P281424
/
AMR
mirror of https://github.com/msberends/AMR.git
1
0
Fork 0
Code Releases Activity

as.mo improvement

This commit is contained in:
dr. M.S. (Matthijs) Berends 2019-02-25 10:42:57 +01:00
parent e65d1a3036
commit 0ec76cfa98
20 changed files with 379 additions and 324 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
DESCRIPTION
View File

@ -1,6 +1,6 @@
Package: AMR
Version: 0.5.0.9018
Date: 2019-02-23
Date: 2019-02-25
Title: Antimicrobial Resistance Analysis
Authors@R: c(
person(

19
R/mo.R
View File

@ -56,7 +56,7 @@
#' This function uses Artificial Intelligence (AI) to help getting fast and logical results. It tries to find matches in this order:
#' \itemize{
#' \item{Taxonomic kingdom: it first searches in Bacteria, then Fungi, then Protozoa}
#' \item{Human pathogenic prevalence: it first searches in more prevalent microorganisms, then less prevalent ones}
#' \item{Human pathogenic prevalence: it first searches in more prevalent microorganisms, then less prevalent ones (see section \emph{Microbial prevalence of pathogens in humans})}
#' \item{Valid MO codes and full names: it first searches in already valid MO code and known genus/species combinations}
#' \item{Breakdown of input values: from here it starts to breakdown input values to find possible matches}
#' }
@ -93,6 +93,17 @@
#'
#' Use \code{mo_renamed()} to get a vector with all values that could be coerced based on an old, previously accepted taxonomic name.
#'
#' @section Microbial prevalence of pathogens in humans:
#' The artificial intelligence takes into account microbial prevalence of pathogens in humans. It uses three groups and every (sub)species is in the group it matches first. These groups are:
#' \itemize{
#' \item{1 (most prevalent): class is Gammaproteobacteria \strong{or} genus is one of: \emph{Enterococcus}, \emph{Staphylococcus}, \emph{Streptococcus}.}
#' \item{2: phylum is one of: Proteobacteria, Firmicutes, Actinobacteria, Sarcomastigophora \strong{or} genus is one of: \emph{Aspergillus}, \emph{Bacteroides}, \emph{Candida}, \emph{Capnocytophaga}, \emph{Chryseobacterium}, \emph{Cryptococcus}, \emph{Elisabethkingia}, \emph{Flavobacterium}, \emph{Fusobacterium}, \emph{Giardia}, \emph{Leptotrichia}, \emph{Mycoplasma}, \emph{Prevotella}, \emph{Rhodotorula}, \emph{Treponema}, \emph{Trichophyton}.}
#' \item{3 (least prevalent): all others.}
#' }
#'
#' Group 1 contains all common Gram negatives, like all Enterobacteriaceae and e.g. \emph{Pseudomonas} and \emph{Legionella}.
#'
#' Group 2 probably contains all microbial pathogens ever found in humans.
#' @inheritSection catalogue_of_life Catalogue of Life
# (source as a section, so it can be inherited by other man pages)
#' @section Source:
@ -251,7 +262,7 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
}
} else if (all(x %in% reference_df[, 1])
& all(reference_df[, "mo"] %in% microorganismsDT[["mo"]])) {
& all(reference_df[, "mo"] %in% microorganismsDT[, "mo"][[1]])) {
# all in reference df
colnames(reference_df)[1] <- "x"
suppressWarnings(
@ -261,7 +272,7 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
pull(property)
)
} else if (all(x %in% microorganismsDT[["mo"]])) {
} else if (all(x %in% microorganismsDT[, "mo"][[1]])) {
# existing mo codes when not looking for property "mo", like mo_genus("B_ESCHR_COL")
x <- microorganismsDT[data.table(mo = x), on = "mo", ..property][[1]]
@ -278,7 +289,7 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
y <- as.data.table(microorganisms.codes)[data.table(code = toupper(x)), on = "code", ]
x <- microorganismsDT[data.table(mo = y[["mo"]]), on = "mo", ..property][[1]]
} else if (!all(x %in% microorganismsDT[[property]])) {
} else if (!all(x %in% microorganismsDT[, ..property][[1]])) {
x_backup <- x

2
R/mo_property.R
View File

@ -494,7 +494,7 @@ mo_validate <- function(x, property, ...) {
# check onLoad() in R/zzz.R: data tables are created there.
}
if (!all(x %in% microorganismsDT[[property]])
if (!all(x %in% microorganismsDT[, ..property][[1]])
| Becker %in% c(TRUE, "all")
| Lancefield %in% c(TRUE, "all")) {
exec_as.mo(x, property = property, ...)

26
R/zzz.R
View File

@ -50,18 +50,28 @@ make_DT <- function() {
microorganismsDT <- AMR::microorganisms %>%
mutate(prevalence = case_when(
class == "Gammaproteobacteria"
| order %in% c("Lactobacillales", "Bacillales")
| genus %in% c("Enterococcus", "Staphylococcus", "Streptococcus")
~ 1,
phylum %in% c("Proteobacteria",
"Firmicutes",
"Actinobacteria",
"Bacteroidetes")
| genus %in% c("Candida",
"Aspergillus",
"Trichophyton",
"Sarcomastigophora")
| genus %in% c("Aspergillus",
"Bacteroides",
"Candida",
"Capnocytophaga",
"Chryseobacterium",
"Cryptococcus",
"Elisabethkingia",
"Flavobacterium",
"Fusobacterium",
"Giardia",
"Dientamoeba",
"Entamoeba")
"Leptotrichia",
"Mycoplasma",
"Prevotella",
"Rhodotorula",
"Treponema",
"Trichophyton")
~ 2,
TRUE ~ 3
)) %>%
@ -74,7 +84,7 @@ make_DT <- function() {
}
make_trans_tbl <- function() {
# conversion of old MO codes from v0.5.0 (ITIS) to later versions (Catalogue of Life)
# conversion of old MO codes from v0.5.0 (ITIS) to later versions (Catalogue of Life)
c(B_ACHRMB = "B_ACHRM", B_ANNMA = "B_ACTNS", B_ACLLS = "B_ALCYC",
B_AHNGM = "B_ARCHN", B_ARMTM = "B_ARMTMN", B_ARTHRS = "B_ARTHR",
B_APHLS = "B_AZRHZP", B_BRCHA = "B_BRCHY", B_BCTRM = "B_BRVBCT",

