P281424/AMR
1
0
Fork 0
mirror of https://github.com/msberends/AMR.git synced 2025-12-15 17:10:18 +01:00
Code Releases Activity

AI improvements

Browse Source
This commit is contained in:
dr. M.S. (Matthijs) Berends
2018-12-07 12:04:55 +01:00
parent 87ad6da745
commit 8e8a9cd190
19 changed files with 199 additions and 140 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
man/as.mo.Rd
View File

@@ -7,13 +7,13 @@
\alias{guess_mo}
\title{Transform to microorganism ID}
\usage{
as.mo(x, Becker = FALSE, Lancefield = FALSE, allow_uncertain = FALSE,
as.mo(x, Becker = FALSE, Lancefield = FALSE, allow_uncertain = TRUE,
reference_df = NULL)
is.mo(x)
guess_mo(x, Becker = FALSE, Lancefield = FALSE,
allow_uncertain = FALSE, reference_df = NULL)
allow_uncertain = TRUE, reference_df = NULL)
}
\arguments{
\item{x}{a character vector or a \code{data.frame} with one or two columns}
@@ -26,7 +26,7 @@ guess_mo(x, Becker = FALSE, Lancefield = FALSE,
This excludes \emph{Enterococci} at default (who are in group D), use \code{Lancefield = "all"} to also categorise all \emph{Enterococci} as group D.}
\item{allow_uncertain}{a logical to indicate whether empty results should be checked for only a part of the input string. When results are found, a warning will be given about the uncertainty and the result.}
\item{allow_uncertain}{a logical to indicate whether the input should be checked for less possible results, see Details}
\item{reference_df}{a \code{data.frame} to use for extra reference when translating \code{x} to a valid \code{mo}. The first column can be any microbial name, code or ID (used in your analysis or organisation), the second column must be a valid \code{mo} as found in the \code{\link{microorganisms}} data set.}
}
@@ -39,11 +39,11 @@ Use this function to determine a valid microorganism ID (\code{mo}). Determinati
\details{
A microbial ID from this package (class: \code{mo}) typically looks like these examples:\cr
\preformatted{
Code Full name
--------------- --------------------------------------
B_KLBSL Klebsiella
B_KLBSL_PNE Klebsiella pneumoniae
B_KLBSL_PNE_RHI Klebsiella pneumoniae rhinoscleromatis
Code Full name
--------------- --------------------------------------
B_KLBSL Klebsiella
B_KLBSL_PNE Klebsiella pneumoniae
B_KLBSL_PNE_RHI Klebsiella pneumoniae rhinoscleromatis
| | | |
| | | |
| | | ----> subspecies, a 3-4 letter acronym
@@ -62,7 +62,7 @@ This function uses Artificial Intelligence (AI) to help getting fast and logical
\item{Breakdown of input values: from here it starts to breakdown input values to find possible matches}
}
A couple of effects because of these rules
A couple of effects because of these rules:
\itemize{
\item{\code{"E. coli"} will return the ID of \emph{Escherichia coli} and not \emph{Entamoeba coli}, although the latter would alphabetically come first}
\item{\code{"H. influenzae"} will return the ID of \emph{Haemophilus influenzae} and not \emph{Haematobacter influenzae} for the same reason}
@@ -71,6 +71,13 @@ A couple of effects because of these rules
}
This means that looking up human pathogenic microorganisms takes less time than looking up human \strong{non}-pathogenic microorganisms.
When using \code{allow_uncertain = TRUE} (which is the default setting), it will use additional rules if all previous AI rules failed to get valid results. Examples:
\itemize{
\item{\code{"Streptococcus group B (known as S. agalactiae)"}. The text between brackets will be removed and a warning will be thrown that the result \emph{Streptococcus group B} (\code{B_STRPTC_GRB}) needs review.}
\item{\code{"S. aureus - please mind: MRSA"}. The last word will be stripped, after which the function will try to find a match. If it does not, the second last word will be stripped, etc. Again, a warning will be thrown that the result \emph{Staphylococcus aureus} (\code{B_STPHY_AUR}) needs review.}
\item{\code{"D. spartina"}. This is the abbreviation of an old taxonomic name: \emph{Didymosphaeria spartinae} (the last "e" was missing from the input). This fungus was renamed to \emph{Leptosphaeria obiones}, so a warning will be thrown that this result (\code{F_LPTSP_OBI}) needs review.}
}
\code{guess_mo} is an alias of \code{as.mo}.
}
\section{ITIS}{
@@ -100,6 +107,7 @@ as.mo("staaur")
as.mo("S. aureus")
as.mo("S aureus")
as.mo("Staphylococcus aureus")
as.mo("Staphylococcus aureus (MRSA)")
as.mo("MRSA") # Methicillin Resistant S. aureus
as.mo("VISA") # Vancomycin Intermediate S. aureus
as.mo("VRSA") # Vancomycin Resistant S. aureus