# HG changeset patch
# User ufz
# Date 1753182564 0
# Node ID 3a7f73d638ba5b651438b2e9b88833a336bb8e6a
# Parent  315c2ed31af1d35b3a6af913eac8d1bff4b3b1ca
planemo upload for repository https://github.com/Helmholtz-UFZ/ufz-galaxy-tools/blob/main/tools/phi-toolkit commit 368e8a7322c9763c648637263d4695abc146be13

diff -r 315c2ed31af1 -r 3a7f73d638ba logo.jpg
Binary file logo.jpg has changed
diff -r 315c2ed31af1 -r 3a7f73d638ba phitk.xml
--- a/phitk.xml	Wed Jun 04 17:36:40 2025 +0000
+++ b/phitk.xml	Tue Jul 22 11:09:24 2025 +0000
@@ -1,47 +1,48 @@
 <tool id="phi_toolkit_report" name="PHI toolkit report" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.01" license="MIT">
     <description></description>
+    <icon src="logo.jpg"/>
     <macros>
-        <token name="@TOOL_VERSION@">0.1.0</token>
+        <token name="@TOOL_VERSION@">0.2.0</token>
         <token name="@VERSION_SUFFIX@">0</token>
 
-        <xml name="zenodo_collection_element" tokens="id">
-            <element name="@ID@" location="https://zenodo.org/records/15594463/files/NC_000913.fasta.fasta?download=1" value="genomes/@ID@.fasta.fasta" ftype="fasta"/>
+        <xml name="zenodo_collection_element" tokens="id" token_suffix="">
+            <element name="@ID@@SUFFIX@" location="https://zenodo.org/records/15594463/files/@ID@.fasta.fasta?download=1" value="genomes/@ID@.fasta" ftype="fasta"/>
         </xml>
 
-        <xml name="test_collection_element" tokens="id,folder,ext">
-            <element name="@ID@" value="@FOLDER@/@ID@.fasta.@EXT@" ftype="@EXT@"/>
+        <xml name="test_collection_element" tokens="id,folder,ext,suffix">
+            <element name="@ID@@SUFFIX@" value="@FOLDER@/@ID@.fasta.@EXT@" ftype="@EXT@"/>
         </xml>
-        <xml name="test_collection_non_empty" tokens="name,folder,ext">
+        <xml name="test_collection_non_empty" tokens="name,folder,ext" token_suffix="">
             <param name="@NAME@">
                 <collection type="list">
-                    <expand macro="test_collection_element" id="NC_000913" folder="@FOLDER@" ext="@EXT@"/>
-                    <expand macro="test_collection_element" id="NC_002737" folder="@FOLDER@" ext="@EXT@"/>
-                    <expand macro="test_collection_element" id="NC_008261" folder="@FOLDER@" ext="@EXT@"/>
-                    <expand macro="test_collection_element" id="NC_009012" folder="@FOLDER@" ext="@EXT@"/>
-                    <expand macro="test_collection_element" id="NC_014168" folder="@FOLDER@" ext="@EXT@"/>
-                    <expand macro="test_collection_element" id="NC_014212" folder="@FOLDER@" ext="@EXT@"/>
-                    <expand macro="test_collection_element" id="NC_014364" folder="@FOLDER@" ext="@EXT@"/>
-                    <expand macro="test_collection_element" id="NC_015761" folder="@FOLDER@" ext="@EXT@"/>
-                    <expand macro="test_collection_element" id="NC_017033" folder="@FOLDER@" ext="@EXT@"/>
-                    <expand macro="test_collection_element" id="NC_018068" folder="@FOLDER@" ext="@EXT@"/>
-                    <expand macro="test_collection_element" id="NC_018515" folder="@FOLDER@" ext="@EXT@"/>
-                    <expand macro="test_collection_element" id="NC_019936" folder="@FOLDER@" ext="@EXT@"/>
-                    <expand macro="test_collection_element" id="NC_021184" folder="@FOLDER@" ext="@EXT@"/>
+                    <expand macro="test_collection_element" id="NC_000913" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
+                    <expand macro="test_collection_element" id="NC_002737" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
+                    <expand macro="test_collection_element" id="NC_008261" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
+                    <expand macro="test_collection_element" id="NC_009012" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
+                    <expand macro="test_collection_element" id="NC_014168" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
+                    <expand macro="test_collection_element" id="NC_014212" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
+                    <expand macro="test_collection_element" id="NC_014364" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
+                    <expand macro="test_collection_element" id="NC_015761" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
+                    <expand macro="test_collection_element" id="NC_017033" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
+                    <expand macro="test_collection_element" id="NC_018068" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
+                    <expand macro="test_collection_element" id="NC_018515" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
+                    <expand macro="test_collection_element" id="NC_019936" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
+                    <expand macro="test_collection_element" id="NC_021184" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
                     <yield/>
                 </collection>
             </param>
         </xml>
-        <xml name="test_collection" tokens="name,folder,ext">
-            <expand macro="test_collection_non_empty" name="@NAME@" folder="@FOLDER@" ext="@EXT@">
-                <expand macro="test_collection_element" id="NC_003450" folder="@FOLDER@" ext="@EXT@"/>
-                <expand macro="test_collection_element" id="NC_012982" folder="@FOLDER@" ext="@EXT@"/>
-                <expand macro="test_collection_element" id="NC_014008" folder="@FOLDER@" ext="@EXT@"/>
-                <expand macro="test_collection_element" id="NC_014211" folder="@FOLDER@" ext="@EXT@"/>
-                <expand macro="test_collection_element" id="NC_014363" folder="@FOLDER@" ext="@EXT@"/>
-                <expand macro="test_collection_element" id="NC_017095" folder="@FOLDER@" ext="@EXT@"/>
-                <expand macro="test_collection_element" id="NC_018014" folder="@FOLDER@" ext="@EXT@"/>
-                <expand macro="test_collection_element" id="NC_019897" folder="@FOLDER@" ext="@EXT@"/>
-                <expand macro="test_collection_element" id="NC_019904" folder="@FOLDER@" ext="@EXT@"/>
+        <xml name="test_collection" tokens="name,folder,ext" token_suffix="">
+            <expand macro="test_collection_non_empty" name="@NAME@" folder="@FOLDER@" ext="@EXT@" suffix="@SUFFIX@">
+                <expand macro="test_collection_element" id="NC_003450" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
+                <expand macro="test_collection_element" id="NC_012982" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
+                <expand macro="test_collection_element" id="NC_014008" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
+                <expand macro="test_collection_element" id="NC_014211" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
+                <expand macro="test_collection_element" id="NC_014363" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
+                <expand macro="test_collection_element" id="NC_017095" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
+                <expand macro="test_collection_element" id="NC_018014" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
+                <expand macro="test_collection_element" id="NC_019897" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
+                <expand macro="test_collection_element" id="NC_019904" suffix="@SUFFIX@" folder="@FOLDER@" ext="@EXT@"/>
             </expand>
         </xml>
         
@@ -62,10 +63,15 @@
         <requirement type="package" version="2.0.2">r-base64</requirement>
         <requirement type="package" version="3.5.0">r-pdftools</requirement>
     </requirements>
+    <version_command><![CDATA[
+        echo $(R --vanilla --slave -e 'required_packages <- c("tidyverse", "janitor", "here", "kableExtra", "gmoviz", "circlize", "GenomicRanges", "patchwork", "fs", "tools", "scales", "formattable", "pdftools", "base64"); invisible(lapply(required_packages, library, character.only = TRUE, quietly=TRUE, verbose=FALSE)); sessionInfo()' 2> /dev/null)
+    ]]></version_command>
     <command detect_errors="exit_code"><![CDATA[
-       mkdir -p data/genomes &&
+        #import re
+        mkdir -p data/genomes &&
         #for e in $genomes
-            ln -s '$e' 'data/genomes/${e.element_identifier}.fna' &&
+            #set id=re.sub(r'[^\w\-.]', '_', $e.element_identifier)
+            ln -s '$e' 'data/genomes/${id}.fna' &&
         #end for
 
         mkdir -p data/host_analyses &&
@@ -78,23 +84,27 @@
         ## defense-finder inputs
         mkdir -p data/host_analyses/defense-finder &&
         #for e in $defense_finder
-            mkdir -p 'data/host_analyses/defense-finder/${e.element_identifier}/' &&
-            ln -s '$e' 'data/host_analyses/defense-finder/${e.element_identifier}/${e.element_identifier}_defense_finder_systems.tsv' &&
+            #set id=re.sub(r'[^\w\-.]', '_', $e.element_identifier)
+            mkdir -p 'data/host_analyses/defense-finder/${id}/' &&
+            ln -s '$e' 'data/host_analyses/defense-finder/${id}/${id}_defense_finder_systems.tsv' &&
         #end for
 
         ## genomad inputs
         mkdir -p data/host_analyses/genomad &&
         #for e in $genomad
-            mkdir -p 'data/host_analyses/genomad/${e.element_identifier}/${e.element_identifier}_summary/' &&
-            ln -s '$e' 'data/host_analyses/genomad/${e.element_identifier}/${e.element_identifier}_summary/${e.element_identifier}_virus_summary.tsv' &&
+            #set id=re.sub(r'[^\w\-.]', '_', $e.element_identifier)
+            mkdir -p 'data/host_analyses/genomad/${id}/${id}_summary/' &&
+            ln -s '$e' 'data/host_analyses/genomad/${id}/${id}_summary/${id}_virus_summary.tsv' &&
         #end for
         #for e in $genomad_phages
-            mkdir -p 'data/host_analyses/genomad/${e.element_identifier}/${e.element_identifier}_summary/' &&
-            ln -s '$e' 'data/host_analyses/genomad/${e.element_identifier}/${e.element_identifier}_summary/${e.element_identifier}_virus.fna' &&
+            #set id=re.sub(r'[^\w\-.]', '_', $e.element_identifier)
+            mkdir -p 'data/host_analyses/genomad/${id}/${id}_summary/' &&
+            ln -s '$e' 'data/host_analyses/genomad/${id}/${id}_summary/${id}_virus.fna' &&
         #end for
         #for e in $genomad_annotations
-            mkdir -p 'data/host_analyses/genomad/${e.element_identifier}/${e.element_identifier}_summary/' &&
-            ln -s '$e' 'data/host_analyses/genomad/${e.element_identifier}/${e.element_identifier}_summary/${e.element_identifier}_virus_genes.tsv' &&
+            #set id=re.sub(r'[^\w\-.]', '_', $e.element_identifier)
+            mkdir -p 'data/host_analyses/genomad/${id}/${id}_summary/' &&
+            ln -s '$e' 'data/host_analyses/genomad/${id}/${id}_summary/${id}_virus_genes.tsv' &&
         #end for
 
         ## GTDBTK
@@ -104,44 +114,52 @@
         ## CheckV
         mkdir -p data/virus_analyses/checkv &&
         #for e in $checkv
-            mkdir -p 'data/virus_analyses/checkv/${e.element_identifier}/' &&
-            ln -s '$e' 'data/virus_analyses/checkv/${e.element_identifier}/quality_summary.tsv' &&
+            #set id=re.sub(r'[^\w\-.]', '_', $e.element_identifier)
+            mkdir -p 'data/virus_analyses/checkv/${id}/' &&
+            ln -s '$e' 'data/virus_analyses/checkv/${id}/quality_summary.tsv' &&
         #end for
 
         ## drep compare
         mkdir -p data/virus_analyses/drep_compare &&
         #for e in $drep_compare
-            mkdir -p 'data/virus_analyses/drep_compare/${e.element_identifier}/data_tables' &&
-            ln -s '$e' 'data/virus_analyses/drep_compare/${e.element_identifier}/data_tables/Cdb.csv' &&
+            #set id=re.sub(r'[^\w\-.]', '_', $e.element_identifier)
+            mkdir -p 'data/virus_analyses/drep_compare/${id}/data_tables' &&
+            ln -s '$e' 'data/virus_analyses/drep_compare/${id}/data_tables/Cdb.csv' &&
         #end for
         #for e in $drep_compare_clustering_dendrogram
-            mkdir 'data/virus_analyses/drep_compare/${e.element_identifier}/figures/' &&
-            ln -s '$e' 'data/virus_analyses/drep_compare/${e.element_identifier}/figures/Primary_clustering_dendrogram.pdf' &&
+            #set id=re.sub(r'[^\w\-.]', '_', $e.element_identifier)
+            mkdir 'data/virus_analyses/drep_compare/${id}/figures/' &&
+            ln -s '$e' 'data/virus_analyses/drep_compare/${id}/figures/Primary_clustering_dendrogram.pdf' &&
         #end for
 
         ## iphop
         mkdir -p data/virus_analyses/iphop &&
         #for e in $iphop
-            mkdir -p 'data/virus_analyses/iphop/${e.element_identifier}/' &&
-            ln -s '$e' 'data/virus_analyses/iphop/${e.element_identifier}/Host_prediction_to_genome_m90.csv' &&
+            #set id=re.sub(r'[^\w\-.]', '_', $e.element_identifier)
+            mkdir -p 'data/virus_analyses/iphop/${id}/' &&
+            ln -s '$e' 'data/virus_analyses/iphop/${id}/Host_prediction_to_genome_m90.csv' &&
         #end for
 
         ## abricate
         mkdir -p data/virus_analyses/abricate &&
         #for e in $abricate
-            mkdir -p 'data/virus_analyses/abricate/${e.element_identifier}/' &&
-            ln -s '$e' 'data/virus_analyses/abricate/${e.element_identifier}/${e.element_identifier}_virus_vfdb.tsv' &&
+            #set id=re.sub(r'[^\w\-.]', '_', $e.element_identifier)
+            mkdir -p 'data/virus_analyses/abricate/${id}/' &&
+            ln -s '$e' 'data/virus_analyses/abricate/${id}/${id}_virus_vfdb.tsv' &&
         #end for
 
         ## vibrant
         mkdir -p data/virus_analyses/vibrant &&
         #for e in $vibrant
-            mkdir -p 'data/virus_analyses/vibrant/${e.element_identifier}/VIBRANT_${e.element_identifier}_virus/VIBRANT_results_${e.element_identifier}_virus/' &&
-            ln -s '$e' 'data/virus_analyses/vibrant/${e.element_identifier}/VIBRANT_${e.element_identifier}_virus/VIBRANT_results_${e.element_identifier}_virus/VIBRANT_AMG_individuals_${e.element_identifier}_virus.tsv' &&
+            #set id=re.sub(r'[^\w\-.]', '_', $e.element_identifier)
+            mkdir -p 'data/virus_analyses/vibrant/${id}/VIBRANT_${id}_virus/VIBRANT_results_${id}_virus/' &&
+            ln -s '$e' 'data/virus_analyses/vibrant/${id}/VIBRANT_${id}_virus/VIBRANT_results_${id}_virus/VIBRANT_AMG_individuals_${id}_virus.tsv' &&
         #end for
 
         Rscript -e "library(rmarkdown); render('$__tool_directory__/report.Rmd', output_dir='"\$(pwd)"', output_format = 'html_document', intermediates_dir = '"\$(pwd)"', knit_root_dir='"\$(pwd)"')" &&
         cp report.html '$report'
+        && >&2 echo "debug.log:"
+        && >&2 cat debug.log
     ]]></command>
     <inputs>
         <param type="data_collection" name="genomes" format="fasta" label="Genomes"/>
@@ -163,7 +181,6 @@
     </outputs>
     <tests>
         <test>
-            <!-- <expand macro="test_collection" name="genomes" folder="genomes" ext="fasta"/> -->
             <param name="genomes">
                 <collection type="list">
                     <expand macro="zenodo_collection_element" id="NC_000913"/>
@@ -200,13 +217,64 @@
             <expand macro="test_collection_non_empty" name="drep_compare" folder="drep_compare" ext="csv"/>
             <expand macro="test_collection_non_empty" name="drep_compare_clustering_dendrogram" folder="drep_compare_clustering_dendrogram" ext="pdf"/>
             <expand macro="test_collection_non_empty" name="iphop" folder="iphop_host_prediction_to_genome" ext="csv"/> 
-            <!-- TODO remove from test-data <expand macro="test_collection_non_empty" name="phatyp" folder="phabox_phatyp" ext="tabular"/>  -->
             <expand macro="test_collection_non_empty" name="abricate" folder="abricate_results" ext="tabular"/> 
             <expand macro="test_collection_non_empty" name="vibrant" folder="vibrant_amg_individuals" ext="tabular"/> 
             <output name="report">
                 <assert_contents>
                     <has_size min="100"/>
                     <has_line line="&lt;html&gt;"/>
+                    <has_text text="Error: " negate="true"/>
+                </assert_contents>
+            </output>
+        </test>
+
+        <!-- test with collection element identifiers contain suffix .fasta
+             also GTDBTk and CheckM2 output tables contain the .fasta suffix-->
+        <test>
+            <param name="genomes">
+                <collection type="list">
+                    <expand macro="zenodo_collection_element" id="NC_000913" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_002737" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_008261" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_009012" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_014168" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_014212" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_014364" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_015761" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_017033" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_018068" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_018515" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_019936" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_021184" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_003450" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_012982" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_014008" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_014211" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_014363" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_017095" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_018014" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_019897" suffix=".fasta"/>
+                    <expand macro="zenodo_collection_element" id="NC_019904" suffix=".fasta"/>
+                </collection>
+            </param>
+            <param name="checkm" value="checkm2.Quality_report-wext.tabular"/>
+            <expand macro="test_collection" name="genomad" suffix=".fasta" folder="genomad_virus_summary" ext="tabular"/>
+            <expand macro="test_collection" name="genomad_phages" suffix=".fasta" folder="genomad_virus_fasta" ext="fasta"/>
+            <expand macro="test_collection" name="genomad_annotations" suffix=".fasta" folder="genomad_virus_genes" ext="tabular"/>
+            <expand macro="test_collection" name="defense_finder" suffix=".fasta" folder="defense_finder_systems" ext="tabular"/>
+            <param name="gtdb_summary" value="gtdbtk.bac120-wext.summary"/>
+            <expand macro="test_collection_non_empty" name="checkv" suffix=".fasta" folder="checkv_quality_summary" ext="tabular"/>
+            <expand macro="test_collection_non_empty" name="drep_compare" suffix=".fasta" folder="drep_compare" ext="csv"/>
+            <expand macro="test_collection_non_empty" name="drep_compare_clustering_dendrogram" suffix=".fasta" folder="drep_compare_clustering_dendrogram" ext="pdf"/>
+            <expand macro="test_collection_non_empty" name="iphop" suffix=".fasta" folder="iphop_host_prediction_to_genome" ext="csv"/> 
+            <!-- TODO remove from test-data <expand macro="test_collection_non_empty" name="phatyp" folder="phabox_phatyp" ext="tabular"/>  -->
+            <expand macro="test_collection_non_empty" name="abricate" suffix=".fasta" folder="abricate_results" ext="tabular"/> 
+            <expand macro="test_collection_non_empty" name="vibrant" suffix=".fasta" folder="vibrant_amg_individuals" ext="tabular"/> 
+            <output name="report">
+                <assert_contents>
+                    <has_size min="100"/>
+                    <has_line line="&lt;html&gt;"/>
+                    <has_text text="Error: " negate="true"/>
                 </assert_contents>
             </output>
         </test>
@@ -244,4 +312,4 @@
     <!-- <citations>
         <citation type="doi"> </citation>
     </citations> -->
-</tool>
\ No newline at end of file
+</tool>
diff -r 315c2ed31af1 -r 3a7f73d638ba report.Rmd
--- a/report.Rmd	Wed Jun 04 17:36:40 2025 +0000
+++ b/report.Rmd	Tue Jul 22 11:09:24 2025 +0000
@@ -25,17 +25,21 @@
 
 ```{r setup_env, include=FALSE}
 knitr::opts_chunk$set(echo = FALSE)
+knitr::opts_chunk$set(dev = "svglite") # set output device to svg
 
 cat("params$outdir:", params$outdir, "\n")
 ```
 
 ```{r setup_libraries, message=FALSE, warning=FALSE, echo=FALSE, results='asis'}
 # Define required packages
-required_packages <- c("tidyverse", "janitor", "here",
-                       "kableExtra", "gmoviz", "circlize",
-                       "GenomicRanges", "patchwork", "fs",
-                       "tools", "scales", "formattable",
-                       "pdftools", "base64")
+# Note: update version_command if changed here!
+required_packages <- c(
+    "tidyverse", "janitor", "here",
+    "kableExtra", "gmoviz", "circlize",
+    "GenomicRanges", "patchwork", "fs",
+    "tools", "scales", "formattable",
+    "pdftools", "base64"
+)
 
 # Load required packages
 invisible(lapply(required_packages, library, character.only = TRUE))
@@ -45,180 +49,185 @@
 log_file <- "debug.log"
 
 log_debug <- function(message) {
-  if (!exists("log_initialized") || !log_initialized) {
-    cat(paste0(Sys.time(), " - DEBUG: ", message, "\n"), file = log_file, append = FALSE)
-    assign("log_initialized", TRUE, envir = .GlobalEnv)
-  } else {
-    cat(paste0(Sys.time(), " - DEBUG: ", message, "\n"), file = log_file, append = TRUE)
-  }
+    if (!exists("log_initialized") || !log_initialized) {
+        cat(paste0(Sys.time(), " - DEBUG: ", message, "\n"), file = log_file, append = FALSE)
+        assign("log_initialized", TRUE, envir = .GlobalEnv)
+    } else {
+        cat(paste0(Sys.time(), " - DEBUG: ", message, "\n"), file = log_file, append = TRUE)
+    }
 }
 
 load_file <- function(path) {
-  log_debug(paste("Attempting to load:", path))
-  if (file.exists(path)) {
-    ext <- tools::file_ext(path)
-    if (ext %in% c("tsv", "csv")) {
-      data <- read_delim(path, delim = ifelse(ext == "csv", ",", "\t"), show_col_types = FALSE) %>% clean_names
-      log_debug(paste("Loaded", nrow(data), "rows from", path))
-      data
-    } else if (ext == "fna") {
-      data <- Biostrings::readDNAStringSet(path)
-      log_debug(paste("Loaded", length(data), "sequences from", path))
-      data
+    log_debug(paste("Attempting to load:", path))
+    if (file.exists(path)) {
+        ext <- tools::file_ext(path)
+        if (ext %in% c("tsv", "csv")) {
+            data <- read_delim(path, delim = ifelse(ext == "csv", ",", "\t"), show_col_types = FALSE) %>% janitor::clean_names()
+            log_debug(paste("Loaded", nrow(data), "rows from", path))
+            data
+        } else if (ext == "fna") {
+            data <- Biostrings::readDNAStringSet(path)
+            log_debug(paste("Loaded", length(data), "sequences from", path))
+            data
+        } else {
+            log_debug(paste("Skipping", path, "- unsupported file type"))
+            NULL
+        }
     } else {
-      log_debug(paste("Skipping", path, "- unsupported file type"))
-      NULL
+        log_debug(paste("File does not exist:", path))
+        NULL
     }
-  } else {
-    log_debug(paste("File does not exist:", path))
-    NULL
-  }
 }
 
 get_file_info <- function(path, loaded_data) {
-  log_debug(paste("Processing file info for:", path))
-  if (file.exists(path)) {
-    ext <- tools::file_ext(path)
-    if (ext %in% c("tsv", "csv", "fna")) {
-      data <- loaded_data[[basename(path)]]
-      rows <- if(ext == "fna") length(data) else nrow(data)
-      tibble(exists = TRUE, rows = rows, size = file.size(path), path = path)
+    log_debug(paste("Processing file info for:", path))
+    if (file.exists(path)) {
+        ext <- tools::file_ext(path)
+        if (ext %in% c("tsv", "csv", "fna")) {
+            data <- loaded_data[[basename(path)]]
+            rows <- if (ext == "fna") length(data) else nrow(data)
+            tibble::tibble(exists = TRUE, rows = rows, size = file.size(path), path = path)
+        } else {
+            tibble::tibble(exists = TRUE, rows = NA_integer_, size = file.size(path), path = path)
+        }
     } else {
-      tibble(exists = TRUE, rows = NA_integer_, size = file.size(path), path = path)
+        tibble::tibble(exists = FALSE, rows = NA_integer_, size = NA_real_, path = NA_character_)
     }
-  } else {
-    tibble(exists = FALSE, rows = NA_integer_, size = NA_real_, path = NA_character_)
-  }
 }
 
 process_genome_folder <- function(folder, host_analyses_dir, virus_analyses_dir) {
-  log_debug(paste("Processing folder:", folder))
-  genome_name <- basename(folder)
+    log_debug(paste("Processing folder:", folder))
+    genome_name <- basename(folder)
 
-  paths <- list(
-    genomad = file.path(host_analyses_dir, "genomad", genome_name, paste0(genome_name, "_summary"), paste0(genome_name, "_virus_summary.tsv")),
-    genomad_phages = file.path(host_analyses_dir, "genomad", genome_name, paste0(genome_name, "_summary"), paste0(genome_name, "_virus.fna")),
-    genomad_annotations = file.path(host_analyses_dir, "genomad", genome_name, paste0(genome_name, "_summary"), paste0(genome_name, "_virus_genes.tsv")),
-    defense_finder = file.path(host_analyses_dir, "defense-finder", genome_name, paste0(genome_name, "_defense_finder_systems.tsv")),
-    checkv = file.path(virus_analyses_dir, "checkv", genome_name, "quality_summary.tsv"),
-    iphop = file.path(virus_analyses_dir, "iphop", genome_name, "Host_prediction_to_genome_m90.csv"),
-    drep = file.path(virus_analyses_dir, "drep_compare", genome_name, "data_tables", "Cdb.csv"),
-    phatyp = file.path(virus_analyses_dir, "phatyp", genome_name, "phatyp.csv"),
-    abricate = file.path(virus_analyses_dir, "abricate", genome_name, paste0(genome_name, "_virus_vfdb.tsv")),
-    vibrant = file.path(virus_analyses_dir, "vibrant", genome_name, 
-                        paste0("VIBRANT_", genome_name, "_virus"),
-                        paste0("VIBRANT_results_", genome_name, "_virus"),
-                        paste0("VIBRANT_AMG_individuals_", genome_name, "_virus.tsv"))
-  )
+    paths <- list(
+        genomad = file.path(host_analyses_dir, "genomad", genome_name, paste0(genome_name, "_summary"), paste0(genome_name, "_virus_summary.tsv")),
+        genomad_phages = file.path(host_analyses_dir, "genomad", genome_name, paste0(genome_name, "_summary"), paste0(genome_name, "_virus.fna")),
+        genomad_annotations = file.path(host_analyses_dir, "genomad", genome_name, paste0(genome_name, "_summary"), paste0(genome_name, "_virus_genes.tsv")),
+        defense_finder = file.path(host_analyses_dir, "defense-finder", genome_name, paste0(genome_name, "_defense_finder_systems.tsv")),
+        checkv = file.path(virus_analyses_dir, "checkv", genome_name, "quality_summary.tsv"),
+        iphop = file.path(virus_analyses_dir, "iphop", genome_name, "Host_prediction_to_genome_m90.csv"),
+        drep = file.path(virus_analyses_dir, "drep_compare", genome_name, "data_tables", "Cdb.csv"),
+        phatyp = file.path(virus_analyses_dir, "phatyp", genome_name, "phatyp.csv"),
+        abricate = file.path(virus_analyses_dir, "abricate", genome_name, paste0(genome_name, "_virus_vfdb.tsv")),
+        vibrant = file.path(
+            virus_analyses_dir, "vibrant", genome_name,
+            paste0("VIBRANT_", genome_name, "_virus"),
+            paste0("VIBRANT_results_", genome_name, "_virus"),
+            paste0("VIBRANT_AMG_individuals_", genome_name, "_virus.tsv")
+        )
+    )
 
-  loaded_data <- map(paths, load_file)
-  file_info <- map_dfr(paths, ~get_file_info(.x, loaded_data), .id = "file_type")
+    loaded_data <- map(paths, load_file)
+    file_info <- purrr::map_dfr(paths, ~ get_file_info(.x, loaded_data), .id = "file_type")
 
-  virus_count <- if(!is.null(loaded_data$genomad)) {
-    count <- sum(loaded_data$genomad$virus_score > 0.5, na.rm = TRUE)
-    log_debug(paste("Virus count:", count))
-    count
-  } else {
-    log_debug("No genomad summary found, virus count set to 0")
-    0
-  }
+    virus_count <- if (!is.null(loaded_data$genomad)) {
+        count <- sum(loaded_data$genomad$virus_score > 0.5, na.rm = TRUE)
+        log_debug(paste("Virus count:", count))
+        count
+    } else {
+        log_debug("No genomad summary found, virus count set to 0")
+        0
+    }
 
-  log_debug("Returning results from process_genome_folder")
-  list(file_info = file_info, virus_count = virus_count, loaded_data = loaded_data)
+    log_debug("Returning results from process_genome_folder")
+    list(file_info = file_info, virus_count = virus_count, loaded_data = loaded_data)
 }
 ```
 