526
docs/articles/AMR.html
View File

@ -192,7 +192,7 @@
<h1>How to conduct AMR analysis</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">23 February 2019</h4>
<h4 class="date">25 February 2019</h4>
<div class="hidden name"><code>AMR.Rmd</code></div>
@ -201,7 +201,7 @@
<p><strong>Note:</strong> values on this page will change with every website update since they are based on randomly created values and the page was written in <a href="https://rmarkdown.rstudio.com/">RMarkdown</a>. However, the methodology remains unchanged. This page was generated on 23 February 2019.</p>
<p><strong>Note:</strong> values on this page will change with every website update since they are based on randomly created values and the page was written in <a href="https://rmarkdown.rstudio.com/">RMarkdown</a>. However, the methodology remains unchanged. This page was generated on 25 February 2019.</p>
<div id="introduction" class="section level1">
<h1 class="hasAnchor">
<a href="#introduction" class="anchor"></a>Introduction</h1>
@ -217,21 +217,21 @@
</tr></thead>
<tbody>
<tr class="odd">
<td align="center">2019-02-23</td>
<td align="center">2019-02-25</td>
<td align="center">abcd</td>
<td align="center">Escherichia coli</td>
<td align="center">S</td>
<td align="center">S</td>
</tr>
<tr class="even">
<td align="center">2019-02-23</td>
<td align="center">2019-02-25</td>
<td align="center">abcd</td>
<td align="center">Escherichia coli</td>
<td align="center">S</td>
<td align="center">R</td>
</tr>
<tr class="odd">
<td align="center">2019-02-23</td>
<td align="center">2019-02-25</td>
<td align="center">efgh</td>
<td align="center">Escherichia coli</td>
<td align="center">R</td>
@ -327,70 +327,70 @@
</tr></thead>
<tbody>
<tr class="odd">
<td align="center">2017-04-07</td>
<td align="center">O7</td>
<td align="center">2016-10-19</td>
<td align="center">U5</td>
<td align="center">Hospital B</td>
<td align="center">Staphylococcus aureus</td>
<td align="center">Escherichia coli</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">F</td>
</tr>
<tr class="even">
<td align="center">2017-04-12</td>
<td align="center">H4</td>
<td align="center">Hospital B</td>
<td align="center">Staphylococcus aureus</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">M</td>
</tr>
<tr class="odd">
<td align="center">2013-08-17</td>
<td align="center">C3</td>
<td align="center">Hospital B</td>
<td align="center">Streptococcus pneumoniae</td>
<td align="center">R</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
</tr>
<tr class="even">
<td align="center">2015-05-18</td>
<td align="center">E9</td>
<td align="center">Hospital B</td>
<td align="center">Klebsiella pneumoniae</td>
<td align="center">R</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
</tr>
<tr class="odd">
<td align="center">2012-12-26</td>
<td align="center">W4</td>
<td align="center">2016-05-27</td>
<td align="center">C10</td>
<td align="center">Hospital A</td>
<td align="center">Staphylococcus aureus</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
</tr>
<tr class="odd">
<td align="center">2014-11-05</td>
<td align="center">A2</td>
<td align="center">Hospital A</td>
<td align="center">Staphylococcus aureus</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">M</td>
</tr>
<tr class="even">
<td align="center">2017-03-21</td>
<td align="center">N6</td>
<td align="center">Hospital B</td>
<td align="center">Staphylococcus aureus</td>
<td align="center">S</td>
<td align="center">I</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">F</td>
</tr>
<tr class="odd">
<td align="center">2010-03-02</td>
<td align="center">X6</td>
<td align="center">Hospital B</td>
<td align="center">Escherichia coli</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">F</td>
</tr>
<tr class="even">
<td align="center">2016-09-28</td>
<td align="center">W1</td>
<td align="center">2015-08-17</td>
<td align="center">B8</td>
<td align="center">Hospital D</td>
<td align="center">Staphylococcus aureus</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">F</td>
<td align="center">M</td>
</tr>
</tbody>
</table>
@ -411,8 +411,8 @@
#&gt;
#&gt; Item Count Percent Cum. Count Cum. Percent
#&gt; --- ----- ------- -------- ----------- -------------
#&gt; 1 M 10,466 52.3% 10,466 52.3%
#&gt; 2 F 9,534 47.7% 20,000 100.0%</code></pre>
#&gt; 1 M 10,390 52.0% 10,390 52.0%
#&gt; 2 F 9,610 48.1% 20,000 100.0%</code></pre>
<p>So, we can draw at least two conclusions immediately. From a data scientist perspective, the data looks clean: only values <code>M</code> and <code>F</code>. From a researcher perspective: there are slightly more men. Nothing we didn’t already know.</p>
<p>The data is already quite clean, but we still need to transform some variables. The <code>bacteria</code> column now consists of text, and we want to add more variables based on microbial IDs later on. So, we will transform this column to valid IDs. The <code><a href="https://dplyr.tidyverse.org/reference/mutate.html">mutate()</a></code> function of the <code>dplyr</code> package makes this really easy:</p>
<div class="sourceCode" id="cb12"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb12-1" title="1">data &lt;-<span class="st"> </span>data <span class="op">%&gt;%</span></a>
@ -443,10 +443,10 @@
<a class="sourceLine" id="cb14-19" title="19"><span class="co">#&gt; Kingella kingae (no changes)</span></a>
<a class="sourceLine" id="cb14-20" title="20"><span class="co">#&gt; </span></a>
<a class="sourceLine" id="cb14-21" title="21"><span class="co">#&gt; EUCAST Expert Rules, Intrinsic Resistance and Exceptional Phenotypes (v3.1, 2016)</span></a>
<a class="sourceLine" id="cb14-22" title="22"><span class="co">#&gt; Table 1: Intrinsic resistance in Enterobacteriaceae (1291 changes)</span></a>
<a class="sourceLine" id="cb14-22" title="22"><span class="co">#&gt; Table 1: Intrinsic resistance in Enterobacteriaceae (1369 changes)</span></a>
<a class="sourceLine" id="cb14-23" title="23"><span class="co">#&gt; Table 2: Intrinsic resistance in non-fermentative Gram-negative bacteria (no changes)</span></a>
<a class="sourceLine" id="cb14-24" title="24"><span class="co">#&gt; Table 3: Intrinsic resistance in other Gram-negative bacteria (no changes)</span></a>
<a class="sourceLine" id="cb14-25" title="25"><span class="co">#&gt; Table 4: Intrinsic resistance in Gram-positive bacteria (2705 changes)</span></a>
<a class="sourceLine" id="cb14-25" title="25"><span class="co">#&gt; Table 4: Intrinsic resistance in Gram-positive bacteria (2815 changes)</span></a>
<a class="sourceLine" id="cb14-26" title="26"><span class="co">#&gt; Table 8: Interpretive rules for B-lactam agents and Gram-positive cocci (no changes)</span></a>
<a class="sourceLine" id="cb14-27" title="27"><span class="co">#&gt; Table 9: Interpretive rules for B-lactam agents and Gram-negative rods (no changes)</span></a>
<a class="sourceLine" id="cb14-28" title="28"><span class="co">#&gt; Table 10: Interpretive rules for B-lactam agents and other Gram-negative bacteria (no changes)</span></a>
@ -462,9 +462,9 @@
<a class="sourceLine" id="cb14-38" title="38"><span class="co">#&gt; Non-EUCAST: piperacillin/tazobactam = S where piperacillin = S (no changes)</span></a>
<a class="sourceLine" id="cb14-39" title="39"><span class="co">#&gt; Non-EUCAST: trimethoprim/sulfa = S where trimethoprim = S (no changes)</span></a>
<a class="sourceLine" id="cb14-40" title="40"><span class="co">#&gt; </span></a>
<a class="sourceLine" id="cb14-41" title="41"><span class="co">#&gt; =&gt; EUCAST rules affected 7,376 out of 20,000 rows</span></a>
<a class="sourceLine" id="cb14-41" title="41"><span class="co">#&gt; =&gt; EUCAST rules affected 7,563 out of 20,000 rows</span></a>
<a class="sourceLine" id="cb14-42" title="42"><span class="co">#&gt; -&gt; added 0 test results</span></a>
<a class="sourceLine" id="cb14-43" title="43"><span class="co">#&gt; -&gt; changed 3,996 test results (0 to S; 0 to I; 3,996 to R)</span></a></code></pre></div>
<a class="sourceLine" id="cb14-43" title="43"><span class="co">#&gt; -&gt; changed 4,184 test results (0 to S; 0 to I; 4,184 to R)</span></a></code></pre></div>
</div>
<div id="adding-new-variables" class="section level1">
<h1 class="hasAnchor">
@ -489,8 +489,8 @@
<a class="sourceLine" id="cb16-3" title="3"><span class="co">#&gt; </span><span class="al">NOTE</span><span class="co">: Using column `bacteria` as input for `col_mo`.</span></a>
<a class="sourceLine" id="cb16-4" title="4"><span class="co">#&gt; </span><span class="al">NOTE</span><span class="co">: Using column `date` as input for `col_date`.</span></a>
<a class="sourceLine" id="cb16-5" title="5"><span class="co">#&gt; </span><span class="al">NOTE</span><span class="co">: Using column `patient_id` as input for `col_patient_id`.</span></a>
<a class="sourceLine" id="cb16-6" title="6"><span class="co">#&gt; =&gt; Found 5,641 first isolates (28.2% of total)</span></a></code></pre></div>
<p>So only 28.2% is suitable for resistance analysis! We can now filter on it with the <code><a href="https://dplyr.tidyverse.org/reference/filter.html">filter()</a></code> function, also from the <code>dplyr</code> package:</p>
<a class="sourceLine" id="cb16-6" title="6"><span class="co">#&gt; =&gt; Found 5,780 first isolates (28.9% of total)</span></a></code></pre></div>
