1
0
mirror of https://github.com/msberends/AMR.git synced 2024-12-25 07:26:12 +01:00

(v1.3.0.9031) matching score update

This commit is contained in:
dr. M.S. (Matthijs) Berends 2020-09-26 16:51:17 +02:00
parent 050a9a04fb
commit 22f6ceb3e4
19 changed files with 85 additions and 81 deletions

View File

@ -1,5 +1,5 @@
Package: AMR
Version: 1.3.0.9030
Version: 1.3.0.9031
Date: 2020-09-26
Title: Antimicrobial Resistance Analysis
Authors@R: c(

View File

@ -1,4 +1,4 @@
# AMR 1.3.0.9030
# AMR 1.3.0.9031
## <small>Last updated: 26 September 2020</small>
Note: some changes in this version were suggested by anonymous reviewers from the journal we submitted our manuscipt to. We are those reviewers very grateful for going through our code so thoroughly!

16
R/mo.R
View File

@ -301,7 +301,7 @@ exec_as.mo <- function(x,
initial = initial_search,
uncertainty = actual_uncertainty,
input_actual = actual_input) {
if (!is.null(input_actual)) {
input <- input_actual
} else {
@ -318,7 +318,7 @@ exec_as.mo <- function(x,
if (NROW(res_df) > 1 & uncertainty != -1) {
# sort the findings on matching score
scores <- mo_matching_score(x = input,
fullname = res_df[, "fullname", drop = TRUE])
n = res_df[, "fullname", drop = TRUE])
res_df <- res_df[order(scores, decreasing = TRUE), , drop = FALSE]
}
res <- as.character(res_df[, column, drop = TRUE])
@ -442,7 +442,7 @@ exec_as.mo <- function(x,
# we need special treatment for very prevalent full names, they are likely!
# e.g. as.mo("Staphylococcus aureus")
x <- MO_lookup[match(tolower(x), MO_lookup$fullname_lower), property, drop = TRUE]
} else if (all(x %in% reference_data_to_use$fullname)) {
# we need special treatment for very prevalent full names, they are likely!
# e.g. as.mo("Staphylococcus aureus")
@ -1544,7 +1544,7 @@ exec_as.mo <- function(x,
# this will save the uncertain items as attribute, so they can be bound to `uncertainties` in the uncertain_fn() function
x <- structure(x, uncertainties = uncertainties)
}
if (old_mo_warning == TRUE & property != "mo") {
warning("The input contained old microorganism IDs from previous versions of this package.\nPlease use `as.mo()` on these old IDs to transform them to the new format.\nSUPPORT FOR THIS WILL BE DROPPED IN A FUTURE VERSION.", call. = FALSE)
@ -1639,7 +1639,7 @@ freq.mo <- function(x, ...) {
")"),
`No. of genera` = pm_n_distinct(mo_genus(x_noNA, language = NULL)),
`No. of species` = pm_n_distinct(paste(mo_genus(x_noNA, language = NULL),
mo_species(x_noNA, language = NULL)))))
mo_species(x_noNA, language = NULL)))))
}
#' @method print mo
@ -1773,7 +1773,7 @@ print.mo_uncertainties <- function(x, ...) {
if (x[i, ]$candidates != "") {
candidates <- unlist(strsplit(x[i, ]$candidates, ", ", fixed = TRUE))
scores <- mo_matching_score(x = x[i, ]$input,
fullname = candidates)
n = candidates)
# sort on descending scores
candidates <- candidates[order(1 - scores)]
n_candidates <- length(candidates)
@ -1799,8 +1799,8 @@ print.mo_uncertainties <- function(x, ...) {
ifelse(!is.na(x[i, ]$renamed_to), paste(", renamed to", font_italic(x[i, ]$renamed_to)), ""),
" (", x[i, ]$mo,
", matching score = ", trimws(percentage(mo_matching_score(x = x[i, ]$input,
fullname = x[i, ]$fullname),
digits = 1)),
n = x[i, ]$fullname),
digits = 1)),
") "),
uncertainty_interpretation,
candidates),