 
 ```{r compile_results, message=FALSE, warning=FALSE, echo=FALSE}
 compile_results <- function() {
-  base_dir <- params$outdir
-  log_debug(paste("Base directory:", base_dir))
-
-  host_analyses_dir <- file.path(base_dir, "host_analyses")
-  virus_analyses_dir <- file.path(base_dir, "virus_analyses")
+    base_dir <- params$outdir
+    log_debug(paste("Base directory:", base_dir))
 
-  # List all sample-level directories from all tools under virus_analyses
-  tool_dirs <- list.dirs(virus_analyses_dir, full.names = TRUE, recursive = FALSE)
-  
-  genome_folders <- list.dirs(file.path(base_dir, "host_analyses", "genomad"), 
-                              full.names = TRUE, recursive = FALSE)
-  
-  # cat(length(genome_folders), "sample(s) processed\n")
-
-  log_debug("Processing genome folders")
-  genome_data <- map(genome_folders, process_genome_folder, 
-                     host_analyses_dir = host_analyses_dir, 
-                     virus_analyses_dir = virus_analyses_dir) %>%
-    set_names(basename(genome_folders)) %>%
-    compact()
+    host_analyses_dir <- file.path(base_dir, "host_analyses")
+    virus_analyses_dir <- file.path(base_dir, "virus_analyses")
 
-  log_debug("Creating summary dataframe")
-  summary_df <- map_dfr(genome_data, ~{
-    file_info <- .x$file_info
-    tibble(
-      Sample = basename(file_info$path[1]),
-      Virus_Count = .x$virus_count,
-      geNomad = file_info$exists[file_info$file_type == "genomad"],
-      CheckV = file_info$exists[file_info$file_type == "checkv"],
-      VIBRANT = file_info$exists[file_info$file_type == "vibrant"],
-      dRep = file_info$exists[file_info$file_type == "drep"],
-      iPHOP = file_info$exists[file_info$file_type == "iphop"],
-      PhaTYP = file_info$exists[file_info$file_type == "phatyp"],
-      Defense_Finder = file_info$exists[file_info$file_type == "defense_finder"],
-      geNomad_Path = file_info$path[file_info$file_type == "genomad"],
-      CheckV_Path = file_info$path[file_info$file_type == "checkv"],
-      VIBRANT_Path = file_info$path[file_info$file_type == "vibrant"],
-      dRep_Path = file_info$path[file_info$file_type == "drep"],
-      PhaTYP_Path = file_info$path[file_info$file_type == "phatyp"],
-      Defense_Finder_Path = file_info$path[file_info$file_type == "defense_finder"],
-      Virus_Contigs = ifelse(file_info$exists[file_info$file_type == "genomad_phages"],
-                            file_info$rows[file_info$file_type == "genomad_phages"],
-                            0)
+    # List all sample-level directories from all tools under virus_analyses
+    tool_dirs <- list.dirs(virus_analyses_dir, full.names = TRUE, recursive = FALSE)
+
+    genome_folders <- list.dirs(file.path(base_dir, "host_analyses", "genomad"),
+        full.names = TRUE, recursive = FALSE
     )
-  }) %>%
-    mutate(across(ends_with("_Path"), ~ifelse(is.na(.), "Not available", as.character(.))))
+
+    # cat(length(genome_folders), "sample(s) processed\n")
+
+    log_debug("Processing genome folders")
+    genome_data <- map(genome_folders, process_genome_folder,
+        host_analyses_dir = host_analyses_dir,
+        virus_analyses_dir = virus_analyses_dir
+    ) %>%
+        purrr::set_names(basename(genome_folders)) %>%
+        compact()
 
-  host_genomes_fasta <- list.files(
-    path = file.path(params$outdir, "genomes"),
-    pattern = "\\.fna$",
-    full.names = TRUE
-  )
-  
-  host_genomes_paths <- tibble(
-    name = tools::file_path_sans_ext(basename(host_genomes_fasta)),
-    path = host_genomes_fasta
-  )
-
-  data_gtdbtk_host <- read_tsv(
-    file.path(params$outdir, "host_analyses/gtdbtk/gtdbtk.bac120.summary.tsv"),
-    show_col_types = FALSE
-  ) %>% clean_names()
+    log_debug("Creating summary dataframe")
+    summary_df <- purrr::map_dfr(genome_data, ~ {
+        file_info <- .x$file_info
+        tibble::tibble(
+            Sample = basename(file_info$path[1]),
+            Virus_Count = .x$virus_count,
+            geNomad = file_info$exists[file_info$file_type == "genomad"],
+            CheckV = file_info$exists[file_info$file_type == "checkv"],
+            VIBRANT = file_info$exists[file_info$file_type == "vibrant"],
+            dRep = file_info$exists[file_info$file_type == "drep"],
+            iPHOP = file_info$exists[file_info$file_type == "iphop"],
+            PhaTYP = file_info$exists[file_info$file_type == "phatyp"],
+            Defense_Finder = file_info$exists[file_info$file_type == "defense_finder"],
+            geNomad_Path = file_info$path[file_info$file_type == "genomad"],
+            CheckV_Path = file_info$path[file_info$file_type == "checkv"],
+            VIBRANT_Path = file_info$path[file_info$file_type == "vibrant"],
+            dRep_Path = file_info$path[file_info$file_type == "drep"],
+            PhaTYP_Path = file_info$path[file_info$file_type == "phatyp"],
+            Defense_Finder_Path = file_info$path[file_info$file_type == "defense_finder"],
+            Virus_Contigs = ifelse(file_info$exists[file_info$file_type == "genomad_phages"],
+                file_info$rows[file_info$file_type == "genomad_phages"],
+                0
+            )
+        )
+    }) %>%
+        dplyr::mutate(dplyr::across(ends_with("_Path"), ~ ifelse(is.na(.), "Not available", as.character(.))))
 
-  data_checkm_host <- read_tsv(
-    file.path(params$outdir, "host_analyses/checkm2/quality_report.tsv"),
-    show_col_types = FALSE
-  ) %>% clean_names()
+    host_genomes_fasta <- list.files(
+        path = file.path(params$outdir, "genomes"),
+        pattern = "\\.fna$",
+        full.names = TRUE
+    )
 
-  log_debug("Returning summary dataframe, genome data, and host data")
+    host_genomes_paths <- tibble::tibble(
+        name = tools::file_path_sans_ext(basename(host_genomes_fasta)),
+        path = host_genomes_fasta
+    )
+
+    data_gtdbtk_host <- read_tsv(
+        file.path(params$outdir, "host_analyses/gtdbtk/gtdbtk.bac120.summary.tsv"),
+        show_col_types = FALSE
+    ) %>% janitor::clean_names()
+
+    data_checkm_host <- read_tsv(
+        file.path(params$outdir, "host_analyses/checkm2/quality_report.tsv"),
+        show_col_types = FALSE
+    ) %>% janitor::clean_names()
 
-  log_debug(paste("summary_df dimensions:", nrow(summary_df), "rows,", ncol(summary_df), "columns"))
-  log_debug(paste("summary_df column names:", paste(colnames(summary_df), collapse = ", ")))
-  log_debug(paste("genome_data length:", length(genome_data)))
-  log_debug(paste("genome_data names:", paste(names(genome_data), collapse = ", ")))
-  log_debug(paste("host_genomes_paths dimensions:", nrow(host_genomes_paths), "rows,", ncol(host_genomes_paths), "columns"))
-  log_debug(paste("host_genomes_paths column names:", paste(colnames(host_genomes_paths), collapse = ", ")))
-  log_debug(paste("data_gtdbtk_host dimensions:", nrow(data_gtdbtk_host), "rows,", ncol(data_gtdbtk_host), "columns"))
-  log_debug(paste("data_gtdbtk_host column names:", paste(colnames(data_gtdbtk_host), collapse = ", ")))
-  log_debug(paste("data_checkm_host dimensions:", nrow(data_checkm_host), "rows,", ncol(data_checkm_host), "columns"))
-  log_debug(paste("data_checkm_host column names:", paste(colnames(data_checkm_host), collapse = ", ")))
-  
-  list(
-    summary = summary_df, 
-    genome_data = genome_data,
-    host_genomes_paths = host_genomes_paths,
-    data_gtdbtk_host = data_gtdbtk_host,
-    data_checkm_host = data_checkm_host
-  )
+    log_debug("Returning summary dataframe, genome data, and host data")
+
+    log_debug(paste("summary_df dimensions:", nrow(summary_df), "rows,", ncol(summary_df), "columns"))
+    log_debug(paste("summary_df column names:", paste(colnames(summary_df), collapse = ", ")))
+    log_debug(paste("genome_data length:", length(genome_data)))
+    log_debug(paste("genome_data names:", paste(names(genome_data), collapse = ", ")))
+    log_debug(paste("host_genomes_paths dimensions:", nrow(host_genomes_paths), "rows,", ncol(host_genomes_paths), "columns"))
+    log_debug(paste("host_genomes_paths column names:", paste(colnames(host_genomes_paths), collapse = ", ")))
+    log_debug(paste("data_gtdbtk_host dimensions:", nrow(data_gtdbtk_host), "rows,", ncol(data_gtdbtk_host), "columns"))
+    log_debug(paste("data_gtdbtk_host column names:", paste(colnames(data_gtdbtk_host), collapse = ", ")))
+    log_debug(paste("data_checkm_host dimensions:", nrow(data_checkm_host), "rows,", ncol(data_checkm_host), "columns"))
+    log_debug(paste("data_checkm_host column names:", paste(colnames(data_checkm_host), collapse = ", ")))
+
+    list(
+        summary = summary_df,
+        genome_data = genome_data,
+        host_genomes_paths = host_genomes_paths,
+        data_gtdbtk_host = data_gtdbtk_host,
+        data_checkm_host = data_checkm_host
+    )
 }
 ```
 
@@ -227,8 +236,8 @@
 result <- compile_results()
 
 if (is.null(result)) {
-  log_debug("Main function execution failed")
-  stop("Main function execution failed")
+    log_debug("Main function execution failed")
+    stop("Main function execution failed")
 }
 
 summary_df <- result$summary
@@ -238,263 +247,229 @@
 data_checkm_host <- result$data_checkm_host
 log_debug("Data extracted successfully")
 
-# Remove any extensions from names in data gtdbtk and checm2
-data_gtdbtk_host <- data_gtdbtk_host %>%
-  mutate(user_genome = str_remove(user_genome, "\\.[^.]+$"))
-
-data_checkm_host <- data_checkm_host %>%
-  mutate(name = str_remove(name, "\\.[^.]+$"))
-
 result$summary <- result$summary %>%
-  mutate(Sample = str_remove(Sample, "_virus_summary.tsv"))
+    dplyr::mutate(Sample = stringr::str_remove(Sample, "_virus_summary.tsv"))
 ```
 
 # Summary {.tabset .tabset-fade}
 
-## Overview Table
-
 This table provides sample-by-sample information on detected viruses and key host genome statistics. It includes taxonomy, virus count, genome quality classification, CheckM2 metrics (completeness and contamination), and genome assembly statistics such as size and N50.
 
 ```{r render_table, message=FALSE, warning=FALSE, echo=FALSE, results='asis'}
 data <- result$summary
 
 log_debug("Assigning checkm2 host data")
-checkm_host_data <- data_checkm_host %>% clean_names() %>%
-  select(name, completeness, contamination, 
-         contig_n50, genome_size)
+checkm_host_data <- data_checkm_host %>%
+    janitor::clean_names() %>%
+    dplyr::select(
+        name, completeness, contamination,
+        contig_n50, genome_size
+    )
 
 log_debug("Assigning GTDB-Tk host data")
-gtdbtk_data <- data_gtdbtk_host %>% 
-  select(user_genome, classification)
+gtdbtk_data <- data_gtdbtk_host %>%
+    dplyr::select(user_genome, classification)
 
 log_debug("Defining color-blind friendly palette")
 cb_friendly_colors <- list(
-  green = "#009E73",
-  blue = "#0072B2",
-  orange = "#E69F00",
-  red = "#D55E00",
-  grey = "#999999"
+    green = "#009E73",
+    blue = "#0072B2",
+    orange = "#E69F00",
+    red = "#D55E00",
+    grey = "#999999"
 )
 
 log_debug("Defining function to color cells")
-color_cell <- function(values, color_true = cb_friendly_colors$green, 
+color_cell <- function(values, color_true = cb_friendly_colors$green,
                        color_false = cb_friendly_colors$red) {
-  ifelse(values,
-         cell_spec("Yes", color = "white", bold = TRUE, background = color_true),
-         cell_spec("No", color = "white", bold = TRUE, background = color_false))
+    ifelse(values,
+        kableExtra::cell_spec("Yes", color = "white", bold = TRUE, background = color_true),
+        kableExtra::cell_spec("No", color = "white", bold = TRUE, background = color_false)
+    )
 }
 
 log_debug("Defining function to create bar plot")
 create_bar_plot <- function(values, max_value, color = cb_friendly_colors$grey) {
-  sapply(values, function(value) {
-    if(is.na(value) || !is.numeric(value)) {
-      return("N/A")
-    }
-    bar_width <- min(max(value, 0), max_value) / max_value * 100
-    sprintf('<div style="background-color: %s; width: %f%%; height: 10px;"></div>%.1f%%', 
-            color, bar_width, value)
-  })
+    sapply(values, function(value) {
+        if (is.na(value) || !is.numeric(value)) {
+            return("N/A")
+        }
+        bar_width <- min(max(value, 0), max_value) / max_value * 100
+        sprintf(
+            '<div style="background-color: %s; width: %f%%; height: 10px;"></div>%.1f%%',
+            color, bar_width, value
+        )
+    })
 }
 
 log_debug("Defining function to format large numbers")
 format_large_number <- function(x) {
-  sapply(x, function(value) {
-    if (is.na(value) || !is.numeric(value)) {
-      return("N/A")
-    } else if (value < 1000) {
-      return(as.character(value))
-    } else if (value < 1e6) {
-      return(paste0(round(value / 1e3, 1), "K"))
-    } else if (value < 1e9) {
-      return(paste0(round(value / 1e6, 1), "M"))
-    } else {
-      return(paste0(round(value / 1e9, 1), "G"))
-    }
-  })
+    sapply(x, function(value) {
+        if (is.na(value) || !is.numeric(value)) {
+            return("N/A")
+        } else if (value < 1000) {
+            return(as.character(value))
+        } else if (value < 1e6) {
+            return(paste0(round(value / 1e3, 1), "K"))
+        } else if (value < 1e9) {
+            return(paste0(round(value / 1e6, 1), "M"))
+        } else {
+            return(paste0(round(value / 1e9, 1), "G"))
+        }
+    })
 }
 
 log_debug("Defining function to extract last known taxonomy level")
 extract_last_known_taxonomy <- function(classification) {
-  if (is.na(classification) || classification == "") {
+    if (is.na(classification) || classification == "") {
+        return(list(level = "Unknown", name = "Unknown"))
+    }
+
+    parts <- strsplit(classification, ";")[[1]]
+    for (i in length(parts):1) {
+        level <- sub("^[a-z]__", "", parts[i])
+        if (level != "") {
+            prefix <- sub("__.*$", "", parts[i])
+            return(list(level = prefix, name = level))
+        }
+    }
     return(list(level = "Unknown", name = "Unknown"))
-  }
-  
-  parts <- strsplit(classification, ";")[[1]]
-  for (i in length(parts):1) {
-    level <- sub("^[a-z]__", "", parts[i])
-    if (level != "") {
-      prefix <- sub("__.*$", "", parts[i])
-      return(list(level = prefix, name = level))
-    }
-  }
-  return(list(level = "Unknown", name = "Unknown"))
 }
 
 log_debug("Defining function to format taxonomy")
 format_taxonomy <- function(classification) {
-  result <- extract_last_known_taxonomy(classification)
-  if (result$level == "Unknown") {
-    return("Unknown")
-  } else if (result$level == "s") {
-    return(paste0("<i>", result$name, "</i>"))
-  } else {
-    genus <- str_replace_all(result$name, "_", " ")
-    return(paste0("<i>", genus, "</i> sp."))
-  }
+    result <- extract_last_known_taxonomy(classification)
+    if (result$level == "Unknown") {
+        return("Unknown")
+    } else if (result$level == "s") {
+        return(paste0("<i>", result$name, "</i>"))
+    } else {
+        genus <- str_replace_all(result$name, "_", " ")
+        return(paste0("<i>", genus, "</i> sp."))
+    }
 }
 
 log_debug("Defining function to calculate quality score and determine genome quality class")
 calculate_quality_score_and_class <- function(completeness, contamination) {
-  if (is.na(completeness) || is.na(contamination)) {
-    return(list(
-      score = cell_spec("N/A", color = "white", bold = TRUE, background = cb_friendly_colors$grey),
-      class = cell_spec("Unknown", color = "white", bold = TRUE, background = cb_friendly_colors$grey),
-      numeric_score = NA
-    ))
-  }
-  
-  quality_score <- completeness - (5 * contamination)
-  formatted_score <- sprintf("%.1f", quality_score)
-  
-  if (completeness > 90 && contamination < 5) {
-    class <- "High-quality draft"
-    color <- cb_friendly_colors$green
-  } else if (completeness >= 50 && contamination < 10) {
-    class <- "Medium-quality draft"
-    color <- cb_friendly_colors$blue
-  } else {
-    class <- "Low-quality draft"
-    color <- cb_friendly_colors$red
-  }
-  
-  list(
-    score = cell_spec(formatted_score, color = "white", bold = TRUE, background = color),
-    class = cell_spec(class, color = "white", bold = TRUE, background = color),
-    numeric_score = quality_score
-  )
+    if (is.na(completeness) || is.na(contamination)) {
+        return(list(
+            score = kableExtra::cell_spec("N/A", color = "white", bold = TRUE, background = cb_friendly_colors$grey),
+            class = kableExtra::cell_spec("Unknown", color = "white", bold = TRUE, background = cb_friendly_colors$grey),
+            numeric_score = NA
+        ))
+    }
+
+    quality_score <- completeness - (5 * contamination)
+    formatted_score <- sprintf("%.1f", quality_score)
+
+    if (completeness > 90 && contamination < 5) {
+        class <- "High-quality draft"
+        color <- cb_friendly_colors$green
+    } else if (completeness >= 50 && contamination < 10) {
+        class <- "Medium-quality draft"
+        color <- cb_friendly_colors$blue
+    } else {
+        class <- "Low-quality draft"
+        color <- cb_friendly_colors$red
+    }
+
+    list(
+        score = kableExtra::cell_spec(formatted_score, color = "white", bold = TRUE, background = color),
+        class = kableExtra::cell_spec(class, color = "white", bold = TRUE, background = color),
+        numeric_score = quality_score
+    )
 }
 
 log_debug("Preparing the data")
 