<p>So only 28.9% is suitable for resistance analysis! We can now filter on it with the <code><a href="https://dplyr.tidyverse.org/reference/filter.html">filter()</a></code> function, also from the <code>dplyr</code> package:</p>
<div class="sourceCode" id="cb17"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb17-1" title="1">data_1st &lt;-<span class="st"> </span>data <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb17-2" title="2"><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/filter.html">filter</a></span>(first <span class="op">==</span><span class="st"> </span><span class="ot">TRUE</span>)</a></code></pre></div>
<p>For future use, the above two syntaxes can be shortened with the <code><a href="../reference/first_isolate.html">filter_first_isolate()</a></code> function:</p>
@ -516,32 +516,32 @@
<tbody>
<tr class="odd">
<td align="center">1</td>
<td align="center">2010-01-24</td>
<td align="center">A4</td>
<td align="center">2010-01-05</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td align="center">2</td>
<td align="center">2010-03-30</td>
<td align="center">A4</td>
<td align="center">2010-03-10</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">I</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
</tr>
<tr class="odd">
<td align="center">3</td>
<td align="center">2010-07-21</td>
<td align="center">A4</td>
<td align="center">2010-07-15</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
@ -549,8 +549,8 @@
</tr>
<tr class="even">
<td align="center">4</td>
<td align="center">2010-09-23</td>
<td align="center">A4</td>
<td align="center">2010-09-07</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
@ -560,8 +560,8 @@
</tr>
<tr class="odd">
<td align="center">5</td>
<td align="center">2010-10-05</td>
<td align="center">A4</td>
<td align="center">2010-11-10</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
@ -571,55 +571,55 @@
</tr>
<tr class="even">
<td align="center">6</td>
<td align="center">2010-10-26</td>
<td align="center">A4</td>
<td align="center">2011-01-23</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">I</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
</tr>
<tr class="odd">
<td align="center">7</td>
<td align="center">2011-02-03</td>
<td align="center">A4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td align="center">7</td>
<td align="center">2011-02-21</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">I</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
</tr>
<tr class="even">
<td align="center">8</td>
<td align="center">2011-02-16</td>
<td align="center">A4</td>
<td align="center">2011-02-25</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
</tr>
<tr class="odd">
<td align="center">9</td>
<td align="center">2011-04-19</td>
<td align="center">A4</td>
<td align="center">2011-02-28</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
</tr>
<tr class="even">
<td align="center">10</td>
<td align="center">2011-05-17</td>
<td align="center">A4</td>
<td align="center">2011-04-03</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
@ -637,7 +637,7 @@
<a class="sourceLine" id="cb19-7" title="7"><span class="co">#&gt; </span><span class="al">NOTE</span><span class="co">: Using column `patient_id` as input for `col_patient_id`.</span></a>
<a class="sourceLine" id="cb19-8" title="8"><span class="co">#&gt; </span><span class="al">NOTE</span><span class="co">: Using column `keyab` as input for `col_keyantibiotics`. Use col_keyantibiotics = FALSE to prevent this.</span></a>
<a class="sourceLine" id="cb19-9" title="9"><span class="co">#&gt; [Criterion] Inclusion based on key antibiotics, ignoring I.</span></a>
<a class="sourceLine" id="cb19-10" title="10"><span class="co">#&gt; =&gt; Found 15,939 first weighted isolates (79.7% of total)</span></a></code></pre></div>
<a class="sourceLine" id="cb19-10" title="10"><span class="co">#&gt; =&gt; Found 15,963 first weighted isolates (79.8% of total)</span></a></code></pre></div>
<table class="table">
<thead><tr class="header">
<th align="center">isolate</th>
@ -654,11 +654,11 @@
<tbody>
<tr class="odd">
<td align="center">1</td>
<td align="center">2010-01-24</td>
<td align="center">A4</td>
<td align="center">2010-01-05</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">TRUE</td>
@ -666,20 +666,32 @@
</tr>
<tr class="even">
<td align="center">2</td>
<td align="center">2010-03-30</td>
<td align="center">A4</td>
<td align="center">2010-03-10</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">I</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td align="center">3</td>
<td align="center">2010-07-21</td>
<td align="center">A4</td>
<td align="center">2010-07-15</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">FALSE</td>
</tr>
<tr class="even">
<td align="center">4</td>
<td align="center">2010-09-07</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
@ -688,22 +700,10 @@
<td align="center">FALSE</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td align="center">4</td>
<td align="center">2010-09-23</td>
<td align="center">A4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">FALSE</td>
</tr>
<tr class="odd">
<td align="center">5</td>
<td align="center">2010-10-05</td>
<td align="center">A4</td>
<td align="center">2010-11-10</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
@ -714,47 +714,47 @@
</tr>
<tr class="even">
<td align="center">6</td>
<td align="center">2010-10-26</td>
<td align="center">A4</td>
<td align="center">2011-01-23</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">I</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td align="center">7</td>
<td align="center">2011-02-03</td>
<td align="center">A4</td>
<td align="center">2011-02-21</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">I</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">TRUE</td>
<td align="center">TRUE</td>
<td align="center">FALSE</td>
<td align="center">FALSE</td>
</tr>
<tr class="even">
<td align="center">8</td>
<td align="center">2011-02-16</td>
<td align="center">A4</td>
<td align="center">2011-02-25</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td align="center">9</td>
<td align="center">2011-04-19</td>
<td align="center">A4</td>
<td align="center">2011-02-28</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
@ -762,11 +762,11 @@
</tr>
<tr class="even">
<td align="center">10</td>
<td align="center">2011-05-17</td>
<td align="center">A4</td>
<td align="center">2011-04-03</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
@ -774,11 +774,11 @@
</tr>
</tbody>
</table>
<p>Instead of 2, now 8 isolates are flagged. In total, 79.7% of all isolates are marked ‘first weighted’ - 51.5% more than when using the CLSI guideline. In real life, this novel algorithm will yield 5-10% more isolates than the classic CLSI guideline.</p>
<p>Instead of 2, now 8 isolates are flagged. In total, 79.8% of all isolates are marked ‘first weighted’ - 50.9% more than when using the CLSI guideline. In real life, this novel algorithm will yield 5-10% more isolates than the classic CLSI guideline.</p>
<p>As with <code><a href="../reference/first_isolate.html">filter_first_isolate()</a></code>, there’s a shortcut for this new algorithm too:</p>
<div class="sourceCode" id="cb20"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb20-1" title="1">data_1st &lt;-<span class="st"> </span>data <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb20-2" title="2"><span class="st"> </span><span class="kw"><a href="../reference/first_isolate.html">filter_first_weighted_isolate</a></span>()</a></code></pre></div>
<p>So we end up with 15,939 isolates for analysis.</p>
<p>So we end up with 15,963 isolates for analysis.</p>
<p>We can remove unneeded columns:</p>
<div class="sourceCode" id="cb21"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb21-1" title="1">data_1st &lt;-<span class="st"> </span>data_1st <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb21-2" title="2"><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/select.html">select</a></span>(<span class="op">-</span><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/c">c</a></span>(first, keyab))</a></code></pre></div>
@ -803,89 +803,9 @@
</tr></thead>
<tbody>
<tr class="odd">
<td>2</td>
<td align="center">2017-04-12</td>
<td align="center">H4</td>
<td align="center">Hospital B</td>
<td align="center">B_STPHY_AUR</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">M</td>
<td align="center">Gram positive</td>
<td align="center">Staphylococcus</td>
<td align="center">aureus</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td>3</td>
<td align="center">2013-08-17</td>
<td align="center">C3</td>
<td align="center">Hospital B</td>
<td align="center">B_STRPT_PNE</td>
<td align="center">R</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">M</td>
<td align="center">Gram positive</td>
<td align="center">Streptococcus</td>
<td align="center">pneumoniae</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td>4</td>
<td align="center">2015-05-18</td>
<td align="center">E9</td>
<td align="center">Hospital B</td>
<td align="center">B_KLBSL_PNE</td>
<td align="center">R</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