View File

@ -24,20 +24,21 @@
#' This helper function is used by [as.mo()] to determine the most probable match of taxonomic records, based on user input.
#' @param x Any user input value(s)
#' @param n A full taxonomic name, that exists in [`microorganisms$fullname`][microorganisms]
#' @param uncertainty The level of uncertainty set in [as.mo()], see `allow_uncertain` in that function (here, it defaults to 1, but is automatically determined in [as.mo()] based on the number of transformations needed to get to a result)
#' @section Matching score for microorganisms:
#' With ambiguous user input in [as.mo()] and all the [`mo_*`][mo_property()] functions, the returned results are chosen based on their matching score using [mo_matching_score()]. This matching score \eqn{m} is calculated as:
#' With ambiguous user input in [as.mo()] and all the [`mo_*`][mo_property()] functions, the returned results are chosen based on their matching score using [mo_matching_score()]. This matching score \eqn{m}, ranging from 0 to 100%, is calculated as:
#'
#' \deqn{m_{(x, n)} = \frac{l_{n} - 0.5 \times \min \begin{cases}l_{n} \\ \operatorname{lev}(x, n)\end{cases}}{l_{n} p k}}{m(x, n) = ( l_n * min(l_n, lev(x, n) ) ) / ( l_n * p * k )}
#' \deqn{m_{(x, n)} = \frac{l_{n} - 0.5 \cdot \min \begin{cases}l_{n} \\ \operatorname{lev}(x, n)\end{cases}}{l_{n} \cdot p_{n} \cdot k_{n}}}{m(x, n) = ( l_n * min(l_n, lev(x, n) ) ) / ( l_n * p_n * k_n )}
#'
#' where:
#'
#' * \eqn{x} is the user input;
#' * \eqn{n} is a taxonomic name (genus, species and subspecies);
#' * \eqn{l_{n}}{l_n} is the length of the taxonomic name;
#' * \eqn{\operatorname{lev}}{lev} is the [Levenshtein distance](https://en.wikipedia.org/wiki/Levenshtein_distance) function;
#' * \eqn{p} is the human pathogenic prevalence, categorised into group \eqn{1}, \eqn{2} and \eqn{3} (see *Details* in `?as.mo`), meaning that \eqn{p = \{1, 2 , 3\}}{p = {1, 2, 3}};
#' * \eqn{k} is the kingdom index, set as follows: Bacteria = \eqn{1}, Fungi = \eqn{2}, Protozoa = \eqn{3}, Archaea = \eqn{4}, and all others = \eqn{5}, meaning that \eqn{k = \{1, 2 , 3, 4, 5\}}{k = {1, 2, 3, 4, 5}}.
#' * \eqn{n} is a taxonomic name (genus, species and subspecies) as found in [`microorganisms$fullname`][microorganisms];
#' * \eqn{l_{n}}{l_n} is the length of \eqn{n};
#' * \eqn{\operatorname{lev}}{lev} is the [Levenshtein distance function](https://en.wikipedia.org/wiki/Levenshtein_distance);
#' * \eqn{p_{n}}{p_n} is the human pathogenic prevalence of \eqn{n}, categorised into group \eqn{1}, \eqn{2} and \eqn{3} (see *Details* in `?as.mo`), meaning that \eqn{p = \{1, 2 , 3\}}{p = {1, 2, 3}};
#' * \eqn{k_{n}}{k_n} is the kingdom index of \eqn{n}, set as follows: Bacteria = \eqn{1}, Fungi = \eqn{2}, Protozoa = \eqn{3}, Archaea = \eqn{4}, and all others = \eqn{5}, meaning that \eqn{k = \{1, 2 , 3, 4, 5\}}{k = {1, 2, 3, 4, 5}}.
#'
#' This means that the user input `x = "E. coli"` gets for *Escherichia coli* a matching score of `r percentage(mo_matching_score("E. coli", "Escherichia coli"), 1)` and for *Entamoeba coli* a matching score of `r percentage(mo_matching_score("E. coli", "Entamoeba coli"), 1)`.
#'
#' All matches are sorted descending on their matching score and for all user input values, the top match will be returned.
#' @export

View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="https://msberends.github.io/AMR/index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9030</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9031</span>
</span>
</div>

View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9030</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9031</span>
</span>
</div>

View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="../index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9030</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9031</span>
</span>
</div>