 table_data <- data %>%
-  #mutate(Sample = basename(Sample) %>% trim_sample_name()) %>%
-  mutate(Sample = basename(Sample)) %>%
-  left_join(checkm_host_data, by = c("Sample" = "name")) %>%
-  left_join(gtdbtk_data, by = c("Sample" = "user_genome")) %>%
-  mutate(
-    quality_data = pmap(list(as.numeric(completeness),
-                             as.numeric(contamination)),
-                        calculate_quality_score_and_class),
-    Quality_Score = map_chr(quality_data, ~.$score),
-    Genome_Quality = map_chr(quality_data, ~.$class),
-    Quality_Score_Numeric = map_dbl(quality_data, ~.$numeric_score),
-    Virus_Count_Numeric = as.numeric(Virus_Count),
-    Virus_Count = cell_spec(
-      Virus_Count,
-      color = "white",
-      bold = TRUE,
-      background = case_when(
-        Virus_Count == 0 ~ cb_friendly_colors$red,
-        Virus_Count == 1 ~ cb_friendly_colors$blue,
-        Virus_Count > 1 ~ cb_friendly_colors$green
-      )
-    ),
-    Completeness_Numeric = as.numeric(completeness),
-    Completeness = create_bar_plot(as.numeric(completeness), 100),
-    Contamination = create_bar_plot(as.numeric(contamination), 100),
-    `N50 (contigs)` = format_large_number(as.numeric(contig_n50)),
-    `Genome size (bp)` = format_large_number(as.numeric(genome_size)),
-    `GTDB Taxonomy` = sapply(classification, format_taxonomy)
-  ) %>%
-  mutate(`#` = row_number()) %>%
-  select(`#`, Sample, `GTDB Taxonomy`, Virus_Count,
-         Quality_Score, Genome_Quality, Completeness, Contamination,
-         `Genome size (bp)`, `N50 (contigs)`)
+    # dplyr::mutate(Sample = basename(Sample) %>% trim_sample_name()) %>%
+    dplyr::mutate(Sample = basename(Sample)) %>%
+    dplyr::left_join(checkm_host_data, by = c("Sample" = "name")) %>%
+    dplyr::left_join(gtdbtk_data, by = c("Sample" = "user_genome")) %>%
+    dplyr::mutate(
+        quality_data = purrr::pmap(
+            list(
+                as.numeric(completeness),
+                as.numeric(contamination)
+            ),
+            calculate_quality_score_and_class
+        ),
+        Quality_Score = purrr::map_chr(quality_data, ~ .$score),
+        Genome_Quality = purrr::map_chr(quality_data, ~ .$class),
+        Quality_Score_Numeric = purrr::map_dbl(quality_data, ~ .$numeric_score),
+        Virus_Count_Numeric = as.numeric(Virus_Count),
+        Virus_Count = kableExtra::cell_spec(
+            Virus_Count,
+            color = "white",
+            bold = TRUE,
+            background = dplyr::case_when(
+                Virus_Count == 0 ~ cb_friendly_colors$red,
+                Virus_Count == 1 ~ cb_friendly_colors$blue,
+                Virus_Count > 1 ~ cb_friendly_colors$green
+            )
+        ),
+        Completeness_Numeric = as.numeric(completeness),
+        Completeness = create_bar_plot(as.numeric(completeness), 100),
+        Contamination = create_bar_plot(as.numeric(contamination), 100),
+        `N50 (contigs)` = format_large_number(as.numeric(contig_n50)),
+        `Genome size (bp)` = format_large_number(as.numeric(genome_size)),
+        `GTDB Taxonomy` = sapply(classification, format_taxonomy)
+    ) %>%
+    dplyr::mutate(`#` = row_number()) %>%
+    dplyr::select(
+        `#`, Sample, `GTDB Taxonomy`, Virus_Count,
+        Quality_Score, Genome_Quality, Completeness, Contamination,
+        `Genome size (bp)`, `N50 (contigs)`
+    )
 
 log_debug("Creating the table")
-kbl(table_data, escape = FALSE,
-    align = c("c", "l", "l", "c", rep("c", 2), rep("r", 2), rep("r", 2))) %>%
-  kable_paper(full_width = TRUE) %>%
-  column_spec(1, bold = TRUE, width = "2em") %>%
-  column_spec(2:3, bold = TRUE) %>%
-  column_spec(4:5, width = "5em") %>%
-  column_spec(6:7, width = "60px") %>%
-  column_spec(8:9, width = "4em") %>%
-  add_header_above(c(" " = 4, "Host Genome Quality" = 2, "CheckM Metrics" = 2,
-                     "Statistics" = 2)) %>%
-  kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive"),
-                font_size = 9,
-                html_font = "Arial",
-                position = "left") %>%
-  row_spec(0, bold = TRUE, color = "white", background = "#333333") %>%
-  row_spec(0, extra_css = "border-bottom: 2px solid #000000;") %>%
-  column_spec(9, extra_css = "border-right: 2px solid #000000;") %>%
-  scroll_box(width = "100%", height = "100%",
-             extra_css = "overflow-x: auto; border: 1px solid #ccc; border-radius: 4px;")
+kableExtra::kbl(table_data,
+    escape = FALSE,
+    align = c("c", "l", "l", "c", rep("c", 2), rep("r", 2), rep("r", 2))
+) %>%
+    kableExtra::kable_paper(full_width = TRUE) %>%
+    kableExtra::column_spec(1, bold = TRUE, width = "2em") %>%
+    kableExtra::column_spec(2:3, bold = TRUE) %>%
+    kableExtra::column_spec(4:5, width = "5em") %>%
+    kableExtra::column_spec(6:7, width = "60px") %>%
+    kableExtra::column_spec(8:9, width = "4em") %>%
+    kableExtra::add_header_above(c(
+        " " = 4, "Host Genome Quality" = 2, "CheckM Metrics" = 2,
+        "Statistics" = 2
+    )) %>%
+    kableExtra::kable_styling(
+        bootstrap_options = c("striped", "hover", "condensed", "responsive"),
+        font_size = 9,
+        html_font = "Arial",
+        position = "left"
+    ) %>%
+    kableExtra::row_spec(0, bold = TRUE, color = "white", background = "#333333") %>%
+    kableExtra::row_spec(0, extra_css = "border-bottom: 2px solid #000000;") %>%
+    kableExtra::column_spec(9, extra_css = "border-right: 2px solid #000000;") %>%
+    kableExtra::scroll_box(
+        width = "100%", height = "100%",
+        extra_css = "overflow-x: auto; border: 1px solid #ccc; border-radius: 4px;"
+    )
 ```
 
-## Tools Documentation
-
-The following tools are utilized in this workflow. Each tool name below is a link to its respective documentation.
-
-**Host-analyses**
-
-- [**CheckM2 v1.1.0**](https://github.com/chklovski/CheckM2): Assesses the quality of the host. Most useful when working with assembled genomes.
-
-- [**GTDB-Tk v2.3.2**](https://ecogenomics.github.io/GTDBTk/index.html): Assigns a taxonomy to the host genome.
-
-- [**Defense-Finder v2.0.0, models 2.0.2**](https://ecogenomics.github.io/GTDBTk/index.html): Detects known anti-phage systems in the host.
-
-- [**geNomad v1.7.1**](https://portal.nersc.gov/genomad/): Predicts and annotates proviruses.
-
-**Virus-analyses**
-
-- [**CheckV v1.0.1**](https://pypi.org/project/checkv/): Evaluates the quality of viral genomes.
-
-- [**dRep v3.4.5**](https://drep.readthedocs.io/en/latest/): Compares viral genomes within the same host.
-
-- [**Abricate v1.0.1**](https://github.com/tseemann/abricate): Identifies virulence genes in the prophage genomes with the [VFDB database](https://www.mgc.ac.cn/VFs/).
-
-- [**iPHOP v1.3.3**](https://bitbucket.org/srouxjgi/iphop/src/main/): Predicts other potential hosts of viral genomes.
-
-- [**VIBRANT v1.2.1**](https://github.com/AnantharamanLab/VIBRANT): Used to identify Auxiliary Metabolic Genes in the prophages.
-
-## Workflow
-
-The workflow begins with the input of bacterial genomes by the user. These are processed by the **host-analyses** tools. Prophage prediction is  
-performed by **geNomad** only. Afterward, prophages identified by **geNomad** are processed by the **virus-analyses** tools.
-
-If more than one prophage is recovered in the same sample, **dRep** is used to compare and determine if the viruses are identical or different within the same host.
-
-*PLACEHOLDER FOR PIPELINE*
-
-## R Session Info
-
-Information about the R session used to render this markdown document.
-
-```{r}
-sessionInfo()
-```
-
-
 # Results {.tabset .tabset-fade}
 
 ```{r}
 # Creating combined_unique object
 
 combined_unique <- bind_rows(
-  checkm_host_data %>%
-    # select(bin_id) %>%
-    # dplyr::rename(Sample = bin_id),
-    select(name) %>%
-    dplyr::rename(Sample = name),
-  
-  data %>%
-    #mutate(Sample = str_remove(Sample, "_virus_summary.tsv")) %>%
-    select(Sample)
+    checkm_host_data %>%
+        # dplyr::select(bin_id) %>%
+        # dplyr::rename(Sample = bin_id),
+        dplyr::select(name) %>%
+        dplyr::rename(Sample = name),
+    data %>%
+        # dplyr::mutate(Sample = stringr::str_remove(Sample, "_virus_summary.tsv")) %>%
+        dplyr::select(Sample)
 ) %>%
-  distinct(Sample) %>%
-  arrange(Sample)
+    distinct(Sample) %>%
+    arrange(Sample)
 
 log_debug(paste("combined_unique samples:", paste(combined_unique$Sample, collapse = ", ")))
 ```
@@ -504,578 +479,621 @@
 ```{r main_workflow, fig.width=6, fig.height=6, out.height="100%", out.width='100%', dpi=300, fig.align='center', warning=FALSE, message=FALSE, results='asis'}
 # Process proviruses data
 process_proviruses <- function(data_genomad) {
-  proviruses <- data_genomad %>%
-    dplyr::filter(topology == "Provirus") %>%
-    dplyr::mutate(contig = sub("\\|provirus_.*", "", seq_name)) %>%  # take everything before "|provirus"
-    dplyr::mutate(contig = paste0("c", as.numeric(factor(contig)))) %>% # map them to c_1, c_2, ...
-    dplyr::select(seq_name, coordinates, length, contig, virus_score, n_hallmarks)
-  
-  proviruses <- proviruses %>%
-    tidyr::separate(coordinates, into = c("start", "end"), sep = "-")
-  
-  proviruses$start <- as.integer(proviruses$start)
-  proviruses$end <- as.integer(proviruses$end)
-  
-  proviruses_gr_features <- GRanges(seqnames = proviruses$contig, 
-                                    ranges = IRanges(start = proviruses$start, 
-                                                     end = proviruses$end))
-  proviruses_gr_features$length <- proviruses_gr_features %>% ranges %>% width
-  proviruses_gr_features$score <- as.numeric(proviruses$virus_score)
-  proviruses_gr_features$n_hallmarks <- as.numeric(proviruses$n_hallmarks)
-  
-  proviruses_gr_features$n_hallmarks_pos <- 
-    abs(start(proviruses_gr_features) - end(proviruses_gr_features)) / 2
-  
-  return(proviruses_gr_features)
+    proviruses <- data_genomad %>%
+        dplyr::filter(topology == "Provirus") %>%
+        dplyr::mutate(contig = sub("\\|provirus_.*", "", seq_name)) %>% # take everything before "|provirus"
+        dplyr::mutate(contig = paste0("c", as.numeric(factor(contig)))) %>% # map them to c_1, c_2, ...
+        dplyr::select(seq_name, coordinates, length, contig, virus_score, n_hallmarks)
+
+    proviruses <- proviruses %>%
+        tidyr::separate(coordinates, into = c("start", "end"), sep = "-")
+
+    proviruses$start <- as.integer(proviruses$start)
+    proviruses$end <- as.integer(proviruses$end)
+
+    proviruses_gr_features <- GRanges(
+        seqnames = proviruses$contig,
+        ranges = IRanges(
+            start = proviruses$start,
+            end = proviruses$end
+        )
+    )
+    proviruses_gr_features$length <- proviruses_gr_features %>%
+        ranges() %>%
+        width()
+    proviruses_gr_features$score <- as.numeric(proviruses$virus_score)
+    proviruses_gr_features$n_hallmarks <- as.numeric(proviruses$n_hallmarks)
+
+    proviruses_gr_features$n_hallmarks_pos <-
+        abs(start(proviruses_gr_features) - end(proviruses_gr_features)) / 2
+
+    return(proviruses_gr_features)
 }
 
 plot_genome_ideogram <- function(genome_current, proviruses_gr_features) {
-  fasta_file_path <- file.path(params$outdir, "genomes", paste0(genome_current, ".fna"))
-  #cat(fasta_file_path, "\n\n")
-  genome_ideogram <- getIdeogramData(fasta_file = fasta_file_path)
-  
-  # Replace any seqlevel to c_1, c_2, c_3, ...
-  new_seqlevels <- paste0("c", seq_along(seqlevels(genome_ideogram)))
-  names(new_seqlevels) <- seqlevels(genome_ideogram)
-  genome_ideogram <- GenomeInfoDb::renameSeqlevels(genome_ideogram, new_seqlevels)
-  colours <- rep("#a58bc5", length(seqlevels(genome_ideogram)))
-  
-  par(mar = c(2, 2, 2, 2))  # minimal margins around the plot
-  
-  gmovizInitialise(genome_ideogram,
-                   sector_colours = colours,
-                   sector_border_colours = colours,
-                   sector_labels = FALSE
-  )
-  
-  for (i in 1:length(proviruses_gr_features)) {
-    name <- as.character(seqnames(proviruses_gr_features[i]))
-    start <- as.numeric(start(proviruses_gr_features[i]))
-    end <- as.numeric(end(proviruses_gr_features[i]))
-    region <- data.frame(start = start, end = end)
-    circos.genomicRect(seqnames = name,
-                       region,
-                       ytop = .5,
-                       ybottom = 0,
-                       track.index = 1,
-                       sector.index = name,
-                       border = "#e9d27d",
-                       col = "#e9d27d")
-  }
-  
-  length <- as.numeric(proviruses_gr_features$length)
-  length <- ifelse(length > 1000000,
-                   paste0(round(length/1000000, 2), "mb"),
-                   paste0(round(length/1000, 2), "kb"))
-  labels <- paste0(as.character(seqnames(proviruses_gr_features)), " (", length, ")")
-  circos.labels(sectors = as.character(seqnames(proviruses_gr_features)),
-                x = as.numeric(start(proviruses_gr_features)),
-                labels,
-                facing = "clockwise")
+    fasta_file_path <- file.path(params$outdir, "genomes", paste0(genome_current, ".fna"))
+    # cat(fasta_file_path, "\n\n")
+    genome_ideogram <- gmoviz::getIdeogramData(fasta_file = fasta_file_path)
+
+    # Replace any seqlevel to c_1, c_2, c_3, ...
+    new_seqlevels <- paste0("c", seq_along(GenomeInfoDb::seqlevels(genome_ideogram)))
+    names(new_seqlevels) <- GenomeInfoDb::seqlevels(genome_ideogram)
+    genome_ideogram <- GenomeInfoDb::renameSeqlevels(genome_ideogram, new_seqlevels)
+    colours <- rep("#a58bc5", length(GenomeInfoDb::seqlevels(genome_ideogram)))
+
+    par(mar = c(2, 2, 2, 2)) # minimal margins around the plot
+
+    gmoviz::gmovizInitialise(genome_ideogram,
+        sector_colours = colours,
+        sector_border_colours = colours,
+        sector_labels = FALSE
+    )
+
+    for (i in 1:length(proviruses_gr_features)) {
+        name <- as.character(seqnames(proviruses_gr_features[i]))
+        start <- as.numeric(start(proviruses_gr_features[i]))
+        end <- as.numeric(end(proviruses_gr_features[i]))
+        region <- data.frame(start = start, end = end)
+        circlize::circos.genomicRect(
+            seqnames = name,
+            region,
+            ytop = .5,
+            ybottom = 0,
+            track.index = 1,
+            sector.index = name,
+            border = "#e9d27d",
+            col = "#e9d27d"
+        )
+    }
+
+    length <- as.numeric(proviruses_gr_features$length)
+    length <- ifelse(length > 1000000,
+        paste0(round(length / 1000000, 2), "mb"),
+        paste0(round(length / 1000, 2), "kb")
+    )
+    labels <- paste0(as.character(seqnames(proviruses_gr_features)), " (", length, ")")
+    circlize::circos.labels(
+        sectors = as.character(seqnames(proviruses_gr_features)),
+        x = as.numeric(start(proviruses_gr_features)),
+        labels,
+        facing = "clockwise"
+    )
 }
 
 process_sample <- function(sample, combined_unique, host_genomes_paths, genome_data) {
-  genome_current <- sample  # Add this line
-  tryCatch({
-    log_debug(paste("Starting to process sample:", sample))
-    
-    # Check if sample exists in genome_data
-    if (!(sample %in% names(genome_data))) {
-      log_debug(paste("Sample", sample, "not found in genome_data"))
-      cat(paste("Error: Sample", sample, "not found in genome_data\n\n"))
-      return()
-    }
-    
-    cat(paste("## ", sample, "{.tabset .tabset-fade} \n\n"))
+    genome_current <- sample # Add this line
+    tryCatch(
+        {
+            log_debug(paste("Starting to process sample:", sample))
+
+            # Check if sample exists in genome_data
+            if (!(sample %in% names(genome_data))) {
+                log_debug(paste("Sample", sample, "not found in genome_data"))
+                cat(paste("Error: Sample", sample, "not found in genome_data\n\n"))
+                return()
+            }
+
+            cat(paste("## ", sample, "{.tabset .tabset-fade} \n\n"))
+
+            host_genome_path <- host_genomes_paths$path[host_genomes_paths$name == sample]
+            if (length(host_genome_path) == 0) {
+                log_debug(paste("Host genome path not found for sample:", sample))
+                cat(paste("Error: Host genome path not found for sample", sample, "\n\n"))
+                return()
+            }
+
+            host_genome_ideogram <- tryCatch(
+                {
+                    gmoviz::getIdeogramData(fasta_file = host_genome_path)
+                },
+                error = function(e) {
+                    log_debug(paste("Error loading host genome ideogram for sample", sample, ":", conditionMessage(e)))
+                    NULL
+                }
+            )
+
+            if (is.null(host_genome_ideogram)) {
+                cat(paste("Error: Unable to load host genome ideogram for sample", sample, "\n\n"))
+                return()
+            }
+
+            sample_data <- genome_data[[sample]]$loaded_data
+            genomad_summary <- sample_data$genomad
+            genomad_annotation <- sample_data$genomad_annotations
+            checkv_data <- sample_data$checkv
+            defense_finder_data <- sample_data$defense_finder
+            abricate_data <- sample_data$abricate
+            iphop_data <- sample_data$iphop
+            vibrant_data <- sample_data$vibrant
 
-    host_genome_path <- host_genomes_paths$path[host_genomes_paths$name == sample]
-    if (length(host_genome_path) == 0) {
-      log_debug(paste("Host genome path not found for sample:", sample))
-      cat(paste("Error: Host genome path not found for sample", sample, "\n\n"))
-      return()
-    }
-    
-    host_genome_ideogram <- tryCatch({
-      getIdeogramData(fasta_file = host_genome_path)
-    }, error = function(e) {
-      log_debug(paste("Error loading host genome ideogram for sample", sample, ":", conditionMessage(e)))
-      NULL
-    })
-    
-    if (is.null(host_genome_ideogram)) {
-      cat(paste("Error: Unable to load host genome ideogram for sample", sample, "\n\n"))
-      return()
-    }
-    
-    sample_data <- genome_data[[sample]]$loaded_data
-    genomad_summary <- sample_data$genomad
-    genomad_annotation <- sample_data$genomad_annotations
-    checkv_data <- sample_data$checkv
-    defense_finder_data <- sample_data$defense_finder
-    abricate_data <- sample_data$abricate
-    iphop_data <- sample_data$iphop
-    vibrant_data <- sample_data$vibrant
-    
-    cat("### Host Genome\n\n")
+            cat("### Host Genome\n\n")
+
+            cat("**GTDB-Tk taxonomy**: \n\n")
+            data_gtdbtk_host %>%
+                dplyr::filter(user_genome == sample) %>%
+                dplyr::select(classification) %>%
+                kableExtra::kbl() %>%
+                kableExtra::kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
+                kableExtra::kable_paper("striped", full_width = TRUE) %>%
+                kableExtra::scroll_box(width = "100%", height = "100%") %>%
+                cat()
 
-    cat("**GTDB-Tk taxonomy**: \n\n")
-    data_gtdbtk_host %>% filter(user_genome == sample) %>%
-      select(classification) %>%
-      kbl() %>%
-      kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
-      kable_paper("striped", full_width = TRUE) %>%
-      scroll_box(width = "100%", height = "100%") %>%
-      cat()
+            # Cat checkm summary for this genome
+            cat("**CheckM2 Summary**:\n\n")
+            # checkm_summary <- data_checkm_host %>% dplyr::filter(`bin_id` == sample)
+            checkm_summary <- data_checkm_host %>% dplyr::filter(`name` == sample)
+            checkm_summary %>%
+                janitor::clean_names() %>%
+                # dplyr::select(number_contigs, n50_contigs, completeness, contamination, strain_heterogeneity) %>%
+                dplyr::select(total_contigs, contig_n50, completeness, contamination) %>%
+                kableExtra::kbl() %>%
+                kableExtra::kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
+                kableExtra::kable_paper("striped", full_width = TRUE) %>%
+                kableExtra::scroll_box(width = "100%", height = "100%") %>%
+                cat()
 
-    # Cat checkm summary for this genome
-    cat("**CheckM2 Summary**:\n\n")
-    #checkm_summary <- data_checkm_host %>% filter(`bin_id` == sample)
-    checkm_summary <- data_checkm_host %>% filter(`name` == sample)
-    checkm_summary %>% clean_names %>%
-      #select(number_contigs, n50_contigs, completeness, contamination, strain_heterogeneity) %>%
-      select(total_contigs, contig_n50, completeness, contamination) %>%
-      kbl() %>%
-      kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
-      kable_paper("striped", full_width = TRUE) %>%
-      scroll_box(width = "100%", height = "100%") %>%
-      cat()
-    
-    # Display defense-finder as a table
-    if (!is.null(defense_finder_data) && nrow(defense_finder_data) > 0) {
-      cat("**Defense-Finder Systems**:\n\n")
+            # Display defense-finder as a table
+            if (!is.null(defense_finder_data) && nrow(defense_finder_data) > 0) {
+                cat("**Defense-Finder Systems**:\n\n")
+
+                defense_finder_data %>%
+                    dplyr::select(sys_id, type, subtype, sys_beg, sys_end, protein_in_syst, genes_count, name_of_profiles_in_sys) %>%
+                    kableExtra::kbl() %>%
+                    kableExtra::kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
+                    kableExtra::kable_paper("striped", full_width = TRUE) %>%
+                    kableExtra::scroll_box(width = "100%", height = "100%") %>%
+                    cat()
+            } else {
+                cat("No Defense-Finder systems detected.\n\n")
+            }
+
+            if (is.null(genomad_summary) || nrow(genomad_summary) == 0) {
+                q
+                log_debug(paste("No geNomad summary data found for sample:", sample))
+                return()
+            }
 
-      defense_finder_data %>%
-        select(sys_id, type, subtype, sys_beg, sys_end, protein_in_syst, genes_count, name_of_profiles_in_sys) %>%
-        kbl() %>%
-        kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
-        kable_paper("striped", full_width = TRUE) %>%
-        scroll_box(width = "100%", height = "100%") %>%
-        cat()
-    } else {
-      cat("No Defense-Finder systems detected.\n\n")
-    }
-    
-    if (is.null(genomad_summary) || nrow(genomad_summary) == 0) {
-      log_debug(paste("No geNomad summary data found for sample:", sample))
-      return()
-    }
-    
-    if (length(seqlevels(host_genome_ideogram)) == 1) {
-      host_genome_size <- sum(width(host_genome_ideogram))
-    } else {
-      virus_containing_contigs <- unique(sub("\\|.*", "", genomad_summary$seq_name))
-      virus_containing_contigs <- paste0("c_", as.numeric(factor(virus_containing_contigs)))
-      filtered_host_genome <- subset_and_update_ideogram(host_genome_ideogram, virus_containing_contigs)
-      host_genome_size <- sum(width(filtered_host_genome))
-    }
-    
-    # Process proviruses
-    proviruses_gr_features <- process_proviruses(genomad_summary)
-    
-    cat("**Genomad and CheckV Summary**:\n\n")
-    genomad_summary %>%
-      select(seq_name, taxonomy, topology, coordinates, length) %>%
-      left_join(
-        checkv_data %>% select(contig_id, gene_count, viral_genes, checkv_quality, miuvig_quality),
-        by = c("seq_name" = "contig_id")) %>%
-      select(seq_name, length, gene_count, viral_genes, checkv_quality, miuvig_quality, taxonomy, topology, coordinates) %>%
-      kbl() %>%
-      kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
-      kable_paper("striped", full_width = TRUE) %>%
-      scroll_box(width = "100%", height = "100%") %>%
-      cat()
-    
-    cat("**Host Genome Ideogram with Phages**:\n\n")
-    plot_genome_ideogram(sample, proviruses_gr_features)
-    cat('In this circular plot, **"c"** indicates the contig, and the number that follows (e.g., **c1**) represents the contig number.  
+            if (length(GenomeInfoDb::seqlevels(host_genome_ideogram)) == 1) {
+                host_genome_size <- sum(width(host_genome_ideogram))
+            } else {
+                virus_containing_contigs <- unique(sub("\\|.*", "", genomad_summary$seq_name))
+                virus_containing_contigs <- paste0("c_", as.numeric(factor(virus_containing_contigs)))
+                filtered_host_genome <- subset_and_update_ideogram(host_genome_ideogram, virus_containing_contigs)
+                host_genome_size <- sum(width(filtered_host_genome))
+            }
+
+            # Process proviruses
+            proviruses_gr_features <- process_proviruses(genomad_summary)
+
+            cat("**Genomad and CheckV Summary**:\n\n")
+            genomad_summary %>%
+                dplyr::select(seq_name, taxonomy, topology, coordinates, length) %>%
+                dplyr::left_join(
+                    checkv_data %>% dplyr::select(contig_id, gene_count, viral_genes, checkv_quality, miuvig_quality),
+                    by = c("seq_name" = "contig_id")
+                ) %>%
+                dplyr::select(seq_name, length, gene_count, viral_genes, checkv_quality, miuvig_quality, taxonomy, topology, coordinates) %>%
+                kableExtra::kbl() %>%
+                kableExtra::kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
+                kableExtra::kable_paper("striped", full_width = TRUE) %>%
+                kableExtra::scroll_box(width = "100%", height = "100%") %>%
+                cat()
+
+            cat("**Host Genome Ideogram with Phages**:\n\n")
+            plot_genome_ideogram(sample, proviruses_gr_features)
+            cat('In this circular plot, **"c"** indicates the contig, and the number that follows (e.g., **c1**) represents the contig number.
 If multiple contigs are present in the genome, each will be shown with a distinct label (e.g., **c1**, **c2**, etc.).\n\n')
-    cat("\n\n")
+            cat("\n\n")
+
+            # Process phage genomes
+            cat("### Prophages {.tabset .tabset-fade} \n\n")
+            cat("**Select prophage to show: ** \n\n")
+            for (i in seq_len(nrow(genomad_summary))) {
+                log_debug(paste("Processing phage", i, "of", nrow(genomad_summary), "for sample", sample))
+                process_phage(genomad_summary[i, ], genomad_summary, genomad_annotation, checkv_data, host_genome_size)
+            }
+
+            # Plot dREP if applicable
+            if (nrow(genomad_summary) > 1) {
+                cat("### vOTUs\n\n")
+                plot_drep(sample, genomad_summary)
+            }
 