<td align="center">Gram negative</td>
<td align="center">Klebsiella</td>
<td align="center">pneumoniae</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td>5</td>
<td align="center">2012-12-26</td>
<td align="center">W4</td>
<td align="center">Hospital A</td>
<td align="center">B_STPHY_AUR</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">F</td>
<td align="center">Gram positive</td>
<td align="center">Staphylococcus</td>
<td align="center">aureus</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td>6</td>
<td align="center">2016-09-28</td>
<td align="center">W1</td>
<td align="center">Hospital D</td>
<td align="center">B_STPHY_AUR</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">F</td>
<td align="center">Gram positive</td>
<td align="center">Staphylococcus</td>
<td align="center">aureus</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td>7</td>
<td align="center">2016-05-04</td>
<td align="center">R2</td>
<td>1</td>
<td align="center">2016-10-19</td>
<td align="center">U5</td>
<td align="center">Hospital B</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
@ -898,6 +818,86 @@
<td align="center">coli</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td>3</td>
<td align="center">2014-11-05</td>
<td align="center">A2</td>
<td align="center">Hospital A</td>
<td align="center">B_STPHY_AUR</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">M</td>
<td align="center">Gram positive</td>
<td align="center">Staphylococcus</td>
<td align="center">aureus</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td>5</td>
<td align="center">2010-03-02</td>
<td align="center">X6</td>
<td align="center">Hospital B</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">F</td>
<td align="center">Gram negative</td>
<td align="center">Escherichia</td>
<td align="center">coli</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td>6</td>
<td align="center">2015-08-17</td>
<td align="center">B8</td>
<td align="center">Hospital D</td>
<td align="center">B_STPHY_AUR</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
<td align="center">Gram positive</td>
<td align="center">Staphylococcus</td>
<td align="center">aureus</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td>7</td>
<td align="center">2013-01-25</td>
<td align="center">M3</td>
<td align="center">Hospital A</td>
<td align="center">B_STPHY_AUR</td>
<td align="center">R</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
<td align="center">Gram positive</td>
<td align="center">Staphylococcus</td>
<td align="center">aureus</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td>8</td>
<td align="center">2013-07-27</td>
<td align="center">E2</td>
<td align="center">Hospital C</td>
<td align="center">B_KLBSL_PNE</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
<td align="center">Gram negative</td>
<td align="center">Klebsiella</td>
<td align="center">pneumoniae</td>
<td align="center">TRUE</td>
</tr>
</tbody>
</table>
<p>Time for the analysis!</p>
@ -915,9 +915,9 @@
<div class="sourceCode" id="cb23"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb23-1" title="1"><span class="kw"><a href="../reference/freq.html">freq</a></span>(<span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/paste">paste</a></span>(data_1st<span class="op">$</span>genus, data_1st<span class="op">$</span>species))</a></code></pre></div>
<p>Or can be used like the <code>dplyr</code> way, which is easier readable:</p>
<div class="sourceCode" id="cb24"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb24-1" title="1">data_1st <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="../reference/freq.html">freq</a></span>(genus, species)</a></code></pre></div>
<p><strong>Frequency table of <code>genus</code> and <code>species</code> from a <code>data.frame</code> (15,939 x 13)</strong></p>
<p><strong>Frequency table of <code>genus</code> and <code>species</code> from a <code>data.frame</code> (15,963 x 13)</strong></p>
<p>Columns: 2<br>
Length: 15,939 (of which NA: 0 = 0.00%)<br>
Length: 15,963 (of which NA: 0 = 0.00%)<br>
Unique: 4</p>
<p>Shortest: 16<br>
Longest: 24</p>
@ -934,33 +934,33 @@ Longest: 24</p>
<tr class="odd">
<td align="left">1</td>
<td align="left">Escherichia coli</td>
<td align="right">8,055</td>
<td align="right">50.5%</td>
<td align="right">8,055</td>
<td align="right">50.5%</td>
<td align="right">7,910</td>
<td align="right">49.6%</td>
<td align="right">7,910</td>
<td align="right">49.6%</td>
</tr>
<tr class="even">
<td align="left">2</td>
<td align="left">Staphylococcus aureus</td>
<td align="right">3,886</td>
<td align="right">3,889</td>
<td align="right">24.4%</td>
<td align="right">11,941</td>
<td align="right">74.9%</td>
<td align="right">11,799</td>
<td align="right">73.9%</td>
</tr>
<tr class="odd">
<td align="left">3</td>
<td align="left">Streptococcus pneumoniae</td>
<td align="right">2,439</td>
<td align="right">15.3%</td>
<td align="right">14,380</td>
<td align="right">90.2%</td>
<td align="right">2,480</td>
<td align="right">15.5%</td>
<td align="right">14,279</td>
<td align="right">89.5%</td>
</tr>
<tr class="even">
<td align="left">4</td>
<td align="left">Klebsiella pneumoniae</td>
<td align="right">1,559</td>
<td align="right">9.8%</td>
<td align="right">15,939</td>
<td align="right">1,684</td>
<td align="right">10.5%</td>
<td align="right">15,963</td>
<td align="right">100.0%</td>
</tr>
</tbody>
@ -971,7 +971,7 @@ Longest: 24</p>
<a href="#resistance-percentages" class="anchor"></a>Resistance percentages</h2>
<p>The functions <code>portion_R</code>, <code>portion_RI</code>, <code>portion_I</code>, <code>portion_IS</code> and <code>portion_S</code> can be used to determine the portion of a specific antimicrobial outcome. They can be used on their own:</p>
<div class="sourceCode" id="cb25"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb25-1" title="1">data_1st <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="../reference/portion.html">portion_IR</a></span>(amox)</a>
<a class="sourceLine" id="cb25-2" title="2"><span class="co">#&gt; [1] 0.4705439</span></a></code></pre></div>
<a class="sourceLine" id="cb25-2" title="2"><span class="co">#&gt; [1] 0.4748481</span></a></code></pre></div>
<p>Or can be used in conjuction with <code><a href="https://dplyr.tidyverse.org/reference/group_by.html">group_by()</a></code> and <code><a href="https://dplyr.tidyverse.org/reference/summarise.html">summarise()</a></code>, both from the <code>dplyr</code> package:</p>
<div class="sourceCode" id="cb26"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb26-1" title="1">data_1st <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb26-2" title="2"><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/group_by.html">group_by</a></span>(hospital) <span class="op">%&gt;%</span><span class="st"> </span></a>
@ -984,19 +984,19 @@ Longest: 24</p>
<tbody>
<tr class="odd">
<td align="center">Hospital A</td>
<td align="center">0.4616191</td>
<td align="center">0.4765396</td>
</tr>
<tr class="even">
<td align="center">Hospital B</td>
<td align="center">0.4714054</td>
<td align="center">0.4750632</td>
</tr>
<tr class="odd">
<td align="center">Hospital C</td>
<td align="center">0.4865089</td>
<td align="center">0.4830405</td>
</tr>
<tr class="even">
<td align="center">Hospital D</td>
<td align="center">0.4703324</td>
<td align="center">0.4657107</td>
</tr>
</tbody>
</table>
@ -1014,23 +1014,23 @@ Longest: 24</p>
<tbody>
<tr class="odd">
<td align="center">Hospital A</td>
<td align="center">0.4616191</td>
<td align="center">4768</td>
<td align="center">0.4765396</td>
<td align="center">4774</td>
</tr>
<tr class="even">
<td align="center">Hospital B</td>
<td align="center">0.4714054</td>
<td align="center">5543</td>
<td align="center">0.4750632</td>
<td align="center">5534</td>
</tr>
<tr class="odd">
<td align="center">Hospital C</td>
<td align="center">0.4865089</td>
<td align="center">2409</td>
<td align="center">0.4830405</td>
<td align="center">2447</td>
</tr>
<tr class="even">
<td align="center">Hospital D</td>
<td align="center">0.4703324</td>
<td align="center">3219</td>
<td align="center">0.4657107</td>
<td align="center">3208</td>
</tr>
</tbody>
</table>
@ -1050,27 +1050,27 @@ Longest: 24</p>
<tbody>
<tr class="odd">
<td align="center">Escherichia</td>
<td align="center">0.7251397</td>
<td align="center">0.9020484</td>
<td align="center">0.9738051</td>
<td align="center">0.7353982</td>
<td align="center">0.8972187</td>
<td align="center">0.9734513</td>
</tr>
<tr class="even">
<td align="center">Klebsiella</td>
<td align="center">0.7305965</td>
<td align="center">0.8941629</td>
<td align="center">0.9737011</td>
<td align="center">0.7369359</td>
<td align="center">0.9014252</td>
<td align="center">0.9786223</td>
</tr>
<tr class="odd">
<td align="center">Staphylococcus</td>
<td align="center">0.7174472</td>
<td align="center">0.9217705</td>
<td align="center">0.9804426</td>
<td align="center">0.7413217</td>
<td align="center">0.9161738</td>
<td align="center">0.9763435</td>
</tr>
<tr class="even">
<td align="center">Streptococcus</td>
<td align="center">0.7437474</td>
<td align="center">0.7181452</td>
<td align="center">0.0000000</td>
<td align="center">0.7437474</td>
<td align="center">0.7181452</td>
</tr>
</tbody>
</table>