View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9030</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9031</span>
</span>
</div>

View File

@ -43,7 +43,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9030</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9031</span>
</span>
</div>

View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="../index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9030</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9031</span>
</span>
</div>
@ -236,9 +236,9 @@
<small>Source: <a href='https://github.com/msberends/AMR/blob/master/NEWS.md'><code>NEWS.md</code></a></small>
</div>
<div id="amr-1309030" class="section level1">
<h1 class="page-header" data-toc-text="1.3.0.9030">
<a href="#amr-1309030" class="anchor"></a>AMR 1.3.0.9030<small> Unreleased </small>
<div id="amr-1309031" class="section level1">
<h1 class="page-header" data-toc-text="1.3.0.9031">
<a href="#amr-1309031" class="anchor"></a>AMR 1.3.0.9031<small> Unreleased </small>
</h1>
<div id="last-updated-26-september-2020" class="section level2">
<h2 class="hasAnchor">

View File

@ -2,7 +2,7 @@ pandoc: 2.7.3
pkgdown: 1.5.1.9000
pkgdown_sha: eae56f08694abebf93cdfc0dd8e9ede06d8c815f
articles: []
last_built: 2020-09-26T14:25Z
last_built: 2020-09-26T14:51Z
urls:
reference: https://msberends.github.io/AMR/reference
article: https://msberends.github.io/AMR/articles

View File

@ -82,7 +82,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="../index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9030</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9031</span>
</span>
</div>
@ -388,17 +388,18 @@ The <a href='lifecycle.html'>lifecycle</a> of this function is <strong>stable</s
<p>With ambiguous user input in <code>as.mo()</code> and all the <code><a href='mo_property.html'>mo_*</a></code> functions, the returned results are chosen based on their matching score using <code><a href='mo_matching_score.html'>mo_matching_score()</a></code>. This matching score \(m\) is calculated as:</p>
<p>$$m_{(x, n)} = \frac{l_{n} - 0.5 \times \min \begin{cases}l_{n} \\ \operatorname{lev}(x, n)\end{cases}}{l_{n} p k}$$</p>
<p>With ambiguous user input in <code>as.mo()</code> and all the <code><a href='mo_property.html'>mo_*</a></code> functions, the returned results are chosen based on their matching score using <code><a href='mo_matching_score.html'>mo_matching_score()</a></code>. This matching score \(m\), ranging from 0 to 100%, is calculated as:</p>
<p>$$m_{(x, n)} = \frac{l_{n} - 0.5 \cdot \min \begin{cases}l_{n} \\ \operatorname{lev}(x, n)\end{cases}}{l_{n} \cdot p_{n} \cdot k_{n}}$$</p>
<p>where:</p><ul>
<li><p>\(x\) is the user input;</p></li>
<li><p>\(n\) is a taxonomic name (genus, species and subspecies);</p></li>
<li><p>\(l_{n}\) is the length of the taxonomic name;</p></li>
<li><p>\(\operatorname{lev}\) is the <a href='https://en.wikipedia.org/wiki/Levenshtein_distance'>Levenshtein distance</a> function;</p></li>
<li><p>\(p\) is the human pathogenic prevalence, categorised into group \(1\), \(2\) and \(3\) (see <em>Details</em> in <code>?as.mo</code>), meaning that \(p = \{1, 2 , 3\}\);</p></li>
<li><p>\(k\) is the kingdom index, set as follows: Bacteria = \(1\), Fungi = \(2\), Protozoa = \(3\), Archaea = \(4\), and all others = \(5\), meaning that \(k = \{1, 2 , 3, 4, 5\}\).</p></li>
<li><p>\(n\) is a taxonomic name (genus, species and subspecies) as found in <code><a href='microorganisms.html'>microorganisms$fullname</a></code>;</p></li>
<li><p>\(l_{n}\) is the length of \(n\);</p></li>
<li><p>\(\operatorname{lev}\) is the <a href='https://en.wikipedia.org/wiki/Levenshtein_distance'>Levenshtein distance function</a>;</p></li>
<li><p>\(p_{n}\) is the human pathogenic prevalence of \(n\), categorised into group \(1\), \(2\) and \(3\) (see <em>Details</em> in <code>?as.mo</code>), meaning that \(p = \{1, 2 , 3\}\);</p></li>
<li><p>\(k_{n}\) is the kingdom index of \(n\), set as follows: Bacteria = \(1\), Fungi = \(2\), Protozoa = \(3\), Archaea = \(4\), and all others = \(5\), meaning that \(k = \{1, 2 , 3, 4, 5\}\).</p></li>
</ul>
<p>This means that the user input <code>x = "E. coli"</code> gets for <em>Escherichia coli</em> a matching score of 68.8% and for <em>Entamoeba coli</em> a matching score of 7.9%.</p>
<p>All matches are sorted descending on their matching score and for all user input values, the top match will be returned.</p>
<h2 class="hasAnchor" id="catalogue-of-life"><a class="anchor" href="#catalogue-of-life"></a>Catalogue of Life</h2>