-    # Process phage genomes
-    cat("### Prophages {.tabset .tabset-fade} \n\n")
-    cat("**Select prophage to show: ** \n\n")
-    for (i in seq_len(nrow(genomad_summary))) {
-      log_debug(paste("Processing phage", i, "of", nrow(genomad_summary), "for sample", sample))
-      process_phage(genomad_summary[i, ], genomad_summary, genomad_annotation, checkv_data, host_genome_size)
-    }
-    
-    # Plot dREP if applicable
-    if (nrow(genomad_summary) > 1) {
-      cat("### vOTUs\n\n")
-      plot_drep(sample, genomad_summary)
-    }
-    
-    # Creating table with Abricate data
-    if (nrow(abricate_data) > 0) {
-      cat("### Virulence Genes {.tabset .tabset-fade} \n\n")
-      cat("Screening of virulence genes present in the prophage contigs. \n\n")
-      abricate_data %>% select(-number_file) %>%
-      kbl() %>%
-      kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
-      kable_paper("striped", full_width = TRUE) %>%
-      scroll_box(width = "100%", height = "100%") %>% cat()
-      cat("\n\n")
-    }
-    
-    # Creating table with iPHOP
-    if (nrow(iphop_data) > 0) {
-      cat("### Prophage-Host Prediction {.tabset .tabset-fade} \n\n")
-      cat("Prediction of potential hosts for the prophage contigs. \n\n")
-      iphop_data %>%
-      kbl() %>%
-      kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
-      kable_paper("striped", full_width = TRUE) %>%
-      scroll_box(width = "100%", height = "100%") %>% cat()
-      cat("\n\n")
-    }
-    
-    # Creating table with VIBRANT AMGs
-    if (nrow(vibrant_data) > 0) {
-      cat("### AMG Predictions {.tabset .tabset-fade} \n\n")
-      cat("Prediction of auxiliary metabolic genes in the prophage contigs. \n\n")
-      vibrant_data %>%
-      kbl() %>%
-      kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
-      kable_paper("striped", full_width = TRUE) %>%
-      scroll_box(width = "100%", height = "100%") %>% cat()
-      cat("\n\n")
-    }
+            # Creating table with Abricate data
+            if (nrow(abricate_data) > 0) {
+                cat("### Virulence Genes {.tabset .tabset-fade} \n\n")
+                cat("Screening of virulence genes present in the prophage contigs. \n\n")
+                abricate_data %>%
+                    dplyr::select(-number_file) %>%
+                    kableExtra::kbl() %>%
+                    kableExtra::kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
+                    kableExtra::kable_paper("striped", full_width = TRUE) %>%
+                    kableExtra::scroll_box(width = "100%", height = "100%") %>%
+                    cat()
+                cat("\n\n")
+            }
 
-  log_debug(paste("Finished processing sample:", sample))
-  }, error = function(e) {
-    log_debug(paste("Error in process_sample for", sample, ":", conditionMessage(e)))
-    cat(paste("Error processing sample", sample, ":", conditionMessage(e), "\n\n"))
-  })
+            # Creating table with iPHOP
+            if (nrow(iphop_data) > 0) {
+                cat("### Prophage-Host Prediction {.tabset .tabset-fade} \n\n")
+                cat("Prediction of potential hosts for the prophage contigs. \n\n")
+                iphop_data %>%
+                    kableExtra::kbl() %>%
+                    kableExtra::kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
+                    kableExtra::kable_paper("striped", full_width = TRUE) %>%
+                    kableExtra::scroll_box(width = "100%", height = "100%") %>%
+                    cat()
+                cat("\n\n")
+            }
+
+            # Creating table with VIBRANT AMGs
+            if (nrow(vibrant_data) > 0) {
+                cat("### AMG Predictions {.tabset .tabset-fade} \n\n")
+                cat("Prediction of auxiliary metabolic genes in the prophage contigs. \n\n")
+                vibrant_data %>%
+                    kableExtra::kbl() %>%
+                    kableExtra::kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
+                    kableExtra::kable_paper("striped", full_width = TRUE) %>%
+                    kableExtra::scroll_box(width = "100%", height = "100%") %>%
+                    cat()
+                cat("\n\n")
+            }
+
+            log_debug(paste("Finished processing sample:", sample))
+        },
+        error = function(e) {
+            log_debug(paste("Error in process_sample for", sample, ":", conditionMessage(e)))
+            cat(paste("Error processing sample", sample, ":", conditionMessage(e), "\n\n"))
+        }
+    )
 }
 
 process_phage <- function(virus, genomad_summary, genomad_annotation, checkv_data, host_genome_size) {
-  cat(paste("#### Phage ID:", virus$seq_name, " {.tabset .tabset-fade} \n\n"))
+    cat(paste("#### Phage ID:", virus$seq_name, " {.tabset .tabset-fade} \n\n"))
+
+    current_contig <- sub("\\|.*", "", virus$seq_name)
+
+    provirus_start <- as.numeric(sub(".*provirus_(\\d+)_\\d+", "\\1", virus$seq_name))
+    provirus_end <- as.numeric(sub(".*provirus_\\d+_(\\d+)", "\\1", virus$seq_name))
+    virus_length <- provirus_end - provirus_start + 1
+
+    current_contig_base <- sub("\\|provirus_.*", "", virus$seq_name)
+    current_provirus_range <- sub(".*\\|provirus_", "", virus$seq_name)
+    current_annotations <- genomad_annotation[grepl(paste0(current_contig_base, "\\|provirus_", current_provirus_range, "_"),
+        genomad_annotation$gene,
+        fixed = FALSE
+    ), ] %>%
+        dplyr::mutate(arrow_pos = ifelse(strand == -1, "start", "end"))
 
-  current_contig <- sub("\\|.*", "", virus$seq_name)
-  
-  provirus_start <- as.numeric(sub(".*provirus_(\\d+)_\\d+", "\\1", virus$seq_name))
-  provirus_end <- as.numeric(sub(".*provirus_\\d+_(\\d+)", "\\1", virus$seq_name))
-  virus_length <- provirus_end - provirus_start + 1
-  
-  current_contig_base <- sub("\\|provirus_.*", "", virus$seq_name)
-  current_provirus_range <- sub(".*\\|provirus_", "", virus$seq_name)
-  current_annotations <- genomad_annotation[grepl(paste0(current_contig_base, "\\|provirus_", current_provirus_range, "_"), 
-                                                  genomad_annotation$gene, fixed = FALSE), ] %>%
-  mutate(arrow_pos = ifelse(strand == -1, "start", "end"))
-  
-  
-  cat("\n\n**Phage–Host Genome Ideogram:**\n\n")
-  
-  plot_phage_circos(virus, genomad_summary, current_annotations, virus_length, host_genome_size, provirus_start, provirus_end, checkv_data)
-  
-  cat("\n\n")
-  cat("\n\n**Genes Annotation (geNomad):**\n\n")
-  
-  current_annotations %>%
-    select(gene, length, marker, annotation_accessions, annotation_description) %>%
-    kbl() %>%
-    kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
-    kable_paper() %>%
-    cat()
-  cat("\n\n")
+
+    cat("\n\n**Phage-Host Genome Ideogram:**\n\n")
+
+    plot_phage_circos(virus, genomad_summary, current_annotations, virus_length, host_genome_size, provirus_start, provirus_end, checkv_data)
+
+    cat("\n\n")
+    cat("\n\n**Genes Annotation (geNomad):**\n\n")
+
+    current_annotations %>%
+        dplyr::select(gene, length, marker, annotation_accessions, annotation_description) %>%
+        kableExtra::kbl() %>%
+        kableExtra::kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
+        kableExtra::kable_paper() %>%
+        cat()
+    cat("\n\n")
 }
 
 plot_phage_circos <- function(virus, genomad_summary, current_annotations, virus_length, host_genome_size, provirus_start, provirus_end, checkv_data) {
-  tryCatch({
-    log_debug("Starting plot_phage_circos function")
-    log_debug(paste("Current virus:", virus$seq_name))
-    log_debug(paste("Virus length:", virus_length))
-    log_debug(paste("Host genome size:", host_genome_size))
-    log_debug(paste("Provirus start:", provirus_start))
-    log_debug(paste("Provirus end:", provirus_end))
-    
-    # Check for NA or invalid values in input parameters
-    if (is.na(virus_length) || virus_length <= 0) {
-      log_debug("Error: Invalid virus length")
-      return(NULL)
-    }
-    if (is.na(host_genome_size) || host_genome_size <= 0) {
-      log_debug("Error: Invalid host genome size")
-      return(NULL)
-    }
-    if (is.na(provirus_start) || provirus_start < 0) {
-      log_debug("Error: Invalid provirus start position")
-      return(NULL)
-    }
-    if (is.na(provirus_end) || provirus_end <= provirus_start) {
-      log_debug("Error: Invalid provirus end position")
-      return(NULL)
-    }
-    
-    # Extract contig information
-    current_contig <- sub("\\|.*", "", virus$seq_name)
-    log_debug(paste("Current contig:", current_contig))
-    
-    contig_viruses <- genomad_summary[grepl(paste0("^", current_contig), genomad_summary$seq_name), ]
-    if (nrow(contig_viruses) == 0) {
-      log_debug("Error: No viruses found for the current contig")
-      return(NULL)
-    }
-    
-    contig_length <- max(as.numeric(sub(".*_(\\d+)$", "\\1", contig_viruses$seq_name)))
-    if (is.na(contig_length) || contig_length <= 0) {
-      contig_length <- virus_length  # Use virus length as fallback if contig length is invalid
-      log_debug(paste("Using virus length as contig length:", contig_length))
-    } else {
-      log_debug(paste("Contig length:", contig_length))
-    }
-    
-    if (provirus_end > contig_length) {
-      log_debug("Error: Provirus end position exceeds contig length")
-      return(NULL)
-    }
-    
-    log_debug("Clearing circos")
-    circos.clear()
-    
-    log_debug("Setting circos parameters")
-    circos.par(start.degree = 180, gap.degree = 10, track.margin = c(0.01, 0.01))
-    
-    main_color <- "#a58bc5"
-    zoom_color <- "#e9d27d"
-    
-    zoom_start <- (provirus_start / contig_length) * 100
-    zoom_end <- (provirus_end / contig_length) * 100
-    
-    log_debug(paste("Zoom start:", zoom_start))
-    log_debug(paste("Zoom end:", zoom_end))
-    
-    log_debug("Initializing circos")
-    circos.initialize(factors = c("Zoom", "Main"), xlim = c(0, 100))
-    
-    format_genome_labels <- function(x) {
-      ifelse(x >= 1e6, paste0(round(x / 1e6, 2), " Mb"),
-             ifelse(x >= 1e3, paste0(round(x / 1e3, 2), " Kb"),
-                    paste0(x, " bp")))
-    }
-    
-    log_debug("Adding link")
-    tryCatch({
-      circos.link("Main", c(zoom_start, zoom_end), "Zoom", c(0, 100),
-                  rou1 = 0.8,
-                  rou2 = 0.97,
-                  h.ratio = 0.55, # width?
-                  lty = 2,
-                  lwd = 0.5,
-                  h2 = 1,
-                  col = "grey99", border = "grey80")
-    }, error = function(e) {
-      log_debug(paste("Error in circos.link:", e$message))
-    })
-    
-    log_debug("Adding zoom track")
-    circos.track(factors = "Zoom", ylim = c(0, 1), track.height = 0.15,
-                 panel.fun = function(x, y) {
-                   circos.rect(0, 0, 100, 1, col = zoom_color, border = NA)
-                   axis_labels <- seq(0, virus_length, length.out = 6)
-                   axis_positions <- seq(0, 100, length.out = 6)
-                   circos.axis(h = "top", major.at = axis_positions,
-                               labels = format_genome_labels(axis_labels),
-                               labels.cex = 0.7, direction = "outside")
+    tryCatch(
+        {
+            log_debug("Starting plot_phage_circos function")
+            log_debug(paste("Current virus:", virus$seq_name))
+            log_debug(paste("Virus length:", virus_length))
+            log_debug(paste("Host genome size:", host_genome_size))
+            log_debug(paste("Provirus start:", provirus_start))
+            log_debug(paste("Provirus end:", provirus_end))
+
+            # Check for NA or invalid values in input parameters
+            if (is.na(virus_length) || virus_length <= 0) {
+                log_debug("Error: Invalid virus length", virus_length)
+                return(NULL)
+            }
+            if (is.na(host_genome_size) || host_genome_size <= 0) {
+                log_debug("Error: Invalid host genome size")
+                return(NULL)
+            }
+            if (is.na(provirus_start) || provirus_start < 0) {
+                log_debug("Error: Invalid provirus start position")
+                return(NULL)
+            }
+            if (is.na(provirus_end) || provirus_end <= provirus_start) {
+                log_debug("Error: Invalid provirus end position")
+                return(NULL)
+            }
+
+            # Extract contig information
+            current_contig <- sub("\\|.*", "", virus$seq_name)
+            log_debug(paste("Current contig:", current_contig))
+
+            contig_viruses <- genomad_summary[grepl(paste0("^", current_contig), genomad_summary$seq_name), ]
+            if (nrow(contig_viruses) == 0) {
+                log_debug("Error: No viruses found for the current contig")
+                return(NULL)
+            }
+
+            contig_length <- max(as.numeric(sub(".*_(\\d+)$", "\\1", contig_viruses$seq_name)))
+            if (is.na(contig_length) || contig_length <= 0) {
+                contig_length <- virus_length # Use virus length as fallback if contig length is invalid
+                log_debug(paste("Using virus length as contig length:", contig_length))
+            } else {
+                log_debug(paste("Contig length:", contig_length))
+            }
+
+            if (provirus_end > contig_length) {
+                log_debug("Error: Provirus end position exceeds contig length")
+                return(NULL)
+            }
+
+            log_debug("Clearing circos")
+            circlize::circos.clear()
+
+            log_debug("Setting circos parameters")
+            circlize::circos.par(start.degree = 180, gap.degree = 10, track.margin = c(0.01, 0.01))
+
+            main_color <- "#a58bc5"
+            zoom_color <- "#e9d27d"
+
+            zoom_start <- (provirus_start / contig_length) * 100
+            zoom_end <- (provirus_end / contig_length) * 100
+
+            log_debug(paste("Zoom start:", zoom_start))
+            log_debug(paste("Zoom end:", zoom_end))
+
+            log_debug("Initializing circos")
+            circlize::circos.initialize(factors = c("Zoom", "Main"), xlim = c(0, 100))
+
+            format_genome_labels <- function(x) {
+                ifelse(x >= 1e6, paste0(round(x / 1e6, 2), " Mb"),
+                    ifelse(x >= 1e3, paste0(round(x / 1e3, 2), " Kb"),
+                        paste0(x, " bp")
+                    )
+                )
+            }
+
+            log_debug("Adding link")
+            tryCatch(
+                {
+                    circlize::circos.link("Main", c(zoom_start, zoom_end), "Zoom", c(0, 100),
+                        rou1 = 0.8,
+                        rou2 = 0.97,
+                        h.ratio = 0.55, # width?
+                        lty = 2,
+                        lwd = 0.5,
+                        h2 = 1,
+                        col = "grey99", border = "grey80"
+                    )
+                },
+                error = function(e) {
+                    log_debug(paste("Error in circlize::circos.link:", e$message))
+                }
+            )
 
-                   for (i in 1:nrow(current_annotations)) {
-                     gene_start <- current_annotations$start[i]
-                     gene_end <- current_annotations$end[i]
-                     arrow_start <- (gene_start - provirus_start) / virus_length * 100
-                     arrow_end <- (gene_end - provirus_start) / virus_length * 100
+            log_debug("Adding zoom track")
+            circlize::circos.track(
+                factors = "Zoom", ylim = c(0, 1), track.height = 0.15,
+                panel.fun = function(x, y) {
+                    circlize::circos.rect(0, 0, 100, 1, col = zoom_color, border = NA)
+                    axis_labels <- seq(0, virus_length, length.out = 6)
+                    axis_positions <- seq(0, 100, length.out = 6)
+                    circlize::circos.axis(
+                        h = "top", major.at = axis_positions,
+                        labels = format_genome_labels(axis_labels),
+                        labels.cex = 0.7, direction = "outside"
+                    )
 
-                     circos.arrow(arrow_start, arrow_end, y1 = 0, y2 = 1,
-                                  arrow.head.width = 0.75, arrow.head.length = cm_x(0.1),
-                                  arrow.position = current_annotations$arrow_pos[i],
-                                  col = ifelse(is.na(current_annotations$annotation_description[i]), "grey", "#7fbfff"),
-                                  border = ifelse(is.na(current_annotations$annotation_description[i]), "grey20", "darkblue"))
-                   }
-                 }, bg.border = NA)
+                    for (i in 1:nrow(current_annotations)) {
+                        gene_start <- current_annotations$start[i]
+                        gene_end <- current_annotations$end[i]
+                        arrow_start <- (gene_start - provirus_start) / virus_length * 100
+                        arrow_end <- (gene_end - provirus_start) / virus_length * 100
 
-    log_debug("Adding main track")
-    circos.track(factors = "Main", ylim = c(0, 1), track.height = 0.1,
-                 panel.fun = function(x, y) {
-                   circos.rect(xleft = 0, ybottom = 0, xright = 100, ytop = 1, col = main_color, border = NA)
-
-                   for (i in 1:nrow(contig_viruses)) {
-                     virus_start <- as.numeric(sub(".*provirus_(\\d+)_\\d+", "\\1", contig_viruses$seq_name[i]))
-                     virus_end <- as.numeric(sub(".*provirus_\\d+_(\\d+)", "\\1", contig_viruses$seq_name[i]))
+                        circlize::circos.arrow(arrow_start, arrow_end,
+                            arrow.head.width = 0.75, arrow.head.length = cm_x(0.1),
+                            arrow.position = current_annotations$arrow_pos[i],
+                            col = ifelse(is.na(current_annotations$annotation_description[i]), "grey", "#7fbfff"),
+                            border = ifelse(is.na(current_annotations$annotation_description[i]), "grey20", "darkblue")
+                        )
+                    }
+                }, bg.border = NA
+            )
 
-                     virus_start_percent <- (virus_start / contig_length) * 100
-                     virus_end_percent <- (virus_end / contig_length) * 100
-
-                     rect_color <- if (contig_viruses$seq_name[i] == virus$seq_name) zoom_color else adjustcolor(zoom_color, alpha.f = 0.7)
+            log_debug("Adding main track")
+            circlize::circos.track(
+                factors = "Main", ylim = c(0, 1), track.height = 0.1,
+                panel.fun = function(x, y) {
+                    circlize::circos.rect(xleft = 0, ybottom = 0, xright = 100, ytop = 1, col = main_color, border = NA)
 
-                     circos.rect(xleft = virus_start_percent, ybottom = 0,
-                                 xright = virus_end_percent, ytop = 1,
-                                 col = rect_color, border = NA)
-                   }
+                    for (i in 1:nrow(contig_viruses)) {
+                        virus_start <- as.numeric(sub(".*provirus_(\\d+)_\\d+", "\\1", contig_viruses$seq_name[i]))
+                        virus_end <- as.numeric(sub(".*provirus_\\d+_(\\d+)", "\\1", contig_viruses$seq_name[i]))
+
+                        virus_start_percent <- (virus_start / contig_length) * 100
+                        virus_end_percent <- (virus_end / contig_length) * 100
+
+                        rect_color <- if (contig_viruses$seq_name[i] == virus$seq_name) zoom_color else adjustcolor(zoom_color, alpha.f = 0.7)
 