BIN
docs/articles/AMR_files/figure-html/plot 1-1.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 33 KiB

After

Width:  |  Height:  |  Size: 33 KiB

BIN
docs/articles/AMR_files/figure-html/plot 3-1.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 21 KiB

After

Width:  |  Height:  |  Size: 21 KiB

BIN
docs/articles/AMR_files/figure-html/plot 4-1.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 68 KiB

After

Width:  |  Height:  |  Size: 68 KiB

BIN
docs/articles/AMR_files/figure-html/plot 5-1.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 50 KiB

After

Width:  |  Height:  |  Size: 50 KiB

2
docs/articles/EUCAST.html
View File

@ -192,7 +192,7 @@
<h1>How to apply EUCAST rules</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">23 February 2019</h4>
<h4 class="date">25 February 2019</h4>
<div class="hidden name"><code>EUCAST.Rmd</code></div>

2
docs/articles/G_test.html
View File

@ -192,7 +192,7 @@
<h1>How to use the <em>G</em>-test</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">23 February 2019</h4>
<h4 class="date">25 February 2019</h4>
<div class="hidden name"><code>G_test.Rmd</code></div>

2
docs/articles/WHONET.html
View File

@ -192,7 +192,7 @@
<h1>How to work with WHONET data</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">23 February 2019</h4>
<h4 class="date">25 February 2019</h4>
<div class="hidden name"><code>WHONET.Rmd</code></div>

2
docs/articles/atc_property.html
View File

@ -192,7 +192,7 @@
<h1>How to get properties of an antibiotic</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">23 February 2019</h4>
<h4 class="date">25 February 2019</h4>
<div class="hidden name"><code>atc_property.Rmd</code></div>