View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="../index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9030</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9031</span>
</span>
</div>

View File

@ -82,7 +82,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="../index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9030</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9031</span>
</span>
</div>
@ -255,27 +255,24 @@
<th>n</th>
<td><p>A full taxonomic name, that exists in <code><a href='microorganisms.html'>microorganisms$fullname</a></code></p></td>
</tr>
<tr>
<th>uncertainty</th>
<td><p>The level of uncertainty set in <code><a href='as.mo.html'>as.mo()</a></code>, see <code>allow_uncertain</code> in that function (here, it defaults to 1, but is automatically determined in <code><a href='as.mo.html'>as.mo()</a></code> based on the number of transformations needed to get to a result)</p></td>
</tr>
</table>
<h2 class="hasAnchor" id="matching-score-for-microorganisms"><a class="anchor" href="#matching-score-for-microorganisms"></a>Matching score for microorganisms</h2>
<p>With ambiguous user input in <code><a href='as.mo.html'>as.mo()</a></code> and all the <code><a href='mo_property.html'>mo_*</a></code> functions, the returned results are chosen based on their matching score using <code>mo_matching_score()</code>. This matching score \(m\) is calculated as:</p>
<p>$$m_{(x, n)} = \frac{l_{n} - 0.5 \times \min \begin{cases}l_{n} \\ \operatorname{lev}(x, n)\end{cases}}{l_{n} p k}$$</p>
<p>With ambiguous user input in <code><a href='as.mo.html'>as.mo()</a></code> and all the <code><a href='mo_property.html'>mo_*</a></code> functions, the returned results are chosen based on their matching score using <code>mo_matching_score()</code>. This matching score \(m\), ranging from 0 to 100%, is calculated as:</p>
<p>$$m_{(x, n)} = \frac{l_{n} - 0.5 \cdot \min \begin{cases}l_{n} \\ \operatorname{lev}(x, n)\end{cases}}{l_{n} \cdot p_{n} \cdot k_{n}}$$</p>
<p>where:</p><ul>
<li><p>\(x\) is the user input;</p></li>
<li><p>\(n\) is a taxonomic name (genus, species and subspecies);</p></li>
<li><p>\(l_{n}\) is the length of the taxonomic name;</p></li>
<li><p>\(\operatorname{lev}\) is the <a href='https://en.wikipedia.org/wiki/Levenshtein_distance'>Levenshtein distance</a> function;</p></li>
<li><p>\(p\) is the human pathogenic prevalence, categorised into group \(1\), \(2\) and \(3\) (see <em>Details</em> in <code><a href='as.mo.html'>?as.mo</a></code>), meaning that \(p = \{1, 2 , 3\}\);</p></li>
<li><p>\(k\) is the kingdom index, set as follows: Bacteria = \(1\), Fungi = \(2\), Protozoa = \(3\), Archaea = \(4\), and all others = \(5\), meaning that \(k = \{1, 2 , 3, 4, 5\}\).</p></li>
<li><p>\(n\) is a taxonomic name (genus, species and subspecies) as found in <code><a href='microorganisms.html'>microorganisms$fullname</a></code>;</p></li>
<li><p>\(l_{n}\) is the length of \(n\);</p></li>
<li><p>\(\operatorname{lev}\) is the <a href='https://en.wikipedia.org/wiki/Levenshtein_distance'>Levenshtein distance function</a>;</p></li>
<li><p>\(p_{n}\) is the human pathogenic prevalence of \(n\), categorised into group \(1\), \(2\) and \(3\) (see <em>Details</em> in <code><a href='as.mo.html'>?as.mo</a></code>), meaning that \(p = \{1, 2 , 3\}\);</p></li>
<li><p>\(k_{n}\) is the kingdom index of \(n\), set as follows: Bacteria = \(1\), Fungi = \(2\), Protozoa = \(3\), Archaea = \(4\), and all others = \(5\), meaning that \(k = \{1, 2 , 3, 4, 5\}\).</p></li>
</ul>
<p>This means that the user input <code>x = "E. coli"</code> gets for <em>Escherichia coli</em> a matching score of 68.8% and for <em>Entamoeba coli</em> a matching score of 7.9%.</p>
<p>All matches are sorted descending on their matching score and for all user input values, the top match will be returned.</p>
<h2 class="hasAnchor" id="examples"><a class="anchor" href="#examples"></a>Examples</h2>