-                   axis_labels <- seq(0, contig_length, length.out = 6)
-                   axis_positions <- seq(0, 100, length.out = 6)
-                   circos.axis(h = "top", major.at = axis_positions,
-                               labels = format_genome_labels(axis_labels),
-                               labels.cex = 0.7, direction = "outside")
-                 }, bg.border = NA)
-    
-    log_debug("Locating phage positions")
-    phage_positions <- sapply(1:nrow(contig_viruses), function(i) {
-      virus_start <- as.numeric(sub(".*provirus_(\\d+)_\\d+", "\\1", contig_viruses$seq_name[i]))
-      virus_end <- as.numeric(sub(".*provirus_\\d+_(\\d+)", "\\1", contig_viruses$seq_name[i]))
-      ((virus_start + virus_end) / 2 / contig_length) * 100
-    })
-    
-    log_debug("Annotating names on phage positions")
-    
-    # Extract start and end positions from sequence names
-    start_positions <- as.numeric(sub(".*provirus_([0-9]+)_.*", "\\1", contig_viruses$seq_name))
-    end_positions <- as.numeric(sub(".*provirus_[0-9]+_([0-9]+)", "\\1", contig_viruses$seq_name))
-    
-    # Create phage labels with the desired format
-    phage_labels <- paste0(round(contig_viruses$length / 1e3, 2), " Kb")
-    
-    # Apply labels to circos plot
-    circos.labels(
-      sectors = "Main",
-      x = phage_positions,
-      labels = phage_labels,
-      facing = "reverse.clockwise",
-      niceFacing = TRUE,
-      col = "black",
-      cex = 0.6,
-      side = "inside",
-      connection_height = 0.02,
-      line_col = "gray"
-    )
-    
-    center_x <- 50
-    virus_name <- virus$seq_name
-    taxonomy <- virus$taxonomy
-    
-    log_debug("Adding taxonomy and virus name to the plot")
-    circos.text(x = center_x, y = -0.2, labels = taxonomy,
+                        circlize::circos.rect(
+                            xleft = virus_start_percent, ybottom = 0,
+                            xright = virus_end_percent, ytop = 1,
+                            col = rect_color, border = NA
+                        )
+                    }
+
+                    axis_labels <- seq(0, contig_length, length.out = 6)
+                    axis_positions <- seq(0, 100, length.out = 6)
+                    circlize::circos.axis(
+                        h = "top", major.at = axis_positions,
+                        labels = format_genome_labels(axis_labels),
+                        labels.cex = 0.7, direction = "outside"
+                    )
+                }, bg.border = NA
+            )
+
+            log_debug("Locating phage positions")
+            phage_positions <- sapply(1:nrow(contig_viruses), function(i) {
+                virus_start <- as.numeric(sub(".*provirus_(\\d+)_\\d+", "\\1", contig_viruses$seq_name[i]))
+                virus_end <- as.numeric(sub(".*provirus_\\d+_(\\d+)", "\\1", contig_viruses$seq_name[i]))
+                ((virus_start + virus_end) / 2 / contig_length) * 100
+            })
+
+            log_debug("Annotating names on phage positions")
+
+            # Extract start and end positions from sequence names
+            start_positions <- as.numeric(sub(".*provirus_([0-9]+)_.*", "\\1", contig_viruses$seq_name))
+            end_positions <- as.numeric(sub(".*provirus_[0-9]+_([0-9]+)", "\\1", contig_viruses$seq_name))
+
+            # Create phage labels with the desired format
+            phage_labels <- paste0(round(contig_viruses$length / 1e3, 2), " Kb")
+
+            # Apply labels to circos plot
+            circlize::circos.labels(
+                sectors = "Main",
+                x = phage_positions,
+                labels = phage_labels,
+                facing = "reverse.clockwise",
+                niceFacing = TRUE,
+                col = "black",
+                cex = 0.6,
+                side = "inside",
+                connection_height = 0.02,
+                line_col = "gray"
+            )
+
+            center_x <- 50
+            virus_name <- virus$seq_name
+            taxonomy <- virus$taxonomy
+
+            log_debug("Adding taxonomy and virus name to the plot")
+            circlize::circos.text(
+                x = center_x, y = -0.2, labels = taxonomy,
                 sector.index = "Zoom", track.index = 1,
                 facing = "bending.inside", niceFacing = TRUE,
-                adj = c(0.5, 0.7), cex = 0.8)
-  
-    checkv_info <- checkv_data[checkv_data$contig_id == virus$seq_name, ]
-    if (nrow(checkv_info) > 0) {
-      checkv_quality <- checkv_info$checkv_quality
-      gene_count <- checkv_info$gene_count
-      viral_genes <- checkv_info$viral_genes
-      host_genes <- checkv_info$host_genes
-      miuvig_quality <- checkv_info$miuvig_quality
-      completeness <- checkv_info$completeness
-      completeness_method <- checkv_info$completeness_method
-      contamination <- checkv_info$contamination
-      
-      circos.text(
-        x = center_x, y = -0.5, 
-        labels = paste("CheckV Quality:", checkv_quality, " - miuvig Quality:", miuvig_quality),
-        sector.index = "Zoom", track.index = 2,
-        facing = "bending.inside", niceFacing = TRUE,
-        adj = c(0.5, 0), cex = 0.7
-      )
-      
-      circos.text(
-        x = center_x, y = -1.5, 
-        labels = paste("Gene Count:", gene_count, " - Viral Genes:", viral_genes, " - Host Genes:", host_genes),
-        sector.index = "Zoom", track.index = 2,
-        facing = "bending.inside", niceFacing = TRUE,
-        adj = c(0.5, 0), cex = 0.7
-      )
-      
-      circos.text(
-        x = center_x, y = -2.5, 
-        labels = paste("Completeness:", completeness, " - Contamination:", contamination),
-        sector.index = "Zoom", track.index = 2,
-        facing = "bending.inside", niceFacing = TRUE,
-        adj = c(0.5, 0), cex = 0.7
-      )
-    }
-    
-    log_debug("Adding legend")
-    # Add legend
-    legend("topright", 
-           legend = c("Annotated gene", "Unknown gene"),
-           fill = c("#7fbfff", "grey"),
-           border = c("darkblue", "grey20"),
-           cex = 0.8,
-           bty = "n")
-    
-    log_debug("Clearing circos")
-    circos.clear()
-    log_debug("Finished plot_phage_circos function successfully")
-  }, error = function(e) {
-    log_debug(paste("Error in plot_phage_circos:", e$message))
-    circos.clear()
-  })
+                adj = c(0.5, 0.7), cex = 0.8
+            )
+
+            checkv_info <- checkv_data[checkv_data$contig_id == virus$seq_name, ]
+            if (nrow(checkv_info) > 0) {
+                checkv_quality <- checkv_info$checkv_quality
+                gene_count <- checkv_info$gene_count
+                viral_genes <- checkv_info$viral_genes
+                host_genes <- checkv_info$host_genes
+                miuvig_quality <- checkv_info$miuvig_quality
+                completeness <- checkv_info$completeness
+                completeness_method <- checkv_info$completeness_method
+                contamination <- checkv_info$contamination
+
+                circlize::circos.text(
+                    x = center_x, y = -0.5,
+                    labels = paste("CheckV Quality:", checkv_quality, " - miuvig Quality:", miuvig_quality),
+                    sector.index = "Zoom", track.index = 2,
+                    facing = "bending.inside", niceFacing = TRUE,
+                    adj = c(0.5, 0), cex = 0.7
+                )
+
+                circlize::circos.text(
+                    x = center_x, y = -1.5,
+                    labels = paste("Gene Count:", gene_count, " - Viral Genes:", viral_genes, " - Host Genes:", host_genes),
+                    sector.index = "Zoom", track.index = 2,
+                    facing = "bending.inside", niceFacing = TRUE,
+                    adj = c(0.5, 0), cex = 0.7
+                )
+
+                circlize::circos.text(
+                    x = center_x, y = -2.5,
+                    labels = paste("Completeness:", completeness, " - Contamination:", contamination),
+                    sector.index = "Zoom", track.index = 2,
+                    facing = "bending.inside", niceFacing = TRUE,
+                    adj = c(0.5, 0), cex = 0.7
+                )
+            }
+
+            log_debug("Adding legend")
+            # Add legend
+            legend("topright",
+                legend = c("Annotated gene", "Unknown gene"),
+                fill = c("#7fbfff", "grey"),
+                border = c("darkblue", "grey20"),
+                cex = 0.8,
+                bty = "n"
+            )
+
+            log_debug("Clearing circos")
+            circlize::circos.clear()
+            log_debug("Finished plot_phage_circos function successfully")
+        },
+        error = function(e) {
+            log_debug(paste("Error in plot_phage_circos:", e$message))
+            circlize::circos.clear()
+        }
+    )
 }
 
 plot_drep <- function(sample, genomad_summary) {
-  drep_file_path <- file.path(params$outdir, "virus_analyses", "drep_compare", sample, "data_tables", "Cdb.csv")
-  drep_data <- read_csv(drep_file_path) %>% clean_names()
-  drep_data <- cbind(genomad_summary$seq_name, drep_data)
-  
-  cat("When more than 1 phage is detected in the host genome, we perform a clustering step using the tool dRep.\n\n")
-  cat("A threshold of 0.95 was applied to the ANI similarity index to define clusters of virus operational taxonomic units (vOTUs).")
-  
-  cat("\n\n**Final cluster designations**\n\n")
-  drep_data %>%
-    kbl() %>%
-    kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
-    kable_paper("striped", full_width = TRUE) %>%
-    cat()
-  
-  # Insert the PDF plot
-  plot_path <- file.path(params$outdir, "virus_analyses", "drep_compare", sample, "figures", "Primary_clustering_dendrogram.pdf")
-  png_path <- file.path(params$outdir, "virus_analyses", "drep_compare", sample, "figures", "Primary_clustering_dendrogram.png")
-  
-  if (file.exists(plot_path)) {
-    pdftools::pdf_convert(plot_path, format = "png", filenames = png_path, verbose = FALSE, dpi=150)
-    base64_str <- base64enc::dataURI(file = png_path, mime = "image/png")
-    cat("**Primary clustering plot**\n\n")
-    cat(sprintf(
-      '<div style="text-align: center;"><img src="%s" style="max-width: 100%%; height: auto; border:1px solid #ddd; border-radius:4px; box-shadow: 0 2px 5px rgba(0,0,0,0.1); margin: 1em 0;"></div>',base64_str
-    ))
-  } else {
-    cat("**No dRep clustering plot found.**\n\n")
-  }
-  
+    drep_file_path <- file.path(params$outdir, "virus_analyses", "drep_compare", sample, "data_tables", "Cdb.csv")
+    drep_data <- read_csv(drep_file_path) %>% janitor::clean_names()
+    drep_data <- cbind(genomad_summary$seq_name, drep_data)
+
+    cat("When more than 1 phage is detected in the host genome, we perform a clustering step using the tool dRep.\n\n")
+    cat("A threshold of 0.95 was applied to the ANI similarity index to define clusters of virus operational taxonomic units (vOTUs).")
+
+    cat("\n\n**Final cluster designations**\n\n")
+    drep_data %>%
+        kableExtra::kbl() %>%
+        kableExtra::kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
+        kableExtra::kable_paper("striped", full_width = TRUE) %>%
+        cat()
+
+    # Insert the PDF plot
+    plot_path <- file.path(params$outdir, "virus_analyses", "drep_compare", sample, "figures", "Primary_clustering_dendrogram.pdf")
+    png_path <- file.path(params$outdir, "virus_analyses", "drep_compare", sample, "figures", "Primary_clustering_dendrogram.png")
+
+    if (file.exists(plot_path)) {
+        pdftools::pdf_convert(plot_path, format = "png", filenames = png_path, verbose = FALSE, dpi = 150)
+        base64_str <- base64enc::dataURI(file = png_path, mime = "image/png")
+        cat("**Primary clustering plot**\n\n")
+        cat(sprintf(
+            '<div style="text-align: center;"><img src="%s" style="max-width: 100%%; height: auto; border:1px solid #ddd; border-radius:4px; box-shadow: 0 2px 5px rgba(0,0,0,0.1); margin: 1em 0;"></div>', base64_str
+        ))
+    } else {
+        cat("**No dRep clustering plot found.**\n\n")
+    }
 }
 
 subset_and_update_ideogram <- function(ideogram, contigs) {
-  filtered <- ideogram[seqnames(ideogram) %in% contigs]
-  seqlevels(filtered) <- contigs
-  seqinfo(filtered) <- seqinfo(filtered)[contigs]
-  filtered
+    filtered <- ideogram[seqnames(ideogram) %in% contigs]
+    GenomeInfoDb::seqlevels(filtered) <- contigs
+    seqinfo(filtered) <- seqinfo(filtered)[contigs]
+    filtered
 }
 
 render_all_samples <- function(test_mode = FALSE) {
-  if (test_mode) {
-    if (nrow(combined_unique) > 0) {
-      cat("**Select sample to show:** \n\n\n")
-      current_sample <- combined_unique$Sample[6]
-      process_sample(current_sample, combined_unique, host_genomes_paths, genome_data)
+    if (test_mode) {
+        if (nrow(combined_unique) > 0) {
+            cat("**Select sample to show:** \n\n\n")
+            current_sample <- combined_unique$Sample[6]
+            process_sample(current_sample, combined_unique, host_genomes_paths, genome_data)
+        } else {
+            print("No samples can be further analysed.")
+        }
     } else {
-      print("No samples can be further analysed.")
+        cat("**Select sample to show:** \n\n\n")
+        for (i in seq_len(nrow(combined_unique))) {
+            current_sample <- combined_unique$Sample[i]
+            process_sample(current_sample, combined_unique, host_genomes_paths, genome_data)
+        }
     }
-  } else {
-    cat("**Select sample to show:** \n\n\n")
-    for (i in seq_len(nrow(combined_unique))) {
-      current_sample <- combined_unique$Sample[i]
-      process_sample(current_sample, combined_unique, host_genomes_paths, genome_data)
-    }
-  }
 }
 