83
docs/articles/benchmarks.html
View File

@ -192,7 +192,7 @@
<h1>Benchmarks</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">23 February 2019</h4>
<h4 class="date">25 February 2019</h4>
<div class="hidden name"><code>benchmarks.Rmd</code></div>
@ -217,14 +217,14 @@
<a class="sourceLine" id="cb2-8" title="8"> <span class="dt">times =</span> <span class="dv">10</span>)</a>
<a class="sourceLine" id="cb2-9" title="9"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/print">print</a></span>(S.aureus, <span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">signif =</span> <span class="dv">3</span>)</a>
<a class="sourceLine" id="cb2-10" title="10"><span class="co">#&gt; Unit: milliseconds</span></a>
<a class="sourceLine" id="cb2-11" title="11"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb2-12" title="12"><span class="co">#&gt; as.mo("sau") 15.0 15.0 21.8 15.2 15.5 80.5 10</span></a>
<a class="sourceLine" id="cb2-13" title="13"><span class="co">#&gt; as.mo("stau") 90.4 90.6 106.0 91.0 92.7 180.0 10</span></a>
<a class="sourceLine" id="cb2-14" title="14"><span class="co">#&gt; as.mo("staaur") 15.0 15.1 19.2 15.2 15.7 54.5 10</span></a>
<a class="sourceLine" id="cb2-15" title="15"><span class="co">#&gt; as.mo("S. aureus") 26.5 26.6 34.7 26.9 28.1 65.9 10</span></a>
<a class="sourceLine" id="cb2-16" title="16"><span class="co">#&gt; as.mo("S. aureus") 26.6 26.7 31.8 26.8 26.9 76.8 10</span></a>
<a class="sourceLine" id="cb2-17" title="17"><span class="co">#&gt; as.mo("STAAUR") 15.0 15.1 19.2 15.2 15.5 54.2 10</span></a>
<a class="sourceLine" id="cb2-18" title="18"><span class="co">#&gt; as.mo("Staphylococcus aureus") 13.4 13.5 17.7 13.6 14.7 52.1 10</span></a></code></pre></div>
<a class="sourceLine" id="cb2-11" title="11"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb2-12" title="12"><span class="co">#&gt; as.mo("sau") 16.4 16.5 28.4 16.8 54.9 55.8 10</span></a>
<a class="sourceLine" id="cb2-13" title="13"><span class="co">#&gt; as.mo("stau") 86.0 86.5 97.3 88.9 100.0 132.0 10</span></a>
<a class="sourceLine" id="cb2-14" title="14"><span class="co">#&gt; as.mo("staaur") 16.3 16.6 23.0 16.8 21.0 56.8 10</span></a>
<a class="sourceLine" id="cb2-15" title="15"><span class="co">#&gt; as.mo("S. aureus") 25.3 25.9 39.4 27.2 64.0 74.5 10</span></a>
<a class="sourceLine" id="cb2-16" title="16"><span class="co">#&gt; as.mo("S. aureus") 25.2 25.3 29.7 25.6 27.0 64.3 10</span></a>
<a class="sourceLine" id="cb2-17" title="17"><span class="co">#&gt; as.mo("STAAUR") 16.3 16.7 21.1 17.0 18.0 56.8 10</span></a>
<a class="sourceLine" id="cb2-18" title="18"><span class="co">#&gt; as.mo("Staphylococcus aureus") 13.5 13.9 20.5 14.4 17.5 51.2 10</span></a></code></pre></div>
<p>In the table above, all measurements are shown in milliseconds (thousands of seconds). A value of 10 milliseconds means it can determine 100 input values per second. It case of 50 milliseconds, this is only 20 input values per second. The second input is the only one that has to be looked up thoroughly. All the others are known codes (the first is a WHONET code) or common laboratory codes, or common full organism names like the last one.</p>
<p>To achieve this speed, the <code>as.mo</code> function also takes into account the prevalence of human pathogenic microorganisms. The downside is of course that less prevalent microorganisms will be determined less fast. See this example for the ID of <em>Mycoplasma leonicaptivi</em> (<code>B_MYCPL_LEO</code>), a bug probably never found before in humans:</p>
<div class="sourceCode" id="cb3"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb3-1" title="1">M.leonicaptivi &lt;-<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/microbenchmark/topics/microbenchmark">microbenchmark</a></span>(<span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"myle"</span>),</a>
@ -236,14 +236,21 @@
<a class="sourceLine" id="cb3-7" title="7"> <span class="dt">times =</span> <span class="dv">10</span>)</a>
<a class="sourceLine" id="cb3-8" title="8"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/print">print</a></span>(M.leonicaptivi, <span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">signif =</span> <span class="dv">3</span>)</a>
<a class="sourceLine" id="cb3-9" title="9"><span class="co">#&gt; Unit: milliseconds</span></a>
<a class="sourceLine" id="cb3-10" title="10"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb3-11" title="11"><span class="co">#&gt; as.mo("myle") 136 137 141 137 138 176 10</span></a>
<a class="sourceLine" id="cb3-12" title="12"><span class="co">#&gt; as.mo("mycleo") 447 464 484 487 490 551 10</span></a>
<a class="sourceLine" id="cb3-13" title="13"><span class="co">#&gt; as.mo("M. leonicaptivi") 206 208 225 210 248 252 10</span></a>
<a class="sourceLine" id="cb3-14" title="14"><span class="co">#&gt; as.mo("M. leonicaptivi") 207 208 230 229 251 255 10</span></a>
<a class="sourceLine" id="cb3-15" title="15"><span class="co">#&gt; as.mo("MYCLEO") 444 446 462 446 486 487 10</span></a>
<a class="sourceLine" id="cb3-16" title="16"><span class="co">#&gt; as.mo("Mycoplasma leonicaptivi") 147 148 170 173 187 192 10</span></a></code></pre></div>
<p>That takes 8 times as much time on average! A value of 100 milliseconds means it can only determine ~10 different input values per second. We can conclude that looking up arbitrary codes of less prevalent microorganisms is the worst way to go, in terms of calculation performance.</p>
<a class="sourceLine" id="cb3-10" title="10"><span class="co">#&gt; expr min lq mean median uq max</span></a>
<a class="sourceLine" id="cb3-11" title="11"><span class="co">#&gt; as.mo("myle") 135.0 135.0 147.0 135.0 174.0 176.0</span></a>
<a class="sourceLine" id="cb3-12" title="12"><span class="co">#&gt; as.mo("mycleo") 211.0 213.0 233.0 232.0 251.0 262.0</span></a>
<a class="sourceLine" id="cb3-13" title="13"><span class="co">#&gt; as.mo("M. leonicaptivi") 59.2 59.2 63.6 59.4 59.6 98.7</span></a>
<a class="sourceLine" id="cb3-14" title="14"><span class="co">#&gt; as.mo("M. leonicaptivi") 59.0 59.1 59.3 59.3 59.3 59.7</span></a>
<a class="sourceLine" id="cb3-15" title="15"><span class="co">#&gt; as.mo("MYCLEO") 211.0 211.0 220.0 211.0 222.0 250.0</span></a>
<a class="sourceLine" id="cb3-16" title="16"><span class="co">#&gt; as.mo("Mycoplasma leonicaptivi") 22.5 22.5 26.5 22.6 22.7 61.0</span></a>
<a class="sourceLine" id="cb3-17" title="17"><span class="co">#&gt; neval</span></a>
<a class="sourceLine" id="cb3-18" title="18"><span class="co">#&gt; 10</span></a>
<a class="sourceLine" id="cb3-19" title="19"><span class="co">#&gt; 10</span></a>
<a class="sourceLine" id="cb3-20" title="20"><span class="co">#&gt; 10</span></a>
<a class="sourceLine" id="cb3-21" title="21"><span class="co">#&gt; 10</span></a>
<a class="sourceLine" id="cb3-22" title="22"><span class="co">#&gt; 10</span></a>
<a class="sourceLine" id="cb3-23" title="23"><span class="co">#&gt; 10</span></a></code></pre></div>
<p>That takes 3.4 times as much time on average! A value of 100 milliseconds means it can only determine ~10 different input values per second. We can conclude that looking up arbitrary codes of less prevalent microorganisms is the worst way to go, in terms of calculation performance.</p>
<p>In the figure below, we compare <em>Escherichia coli</em> (which is very common) with <em>Prevotella brevis</em> (which is moderately common) and with <em>Mycoplasma leonicaptivi</em> (which is very uncommon):</p>
<div class="sourceCode" id="cb4"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb4-1" title="1"><span class="kw"><a href="https://www.rdocumentation.org/packages/graphics/topics/par">par</a></span>(<span class="dt">mar =</span> <span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/c">c</a></span>(<span class="dv">5</span>, <span class="dv">16</span>, <span class="dv">4</span>, <span class="dv">2</span>)) <span class="co"># set more space for left margin text (16)</span></a>
<a class="sourceLine" id="cb4-2" title="2"></a>
@ -283,8 +290,8 @@
<a class="sourceLine" id="cb5-18" title="18"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/print">print</a></span>(run_it, <span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">signif =</span> <span class="dv">3</span>)</a>
<a class="sourceLine" id="cb5-19" title="19"><span class="co">#&gt; Unit: milliseconds</span></a>
