I've got the following data frame:
structure(list(Nombre.HIC.HGVS = c("NC_000007.13:g.87178626C>T",
"NC_000007.13:g.87278760G>A", "NC_000012.11:g.22063115A>G"),
Gen = c("ABCB1", "ABCB1", "ABCB1"), Isoforma = c("NM_000927.4",
"NM_000927.4", "NM_000927.4"), Nombre.genómico = c("g.87178626C>T",
"g.87278760G>A", "g.87133993T>C"), Nombre.cDNA = c("c.1725 38G>A",
"c.-330-48366C>T", "c.3637-228A>G"), rs = c("rs2235013",
"rs10267099", "rs1186746"), Zona..Inicial..Final. = c("Intrón: 15 / -",
"Intrón: 1 / -", "Intrón: 28 / -"), Count.... = c("78,947%",
"10,526%", "7,895%"), Count..total. = c("(30 / 38)", "(4 / 38)",
"(3 / 38)"), Count.HiC.... = c("77,652%", "7,961%", "3,544%"
), Profundidad.de.lectura..DP. = c(310L, 406L, 27L), Profundidad.de.lectura.corregida.por.calidad..DP.QUAL. = c(403L,
283L, 20L), Frecuencia.del.alelo.alternativo.en.las.lecturas..FREQ.ALT. = c(50.62,
99.65, 40), Calidad.en.la.identificación.de.la.variante..Qual. = c(255L,
255L, 95L), Cigosidad..AF1. = c("Heterocigosis", "Homocigosis",
"Heterocigosis")), row.names = c(NA, 3L), class = "data.frame")
I need to extract, in two different columns, the numbers i have put between []an highlighted in bold. So for example:
NC_000007.13:g.87278760G>A ->> from here I want to take: NC_00000[7].13:g.[87278760]G>A NC_000012.11:g.22063115A>G ->> from here I want to take: NC_0000[12].11:g.[22063115]A>G
So basically, I want to keep the last number before the first dot (or the last 2 numbers before the first dot - as long as the second to last is not a 0- ), and all numbers after "g."
I've been using the stringr package but these conditions are too many for me to get it right.
Any ideas?
Thanks!
CodePudding user response：
Here is a potential solution:
library(tidyverse)
df <- structure(list(Nombre.HIC.HGVS = c("NC_000007.13:g.87178626C>T",
"NC_000007.13:g.87278760G>A", "NC_000013.11:g.22063115A>G"),
Gen = c("ABCB1", "ABCB1", "ABCB1"), Isoforma = c("NM_000927.4",
"NM_000927.4", "NM_000927.4"), Nombre.genómico = c("g.87178626C>T",
"g.87278760G>A", "g.87133993T>C"), Nombre.cDNA = c("c.1725 38G>A",
"c.-330-48366C>T", "c.3637-228A>G"), rs = c("rs2235013",
"rs10267099", "rs1186746"), Zona..Inicial..Final. = c("Intrón: 15 / -",
"Intrón: 1 / -", "Intrón: 28 / -"), Count.... = c("78,947%",
"10,526%", "7,895%"), Count..total. = c("(30 / 38)", "(4 / 38)",
"(3 / 38)"), Count.HiC.... = c("77,652%", "7,961%", "3,544%"
), Profundidad.de.lectura..DP. = c(310L, 406L, 27L), Profundidad.de.lectura.corregida.por.calidad..DP.QUAL. = c(403L,
283L, 20L), Frecuencia.del.alelo.alternativo.en.las.lecturas..FREQ.ALT. = c(50.62,
99.65, 40), Calidad.en.la.identificación.de.la.variante..Qual. = c(255L,
255L, 95L), Cigosidad..AF1. = c("Heterocigosis", "Homocigosis",
"Heterocigosis")), row.names = c(NA, 3L), class = "data.frame")
df %>%
select(Nombre.HIC.HGVS) %>%
mutate(first = gsub(x = str_extract(Nombre.HIC.HGVS, "\\d "), pattern = "^0 ", ""),
second = str_extract(Nombre.HIC.HGVS, "(?<=g.)\\d (?=[[:alpha:]] )"))
#> Nombre.HIC.HGVS first second
#> 1 NC_000007.13:g.87178626C>T 7 87178626
#> 2 NC_000007.13:g.87278760G>A 7 87278760
#> 3 NC_000013.11:g.22063115A>G 13 22063115
Created on 2022-03-03 by the reprex package (v2.0.1)