 # Execute the main function
 # Test mode processes one sample only
 render_all_samples(test_mode = F)
 ```
-
-# Citation
-
-Cite this work: XXXXX
-
-
diff -r 315c2ed31af1 -r 3a7f73d638ba test-data/checkm2.Quality_report-wext.tabular
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/checkm2.Quality_report-wext.tabular	Tue Jul 22 11:09:24 2025 +0000
@@ -0,0 +1,23 @@
+Name	Completeness	Contamination	Completeness_Model_Used	Translation_Table_Used	Coding_Density	Contig_N50	Average_Gene_Length	Genome_Size	GC_Content	Total_Coding_Sequences	Total_Contigs	Max_Contig_Length	Additional_Notes
+NC_000913.fasta	100.0	0.13	Neural Network (Specific Model)	11	0.876	4641652	314.20629775410976	4641652	0.51	4319	1	4641652	None
+NC_002737.fasta	99.99	0.48	Neural Network (Specific Model)	11	0.856	1852433	298.1390765765766	1852433	0.39	1776	1	1852433	None
+NC_003450.fasta	100.0	0.29	Neural Network (Specific Model)	11	0.872	3309401	313.8808205796158	3309401	0.54	3071	1	3309401	None
+NC_008261.fasta	100.0	0.14	Neural Network (Specific Model)	11	0.837	3256683	316.0170197985412	3256683	0.28	2879	1	3256683	None
+NC_009012.fasta	100.0	1.09	Neural Network (Specific Model)	11	0.849	3843301	320.7092407298411	3843301	0.39	3398	1	3843301	None
+NC_012982.fasta	100.0	0.05	Neural Network (Specific Model)	11	0.897	3455622	328.879173290938	3455622	0.45	3145	1	3455622	None
+NC_014008.fasta	100.0	0.02	Neural Network (Specific Model)	11	0.902	3750771	358.93038779402417	3750771	0.54	3146	1	3750771	None
+NC_014168.fasta	99.99	0.03	Neural Network (Specific Model)	11	0.907	3157527	311.3860162601626	3157527	0.67	3075	1	3157527	None
+NC_014211.fasta	14.07	0.01	Neural Network (Specific Model)	11	0.836	775354	308.61626248216834	775354	0.72	701	1	775354	None
+NC_014212.fasta	99.99	0.16	Neural Network (Specific Model)	11	0.904	3249394	303.41267387944356	3249394	0.62	3235	1	3249394	None
+NC_014363.fasta	99.7	0.35	Neural Network (Specific Model)	11	0.874	2051896	337.48281690140846	2051896	0.65	1775	1	2051896	None
+NC_014364.fasta	99.98	1.88	Neural Network (Specific Model)	11	0.931	4653970	337.5459421641791	4653970	0.49	4288	1	4653970	None
+NC_015761.fasta	100.0	0.14	Neural Network (Specific Model)	11	0.871	4460105	320.1726352185725	4460105	0.51	4049	1	4460105	None
+NC_017033.fasta	99.99	0.04	Neural Network (Specific Model)	11	0.872	3603458	329.2016938519448	3603458	0.63	3188	1	3603458	None
+NC_017095.fasta	99.95	2.67	Neural Network (Specific Model)	11	0.916	2166381	329.75584286424663	2166381	0.39	2011	1	2166381	None
+NC_018014.fasta	99.99	9.38	Neural Network (Specific Model)	11	0.891	5227858	357.07764759935674	5227858	0.6	4353	1	5227858	None
+NC_018068.fasta	99.99	0.42	Neural Network (Specific Model)	11	0.824	4926837	296.0867001528718	4926837	0.42	4579	1	4926837	None
+NC_018515.fasta	100.0	1.83	Neural Network (Specific Model)	11	0.834	4873567	302.3391304347826	4873567	0.42	4485	1	4873567	None
+NC_019897.fasta	99.95	0.34	Neural Network (Specific Model)	11	0.874	4206343	318.1461139896373	4206343	0.61	3860	1	4206343	None
+NC_019904.fasta	100.0	0.23	Neural Network (Specific Model)	11	0.869	5608040	351.0986827898942	5608040	0.45	4631	1	5608040	None
+NC_019936.fasta	100.0	0.13	Neural Network (Specific Model)	11	0.896	4575057	320.7199437543942	4575057	0.63	4267	1	4575057	None
+NC_021184.fasta	100.0	3.04	Neural Network (Specific Model)	11	0.823	4855529	289.67620906527867	4855529	0.45	4611	1	4855529	None
diff -r 315c2ed31af1 -r 3a7f73d638ba test-data/checkm2.Quality_report.tabular
--- a/test-data/checkm2.Quality_report.tabular	Wed Jun 04 17:36:40 2025 +0000
+++ b/test-data/checkm2.Quality_report.tabular	Tue Jul 22 11:09:24 2025 +0000
@@ -1,23 +1,23 @@
 Name	Completeness	Contamination	Completeness_Model_Used	Translation_Table_Used	Coding_Density	Contig_N50	Average_Gene_Length	Genome_Size	GC_Content	Total_Coding_Sequences	Total_Contigs	Max_Contig_Length	Additional_Notes
-NC_000913.fasta	100.0	0.13	Neural Network (Specific Model)	11	0.876	4641652	314.20629775410976	4641652	0.51	4319	1	4641652	None
-NC_002737.fasta	99.99	0.48	Neural Network (Specific Model)	11	0.856	1852433	298.1390765765766	1852433	0.39	1776	1	1852433	None
-NC_003450.fasta	100.0	0.29	Neural Network (Specific Model)	11	0.872	3309401	313.8808205796158	3309401	0.54	3071	1	3309401	None
-NC_008261.fasta	100.0	0.14	Neural Network (Specific Model)	11	0.837	3256683	316.0170197985412	3256683	0.28	2879	1	3256683	None
-NC_009012.fasta	100.0	1.09	Neural Network (Specific Model)	11	0.849	3843301	320.7092407298411	3843301	0.39	3398	1	3843301	None
-NC_012982.fasta	100.0	0.05	Neural Network (Specific Model)	11	0.897	3455622	328.879173290938	3455622	0.45	3145	1	3455622	None
-NC_014008.fasta	100.0	0.02	Neural Network (Specific Model)	11	0.902	3750771	358.93038779402417	3750771	0.54	3146	1	3750771	None
-NC_014168.fasta	99.99	0.03	Neural Network (Specific Model)	11	0.907	3157527	311.3860162601626	3157527	0.67	3075	1	3157527	None
-NC_014211.fasta	14.07	0.01	Neural Network (Specific Model)	11	0.836	775354	308.61626248216834	775354	0.72	701	1	775354	None
-NC_014212.fasta	99.99	0.16	Neural Network (Specific Model)	11	0.904	3249394	303.41267387944356	3249394	0.62	3235	1	3249394	None
-NC_014363.fasta	99.7	0.35	Neural Network (Specific Model)	11	0.874	2051896	337.48281690140846	2051896	0.65	1775	1	2051896	None
-NC_014364.fasta	99.98	1.88	Neural Network (Specific Model)	11	0.931	4653970	337.5459421641791	4653970	0.49	4288	1	4653970	None
-NC_015761.fasta	100.0	0.14	Neural Network (Specific Model)	11	0.871	4460105	320.1726352185725	4460105	0.51	4049	1	4460105	None
-NC_017033.fasta	99.99	0.04	Neural Network (Specific Model)	11	0.872	3603458	329.2016938519448	3603458	0.63	3188	1	3603458	None
-NC_017095.fasta	99.95	2.67	Neural Network (Specific Model)	11	0.916	2166381	329.75584286424663	2166381	0.39	2011	1	2166381	None
-NC_018014.fasta	99.99	9.38	Neural Network (Specific Model)	11	0.891	5227858	357.07764759935674	5227858	0.6	4353	1	5227858	None
-NC_018068.fasta	99.99	0.42	Neural Network (Specific Model)	11	0.824	4926837	296.0867001528718	4926837	0.42	4579	1	4926837	None
-NC_018515.fasta	100.0	1.83	Neural Network (Specific Model)	11	0.834	4873567	302.3391304347826	4873567	0.42	4485	1	4873567	None
-NC_019897.fasta	99.95	0.34	Neural Network (Specific Model)	11	0.874	4206343	318.1461139896373	4206343	0.61	3860	1	4206343	None
-NC_019904.fasta	100.0	0.23	Neural Network (Specific Model)	11	0.869	5608040	351.0986827898942	5608040	0.45	4631	1	5608040	None
-NC_019936.fasta	100.0	0.13	Neural Network (Specific Model)	11	0.896	4575057	320.7199437543942	4575057	0.63	4267	1	4575057	None
-NC_021184.fasta	100.0	3.04	Neural Network (Specific Model)	11	0.823	4855529	289.67620906527867	4855529	0.45	4611	1	4855529	None
+NC_000913	100.0	0.13	Neural Network (Specific Model)	11	0.876	4641652	314.20629775410976	4641652	0.51	4319	1	4641652	None
+NC_002737	99.99	0.48	Neural Network (Specific Model)	11	0.856	1852433	298.1390765765766	1852433	0.39	1776	1	1852433	None
+NC_003450	100.0	0.29	Neural Network (Specific Model)	11	0.872	3309401	313.8808205796158	3309401	0.54	3071	1	3309401	None
+NC_008261	100.0	0.14	Neural Network (Specific Model)	11	0.837	3256683	316.0170197985412	3256683	0.28	2879	1	3256683	None
+NC_009012	100.0	1.09	Neural Network (Specific Model)	11	0.849	3843301	320.7092407298411	3843301	0.39	3398	1	3843301	None
+NC_012982	100.0	0.05	Neural Network (Specific Model)	11	0.897	3455622	328.879173290938	3455622	0.45	3145	1	3455622	None
+NC_014008	100.0	0.02	Neural Network (Specific Model)	11	0.902	3750771	358.93038779402417	3750771	0.54	3146	1	3750771	None
+NC_014168	99.99	0.03	Neural Network (Specific Model)	11	0.907	3157527	311.3860162601626	3157527	0.67	3075	1	3157527	None
+NC_014211	14.07	0.01	Neural Network (Specific Model)	11	0.836	775354	308.61626248216834	775354	0.72	701	1	775354	None
+NC_014212	99.99	0.16	Neural Network (Specific Model)	11	0.904	3249394	303.41267387944356	3249394	0.62	3235	1	3249394	None
+NC_014363	99.7	0.35	Neural Network (Specific Model)	11	0.874	2051896	337.48281690140846	2051896	0.65	1775	1	2051896	None
+NC_014364	99.98	1.88	Neural Network (Specific Model)	11	0.931	4653970	337.5459421641791	4653970	0.49	4288	1	4653970	None
+NC_015761	100.0	0.14	Neural Network (Specific Model)	11	0.871	4460105	320.1726352185725	4460105	0.51	4049	1	4460105	None
+NC_017033	99.99	0.04	Neural Network (Specific Model)	11	0.872	3603458	329.2016938519448	3603458	0.63	3188	1	3603458	None
+NC_017095	99.95	2.67	Neural Network (Specific Model)	11	0.916	2166381	329.75584286424663	2166381	0.39	2011	1	2166381	None
+NC_018014	99.99	9.38	Neural Network (Specific Model)	11	0.891	5227858	357.07764759935674	5227858	0.6	4353	1	5227858	None
+NC_018068	99.99	0.42	Neural Network (Specific Model)	11	0.824	4926837	296.0867001528718	4926837	0.42	4579	1	4926837	None
+NC_018515	100.0	1.83	Neural Network (Specific Model)	11	0.834	4873567	302.3391304347826	4873567	0.42	4485	1	4873567	None
+NC_019897	99.95	0.34	Neural Network (Specific Model)	11	0.874	4206343	318.1461139896373	4206343	0.61	3860	1	4206343	None
+NC_019904	100.0	0.23	Neural Network (Specific Model)	11	0.869	5608040	351.0986827898942	5608040	0.45	4631	1	5608040	None
+NC_019936	100.0	0.13	Neural Network (Specific Model)	11	0.896	4575057	320.7199437543942	4575057	0.63	4267	1	4575057	None
+NC_021184	100.0	3.04	Neural Network (Specific Model)	11	0.823	4855529	289.67620906527867	4855529	0.45	4611	1	4855529	None
diff -r 315c2ed31af1 -r 3a7f73d638ba test-data/gtdbtk.bac120-wext.summary
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/gtdbtk.bac120-wext.summary	Tue Jul 22 11:09:24 2025 +0000
@@ -0,0 +1,23 @@
+user_genome	classification	closest_genome_reference	closest_genome_reference_radius	closest_genome_taxonomy	closest_genome_ani	closest_genome_af	closest_placement_reference	closest_placement_radius	closest_placement_taxonomy	closest_placement_ani	closest_placement_af	pplacer_taxonomy	classification_method	note	other_related_references(genome_id,species_name,radius,ANI,AF)	msa_percent	translation_table	red_value	warnings
+NC_000913.fasta	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia coli	GCF_003697165.2	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia coli	96.74	0.856	GCF_000026225.1	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia fergusonii	91.54	0.56	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__	taxonomic classification defined by topology and ANI	N/A	GCF_000194175.1, s__Escherichia coli_F, 95.0, 95.46, 0.89; GCF_002965065.1, s__Escherichia sp002965065, 95.0, 94.52, 0.691; GCF_004211955.1, s__Escherichia sp004211955, 95.0, 93.12, 0.774; GCF_005843885.1, s__Escherichia sp005843885, 95.0, 92.76, 0.782; GCF_011881725.1, s__Escherichia coli_E, 95.0, 92.37, 0.807; GCF_029876145.1, s__Escherichia ruysiae, 95.0, 92.28, 0.788; GCF_014836715.1, s__Escherichia whittamii, 95.0, 91.78, 0.782; GCF_002900365.1, s__Escherichia marmotae, 95.0, 90.92, 0.738; GCF_000759775.1, s__Escherichia albertii, 95.0, 90.18, 0.68	98.47	11	N/A	N/A
+NC_002737.fasta	d__Bacteria;p__Bacillota;c__Bacilli;o__Lactobacillales;f__Streptococcaceae;g__Streptococcus;s__Streptococcus pyogenes	GCF_002055535.1	95.0	d__Bacteria;p__Bacillota;c__Bacilli;o__Lactobacillales;f__Streptococcaceae;g__Streptococcus;s__Streptococcus pyogenes	99.7	0.968	GCF_002055535.1	95.0	d__Bacteria;p__Bacillota;c__Bacilli;o__Lactobacillales;f__Streptococcaceae;g__Streptococcus;s__Streptococcus pyogenes	99.7	0.968	d__Bacteria;p__Bacillota;c__Bacilli;o__Lactobacillales;f__Streptococcaceae;g__Streptococcus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_900459225.1, s__Streptococcus dysgalactiae, 95.0, 88.16, 0.456; GCF_900636575.1, s__Streptococcus canis, 95.0, 86.81, 0.468	98.31	11	N/A	N/A
+NC_003450.fasta	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Corynebacterium;s__Corynebacterium glutamicum	GCF_000011325.1	95.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Corynebacterium;s__Corynebacterium glutamicum	100.0	1.0	GCF_000011325.1	95.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Corynebacterium;s__Corynebacterium glutamicum	100.0	1.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Corynebacterium;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_002355155.1, s__Corynebacterium suranareeae, 95.0, 86.55, 0.531; GCF_001643015.1, s__Corynebacterium crudilactis, 95.0, 84.07, 0.363; GCF_001277995.1, s__Corynebacterium deserti, 95.0, 83.77, 0.275	96.43	11	N/A	N/A
+NC_008261.fasta	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Clostridiales;f__Clostridiaceae;g__Sarcina;s__Sarcina perfringens	GCF_000013285.1	95.0	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Clostridiales;f__Clostridiaceae;g__Sarcina;s__Sarcina perfringens	100.0	1.0	GCF_000013285.1	95.0	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Clostridiales;f__Clostridiaceae;g__Sarcina;s__Sarcina perfringens	100.0	1.0	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Clostridiales;f__Clostridiaceae;g__Sarcina;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_029258205.1, s__Sarcina sp029258205, 95.0, 92.75, 0.744; GCF_029267215.1, s__Sarcina sp029267215, 95.0, 84.03, 0.29	94.4	11	N/A	N/A
+NC_009012.fasta	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Acetivibrionales;f__Acetivibrionaceae;g__Hungateiclostridium;s__Hungateiclostridium thermocellum	GCF_000015865.1	95.0	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Acetivibrionales;f__Acetivibrionaceae;g__Hungateiclostridium;s__Hungateiclostridium thermocellum	100.0	1.0	GCF_000015865.1	95.0	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Acetivibrionales;f__Acetivibrionaceae;g__Hungateiclostridium;s__Hungateiclostridium thermocellum	100.0	1.0	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Acetivibrionales;f__Acetivibrionaceae;g__Hungateiclostridium;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_000521465.1, s__Hungateiclostridium straminisolvens, 95.0, 84.49, 0.429; GCF_004102745.1, s__Hungateiclostridium mesophilum, 95.0, 81.39, 0.257	94.22	11	N/A	N/A
+NC_012982.fasta	d__Bacteria;p__Pseudomonadota;c__Alphaproteobacteria;o__Caulobacterales;f__Hyphomonadaceae;g__Hirschia;s__Hirschia baltica	GCF_000023785.1	95.0	d__Bacteria;p__Pseudomonadota;c__Alphaproteobacteria;o__Caulobacterales;f__Hyphomonadaceae;g__Hirschia;s__Hirschia baltica	100.0	1.0	GCF_000023785.1	95.0	d__Bacteria;p__Pseudomonadota;c__Alphaproteobacteria;o__Caulobacterales;f__Hyphomonadaceae;g__Hirschia;s__Hirschia baltica	100.0	1.0	d__Bacteria;p__Pseudomonadota;c__Alphaproteobacteria;o__Caulobacterales;f__Hyphomonadaceae;g__Hirschia;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	N/A	98.25	11	N/A	N/A
+NC_014008.fasta	d__Bacteria;p__Verrucomicrobiota;c__Verrucomicrobiae;o__Opitutales;f__Coraliomargaritaceae;g__Coraliomargarita;s__Coraliomargarita akajimensis	GCF_000025905.1	95.0	d__Bacteria;p__Verrucomicrobiota;c__Verrucomicrobiae;o__Opitutales;f__Coraliomargaritaceae;g__Coraliomargarita;s__Coraliomargarita akajimensis	100.0	1.0	GCF_000025905.1	95.0	d__Bacteria;p__Verrucomicrobiota;c__Verrucomicrobiae;o__Opitutales;f__Coraliomargaritaceae;g__Coraliomargarita;s__Coraliomargarita akajimensis	100.0	1.0	d__Bacteria;p__Verrucomicrobiota;c__Verrucomicrobiae;o__Opitutales;f__Coraliomargaritaceae;g__;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	N/A	90.76	11	N/A	N/A
+NC_014168.fasta	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Segniliparus;s__Segniliparus rotundus	GCF_000092825.1	95.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Segniliparus;s__Segniliparus rotundus	100.0	1.0	GCF_000092825.1	95.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Segniliparus;s__Segniliparus rotundus	100.0	1.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Segniliparus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_000185725.2, s__Segniliparus rugosus, 95.0, 80.18, 0.178	96.56	11	N/A	N/A
+NC_014211.fasta	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Streptosporangiales;f__Streptosporangiaceae;g__Nocardiopsis;s__Nocardiopsis dassonvillei	GCF_000092985.1	95.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Streptosporangiales;f__Streptosporangiaceae;g__Nocardiopsis;s__Nocardiopsis dassonvillei	100.0	1.0	GCF_000092985.1	95.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Streptosporangiales;f__Streptosporangiaceae;g__Nocardiopsis;s__Nocardiopsis dassonvillei	100.0	1.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Streptosporangiales;f__Streptosporangiaceae;g__Nocardiopsis;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_012396365.1, s__Nocardiopsis alborubida, 95.0, 94.89, 0.822; GCA_000340945.1, s__Nocardiopsis synnemataformans, 95.0, 94.67, 0.838; GCA_002529455.1, s__Nocardiopsis fusca, 95.0, 93.48, 0.743; GCF_000341065.1, s__Nocardiopsis halotolerans, 95.0, 89.3, 0.575; GCF_001905145.1, s__Nocardiopsis sp001905145, 95.0, 89.08, 0.554; GCF_008638415.1, s__Nocardiopsis sinuspersici, 95.0, 88.61, 0.531; GCF_008638365.1, s__Nocardiopsis quinghaiensis, 95.0, 88.23, 0.498; GCF_009830945.1, s__Nocardiopsis sp009830945, 95.0, 87.99, 0.442; GCA_937957845.1, s__Nocardiopsis sp937957845, 95.0, 87.38, 0.277; GCF_026642255.1, s__Nocardiopsis nanhaiensis_A, 95.0, 86.06, 0.436; GCF_030271535.1, s__Nocardiopsis sp030271535, 95.0, 84.81, 0.338; GCF_013410755.1, s__Nocardiopsis aegyptia, 95.0, 84.69, 0.277; GCF_018316655.1, s__Nocardiopsis changdeensis, 95.0, 84.65, 0.301; GCF_000341125.1, s__Nocardiopsis lucentensis, 95.0, 84.45, 0.226; GCF_001279585.1, s__Nocardiopsis sp001279585, 95.0, 84.4, 0.267; GCA_018388625.1, s__Nocardiopsis eucommiae, 95.0, 84.39, 0.264; GCF_014201115.1, s__Nocardiopsis metallicus, 95.0, 84.3, 0.268; GCF_003634495.1, s__Nocardiopsis sp003634495, 95.0, 84.18, 0.288; GCF_030766825.1, s__Nocardiopsis sp030766825, 95.0, 84.18, 0.286; GCF_000341085.1, s__Nocardiopsis ganjiahuensis, 95.0, 84.16, 0.28; GCF_030555055.1, s__Nocardiopsis sp030555055, 95.0, 84.06, 0.267; GCF_024134545.1, s__Nocardiopsis exhalans, 95.08, 84.04, 0.267; GCF_900141985.1, s__Nocardiopsis flavescens, 95.0, 83.82, 0.272; GCF_003386285.1, s__Nocardiopsis sp003386285, 95.0, 83.73, 0.264; GCF_014651695.1, s__Nocardiopsis terrae, 95.0, 83.6, 0.27; GCF_014203695.1, s__Nocardiopsis algeriensis, 95.0, 83.59, 0.238; GCF_020741345.1, s__Nocardiopsis listeri_A, 95.0, 83.53, 0.202; GCF_000341225.1, s__Nocardiopsis alba, 95.0, 83.47, 0.217; GCF_018207095.1, s__Nocardiopsis sp018207095, 95.0, 83.32, 0.229; GCF_028882275.1, s__Nocardiopsis sp028882275, 95.0, 83.25, 0.266; GCF_900143625.1, s__Nocardiopsis sp900143625, 95.0, 83.09, 0.229; GCF_000515115.1, s__Nocardiopsis sp000515115, 95.0, 83.02, 0.181; GCF_014892575.1, s__Nocardiopsis coralli, 95.0, 82.85, 0.213; GCF_000341265.1, s__Nocardiopsis prasina, 95.0, 82.63, 0.245; GCF_001942255.1, s__Nocardiopsis sp001942255, 95.0, 82.61, 0.248; GCF_000341005.1, s__Nocardiopsis alkaliphila, 95.0, 82.53, 0.186; GCF_001570765.1, s__Nocardiopsis listeri, 95.0, 82.26, 0.198; GCF_000341025.1, s__Nocardiopsis salina, 95.0, 82.22, 0.158; GCF_000341145.1, s__Nocardiopsis xinjiangensis, 95.0, 81.14, 0.168	26.24	11	N/A	N/A
+NC_014212.fasta	d__Bacteria;p__Deinococcota;c__Deinococci;o__Deinococcales;f__Thermaceae;g__Allomeiothermus;s__Allomeiothermus silvanus	GCF_000092125.1	95.0	d__Bacteria;p__Deinococcota;c__Deinococci;o__Deinococcales;f__Thermaceae;g__Allomeiothermus;s__Allomeiothermus silvanus	100.0	0.999	GCF_000092125.1	95.0	d__Bacteria;p__Deinococcota;c__Deinococci;o__Deinococcales;f__Thermaceae;g__Allomeiothermus;s__Allomeiothermus silvanus	100.0	0.999	d__Bacteria;p__Deinococcota;c__Deinococci;o__Deinococcales;f__Thermaceae;g__Allomeiothermus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_003226535.1, s__Allomeiothermus sp003226535, 95.0, 87.73, 0.485	93.82	11	N/A	N/A
+NC_014363.fasta	d__Bacteria;p__Actinomycetota;c__Coriobacteriia;o__Coriobacteriales;f__Atopobiaceae;g__Olsenella;s__Olsenella uli	GCF_000143845.1	95.0	d__Bacteria;p__Actinomycetota;c__Coriobacteriia;o__Coriobacteriales;f__Atopobiaceae;g__Olsenella;s__Olsenella uli	100.0	1.0	GCF_000143845.1	95.0	d__Bacteria;p__Actinomycetota;c__Coriobacteriia;o__Coriobacteriales;f__Atopobiaceae;g__Olsenella;s__Olsenella uli	100.0	1.0	d__Bacteria;p__Actinomycetota;c__Coriobacteriia;o__Coriobacteriales;f__Atopobiaceae;g__;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	N/A	95.47	11	N/A	N/A
+NC_014364.fasta	d__Bacteria;p__Spirochaetota;c__Spirochaetia;o__DSM-16054;f__Sediminispirochaetaceae;g__Sediminispirochaeta;s__Sediminispirochaeta smaragdinae	GCF_000143985.1	95.0	d__Bacteria;p__Spirochaetota;c__Spirochaetia;o__DSM-16054;f__Sediminispirochaetaceae;g__Sediminispirochaeta;s__Sediminispirochaeta smaragdinae	100.0	1.0	GCF_000143985.1	95.0	d__Bacteria;p__Spirochaetota;c__Spirochaetia;o__DSM-16054;f__Sediminispirochaetaceae;g__Sediminispirochaeta;s__Sediminispirochaeta smaragdinae	100.0	1.0	d__Bacteria;p__Spirochaetota;c__Spirochaetia;o__DSM-16054;f__Sediminispirochaetaceae;g__Sediminispirochaeta;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_000378205.1, s__Sediminispirochaeta bajacaliforniensis, 95.0, 94.41, 0.82	88.42	11	N/A	N/A
+NC_015761.fasta	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Salmonella;s__Salmonella bongori	GCF_000252995.1	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Salmonella;s__Salmonella bongori	100.0	1.0	GCF_000252995.1	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Salmonella;s__Salmonella bongori	100.0	1.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Salmonella;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_000006945.2, s__Salmonella enterica, 95.0, 90.34, 0.758; GCA_900478215.1, s__Salmonella houtenae, 95.0, 90.05, 0.755; GCF_008692785.1, s__Salmonella diarizonae, 95.0, 89.91, 0.746; GCF_008692845.1, s__Salmonella arizonae, 95.0, 89.51, 0.704	97.58	11	N/A	N/A
+NC_017033.fasta	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Xanthomonadales;f__Rhodanobacteraceae;g__Frateuria;s__Frateuria aurantia	GCF_000242255.2	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Xanthomonadales;f__Rhodanobacteraceae;g__Frateuria;s__Frateuria aurantia	100.0	1.0	GCF_000242255.2	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Xanthomonadales;f__Rhodanobacteraceae;g__Frateuria;s__Frateuria aurantia	100.0	1.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Xanthomonadales;f__Rhodanobacteraceae;g__;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	N/A	98.45	11	N/A	N/A
+NC_017095.fasta	d__Bacteria;p__Thermotogota;c__Thermotogae;o__Thermotogales;f__Fervidobacteriaceae;g__Fervidobacterium;s__Fervidobacterium pennivorans	GCF_000235405.2	95.0	d__Bacteria;p__Thermotogota;c__Thermotogae;o__Thermotogales;f__Fervidobacteriaceae;g__Fervidobacterium;s__Fervidobacterium pennivorans	100.0	1.0	GCF_000235405.2	95.0	d__Bacteria;p__Thermotogota;c__Thermotogae;o__Thermotogales;f__Fervidobacteriaceae;g__Fervidobacterium;s__Fervidobacterium pennivorans	100.0	1.0	d__Bacteria;p__Thermotogota;c__Thermotogae;o__Thermotogales;f__Fervidobacteriaceae;g__Fervidobacterium;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_001644665.1, s__Fervidobacterium pennivorans_A, 95.0, 92.25, 0.827	90.82	11	N/A	N/A
+NC_018014.fasta	d__Bacteria;p__Acidobacteriota;c__Terriglobia;o__Terriglobales;f__Acidobacteriaceae;g__Terriglobus;s__Terriglobus roseus	GCF_000265425.1	95.0	d__Bacteria;p__Acidobacteriota;c__Terriglobia;o__Terriglobales;f__Acidobacteriaceae;g__Terriglobus;s__Terriglobus roseus	100.0	1.0	GCF_000265425.1	95.0	d__Bacteria;p__Acidobacteriota;c__Terriglobia;o__Terriglobales;f__Acidobacteriaceae;g__Terriglobus;s__Terriglobus roseus	100.0	1.0	d__Bacteria;p__Acidobacteriota;c__Terriglobia;o__Terriglobales;f__Acidobacteriaceae;g__Terriglobus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_900105625.1, s__Terriglobus roseus_B, 95.0, 82.2, 0.254	94.06	11	N/A	N/A