<a class="sourceLine" id="cb5-20" title="20"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb5-21" title="21"><span class="co">#&gt; mo_fullname(x) 615 647 698 649 801 851 10</span></a></code></pre></div>
<p>So transforming 500,000 values (!) of 95 unique values only takes 0.65 seconds (649 ms). You only lose time on your unique input values.</p>
<a class="sourceLine" id="cb5-21" title="21"><span class="co">#&gt; mo_fullname(x) 610 641 644 644 657 665 10</span></a></code></pre></div>
<p>So transforming 500,000 values (!) of 95 unique values only takes 0.64 seconds (644 ms). You only lose time on your unique input values.</p>
</div>
<div id="precalculated-results" class="section level3">
<h3 class="hasAnchor">
@ -297,10 +304,10 @@
<a class="sourceLine" id="cb6-5" title="5"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/print">print</a></span>(run_it, <span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">signif =</span> <span class="dv">3</span>)</a>
<a class="sourceLine" id="cb6-6" title="6"><span class="co">#&gt; Unit: milliseconds</span></a>
<a class="sourceLine" id="cb6-7" title="7"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb6-8" title="8"><span class="co">#&gt; A 6.420 6.570 6.670 6.730 6.760 6.780 10</span></a>
<a class="sourceLine" id="cb6-9" title="9"><span class="co">#&gt; B 27.100 27.200 28.000 27.600 27.800 32.900 10</span></a>
<a class="sourceLine" id="cb6-10" title="10"><span class="co">#&gt; C 0.255 0.383 0.394 0.412 0.431 0.527 10</span></a></code></pre></div>
<p>So going from <code><a href="../reference/mo_property.html">mo_fullname("Staphylococcus aureus")</a></code> to <code>"Staphylococcus aureus"</code> takes 0.0004 seconds - it doesn’t even start calculating <em>if the result would be the same as the expected resulting value</em>. That goes for all helper functions:</p>
<a class="sourceLine" id="cb6-8" title="8"><span class="co">#&gt; A 7.500 7.540 7.720 7.610 7.710 8.750 10</span></a>
<a class="sourceLine" id="cb6-9" title="9"><span class="co">#&gt; B 25.800 26.200 27.100 27.800 27.800 27.900 10</span></a>
<a class="sourceLine" id="cb6-10" title="10"><span class="co">#&gt; C 0.604 0.628 0.704 0.729 0.755 0.791 10</span></a></code></pre></div>
<p>So going from <code><a href="../reference/mo_property.html">mo_fullname("Staphylococcus aureus")</a></code> to <code>"Staphylococcus aureus"</code> takes 0.0007 seconds - it doesn’t even start calculating <em>if the result would be the same as the expected resulting value</em>. That goes for all helper functions:</p>
<div class="sourceCode" id="cb7"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb7-1" title="1">run_it &lt;-<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/microbenchmark/topics/microbenchmark">microbenchmark</a></span>(<span class="dt">A =</span> <span class="kw"><a href="../reference/mo_property.html">mo_species</a></span>(<span class="st">"aureus"</span>),</a>
<a class="sourceLine" id="cb7-2" title="2"> <span class="dt">B =</span> <span class="kw"><a href="../reference/mo_property.html">mo_genus</a></span>(<span class="st">"Staphylococcus"</span>),</a>
<a class="sourceLine" id="cb7-3" title="3"> <span class="dt">C =</span> <span class="kw"><a href="../reference/mo_property.html">mo_fullname</a></span>(<span class="st">"Staphylococcus aureus"</span>),</a>
@ -313,14 +320,14 @@
<a class="sourceLine" id="cb7-10" title="10"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/print">print</a></span>(run_it, <span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">signif =</span> <span class="dv">3</span>)</a>
<a class="sourceLine" id="cb7-11" title="11"><span class="co">#&gt; Unit: milliseconds</span></a>
<a class="sourceLine" id="cb7-12" title="12"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb7-13" title="13"><span class="co">#&gt; A 0.311 0.355 0.435 0.437 0.492 0.566 10</span></a>
<a class="sourceLine" id="cb7-14" title="14"><span class="co">#&gt; B 0.283 0.299 0.340 0.337 0.362 0.411 10</span></a>
<a class="sourceLine" id="cb7-15" title="15"><span class="co">#&gt; C 0.393 0.447 0.503 0.496 0.566 0.662 10</span></a>
<a class="sourceLine" id="cb7-16" title="16"><span class="co">#&gt; D 0.253 0.288 0.324 0.305 0.325 0.523 10</span></a>
<a class="sourceLine" id="cb7-17" title="17"><span class="co">#&gt; E 0.243 0.249 0.315 0.288 0.342 0.506 10</span></a>
<a class="sourceLine" id="cb7-18" title="18"><span class="co">#&gt; F 0.239 0.295 0.349 0.327 0.411 0.482 10</span></a>
<a class="sourceLine" id="cb7-19" title="19"><span class="co">#&gt; G 0.249 0.323 0.364 0.347 0.410 0.493 10</span></a>
<a class="sourceLine" id="cb7-20" title="20"><span class="co">#&gt; H 0.226 0.303 0.368 0.339 0.478 0.523 10</span></a></code></pre></div>
<a class="sourceLine" id="cb7-13" title="13"><span class="co">#&gt; A 0.704 0.806 0.897 0.867 1.040 1.130 10</span></a>
<a class="sourceLine" id="cb7-14" title="14"><span class="co">#&gt; B 0.671 0.722 0.841 0.807 0.903 1.110 10</span></a>
<a class="sourceLine" id="cb7-15" title="15"><span class="co">#&gt; C 0.702 0.768 0.856 0.816 0.967 1.160 10</span></a>
<a class="sourceLine" id="cb7-16" title="16"><span class="co">#&gt; D 0.641 0.695 0.746 0.746 0.755 0.976 10</span></a>
<a class="sourceLine" id="cb7-17" title="17"><span class="co">#&gt; E 0.627 0.702 0.781 0.762 0.789 1.100 10</span></a>
<a class="sourceLine" id="cb7-18" title="18"><span class="co">#&gt; F 0.651 0.694 0.779 0.733 0.761 1.220 10</span></a>
<a class="sourceLine" id="cb7-19" title="19"><span class="co">#&gt; G 0.552 0.745 0.801 0.764 0.815 1.090 10</span></a>
<a class="sourceLine" id="cb7-20" title="20"><span class="co">#&gt; H 0.637 0.661 0.722 0.724 0.766 0.803 10</span></a></code></pre></div>
<p>Of course, when running <code><a href="../reference/mo_property.html">mo_phylum("Firmicutes")</a></code> the function has zero knowledge about the actual microorganism, namely <em>S. aureus</em>. But since the result would be <code>"Firmicutes"</code> too, there is no point in calculating the result. And because this package ‘knows’ all phyla of all known bacteria (according to the Catalogue of Life), it can just return the initial value immediately.</p>
</div>
<div id="results-in-other-languages" class="section level3">
@ -347,13 +354,13 @@
<a class="sourceLine" id="cb8-18" title="18"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/print">print</a></span>(run_it, <span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">signif =</span> <span class="dv">4</span>)</a>
<a class="sourceLine" id="cb8-19" title="19"><span class="co">#&gt; Unit: milliseconds</span></a>
<a class="sourceLine" id="cb8-20" title="20"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb8-21" title="21"><span class="co">#&gt; en 17.14 17.39 20.87 17.54 17.93 50.49 10</span></a>
<a class="sourceLine" id="cb8-22" title="22"><span class="co">#&gt; de 25.94 26.02 32.71 26.11 26.24 59.33 10</span></a>
<a class="sourceLine" id="cb8-23" title="23"><span class="co">#&gt; nl 25.41 25.86 29.47 26.04 27.08 59.40 10</span></a>
<a class="sourceLine" id="cb8-24" title="24"><span class="co">#&gt; es 25.55 25.97 32.75 26.11 26.77 59.62 10</span></a>
<a class="sourceLine" id="cb8-25" title="25"><span class="co">#&gt; it 25.65 25.90 26.07 26.09 26.11 26.75 10</span></a>
<a class="sourceLine" id="cb8-26" title="26"><span class="co">#&gt; fr 25.47 25.79 26.10 26.09 26.20 27.23 10</span></a>
<a class="sourceLine" id="cb8-27" title="27"><span class="co">#&gt; pt 25.72 25.85 29.33 26.07 26.09 59.41 10</span></a></code></pre></div>
<a class="sourceLine" id="cb8-21" title="21"><span class="co">#&gt; en 18.95 18.99 19.59 19.04 19.49 23.47 10</span></a>
<a class="sourceLine" id="cb8-22" title="22"><span class="co">#&gt; de 27.13 27.26 27.69 27.63 27.88 29.05 10</span></a>
<a class="sourceLine" id="cb8-23" title="23"><span class="co">#&gt; nl 26.95 27.62 34.90 27.99 32.35 61.05 10</span></a>
<a class="sourceLine" id="cb8-24" title="24"><span class="co">#&gt; es 27.42 27.55 38.05 27.75 60.86 61.40 10</span></a>
<a class="sourceLine" id="cb8-25" title="25"><span class="co">#&gt; it 26.99 27.30 34.13 27.48 27.70 61.28 10</span></a>
<a class="sourceLine" id="cb8-26" title="26"><span class="co">#&gt; fr 27.35 27.52 30.95 27.58 27.72 61.11 10</span></a>
<a class="sourceLine" id="cb8-27" title="27"><span class="co">#&gt; pt 27.26 27.33 27.67 27.53 27.91 28.44 10</span></a></code></pre></div>
<p>Currently supported are German, Dutch, Spanish, Italian, French and Portuguese.</p>
</div>
</div>

