This takes a column that has entries like "Probably damaging(0.999)" and returns a data frame with two columns containing the text description and the number.

extract_polyphen(pphen)

Examples

testing = c("probably_damaging(0.999)") extract_polyphen(testing)
#> # A tibble: 2 x 1 #> polyphen_prediction #> <chr> #> 1 probably_damaging #> 2 0.999