+NC_018068.fasta	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__Desulfosporosinus acidiphilus	GCF_000255115.2	95.0	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__Desulfosporosinus acidiphilus	100.0	1.0	GCF_000255115.2	95.0	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__Desulfosporosinus acidiphilus	100.0	1.0	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_002196705.1, s__Desulfosporosinus sp002196705, 95.0, 81.15, 0.156	93.92	11	N/A	N/A
+NC_018515.fasta	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__Desulfosporosinus meridiei	GCF_000231385.2	95.0	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__Desulfosporosinus meridiei	100.0	1.0	GCF_000231385.2	95.0	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__Desulfosporosinus meridiei	100.0	1.0	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_900100785.1, s__Desulfosporosinus hippei, 95.0, 94.11, 0.765; GCF_000765145.1, s__Desulfosporosinus sp000765145, 95.0, 92.48, 0.692	94.5	11	N/A	N/A
+NC_019897.fasta	d__Bacteria;p__Bacillota;c__Bacilli;o__Paenibacillales;f__Paenibacillaceae;g__Thermobacillus;s__Thermobacillus xylanilyticus	GCF_907165215.1	95.0	d__Bacteria;p__Bacillota;c__Bacilli;o__Paenibacillales;f__Paenibacillaceae;g__Thermobacillus;s__Thermobacillus xylanilyticus	97.81	0.815	GCF_907165215.1	95.0	d__Bacteria;p__Bacillota;c__Bacilli;o__Paenibacillales;f__Paenibacillaceae;g__Thermobacillus;s__Thermobacillus xylanilyticus	97.81	0.815	d__Bacteria;p__Bacillota;c__Bacilli;o__Paenibacillales;f__Paenibacillaceae;g__Thermobacillus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_002159085.1, s__Thermobacillus sp002159085, 95.0, 85.65, 0.466	95.97	11	N/A	N/A
+NC_019904.fasta	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Cytophagales;f__Cyclobacteriaceae;g__Echinicola;s__Echinicola vietnamensis	GCF_000325705.1	95.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Cytophagales;f__Cyclobacteriaceae;g__Echinicola;s__Echinicola vietnamensis	100.0	1.0	GCF_000325705.1	95.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Cytophagales;f__Cyclobacteriaceae;g__Echinicola;s__Echinicola vietnamensis	100.0	1.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Cytophagales;f__Cyclobacteriaceae;g__Echinicola;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_005281475.1, s__Echinicola rosea, 95.0, 83.28, 0.288; GCF_006575665.1, s__Echinicola soli, 95.0, 81.29, 0.203; GCF_003260975.1, s__Echinicola strongylocentroti, 95.0, 80.38, 0.164	96.96	11	N/A	N/A
+NC_019936.fasta	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Pseudomonadales;f__Pseudomonadaceae;g__Stutzerimonas;s__Stutzerimonas stutzeri_AE	GCF_000327065.1	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Pseudomonadales;f__Pseudomonadaceae;g__Stutzerimonas;s__Stutzerimonas stutzeri_AE	100.0	1.0	GCF_000327065.1	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Pseudomonadales;f__Pseudomonadaceae;g__Stutzerimonas;s__Stutzerimonas stutzeri_AE	100.0	1.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Pseudomonadales;f__Pseudomonadaceae;g__Stutzerimonas;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_003696315.1, s__Stutzerimonas songnenensis, 95.0, 93.2, 0.909; GCF_000661915.1, s__Stutzerimonas decontaminans, 95.0, 91.33, 0.803; GCF_900114065.1, s__Stutzerimonas kunmingensis, 96.6, 90.17, 0.753; GCF_024397475.1, s__Stutzerimonas xanthomarina_A, 97.0, 90.15, 0.746; GCA_007713455.1, s__Stutzerimonas sp007713455, 95.0, 90.03, 0.748; GCF_014764705.1, s__Stutzerimonas sp002692525, 96.82, 90.01, 0.736; GCA_003530955.1, s__Stutzerimonas sp003530955, 96.79, 89.98, 0.727; GCF_002929225.1, s__Stutzerimonas stutzeri_U, 97.04, 89.97, 0.743; GCF_000935215.1, s__Stutzerimonas stutzeri_AD, 96.98, 89.84, 0.723; GCF_000495915.1, s__Stutzerimonas chloritidismutans, 96.78, 89.84, 0.717; GCA_018823765.1, s__Stutzerimonas sp018823765, 97.02, 89.77, 0.71; GCA_003488145.1, s__Stutzerimonas sp003488145, 96.59, 89.74, 0.666; GCF_000341615.1, s__Stutzerimonas stutzeri_G, 95.0, 89.32, 0.697; GCF_002890795.1, s__Stutzerimonas stutzeri_AA, 95.0, 89.28, 0.735; GCF_024448335.1, s__Stutzerimonas frequens, 95.0, 88.75, 0.714; GCF_015291885.1, s__Stutzerimonas stutzeri_AC, 95.0, 88.59, 0.662; GCF_000219605.1, s__Stutzerimonas stutzeri, 95.0, 88.34, 0.673; GCF_002909485.1, s__Stutzerimonas stutzeri_AH, 95.0, 88.19, 0.688; GCF_000307775.2, s__Stutzerimonas stutzeri_B, 95.0, 86.95, 0.549; GCF_002890915.1, s__Stutzerimonas stutzeri_AF, 95.0, 85.91, 0.472; GCF_025966695.1, s__Stutzerimonas sp025966695, 95.0, 85.39, 0.44; GCA_000263395.1, s__Stutzerimonas stutzeri_C, 95.0, 85.38, 0.392; GCF_024448505.1, s__Stutzerimonas degradans, 96.08, 85.26, 0.426; GCF_021432765.1, s__Stutzerimonas phenolilytica, 95.0, 85.11, 0.435; GCF_015070855.1, s__Stutzerimonas lopnurensis, 95.0, 85.07, 0.41; GCF_021726475.1, s__Stutzerimonas oligotrophica, 95.0, 84.76, 0.419; GCF_000818015.1, s__Stutzerimonas balearica, 95.0, 83.88, 0.33; GCF_003696285.1, s__Stutzerimonas nitrititolerans, 95.0, 82.51, 0.26; GCF_018138085.1, s__Stutzerimonas stutzeri_AI, 95.0, 82.03, 0.245; GCF_005876855.1, s__Stutzerimonas nosocomialis, 95.0, 81.99, 0.242; GCF_019090095.1, s__Stutzerimonas stutzeri_AN, 95.0, 81.91, 0.245; GCF_013522825.1, s__Stutzerimonas stutzeri_AK, 95.0, 81.91, 0.2; GCA_002339675.1, s__Stutzerimonas stutzeri_O, 95.0, 81.89, 0.253; GCF_019355055.1, s__Stutzerimonas sp004331835, 95.0, 81.83, 0.222; GCF_024448955.1, s__Stutzerimonas stutzeri_AQ, 95.0, 81.79, 0.232; GCF_024448695.1, s__Stutzerimonas stutzeri_T, 95.0, 81.71, 0.242; GCF_022810315.1, s__Stutzerimonas marianensis, 95.0, 81.66, 0.218; GCF_024448935.1, s__Stutzerimonas stutzeri_AO, 95.0, 81.57, 0.177; GCF_009789555.1, s__Stutzerimonas stutzeri_R, 95.0, 81.41, 0.22; GCA_022448005.1, s__Stutzerimonas sp022448005, 95.0, 81.35, 0.194; GCF_003325755.1, s__Stutzerimonas sp003325755, 95.0, 81.28, 0.206; GCA_004010935.1, s__Stutzerimonas sp004010935, 95.0, 81.27, 0.216; GCA_002387205.1, s__Stutzerimonas stutzeri_N, 95.0, 81.26, 0.195; GCF_024448985.1, s__Stutzerimonas stutzeri_AP, 95.0, 81.22, 0.203; GCF_000425625.1, s__Stutzerimonas azotifigens, 95.0, 81.18, 0.187; GCF_000756775.1, s__Stutzerimonas saudiphocaensis, 95.0, 81.13, 0.219; GCF_000952685.1, s__Stutzerimonas stutzeri_E, 95.0, 81.08, 0.216; GCF_000235745.1, s__Stutzerimonas stutzeri_H, 95.0, 81.07, 0.199; GCF_013522725.1, s__Stutzerimonas azotifigens_A, 95.0, 80.99, 0.203; GCA_900766265.1, s__Stutzerimonas sp900766265, 95.0, 80.94, 0.196; GCF_024448895.1, s__Stutzerimonas stutzeri_Q, 95.0, 80.91, 0.193; GCF_900129835.1, s__Stutzerimonas xanthomarina, 95.0, 80.89, 0.2; GCF_002890895.1, s__Stutzerimonas stutzeri_AB, 95.0, 80.87, 0.198; GCF_019880365.1, s__Stutzerimonas stutzeri_P, 95.0, 80.81, 0.187; GCA_002345575.1, s__Stutzerimonas stutzeri_S, 95.0, 80.74, 0.191; GCF_013620795.1, s__Stutzerimonas sp013620795, 95.0, 80.74, 0.187; GCF_024448715.1, s__Stutzerimonas stutzeri_AR, 95.0, 80.6, 0.18; GCF_000590475.1, s__Stutzerimonas stutzeri_D, 95.0, 80.4, 0.167; GCF_003696365.1, s__Stutzerimonas zhaodongensis, 95.0, 79.95, 0.152	97.72	11	N/A	N/A
+NC_021184.fasta	d__Bacteria;p__Bacillota_B;c__Desulfotomaculia;o__Desulfotomaculales;f__Desulfallaceae;g__Sporotomaculum;s__Sporotomaculum gibsoniae	GCF_000233715.2	95.0	d__Bacteria;p__Bacillota_B;c__Desulfotomaculia;o__Desulfotomaculales;f__Desulfallaceae;g__Sporotomaculum;s__Sporotomaculum gibsoniae	100.0	1.0	GCF_000233715.2	95.0	d__Bacteria;p__Bacillota_B;c__Desulfotomaculia;o__Desulfotomaculales;f__Desulfallaceae;g__Sporotomaculum;s__Sporotomaculum gibsoniae	100.0	1.0	d__Bacteria;p__Bacillota_B;c__Desulfotomaculia;o__Desulfotomaculales;f__Desulfallaceae;g__Sporotomaculum;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	N/A	95.73	11	N/A	N/A
diff -r 315c2ed31af1 -r 3a7f73d638ba test-data/gtdbtk.bac120.summary
--- a/test-data/gtdbtk.bac120.summary	Wed Jun 04 17:36:40 2025 +0000
+++ b/test-data/gtdbtk.bac120.summary	Tue Jul 22 11:09:24 2025 +0000
@@ -1,23 +1,23 @@
 user_genome	classification	closest_genome_reference	closest_genome_reference_radius	closest_genome_taxonomy	closest_genome_ani	closest_genome_af	closest_placement_reference	closest_placement_radius	closest_placement_taxonomy	closest_placement_ani	closest_placement_af	pplacer_taxonomy	classification_method	note	other_related_references(genome_id,species_name,radius,ANI,AF)	msa_percent	translation_table	red_value	warnings
-NC_000913.fasta	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia coli	GCF_003697165.2	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia coli	96.74	0.856	GCF_000026225.1	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia fergusonii	91.54	0.56	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__	taxonomic classification defined by topology and ANI	N/A	GCF_000194175.1, s__Escherichia coli_F, 95.0, 95.46, 0.89; GCF_002965065.1, s__Escherichia sp002965065, 95.0, 94.52, 0.691; GCF_004211955.1, s__Escherichia sp004211955, 95.0, 93.12, 0.774; GCF_005843885.1, s__Escherichia sp005843885, 95.0, 92.76, 0.782; GCF_011881725.1, s__Escherichia coli_E, 95.0, 92.37, 0.807; GCF_029876145.1, s__Escherichia ruysiae, 95.0, 92.28, 0.788; GCF_014836715.1, s__Escherichia whittamii, 95.0, 91.78, 0.782; GCF_002900365.1, s__Escherichia marmotae, 95.0, 90.92, 0.738; GCF_000759775.1, s__Escherichia albertii, 95.0, 90.18, 0.68	98.47	11	N/A	N/A
-NC_002737.fasta	d__Bacteria;p__Bacillota;c__Bacilli;o__Lactobacillales;f__Streptococcaceae;g__Streptococcus;s__Streptococcus pyogenes	GCF_002055535.1	95.0	d__Bacteria;p__Bacillota;c__Bacilli;o__Lactobacillales;f__Streptococcaceae;g__Streptococcus;s__Streptococcus pyogenes	99.7	0.968	GCF_002055535.1	95.0	d__Bacteria;p__Bacillota;c__Bacilli;o__Lactobacillales;f__Streptococcaceae;g__Streptococcus;s__Streptococcus pyogenes	99.7	0.968	d__Bacteria;p__Bacillota;c__Bacilli;o__Lactobacillales;f__Streptococcaceae;g__Streptococcus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_900459225.1, s__Streptococcus dysgalactiae, 95.0, 88.16, 0.456; GCF_900636575.1, s__Streptococcus canis, 95.0, 86.81, 0.468	98.31	11	N/A	N/A
-NC_003450.fasta	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Corynebacterium;s__Corynebacterium glutamicum	GCF_000011325.1	95.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Corynebacterium;s__Corynebacterium glutamicum	100.0	1.0	GCF_000011325.1	95.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Corynebacterium;s__Corynebacterium glutamicum	100.0	1.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Corynebacterium;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_002355155.1, s__Corynebacterium suranareeae, 95.0, 86.55, 0.531; GCF_001643015.1, s__Corynebacterium crudilactis, 95.0, 84.07, 0.363; GCF_001277995.1, s__Corynebacterium deserti, 95.0, 83.77, 0.275	96.43	11	N/A	N/A
-NC_008261.fasta	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Clostridiales;f__Clostridiaceae;g__Sarcina;s__Sarcina perfringens	GCF_000013285.1	95.0	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Clostridiales;f__Clostridiaceae;g__Sarcina;s__Sarcina perfringens	100.0	1.0	GCF_000013285.1	95.0	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Clostridiales;f__Clostridiaceae;g__Sarcina;s__Sarcina perfringens	100.0	1.0	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Clostridiales;f__Clostridiaceae;g__Sarcina;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_029258205.1, s__Sarcina sp029258205, 95.0, 92.75, 0.744; GCF_029267215.1, s__Sarcina sp029267215, 95.0, 84.03, 0.29	94.4	11	N/A	N/A
-NC_009012.fasta	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Acetivibrionales;f__Acetivibrionaceae;g__Hungateiclostridium;s__Hungateiclostridium thermocellum	GCF_000015865.1	95.0	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Acetivibrionales;f__Acetivibrionaceae;g__Hungateiclostridium;s__Hungateiclostridium thermocellum	100.0	1.0	GCF_000015865.1	95.0	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Acetivibrionales;f__Acetivibrionaceae;g__Hungateiclostridium;s__Hungateiclostridium thermocellum	100.0	1.0	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Acetivibrionales;f__Acetivibrionaceae;g__Hungateiclostridium;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_000521465.1, s__Hungateiclostridium straminisolvens, 95.0, 84.49, 0.429; GCF_004102745.1, s__Hungateiclostridium mesophilum, 95.0, 81.39, 0.257	94.22	11	N/A	N/A
-NC_012982.fasta	d__Bacteria;p__Pseudomonadota;c__Alphaproteobacteria;o__Caulobacterales;f__Hyphomonadaceae;g__Hirschia;s__Hirschia baltica	GCF_000023785.1	95.0	d__Bacteria;p__Pseudomonadota;c__Alphaproteobacteria;o__Caulobacterales;f__Hyphomonadaceae;g__Hirschia;s__Hirschia baltica	100.0	1.0	GCF_000023785.1	95.0	d__Bacteria;p__Pseudomonadota;c__Alphaproteobacteria;o__Caulobacterales;f__Hyphomonadaceae;g__Hirschia;s__Hirschia baltica	100.0	1.0	d__Bacteria;p__Pseudomonadota;c__Alphaproteobacteria;o__Caulobacterales;f__Hyphomonadaceae;g__Hirschia;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	N/A	98.25	11	N/A	N/A
-NC_014008.fasta	d__Bacteria;p__Verrucomicrobiota;c__Verrucomicrobiae;o__Opitutales;f__Coraliomargaritaceae;g__Coraliomargarita;s__Coraliomargarita akajimensis	GCF_000025905.1	95.0	d__Bacteria;p__Verrucomicrobiota;c__Verrucomicrobiae;o__Opitutales;f__Coraliomargaritaceae;g__Coraliomargarita;s__Coraliomargarita akajimensis	100.0	1.0	GCF_000025905.1	95.0	d__Bacteria;p__Verrucomicrobiota;c__Verrucomicrobiae;o__Opitutales;f__Coraliomargaritaceae;g__Coraliomargarita;s__Coraliomargarita akajimensis	100.0	1.0	d__Bacteria;p__Verrucomicrobiota;c__Verrucomicrobiae;o__Opitutales;f__Coraliomargaritaceae;g__;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	N/A	90.76	11	N/A	N/A
-NC_014168.fasta	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Segniliparus;s__Segniliparus rotundus	GCF_000092825.1	95.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Segniliparus;s__Segniliparus rotundus	100.0	1.0	GCF_000092825.1	95.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Segniliparus;s__Segniliparus rotundus	100.0	1.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Segniliparus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_000185725.2, s__Segniliparus rugosus, 95.0, 80.18, 0.178	96.56	11	N/A	N/A
-NC_014211.fasta	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Streptosporangiales;f__Streptosporangiaceae;g__Nocardiopsis;s__Nocardiopsis dassonvillei	GCF_000092985.1	95.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Streptosporangiales;f__Streptosporangiaceae;g__Nocardiopsis;s__Nocardiopsis dassonvillei	100.0	1.0	GCF_000092985.1	95.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Streptosporangiales;f__Streptosporangiaceae;g__Nocardiopsis;s__Nocardiopsis dassonvillei	100.0	1.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Streptosporangiales;f__Streptosporangiaceae;g__Nocardiopsis;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_012396365.1, s__Nocardiopsis alborubida, 95.0, 94.89, 0.822; GCA_000340945.1, s__Nocardiopsis synnemataformans, 95.0, 94.67, 0.838; GCA_002529455.1, s__Nocardiopsis fusca, 95.0, 93.48, 0.743; GCF_000341065.1, s__Nocardiopsis halotolerans, 95.0, 89.3, 0.575; GCF_001905145.1, s__Nocardiopsis sp001905145, 95.0, 89.08, 0.554; GCF_008638415.1, s__Nocardiopsis sinuspersici, 95.0, 88.61, 0.531; GCF_008638365.1, s__Nocardiopsis quinghaiensis, 95.0, 88.23, 0.498; GCF_009830945.1, s__Nocardiopsis sp009830945, 95.0, 87.99, 0.442; GCA_937957845.1, s__Nocardiopsis sp937957845, 95.0, 87.38, 0.277; GCF_026642255.1, s__Nocardiopsis nanhaiensis_A, 95.0, 86.06, 0.436; GCF_030271535.1, s__Nocardiopsis sp030271535, 95.0, 84.81, 0.338; GCF_013410755.1, s__Nocardiopsis aegyptia, 95.0, 84.69, 0.277; GCF_018316655.1, s__Nocardiopsis changdeensis, 95.0, 84.65, 0.301; GCF_000341125.1, s__Nocardiopsis lucentensis, 95.0, 84.45, 0.226; GCF_001279585.1, s__Nocardiopsis sp001279585, 95.0, 84.4, 0.267; GCA_018388625.1, s__Nocardiopsis eucommiae, 95.0, 84.39, 0.264; GCF_014201115.1, s__Nocardiopsis metallicus, 95.0, 84.3, 0.268; GCF_003634495.1, s__Nocardiopsis sp003634495, 95.0, 84.18, 0.288; GCF_030766825.1, s__Nocardiopsis sp030766825, 95.0, 84.18, 0.286; GCF_000341085.1, s__Nocardiopsis ganjiahuensis, 95.0, 84.16, 0.28; GCF_030555055.1, s__Nocardiopsis sp030555055, 95.0, 84.06, 0.267; GCF_024134545.1, s__Nocardiopsis exhalans, 95.08, 84.04, 0.267; GCF_900141985.1, s__Nocardiopsis flavescens, 95.0, 83.82, 0.272; GCF_003386285.1, s__Nocardiopsis sp003386285, 95.0, 83.73, 0.264; GCF_014651695.1, s__Nocardiopsis terrae, 95.0, 83.6, 0.27; GCF_014203695.1, s__Nocardiopsis algeriensis, 95.0, 83.59, 0.238; GCF_020741345.1, s__Nocardiopsis listeri_A, 95.0, 83.53, 0.202; GCF_000341225.1, s__Nocardiopsis alba, 95.0, 83.47, 0.217; GCF_018207095.1, s__Nocardiopsis sp018207095, 95.0, 83.32, 0.229; GCF_028882275.1, s__Nocardiopsis sp028882275, 95.0, 83.25, 0.266; GCF_900143625.1, s__Nocardiopsis sp900143625, 95.0, 83.09, 0.229; GCF_000515115.1, s__Nocardiopsis sp000515115, 95.0, 83.02, 0.181; GCF_014892575.1, s__Nocardiopsis coralli, 95.0, 82.85, 0.213; GCF_000341265.1, s__Nocardiopsis prasina, 95.0, 82.63, 0.245; GCF_001942255.1, s__Nocardiopsis sp001942255, 95.0, 82.61, 0.248; GCF_000341005.1, s__Nocardiopsis alkaliphila, 95.0, 82.53, 0.186; GCF_001570765.1, s__Nocardiopsis listeri, 95.0, 82.26, 0.198; GCF_000341025.1, s__Nocardiopsis salina, 95.0, 82.22, 0.158; GCF_000341145.1, s__Nocardiopsis xinjiangensis, 95.0, 81.14, 0.168	26.24	11	N/A	N/A
-NC_014212.fasta	d__Bacteria;p__Deinococcota;c__Deinococci;o__Deinococcales;f__Thermaceae;g__Allomeiothermus;s__Allomeiothermus silvanus	GCF_000092125.1	95.0	d__Bacteria;p__Deinococcota;c__Deinococci;o__Deinococcales;f__Thermaceae;g__Allomeiothermus;s__Allomeiothermus silvanus	100.0	0.999	GCF_000092125.1	95.0	d__Bacteria;p__Deinococcota;c__Deinococci;o__Deinococcales;f__Thermaceae;g__Allomeiothermus;s__Allomeiothermus silvanus	100.0	0.999	d__Bacteria;p__Deinococcota;c__Deinococci;o__Deinococcales;f__Thermaceae;g__Allomeiothermus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_003226535.1, s__Allomeiothermus sp003226535, 95.0, 87.73, 0.485	93.82	11	N/A	N/A
-NC_014363.fasta	d__Bacteria;p__Actinomycetota;c__Coriobacteriia;o__Coriobacteriales;f__Atopobiaceae;g__Olsenella;s__Olsenella uli	GCF_000143845.1	95.0	d__Bacteria;p__Actinomycetota;c__Coriobacteriia;o__Coriobacteriales;f__Atopobiaceae;g__Olsenella;s__Olsenella uli	100.0	1.0	GCF_000143845.1	95.0	d__Bacteria;p__Actinomycetota;c__Coriobacteriia;o__Coriobacteriales;f__Atopobiaceae;g__Olsenella;s__Olsenella uli	100.0	1.0	d__Bacteria;p__Actinomycetota;c__Coriobacteriia;o__Coriobacteriales;f__Atopobiaceae;g__;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	N/A	95.47	11	N/A	N/A
-NC_014364.fasta	d__Bacteria;p__Spirochaetota;c__Spirochaetia;o__DSM-16054;f__Sediminispirochaetaceae;g__Sediminispirochaeta;s__Sediminispirochaeta smaragdinae	GCF_000143985.1	95.0	d__Bacteria;p__Spirochaetota;c__Spirochaetia;o__DSM-16054;f__Sediminispirochaetaceae;g__Sediminispirochaeta;s__Sediminispirochaeta smaragdinae	100.0	1.0	GCF_000143985.1	95.0	d__Bacteria;p__Spirochaetota;c__Spirochaetia;o__DSM-16054;f__Sediminispirochaetaceae;g__Sediminispirochaeta;s__Sediminispirochaeta smaragdinae	100.0	1.0	d__Bacteria;p__Spirochaetota;c__Spirochaetia;o__DSM-16054;f__Sediminispirochaetaceae;g__Sediminispirochaeta;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_000378205.1, s__Sediminispirochaeta bajacaliforniensis, 95.0, 94.41, 0.82	88.42	11	N/A	N/A
-NC_015761.fasta	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Salmonella;s__Salmonella bongori	GCF_000252995.1	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Salmonella;s__Salmonella bongori	100.0	1.0	GCF_000252995.1	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Salmonella;s__Salmonella bongori	100.0	1.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Salmonella;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_000006945.2, s__Salmonella enterica, 95.0, 90.34, 0.758; GCA_900478215.1, s__Salmonella houtenae, 95.0, 90.05, 0.755; GCF_008692785.1, s__Salmonella diarizonae, 95.0, 89.91, 0.746; GCF_008692845.1, s__Salmonella arizonae, 95.0, 89.51, 0.704	97.58	11	N/A	N/A
-NC_017033.fasta	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Xanthomonadales;f__Rhodanobacteraceae;g__Frateuria;s__Frateuria aurantia	GCF_000242255.2	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Xanthomonadales;f__Rhodanobacteraceae;g__Frateuria;s__Frateuria aurantia	100.0	1.0	GCF_000242255.2	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Xanthomonadales;f__Rhodanobacteraceae;g__Frateuria;s__Frateuria aurantia	100.0	1.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Xanthomonadales;f__Rhodanobacteraceae;g__;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	N/A	98.45	11	N/A	N/A
-NC_017095.fasta	d__Bacteria;p__Thermotogota;c__Thermotogae;o__Thermotogales;f__Fervidobacteriaceae;g__Fervidobacterium;s__Fervidobacterium pennivorans	GCF_000235405.2	95.0	d__Bacteria;p__Thermotogota;c__Thermotogae;o__Thermotogales;f__Fervidobacteriaceae;g__Fervidobacterium;s__Fervidobacterium pennivorans	100.0	1.0	GCF_000235405.2	95.0	d__Bacteria;p__Thermotogota;c__Thermotogae;o__Thermotogales;f__Fervidobacteriaceae;g__Fervidobacterium;s__Fervidobacterium pennivorans	100.0	1.0	d__Bacteria;p__Thermotogota;c__Thermotogae;o__Thermotogales;f__Fervidobacteriaceae;g__Fervidobacterium;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_001644665.1, s__Fervidobacterium pennivorans_A, 95.0, 92.25, 0.827	90.82	11	N/A	N/A
-NC_018014.fasta	d__Bacteria;p__Acidobacteriota;c__Terriglobia;o__Terriglobales;f__Acidobacteriaceae;g__Terriglobus;s__Terriglobus roseus	GCF_000265425.1	95.0	d__Bacteria;p__Acidobacteriota;c__Terriglobia;o__Terriglobales;f__Acidobacteriaceae;g__Terriglobus;s__Terriglobus roseus	100.0	1.0	GCF_000265425.1	95.0	d__Bacteria;p__Acidobacteriota;c__Terriglobia;o__Terriglobales;f__Acidobacteriaceae;g__Terriglobus;s__Terriglobus roseus	100.0	1.0	d__Bacteria;p__Acidobacteriota;c__Terriglobia;o__Terriglobales;f__Acidobacteriaceae;g__Terriglobus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_900105625.1, s__Terriglobus roseus_B, 95.0, 82.2, 0.254	94.06	11	N/A	N/A
-NC_018068.fasta	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__Desulfosporosinus acidiphilus	GCF_000255115.2	95.0	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__Desulfosporosinus acidiphilus	100.0	1.0	GCF_000255115.2	95.0	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__Desulfosporosinus acidiphilus	100.0	1.0	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_002196705.1, s__Desulfosporosinus sp002196705, 95.0, 81.15, 0.156	93.92	11	N/A	N/A
-NC_018515.fasta	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__Desulfosporosinus meridiei	GCF_000231385.2	95.0	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__Desulfosporosinus meridiei	100.0	1.0	GCF_000231385.2	95.0	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__Desulfosporosinus meridiei	100.0	1.0	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_900100785.1, s__Desulfosporosinus hippei, 95.0, 94.11, 0.765; GCF_000765145.1, s__Desulfosporosinus sp000765145, 95.0, 92.48, 0.692	94.5	11	N/A	N/A
-NC_019897.fasta	d__Bacteria;p__Bacillota;c__Bacilli;o__Paenibacillales;f__Paenibacillaceae;g__Thermobacillus;s__Thermobacillus xylanilyticus	GCF_907165215.1	95.0	d__Bacteria;p__Bacillota;c__Bacilli;o__Paenibacillales;f__Paenibacillaceae;g__Thermobacillus;s__Thermobacillus xylanilyticus	97.81	0.815	GCF_907165215.1	95.0	d__Bacteria;p__Bacillota;c__Bacilli;o__Paenibacillales;f__Paenibacillaceae;g__Thermobacillus;s__Thermobacillus xylanilyticus	97.81	0.815	d__Bacteria;p__Bacillota;c__Bacilli;o__Paenibacillales;f__Paenibacillaceae;g__Thermobacillus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_002159085.1, s__Thermobacillus sp002159085, 95.0, 85.65, 0.466	95.97	11	N/A	N/A