BIN
docs/articles/benchmarks_files/figure-html/unnamed-chunk-5-1.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 29 KiB

After

Width:  |  Height:  |  Size: 32 KiB

2
docs/articles/freq.html
View File

@ -192,7 +192,7 @@
<h1>How to create frequency tables</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">23 February 2019</h4>
<h4 class="date">25 February 2019</h4>
<div class="hidden name"><code>freq.Rmd</code></div>

2
docs/articles/mo_property.html
View File

@ -192,7 +192,7 @@
<h1>How to get properties of a microorganism</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">23 February 2019</h4>
<h4 class="date">25 February 2019</h4>
<div class="hidden name"><code>mo_property.Rmd</code></div>

2
docs/articles/resistance_predict.html
View File

@ -192,7 +192,7 @@
<h1>How to predict antimicrobial resistance</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">23 February 2019</h4>
<h4 class="date">25 February 2019</h4>
<div class="hidden name"><code>resistance_predict.Rmd</code></div>

15
docs/reference/as.mo.html
View File

@ -302,7 +302,7 @@
<p>Use the <code><a href='mo_property.html'>mo_property</a></code> functions to get properties based on the returned code, see Examples.</p>
<p>This function uses Artificial Intelligence (AI) to help getting fast and logical results. It tries to find matches in this order:</p><ul>
<li><p>Taxonomic kingdom: it first searches in Bacteria, then Fungi, then Protozoa</p></li>
<li><p>Human pathogenic prevalence: it first searches in more prevalent microorganisms, then less prevalent ones</p></li>
<li><p>Human pathogenic prevalence: it first searches in more prevalent microorganisms, then less prevalent ones (see section <em>Microbial prevalence of pathogens in humans</em>)</p></li>
<li><p>Valid MO codes and full names: it first searches in already valid MO code and known genus/species combinations</p></li>
<li><p>Breakdown of input values: from here it starts to breakdown input values to find possible matches</p></li>
</ul>
@ -329,6 +329,17 @@ When using <code>allow_uncertain = TRUE</code> (which is the default setting), i
<p>Use <code>mo_uncertainties()</code> to get a vector with all values that were coerced to a valid value, but with uncertainty.</p>
<p>Use <code>mo_renamed()</code> to get a vector with all values that could be coerced based on an old, previously accepted taxonomic name.</p>
<h2 class="hasAnchor" id="microbial-prevalence-of-pathogens-in-humans"><a class="anchor" href="#microbial-prevalence-of-pathogens-in-humans"></a>Microbial prevalence of pathogens in humans</h2>
<p>The artificial intelligence takes into account microbial prevalence of pathogens in humans. It uses three groups and every (sub)species is in the group it matches first. These groups are:</p><ul>
<li><p>1 (most prevalent): class is Gammaproteobacteria <strong>or</strong> genus is one of: <em>Enterococcus</em>, <em>Staphylococcus</em>, <em>Streptococcus</em>.</p></li>
<li><p>2: phylum is one of: Proteobacteria, Firmicutes, Actinobacteria, Sarcomastigophora <strong>or</strong> genus is one of: <em>Aspergillus</em>, <em>Bacteroides</em>, <em>Candida</em>, <em>Capnocytophaga</em>, <em>Chryseobacterium</em>, <em>Cryptococcus</em>, <em>Elisabethkingia</em>, <em>Flavobacterium</em>, <em>Fusobacterium</em>, <em>Giardia</em>, <em>Leptotrichia</em>, <em>Mycoplasma</em>, <em>Prevotella</em>, <em>Rhodotorula</em>, <em>Treponema</em>, <em>Trichophyton</em>.</p></li>
<li><p>3 (least prevalent): all others.</p></li>
</ul>
<p>Group 1 contains all common Gram negatives, like all Enterobacteriaceae and e.g. <em>Pseudomonas</em> and <em>Legionella</em>.</p>
<p>Group 2 probably contains all microbial pathogens ever found in humans.</p>
<h2 class="hasAnchor" id="source"><a class="anchor" href="#source"></a>Source</h2>
@ -421,6 +432,8 @@ The <code><a href='mo_property.html'>mo_property</a></code> functions (like <cod
<li><a href="#details">Details</a></li>
<li><a href="#microbial-prevalence-of-pathogens-in-humans">Microbial prevalence of pathogens in humans</a></li>
<li><a href="#source">Source</a></li>
<li><a href="#catalogue-of-life">Catalogue of Life</a></li>

16
man/as.mo.Rd
View File

@ -63,7 +63,7 @@ Use the \code{\link{mo_property}} functions to get properties based on the retur
This function uses Artificial Intelligence (AI) to help getting fast and logical results. It tries to find matches in this order:
\itemize{
\item{Taxonomic kingdom: it first searches in Bacteria, then Fungi, then Protozoa}
\item{Human pathogenic prevalence: it first searches in more prevalent microorganisms, then less prevalent ones}
\item{Human pathogenic prevalence: it first searches in more prevalent microorganisms, then less prevalent ones (see section \emph{Microbial prevalence of pathogens in humans})}
\item{Valid MO codes and full names: it first searches in already valid MO code and known genus/species combinations}
\item{Breakdown of input values: from here it starts to breakdown input values to find possible matches}
}
@ -100,6 +100,20 @@ Use \code{mo_uncertainties()} to get a vector with all values that were coerced
Use \code{mo_renamed()} to get a vector with all values that could be coerced based on an old, previously accepted taxonomic name.
}
\section{Microbial prevalence of pathogens in humans}{
The artificial intelligence takes into account microbial prevalence of pathogens in humans. It uses three groups and every (sub)species is in the group it matches first. These groups are:
\itemize{
\item{1 (most prevalent): class is Gammaproteobacteria \strong{or} genus is one of: \emph{Enterococcus}, \emph{Staphylococcus}, \emph{Streptococcus}.}
\item{2: phylum is one of: Proteobacteria, Firmicutes, Actinobacteria, Sarcomastigophora \strong{or} genus is one of: \emph{Aspergillus}, \emph{Bacteroides}, \emph{Candida}, \emph{Capnocytophaga}, \emph{Chryseobacterium}, \emph{Cryptococcus}, \emph{Elisabethkingia}, \emph{Flavobacterium}, \emph{Fusobacterium}, \emph{Giardia}, \emph{Leptotrichia}, \emph{Mycoplasma}, \emph{Prevotella}, \emph{Rhodotorula}, \emph{Treponema}, \emph{Trichophyton}.}
\item{3 (least prevalent): all others.}
}
Group 1 contains all common Gram negatives, like all Enterobacteriaceae and e.g. \emph{Pseudomonas} and \emph{Legionella}.
Group 2 probably contains all microbial pathogens ever found in humans.
}
\section{Source}{
[1] Becker K \emph{et al.} \strong{Coagulase-Negative Staphylococci}. 2014. Clin Microbiol Rev. 27(4): 870–926. \url{https://dx.doi.org/10.1128/CMR.00109-13}