; A&#34;,&#34; T&#34 ;,&#34; C&#34;,&#34; T&#34;,&#34; C&#34;), ALT = c(&#34; A&#34;,&#34; G&#34;,&#34; A&#34;,&#34; T&#34;,&#34; A&#34;,& #34; T&#34;),QUAL = c(NA,NA,NA,NA,NA, NA),FILTER = c(NA,NA,NA,NA,NA,NA),INFO = C(&#34; AC = 1606; AF = 0.320687; AN = 5008; NS = 2504; DP = 21565; EAS_AF = 0.1419; AMR_AF = 0.2983; AFR_AF = 0.525; EUR_AF = 0.3509; SAS_AF = 0.2137; AA = G | ||; CSQ = A | ENSG00000162458 | ENST00000441801 |文稿| upstream_gene_variant ||||||| 96 | 1 ||||||; ERB = A || proximal_1216 | Regulatory_Feature | proximal_enhancer; FUNSEQ = 0.3335&#34 ;, &#34; AC = 1690; AF = 0.33746; AN = 5008; NS = 2504; DP = 20247; EAS_AF = 0.1498; AMR_AF = 0.3012; AFR_AF = 0.5681; EUR_AF = 0.3549; SAS_AF = 0.227; AA = G ||| ; CSQ = G | ENSG00000162458 | ENST00000441801 | Transcript | 5_prime_UTR_variant | 81 ||||||| 1 ||||||; ERB = G || proximal_1216 | Regulatory_Feature | proximal_enhancer; FUNSEQ = 0.3335&#34;,NA, &#34; AC = 8; AF = 0.00159744; AN = 5008; NS = 2504; DP = 19197; EAS_AF = 0.0079; AMR_AF = 0; AFR_AF = 0; EUR_AF = 0; SAS_AF = 0; AA = C ||| ; CSQ = T | ENSG00000162458 | ENST00000441801 |文稿| intron_variant |||||||| 1 ||||||; GENCODE = ENST00000441801; ERB = T || proximal_1216 | Regulatory_Feature | proximal_enhancer; FUNSEQ = 0.3335&#34; ,&#34; AC = 3282; AF = 0.655351; AN = 5008; NS = 2504; DP = 14721; EAS_AF = 0.8343; AMR_AF = 0.6916; AFR_AF = 0.4259; EUR_AF = 0.6531; SAS_AF = 0.7577; AA = A || |; CSQ = A | ENSG00000162458 | ENST00000441801 |文稿| intron_variant |||||||| 1 ||||||; GENCODE = ENST00000441801; FUNSEQ = 0.1483&#34 ;, &#34; AC = 5; AF = 0.000998403; AN = 5008; NS = 2504; DP = 14736; EAS_AF = 0.003; AMR_AF = 0; AFR_AF = 0; EUR_AF = 0; SAS_AF = 0.002; AA = C ||| ; CSQ = T | ENSG00000162458 | ENST00000441801 |文稿| intron_variant |||||||| 1 ||||||; GENCODE = ENST00000441801; FUNSEQ = 0.1483&#34; )),row.names = 14:19,class =&#34; data.frame&#34;,。Name = c(&#34; CHROM&#34;, &#34; POS&#34;,&#34; ID&#34;,&#34; REF&#34;,&#34; ALT&#34;,&#34; QUAL&#34;,&#34; FILTER& #34;,&#34; INFO&#34;))
答案 0 :(得分:3)
您可能不需要这些公式,因为sub
是矢量化的。首先创建所有可能代码的变量,如(AFR,AMR,EUR等)。使用该向量创建搜索模式以浏览Info
列并返回包含所有匹配项的新数据框:
all_pop <- c("AMR_AF", "AFR_AF", "EUR_AF", "SAS_AF", "EAS_AF")
pat <- paste0(".*\\b", all_pop, "=(\\d+(\\.\\d+)?)\\b.*")
out <- sapply(pat, sub, "\\1", samp$Info)
newdf <- setNames(as.data.frame(out), all_pop)
# AMR_AF AFR_AF EUR_AF SAS_AF EAS_AF
# 1 0.8357 0.5779 0.7366 0.8466 0.9921
# 2 0.8444 0.6725 0.7366 0.8538 0.9921
# 3 0.8415 0.6558 0.7376 0.8466 0.9921
# 4 0.8386 0.6339 0.7376 0.8466 0.9921
# 5 0.8487 0.6528 0.7714 0.8599 0.9921
# 6 0.8458 0.6362 0.7714 0.8599 0.9911
# 7 <NA> <NA> <NA> <NA> <NA>
# 8 <NA> <NA> <NA> <NA> <NA>
# 9 0.7954 0.5651 0.7167 0.82 0.9653
# 10 <NA> <NA> <NA> <NA> <NA>
# 11 0.8458 0.6362 0.7724 0.8671 0.9921
# 12 0.8473 0.6528 0.7724 0.8671 0.9921
# 13 0.8473 0.6346 0.7724 0.8671 0.9921