View File

@ -82,7 +82,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="../index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9030</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9031</span>
</span>
</div>
@ -350,17 +350,18 @@ The <a href='lifecycle.html'>lifecycle</a> of this function is <strong>stable</s
<p>With ambiguous user input in <code><a href='as.mo.html'>as.mo()</a></code> and all the <code>mo_*</code> functions, the returned results are chosen based on their matching score using <code><a href='mo_matching_score.html'>mo_matching_score()</a></code>. This matching score \(m\) is calculated as:</p>
<p>$$m_{(x, n)} = \frac{l_{n} - 0.5 \times \min \begin{cases}l_{n} \\ \operatorname{lev}(x, n)\end{cases}}{l_{n} p k}$$</p>
<p>With ambiguous user input in <code><a href='as.mo.html'>as.mo()</a></code> and all the <code>mo_*</code> functions, the returned results are chosen based on their matching score using <code><a href='mo_matching_score.html'>mo_matching_score()</a></code>. This matching score \(m\), ranging from 0 to 100%, is calculated as:</p>
<p>$$m_{(x, n)} = \frac{l_{n} - 0.5 \cdot \min \begin{cases}l_{n} \\ \operatorname{lev}(x, n)\end{cases}}{l_{n} \cdot p_{n} \cdot k_{n}}$$</p>
<p>where:</p><ul>
<li><p>\(x\) is the user input;</p></li>
<li><p>\(n\) is a taxonomic name (genus, species and subspecies);</p></li>
<li><p>\(l_{n}\) is the length of the taxonomic name;</p></li>
<li><p>\(\operatorname{lev}\) is the <a href='https://en.wikipedia.org/wiki/Levenshtein_distance'>Levenshtein distance</a> function;</p></li>
<li><p>\(p\) is the human pathogenic prevalence, categorised into group \(1\), \(2\) and \(3\) (see <em>Details</em> in <code><a href='as.mo.html'>?as.mo</a></code>), meaning that \(p = \{1, 2 , 3\}\);</p></li>
<li><p>\(k\) is the kingdom index, set as follows: Bacteria = \(1\), Fungi = \(2\), Protozoa = \(3\), Archaea = \(4\), and all others = \(5\), meaning that \(k = \{1, 2 , 3, 4, 5\}\).</p></li>
<li><p>\(n\) is a taxonomic name (genus, species and subspecies) as found in <code><a href='microorganisms.html'>microorganisms$fullname</a></code>;</p></li>
<li><p>\(l_{n}\) is the length of \(n\);</p></li>
<li><p>\(\operatorname{lev}\) is the <a href='https://en.wikipedia.org/wiki/Levenshtein_distance'>Levenshtein distance function</a>;</p></li>
<li><p>\(p_{n}\) is the human pathogenic prevalence of \(n\), categorised into group \(1\), \(2\) and \(3\) (see <em>Details</em> in <code><a href='as.mo.html'>?as.mo</a></code>), meaning that \(p = \{1, 2 , 3\}\);</p></li>
<li><p>\(k_{n}\) is the kingdom index of \(n\), set as follows: Bacteria = \(1\), Fungi = \(2\), Protozoa = \(3\), Archaea = \(4\), and all others = \(5\), meaning that \(k = \{1, 2 , 3, 4, 5\}\).</p></li>
</ul>
<p>This means that the user input <code>x = "E. coli"</code> gets for <em>Escherichia coli</em> a matching score of 68.8% and for <em>Entamoeba coli</em> a matching score of 7.9%.</p>
<p>All matches are sorted descending on their matching score and for all user input values, the top match will be returned.</p>
<h2 class="hasAnchor" id="catalogue-of-life"><a class="anchor" href="#catalogue-of-life"></a>Catalogue of Life</h2>

View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9030</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0.9031</span>
</span>
</div>

View File

@ -146,20 +146,22 @@ If the unlying code needs breaking changes, they will occur gradually. For examp
\section{Matching score for microorganisms}{
With ambiguous user input in \code{\link[=as.mo]{as.mo()}} and all the \code{\link[=mo_property]{mo_*}} functions, the returned results are chosen based on their matching score using \code{\link[=mo_matching_score]{mo_matching_score()}}. This matching score \eqn{m} is calculated as:
With ambiguous user input in \code{\link[=as.mo]{as.mo()}} and all the \code{\link[=mo_property]{mo_*}} functions, the returned results are chosen based on their matching score using \code{\link[=mo_matching_score]{mo_matching_score()}}. This matching score \eqn{m}, ranging from 0 to 100\%, is calculated as:
\deqn{m_{(x, n)} = \frac{l_{n} - 0.5 \times \min \begin{cases}l_{n} \\ \operatorname{lev}(x, n)\end{cases}}{l_{n} p k}}{m(x, n) = ( l_n * min(l_n, lev(x, n) ) ) / ( l_n * p * k )}
\deqn{m_{(x, n)} = \frac{l_{n} - 0.5 \cdot \min \begin{cases}l_{n} \\ \operatorname{lev}(x, n)\end{cases}}{l_{n} \cdot p_{n} \cdot k_{n}}}{m(x, n) = ( l_n * min(l_n, lev(x, n) ) ) / ( l_n * p_n * k_n )}
where:
\itemize{
\item \eqn{x} is the user input;
\item \eqn{n} is a taxonomic name (genus, species and subspecies);
\item \eqn{l_{n}}{l_n} is the length of the taxonomic name;
\item \eqn{\operatorname{lev}}{lev} is the \href{https://en.wikipedia.org/wiki/Levenshtein_distance}{Levenshtein distance} function;
\item \eqn{p} is the human pathogenic prevalence, categorised into group \eqn{1}, \eqn{2} and \eqn{3} (see \emph{Details} in \code{?as.mo}), meaning that \eqn{p = \{1, 2 , 3\}}{p = {1, 2, 3}};
\item \eqn{k} is the kingdom index, set as follows: Bacteria = \eqn{1}, Fungi = \eqn{2}, Protozoa = \eqn{3}, Archaea = \eqn{4}, and all others = \eqn{5}, meaning that \eqn{k = \{1, 2 , 3, 4, 5\}}{k = {1, 2, 3, 4, 5}}.
\item \eqn{n} is a taxonomic name (genus, species and subspecies) as found in \code{\link[=microorganisms]{microorganisms$fullname}};
\item \eqn{l_{n}}{l_n} is the length of \eqn{n};
\item \eqn{\operatorname{lev}}{lev} is the \href{https://en.wikipedia.org/wiki/Levenshtein_distance}{Levenshtein distance function};
\item \eqn{p_{n}}{p_n} is the human pathogenic prevalence of \eqn{n}, categorised into group \eqn{1}, \eqn{2} and \eqn{3} (see \emph{Details} in \code{?as.mo}), meaning that \eqn{p = \{1, 2 , 3\}}{p = {1, 2, 3}};
\item \eqn{k_{n}}{k_n} is the kingdom index of \eqn{n}, set as follows: Bacteria = \eqn{1}, Fungi = \eqn{2}, Protozoa = \eqn{3}, Archaea = \eqn{4}, and all others = \eqn{5}, meaning that \eqn{k = \{1, 2 , 3, 4, 5\}}{k = {1, 2, 3, 4, 5}}.
}
This means that the user input \code{x = "E. coli"} gets for \emph{Escherichia coli} a matching score of 68.8\% and for \emph{Entamoeba coli} a matching score of 7.9\%.
All matches are sorted descending on their matching score and for all user input values, the top match will be returned.
}

View File

@ -10,28 +10,28 @@ mo_matching_score(x, n)
\item{x}{Any user input value(s)}
\item{n}{A full taxonomic name, that exists in \code{\link[=microorganisms]{microorganisms$fullname}}}
\item{uncertainty}{The level of uncertainty set in \code{\link[=as.mo]{as.mo()}}, see \code{allow_uncertain} in that function (here, it defaults to 1, but is automatically determined in \code{\link[=as.mo]{as.mo()}} based on the number of transformations needed to get to a result)}
}
\description{
This helper function is used by \code{\link[=as.mo]{as.mo()}} to determine the most probable match of taxonomic records, based on user input.
}
\section{Matching score for microorganisms}{
With ambiguous user input in \code{\link[=as.mo]{as.mo()}} and all the \code{\link[=mo_property]{mo_*}} functions, the returned results are chosen based on their matching score using \code{\link[=mo_matching_score]{mo_matching_score()}}. This matching score \eqn{m} is calculated as:
With ambiguous user input in \code{\link[=as.mo]{as.mo()}} and all the \code{\link[=mo_property]{mo_*}} functions, the returned results are chosen based on their matching score using \code{\link[=mo_matching_score]{mo_matching_score()}}. This matching score \eqn{m}, ranging from 0 to 100\%, is calculated as:
\deqn{m_{(x, n)} = \frac{l_{n} - 0.5 \times \min \begin{cases}l_{n} \\ \operatorname{lev}(x, n)\end{cases}}{l_{n} p k}}{m(x, n) = ( l_n * min(l_n, lev(x, n) ) ) / ( l_n * p * k )}
\deqn{m_{(x, n)} = \frac{l_{n} - 0.5 \cdot \min \begin{cases}l_{n} \\ \operatorname{lev}(x, n)\end{cases}}{l_{n} \cdot p_{n} \cdot k_{n}}}{m(x, n) = ( l_n * min(l_n, lev(x, n) ) ) / ( l_n * p_n * k_n )}
where:
\itemize{
\item \eqn{x} is the user input;
\item \eqn{n} is a taxonomic name (genus, species and subspecies);
\item \eqn{l_{n}}{l_n} is the length of the taxonomic name;
\item \eqn{\operatorname{lev}}{lev} is the \href{https://en.wikipedia.org/wiki/Levenshtein_distance}{Levenshtein distance} function;
\item \eqn{p} is the human pathogenic prevalence, categorised into group \eqn{1}, \eqn{2} and \eqn{3} (see \emph{Details} in \code{?as.mo}), meaning that \eqn{p = \{1, 2 , 3\}}{p = {1, 2, 3}};
\item \eqn{k} is the kingdom index, set as follows: Bacteria = \eqn{1}, Fungi = \eqn{2}, Protozoa = \eqn{3}, Archaea = \eqn{4}, and all others = \eqn{5}, meaning that \eqn{k = \{1, 2 , 3, 4, 5\}}{k = {1, 2, 3, 4, 5}}.
\item \eqn{n} is a taxonomic name (genus, species and subspecies) as found in \code{\link[=microorganisms]{microorganisms$fullname}};
\item \eqn{l_{n}}{l_n} is the length of \eqn{n};
\item \eqn{\operatorname{lev}}{lev} is the \href{https://en.wikipedia.org/wiki/Levenshtein_distance}{Levenshtein distance function};
\item \eqn{p_{n}}{p_n} is the human pathogenic prevalence of \eqn{n}, categorised into group \eqn{1}, \eqn{2} and \eqn{3} (see \emph{Details} in \code{?as.mo}), meaning that \eqn{p = \{1, 2 , 3\}}{p = {1, 2, 3}};
\item \eqn{k_{n}}{k_n} is the kingdom index of \eqn{n}, set as follows: Bacteria = \eqn{1}, Fungi = \eqn{2}, Protozoa = \eqn{3}, Archaea = \eqn{4}, and all others = \eqn{5}, meaning that \eqn{k = \{1, 2 , 3, 4, 5\}}{k = {1, 2, 3, 4, 5}}.
}
This means that the user input \code{x = "E. coli"} gets for \emph{Escherichia coli} a matching score of 68.8\% and for \emph{Entamoeba coli} a matching score of 7.9\%.
All matches are sorted descending on their matching score and for all user input values, the top match will be returned.
}

View File

@ -126,20 +126,22 @@ If the unlying code needs breaking changes, they will occur gradually. For examp
\section{Matching score for microorganisms}{
With ambiguous user input in \code{\link[=as.mo]{as.mo()}} and all the \code{\link[=mo_property]{mo_*}} functions, the returned results are chosen based on their matching score using \code{\link[=mo_matching_score]{mo_matching_score()}}. This matching score \eqn{m} is calculated as:
With ambiguous user input in \code{\link[=as.mo]{as.mo()}} and all the \code{\link[=mo_property]{mo_*}} functions, the returned results are chosen based on their matching score using \code{\link[=mo_matching_score]{mo_matching_score()}}. This matching score \eqn{m}, ranging from 0 to 100\%, is calculated as:
\deqn{m_{(x, n)} = \frac{l_{n} - 0.5 \times \min \begin{cases}l_{n} \\ \operatorname{lev}(x, n)\end{cases}}{l_{n} p k}}{m(x, n) = ( l_n * min(l_n, lev(x, n) ) ) / ( l_n * p * k )}
\deqn{m_{(x, n)} = \frac{l_{n} - 0.5 \cdot \min \begin{cases}l_{n} \\ \operatorname{lev}(x, n)\end{cases}}{l_{n} \cdot p_{n} \cdot k_{n}}}{m(x, n) = ( l_n * min(l_n, lev(x, n) ) ) / ( l_n * p_n * k_n )}
where:
\itemize{
\item \eqn{x} is the user input;
\item \eqn{n} is a taxonomic name (genus, species and subspecies);
\item \eqn{l_{n}}{l_n} is the length of the taxonomic name;
\item \eqn{\operatorname{lev}}{lev} is the \href{https://en.wikipedia.org/wiki/Levenshtein_distance}{Levenshtein distance} function;
\item \eqn{p} is the human pathogenic prevalence, categorised into group \eqn{1}, \eqn{2} and \eqn{3} (see \emph{Details} in \code{?as.mo}), meaning that \eqn{p = \{1, 2 , 3\}}{p = {1, 2, 3}};
\item \eqn{k} is the kingdom index, set as follows: Bacteria = \eqn{1}, Fungi = \eqn{2}, Protozoa = \eqn{3}, Archaea = \eqn{4}, and all others = \eqn{5}, meaning that \eqn{k = \{1, 2 , 3, 4, 5\}}{k = {1, 2, 3, 4, 5}}.
\item \eqn{n} is a taxonomic name (genus, species and subspecies) as found in \code{\link[=microorganisms]{microorganisms$fullname}};
\item \eqn{l_{n}}{l_n} is the length of \eqn{n};
\item \eqn{\operatorname{lev}}{lev} is the \href{https://en.wikipedia.org/wiki/Levenshtein_distance}{Levenshtein distance function};
\item \eqn{p_{n}}{p_n} is the human pathogenic prevalence of \eqn{n}, categorised into group \eqn{1}, \eqn{2} and \eqn{3} (see \emph{Details} in \code{?as.mo}), meaning that \eqn{p = \{1, 2 , 3\}}{p = {1, 2, 3}};
\item \eqn{k_{n}}{k_n} is the kingdom index of \eqn{n}, set as follows: Bacteria = \eqn{1}, Fungi = \eqn{2}, Protozoa = \eqn{3}, Archaea = \eqn{4}, and all others = \eqn{5}, meaning that \eqn{k = \{1, 2 , 3, 4, 5\}}{k = {1, 2, 3, 4, 5}}.
}
This means that the user input \code{x = "E. coli"} gets for \emph{Escherichia coli} a matching score of 68.8\% and for \emph{Entamoeba coli} a matching score of 7.9\%.
All matches are sorted descending on their matching score and for all user input values, the top match will be returned.
}