-NC_019904.fasta	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Cytophagales;f__Cyclobacteriaceae;g__Echinicola;s__Echinicola vietnamensis	GCF_000325705.1	95.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Cytophagales;f__Cyclobacteriaceae;g__Echinicola;s__Echinicola vietnamensis	100.0	1.0	GCF_000325705.1	95.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Cytophagales;f__Cyclobacteriaceae;g__Echinicola;s__Echinicola vietnamensis	100.0	1.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Cytophagales;f__Cyclobacteriaceae;g__Echinicola;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_005281475.1, s__Echinicola rosea, 95.0, 83.28, 0.288; GCF_006575665.1, s__Echinicola soli, 95.0, 81.29, 0.203; GCF_003260975.1, s__Echinicola strongylocentroti, 95.0, 80.38, 0.164	96.96	11	N/A	N/A
-NC_019936.fasta	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Pseudomonadales;f__Pseudomonadaceae;g__Stutzerimonas;s__Stutzerimonas stutzeri_AE	GCF_000327065.1	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Pseudomonadales;f__Pseudomonadaceae;g__Stutzerimonas;s__Stutzerimonas stutzeri_AE	100.0	1.0	GCF_000327065.1	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Pseudomonadales;f__Pseudomonadaceae;g__Stutzerimonas;s__Stutzerimonas stutzeri_AE	100.0	1.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Pseudomonadales;f__Pseudomonadaceae;g__Stutzerimonas;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_003696315.1, s__Stutzerimonas songnenensis, 95.0, 93.2, 0.909; GCF_000661915.1, s__Stutzerimonas decontaminans, 95.0, 91.33, 0.803; GCF_900114065.1, s__Stutzerimonas kunmingensis, 96.6, 90.17, 0.753; GCF_024397475.1, s__Stutzerimonas xanthomarina_A, 97.0, 90.15, 0.746; GCA_007713455.1, s__Stutzerimonas sp007713455, 95.0, 90.03, 0.748; GCF_014764705.1, s__Stutzerimonas sp002692525, 96.82, 90.01, 0.736; GCA_003530955.1, s__Stutzerimonas sp003530955, 96.79, 89.98, 0.727; GCF_002929225.1, s__Stutzerimonas stutzeri_U, 97.04, 89.97, 0.743; GCF_000935215.1, s__Stutzerimonas stutzeri_AD, 96.98, 89.84, 0.723; GCF_000495915.1, s__Stutzerimonas chloritidismutans, 96.78, 89.84, 0.717; GCA_018823765.1, s__Stutzerimonas sp018823765, 97.02, 89.77, 0.71; GCA_003488145.1, s__Stutzerimonas sp003488145, 96.59, 89.74, 0.666; GCF_000341615.1, s__Stutzerimonas stutzeri_G, 95.0, 89.32, 0.697; GCF_002890795.1, s__Stutzerimonas stutzeri_AA, 95.0, 89.28, 0.735; GCF_024448335.1, s__Stutzerimonas frequens, 95.0, 88.75, 0.714; GCF_015291885.1, s__Stutzerimonas stutzeri_AC, 95.0, 88.59, 0.662; GCF_000219605.1, s__Stutzerimonas stutzeri, 95.0, 88.34, 0.673; GCF_002909485.1, s__Stutzerimonas stutzeri_AH, 95.0, 88.19, 0.688; GCF_000307775.2, s__Stutzerimonas stutzeri_B, 95.0, 86.95, 0.549; GCF_002890915.1, s__Stutzerimonas stutzeri_AF, 95.0, 85.91, 0.472; GCF_025966695.1, s__Stutzerimonas sp025966695, 95.0, 85.39, 0.44; GCA_000263395.1, s__Stutzerimonas stutzeri_C, 95.0, 85.38, 0.392; GCF_024448505.1, s__Stutzerimonas degradans, 96.08, 85.26, 0.426; GCF_021432765.1, s__Stutzerimonas phenolilytica, 95.0, 85.11, 0.435; GCF_015070855.1, s__Stutzerimonas lopnurensis, 95.0, 85.07, 0.41; GCF_021726475.1, s__Stutzerimonas oligotrophica, 95.0, 84.76, 0.419; GCF_000818015.1, s__Stutzerimonas balearica, 95.0, 83.88, 0.33; GCF_003696285.1, s__Stutzerimonas nitrititolerans, 95.0, 82.51, 0.26; GCF_018138085.1, s__Stutzerimonas stutzeri_AI, 95.0, 82.03, 0.245; GCF_005876855.1, s__Stutzerimonas nosocomialis, 95.0, 81.99, 0.242; GCF_019090095.1, s__Stutzerimonas stutzeri_AN, 95.0, 81.91, 0.245; GCF_013522825.1, s__Stutzerimonas stutzeri_AK, 95.0, 81.91, 0.2; GCA_002339675.1, s__Stutzerimonas stutzeri_O, 95.0, 81.89, 0.253; GCF_019355055.1, s__Stutzerimonas sp004331835, 95.0, 81.83, 0.222; GCF_024448955.1, s__Stutzerimonas stutzeri_AQ, 95.0, 81.79, 0.232; GCF_024448695.1, s__Stutzerimonas stutzeri_T, 95.0, 81.71, 0.242; GCF_022810315.1, s__Stutzerimonas marianensis, 95.0, 81.66, 0.218; GCF_024448935.1, s__Stutzerimonas stutzeri_AO, 95.0, 81.57, 0.177; GCF_009789555.1, s__Stutzerimonas stutzeri_R, 95.0, 81.41, 0.22; GCA_022448005.1, s__Stutzerimonas sp022448005, 95.0, 81.35, 0.194; GCF_003325755.1, s__Stutzerimonas sp003325755, 95.0, 81.28, 0.206; GCA_004010935.1, s__Stutzerimonas sp004010935, 95.0, 81.27, 0.216; GCA_002387205.1, s__Stutzerimonas stutzeri_N, 95.0, 81.26, 0.195; GCF_024448985.1, s__Stutzerimonas stutzeri_AP, 95.0, 81.22, 0.203; GCF_000425625.1, s__Stutzerimonas azotifigens, 95.0, 81.18, 0.187; GCF_000756775.1, s__Stutzerimonas saudiphocaensis, 95.0, 81.13, 0.219; GCF_000952685.1, s__Stutzerimonas stutzeri_E, 95.0, 81.08, 0.216; GCF_000235745.1, s__Stutzerimonas stutzeri_H, 95.0, 81.07, 0.199; GCF_013522725.1, s__Stutzerimonas azotifigens_A, 95.0, 80.99, 0.203; GCA_900766265.1, s__Stutzerimonas sp900766265, 95.0, 80.94, 0.196; GCF_024448895.1, s__Stutzerimonas stutzeri_Q, 95.0, 80.91, 0.193; GCF_900129835.1, s__Stutzerimonas xanthomarina, 95.0, 80.89, 0.2; GCF_002890895.1, s__Stutzerimonas stutzeri_AB, 95.0, 80.87, 0.198; GCF_019880365.1, s__Stutzerimonas stutzeri_P, 95.0, 80.81, 0.187; GCA_002345575.1, s__Stutzerimonas stutzeri_S, 95.0, 80.74, 0.191; GCF_013620795.1, s__Stutzerimonas sp013620795, 95.0, 80.74, 0.187; GCF_024448715.1, s__Stutzerimonas stutzeri_AR, 95.0, 80.6, 0.18; GCF_000590475.1, s__Stutzerimonas stutzeri_D, 95.0, 80.4, 0.167; GCF_003696365.1, s__Stutzerimonas zhaodongensis, 95.0, 79.95, 0.152	97.72	11	N/A	N/A
-NC_021184.fasta	d__Bacteria;p__Bacillota_B;c__Desulfotomaculia;o__Desulfotomaculales;f__Desulfallaceae;g__Sporotomaculum;s__Sporotomaculum gibsoniae	GCF_000233715.2	95.0	d__Bacteria;p__Bacillota_B;c__Desulfotomaculia;o__Desulfotomaculales;f__Desulfallaceae;g__Sporotomaculum;s__Sporotomaculum gibsoniae	100.0	1.0	GCF_000233715.2	95.0	d__Bacteria;p__Bacillota_B;c__Desulfotomaculia;o__Desulfotomaculales;f__Desulfallaceae;g__Sporotomaculum;s__Sporotomaculum gibsoniae	100.0	1.0	d__Bacteria;p__Bacillota_B;c__Desulfotomaculia;o__Desulfotomaculales;f__Desulfallaceae;g__Sporotomaculum;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	N/A	95.73	11	N/A	N/A
+NC_000913	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia coli	GCF_003697165.2	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia coli	96.74	0.856	GCF_000026225.1	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__Escherichia fergusonii	91.54	0.56	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Escherichia;s__	taxonomic classification defined by topology and ANI	N/A	GCF_000194175.1, s__Escherichia coli_F, 95.0, 95.46, 0.89; GCF_002965065.1, s__Escherichia sp002965065, 95.0, 94.52, 0.691; GCF_004211955.1, s__Escherichia sp004211955, 95.0, 93.12, 0.774; GCF_005843885.1, s__Escherichia sp005843885, 95.0, 92.76, 0.782; GCF_011881725.1, s__Escherichia coli_E, 95.0, 92.37, 0.807; GCF_029876145.1, s__Escherichia ruysiae, 95.0, 92.28, 0.788; GCF_014836715.1, s__Escherichia whittamii, 95.0, 91.78, 0.782; GCF_002900365.1, s__Escherichia marmotae, 95.0, 90.92, 0.738; GCF_000759775.1, s__Escherichia albertii, 95.0, 90.18, 0.68	98.47	11	N/A	N/A
+NC_002737	d__Bacteria;p__Bacillota;c__Bacilli;o__Lactobacillales;f__Streptococcaceae;g__Streptococcus;s__Streptococcus pyogenes	GCF_002055535.1	95.0	d__Bacteria;p__Bacillota;c__Bacilli;o__Lactobacillales;f__Streptococcaceae;g__Streptococcus;s__Streptococcus pyogenes	99.7	0.968	GCF_002055535.1	95.0	d__Bacteria;p__Bacillota;c__Bacilli;o__Lactobacillales;f__Streptococcaceae;g__Streptococcus;s__Streptococcus pyogenes	99.7	0.968	d__Bacteria;p__Bacillota;c__Bacilli;o__Lactobacillales;f__Streptococcaceae;g__Streptococcus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_900459225.1, s__Streptococcus dysgalactiae, 95.0, 88.16, 0.456; GCF_900636575.1, s__Streptococcus canis, 95.0, 86.81, 0.468	98.31	11	N/A	N/A
+NC_003450	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Corynebacterium;s__Corynebacterium glutamicum	GCF_000011325.1	95.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Corynebacterium;s__Corynebacterium glutamicum	100.0	1.0	GCF_000011325.1	95.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Corynebacterium;s__Corynebacterium glutamicum	100.0	1.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Corynebacterium;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_002355155.1, s__Corynebacterium suranareeae, 95.0, 86.55, 0.531; GCF_001643015.1, s__Corynebacterium crudilactis, 95.0, 84.07, 0.363; GCF_001277995.1, s__Corynebacterium deserti, 95.0, 83.77, 0.275	96.43	11	N/A	N/A
+NC_008261	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Clostridiales;f__Clostridiaceae;g__Sarcina;s__Sarcina perfringens	GCF_000013285.1	95.0	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Clostridiales;f__Clostridiaceae;g__Sarcina;s__Sarcina perfringens	100.0	1.0	GCF_000013285.1	95.0	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Clostridiales;f__Clostridiaceae;g__Sarcina;s__Sarcina perfringens	100.0	1.0	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Clostridiales;f__Clostridiaceae;g__Sarcina;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_029258205.1, s__Sarcina sp029258205, 95.0, 92.75, 0.744; GCF_029267215.1, s__Sarcina sp029267215, 95.0, 84.03, 0.29	94.4	11	N/A	N/A
+NC_009012	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Acetivibrionales;f__Acetivibrionaceae;g__Hungateiclostridium;s__Hungateiclostridium thermocellum	GCF_000015865.1	95.0	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Acetivibrionales;f__Acetivibrionaceae;g__Hungateiclostridium;s__Hungateiclostridium thermocellum	100.0	1.0	GCF_000015865.1	95.0	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Acetivibrionales;f__Acetivibrionaceae;g__Hungateiclostridium;s__Hungateiclostridium thermocellum	100.0	1.0	d__Bacteria;p__Bacillota_A;c__Clostridia;o__Acetivibrionales;f__Acetivibrionaceae;g__Hungateiclostridium;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_000521465.1, s__Hungateiclostridium straminisolvens, 95.0, 84.49, 0.429; GCF_004102745.1, s__Hungateiclostridium mesophilum, 95.0, 81.39, 0.257	94.22	11	N/A	N/A
+NC_012982	d__Bacteria;p__Pseudomonadota;c__Alphaproteobacteria;o__Caulobacterales;f__Hyphomonadaceae;g__Hirschia;s__Hirschia baltica	GCF_000023785.1	95.0	d__Bacteria;p__Pseudomonadota;c__Alphaproteobacteria;o__Caulobacterales;f__Hyphomonadaceae;g__Hirschia;s__Hirschia baltica	100.0	1.0	GCF_000023785.1	95.0	d__Bacteria;p__Pseudomonadota;c__Alphaproteobacteria;o__Caulobacterales;f__Hyphomonadaceae;g__Hirschia;s__Hirschia baltica	100.0	1.0	d__Bacteria;p__Pseudomonadota;c__Alphaproteobacteria;o__Caulobacterales;f__Hyphomonadaceae;g__Hirschia;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	N/A	98.25	11	N/A	N/A
+NC_014008	d__Bacteria;p__Verrucomicrobiota;c__Verrucomicrobiae;o__Opitutales;f__Coraliomargaritaceae;g__Coraliomargarita;s__Coraliomargarita akajimensis	GCF_000025905.1	95.0	d__Bacteria;p__Verrucomicrobiota;c__Verrucomicrobiae;o__Opitutales;f__Coraliomargaritaceae;g__Coraliomargarita;s__Coraliomargarita akajimensis	100.0	1.0	GCF_000025905.1	95.0	d__Bacteria;p__Verrucomicrobiota;c__Verrucomicrobiae;o__Opitutales;f__Coraliomargaritaceae;g__Coraliomargarita;s__Coraliomargarita akajimensis	100.0	1.0	d__Bacteria;p__Verrucomicrobiota;c__Verrucomicrobiae;o__Opitutales;f__Coraliomargaritaceae;g__;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	N/A	90.76	11	N/A	N/A
+NC_014168	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Segniliparus;s__Segniliparus rotundus	GCF_000092825.1	95.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Segniliparus;s__Segniliparus rotundus	100.0	1.0	GCF_000092825.1	95.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Segniliparus;s__Segniliparus rotundus	100.0	1.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Mycobacteriales;f__Mycobacteriaceae;g__Segniliparus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_000185725.2, s__Segniliparus rugosus, 95.0, 80.18, 0.178	96.56	11	N/A	N/A
+NC_014211	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Streptosporangiales;f__Streptosporangiaceae;g__Nocardiopsis;s__Nocardiopsis dassonvillei	GCF_000092985.1	95.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Streptosporangiales;f__Streptosporangiaceae;g__Nocardiopsis;s__Nocardiopsis dassonvillei	100.0	1.0	GCF_000092985.1	95.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Streptosporangiales;f__Streptosporangiaceae;g__Nocardiopsis;s__Nocardiopsis dassonvillei	100.0	1.0	d__Bacteria;p__Actinomycetota;c__Actinomycetes;o__Streptosporangiales;f__Streptosporangiaceae;g__Nocardiopsis;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_012396365.1, s__Nocardiopsis alborubida, 95.0, 94.89, 0.822; GCA_000340945.1, s__Nocardiopsis synnemataformans, 95.0, 94.67, 0.838; GCA_002529455.1, s__Nocardiopsis fusca, 95.0, 93.48, 0.743; GCF_000341065.1, s__Nocardiopsis halotolerans, 95.0, 89.3, 0.575; GCF_001905145.1, s__Nocardiopsis sp001905145, 95.0, 89.08, 0.554; GCF_008638415.1, s__Nocardiopsis sinuspersici, 95.0, 88.61, 0.531; GCF_008638365.1, s__Nocardiopsis quinghaiensis, 95.0, 88.23, 0.498; GCF_009830945.1, s__Nocardiopsis sp009830945, 95.0, 87.99, 0.442; GCA_937957845.1, s__Nocardiopsis sp937957845, 95.0, 87.38, 0.277; GCF_026642255.1, s__Nocardiopsis nanhaiensis_A, 95.0, 86.06, 0.436; GCF_030271535.1, s__Nocardiopsis sp030271535, 95.0, 84.81, 0.338; GCF_013410755.1, s__Nocardiopsis aegyptia, 95.0, 84.69, 0.277; GCF_018316655.1, s__Nocardiopsis changdeensis, 95.0, 84.65, 0.301; GCF_000341125.1, s__Nocardiopsis lucentensis, 95.0, 84.45, 0.226; GCF_001279585.1, s__Nocardiopsis sp001279585, 95.0, 84.4, 0.267; GCA_018388625.1, s__Nocardiopsis eucommiae, 95.0, 84.39, 0.264; GCF_014201115.1, s__Nocardiopsis metallicus, 95.0, 84.3, 0.268; GCF_003634495.1, s__Nocardiopsis sp003634495, 95.0, 84.18, 0.288; GCF_030766825.1, s__Nocardiopsis sp030766825, 95.0, 84.18, 0.286; GCF_000341085.1, s__Nocardiopsis ganjiahuensis, 95.0, 84.16, 0.28; GCF_030555055.1, s__Nocardiopsis sp030555055, 95.0, 84.06, 0.267; GCF_024134545.1, s__Nocardiopsis exhalans, 95.08, 84.04, 0.267; GCF_900141985.1, s__Nocardiopsis flavescens, 95.0, 83.82, 0.272; GCF_003386285.1, s__Nocardiopsis sp003386285, 95.0, 83.73, 0.264; GCF_014651695.1, s__Nocardiopsis terrae, 95.0, 83.6, 0.27; GCF_014203695.1, s__Nocardiopsis algeriensis, 95.0, 83.59, 0.238; GCF_020741345.1, s__Nocardiopsis listeri_A, 95.0, 83.53, 0.202; GCF_000341225.1, s__Nocardiopsis alba, 95.0, 83.47, 0.217; GCF_018207095.1, s__Nocardiopsis sp018207095, 95.0, 83.32, 0.229; GCF_028882275.1, s__Nocardiopsis sp028882275, 95.0, 83.25, 0.266; GCF_900143625.1, s__Nocardiopsis sp900143625, 95.0, 83.09, 0.229; GCF_000515115.1, s__Nocardiopsis sp000515115, 95.0, 83.02, 0.181; GCF_014892575.1, s__Nocardiopsis coralli, 95.0, 82.85, 0.213; GCF_000341265.1, s__Nocardiopsis prasina, 95.0, 82.63, 0.245; GCF_001942255.1, s__Nocardiopsis sp001942255, 95.0, 82.61, 0.248; GCF_000341005.1, s__Nocardiopsis alkaliphila, 95.0, 82.53, 0.186; GCF_001570765.1, s__Nocardiopsis listeri, 95.0, 82.26, 0.198; GCF_000341025.1, s__Nocardiopsis salina, 95.0, 82.22, 0.158; GCF_000341145.1, s__Nocardiopsis xinjiangensis, 95.0, 81.14, 0.168	26.24	11	N/A	N/A
+NC_014212	d__Bacteria;p__Deinococcota;c__Deinococci;o__Deinococcales;f__Thermaceae;g__Allomeiothermus;s__Allomeiothermus silvanus	GCF_000092125.1	95.0	d__Bacteria;p__Deinococcota;c__Deinococci;o__Deinococcales;f__Thermaceae;g__Allomeiothermus;s__Allomeiothermus silvanus	100.0	0.999	GCF_000092125.1	95.0	d__Bacteria;p__Deinococcota;c__Deinococci;o__Deinococcales;f__Thermaceae;g__Allomeiothermus;s__Allomeiothermus silvanus	100.0	0.999	d__Bacteria;p__Deinococcota;c__Deinococci;o__Deinococcales;f__Thermaceae;g__Allomeiothermus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_003226535.1, s__Allomeiothermus sp003226535, 95.0, 87.73, 0.485	93.82	11	N/A	N/A
+NC_014363	d__Bacteria;p__Actinomycetota;c__Coriobacteriia;o__Coriobacteriales;f__Atopobiaceae;g__Olsenella;s__Olsenella uli	GCF_000143845.1	95.0	d__Bacteria;p__Actinomycetota;c__Coriobacteriia;o__Coriobacteriales;f__Atopobiaceae;g__Olsenella;s__Olsenella uli	100.0	1.0	GCF_000143845.1	95.0	d__Bacteria;p__Actinomycetota;c__Coriobacteriia;o__Coriobacteriales;f__Atopobiaceae;g__Olsenella;s__Olsenella uli	100.0	1.0	d__Bacteria;p__Actinomycetota;c__Coriobacteriia;o__Coriobacteriales;f__Atopobiaceae;g__;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	N/A	95.47	11	N/A	N/A
+NC_014364	d__Bacteria;p__Spirochaetota;c__Spirochaetia;o__DSM-16054;f__Sediminispirochaetaceae;g__Sediminispirochaeta;s__Sediminispirochaeta smaragdinae	GCF_000143985.1	95.0	d__Bacteria;p__Spirochaetota;c__Spirochaetia;o__DSM-16054;f__Sediminispirochaetaceae;g__Sediminispirochaeta;s__Sediminispirochaeta smaragdinae	100.0	1.0	GCF_000143985.1	95.0	d__Bacteria;p__Spirochaetota;c__Spirochaetia;o__DSM-16054;f__Sediminispirochaetaceae;g__Sediminispirochaeta;s__Sediminispirochaeta smaragdinae	100.0	1.0	d__Bacteria;p__Spirochaetota;c__Spirochaetia;o__DSM-16054;f__Sediminispirochaetaceae;g__Sediminispirochaeta;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_000378205.1, s__Sediminispirochaeta bajacaliforniensis, 95.0, 94.41, 0.82	88.42	11	N/A	N/A
+NC_015761	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Salmonella;s__Salmonella bongori	GCF_000252995.1	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Salmonella;s__Salmonella bongori	100.0	1.0	GCF_000252995.1	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Salmonella;s__Salmonella bongori	100.0	1.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Enterobacterales;f__Enterobacteriaceae;g__Salmonella;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_000006945.2, s__Salmonella enterica, 95.0, 90.34, 0.758; GCA_900478215.1, s__Salmonella houtenae, 95.0, 90.05, 0.755; GCF_008692785.1, s__Salmonella diarizonae, 95.0, 89.91, 0.746; GCF_008692845.1, s__Salmonella arizonae, 95.0, 89.51, 0.704	97.58	11	N/A	N/A
+NC_017033	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Xanthomonadales;f__Rhodanobacteraceae;g__Frateuria;s__Frateuria aurantia	GCF_000242255.2	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Xanthomonadales;f__Rhodanobacteraceae;g__Frateuria;s__Frateuria aurantia	100.0	1.0	GCF_000242255.2	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Xanthomonadales;f__Rhodanobacteraceae;g__Frateuria;s__Frateuria aurantia	100.0	1.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Xanthomonadales;f__Rhodanobacteraceae;g__;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	N/A	98.45	11	N/A	N/A
+NC_017095	d__Bacteria;p__Thermotogota;c__Thermotogae;o__Thermotogales;f__Fervidobacteriaceae;g__Fervidobacterium;s__Fervidobacterium pennivorans	GCF_000235405.2	95.0	d__Bacteria;p__Thermotogota;c__Thermotogae;o__Thermotogales;f__Fervidobacteriaceae;g__Fervidobacterium;s__Fervidobacterium pennivorans	100.0	1.0	GCF_000235405.2	95.0	d__Bacteria;p__Thermotogota;c__Thermotogae;o__Thermotogales;f__Fervidobacteriaceae;g__Fervidobacterium;s__Fervidobacterium pennivorans	100.0	1.0	d__Bacteria;p__Thermotogota;c__Thermotogae;o__Thermotogales;f__Fervidobacteriaceae;g__Fervidobacterium;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_001644665.1, s__Fervidobacterium pennivorans_A, 95.0, 92.25, 0.827	90.82	11	N/A	N/A
+NC_018014	d__Bacteria;p__Acidobacteriota;c__Terriglobia;o__Terriglobales;f__Acidobacteriaceae;g__Terriglobus;s__Terriglobus roseus	GCF_000265425.1	95.0	d__Bacteria;p__Acidobacteriota;c__Terriglobia;o__Terriglobales;f__Acidobacteriaceae;g__Terriglobus;s__Terriglobus roseus	100.0	1.0	GCF_000265425.1	95.0	d__Bacteria;p__Acidobacteriota;c__Terriglobia;o__Terriglobales;f__Acidobacteriaceae;g__Terriglobus;s__Terriglobus roseus	100.0	1.0	d__Bacteria;p__Acidobacteriota;c__Terriglobia;o__Terriglobales;f__Acidobacteriaceae;g__Terriglobus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_900105625.1, s__Terriglobus roseus_B, 95.0, 82.2, 0.254	94.06	11	N/A	N/A
+NC_018068	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__Desulfosporosinus acidiphilus	GCF_000255115.2	95.0	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__Desulfosporosinus acidiphilus	100.0	1.0	GCF_000255115.2	95.0	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__Desulfosporosinus acidiphilus	100.0	1.0	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_002196705.1, s__Desulfosporosinus sp002196705, 95.0, 81.15, 0.156	93.92	11	N/A	N/A
+NC_018515	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__Desulfosporosinus meridiei	GCF_000231385.2	95.0	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__Desulfosporosinus meridiei	100.0	1.0	GCF_000231385.2	95.0	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__Desulfosporosinus meridiei	100.0	1.0	d__Bacteria;p__Bacillota_B;c__Desulfitobacteriia;o__Desulfitobacteriales;f__Desulfitobacteriaceae;g__Desulfosporosinus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_900100785.1, s__Desulfosporosinus hippei, 95.0, 94.11, 0.765; GCF_000765145.1, s__Desulfosporosinus sp000765145, 95.0, 92.48, 0.692	94.5	11	N/A	N/A
+NC_019897	d__Bacteria;p__Bacillota;c__Bacilli;o__Paenibacillales;f__Paenibacillaceae;g__Thermobacillus;s__Thermobacillus xylanilyticus	GCF_907165215.1	95.0	d__Bacteria;p__Bacillota;c__Bacilli;o__Paenibacillales;f__Paenibacillaceae;g__Thermobacillus;s__Thermobacillus xylanilyticus	97.81	0.815	GCF_907165215.1	95.0	d__Bacteria;p__Bacillota;c__Bacilli;o__Paenibacillales;f__Paenibacillaceae;g__Thermobacillus;s__Thermobacillus xylanilyticus	97.81	0.815	d__Bacteria;p__Bacillota;c__Bacilli;o__Paenibacillales;f__Paenibacillaceae;g__Thermobacillus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_002159085.1, s__Thermobacillus sp002159085, 95.0, 85.65, 0.466	95.97	11	N/A	N/A
+NC_019904	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Cytophagales;f__Cyclobacteriaceae;g__Echinicola;s__Echinicola vietnamensis	GCF_000325705.1	95.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Cytophagales;f__Cyclobacteriaceae;g__Echinicola;s__Echinicola vietnamensis	100.0	1.0	GCF_000325705.1	95.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Cytophagales;f__Cyclobacteriaceae;g__Echinicola;s__Echinicola vietnamensis	100.0	1.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Cytophagales;f__Cyclobacteriaceae;g__Echinicola;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_005281475.1, s__Echinicola rosea, 95.0, 83.28, 0.288; GCF_006575665.1, s__Echinicola soli, 95.0, 81.29, 0.203; GCF_003260975.1, s__Echinicola strongylocentroti, 95.0, 80.38, 0.164	96.96	11	N/A	N/A
+NC_019936	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Pseudomonadales;f__Pseudomonadaceae;g__Stutzerimonas;s__Stutzerimonas stutzeri_AE	GCF_000327065.1	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Pseudomonadales;f__Pseudomonadaceae;g__Stutzerimonas;s__Stutzerimonas stutzeri_AE	100.0	1.0	GCF_000327065.1	95.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Pseudomonadales;f__Pseudomonadaceae;g__Stutzerimonas;s__Stutzerimonas stutzeri_AE	100.0	1.0	d__Bacteria;p__Pseudomonadota;c__Gammaproteobacteria;o__Pseudomonadales;f__Pseudomonadaceae;g__Stutzerimonas;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_003696315.1, s__Stutzerimonas songnenensis, 95.0, 93.2, 0.909; GCF_000661915.1, s__Stutzerimonas decontaminans, 95.0, 91.33, 0.803; GCF_900114065.1, s__Stutzerimonas kunmingensis, 96.6, 90.17, 0.753; GCF_024397475.1, s__Stutzerimonas xanthomarina_A, 97.0, 90.15, 0.746; GCA_007713455.1, s__Stutzerimonas sp007713455, 95.0, 90.03, 0.748; GCF_014764705.1, s__Stutzerimonas sp002692525, 96.82, 90.01, 0.736; GCA_003530955.1, s__Stutzerimonas sp003530955, 96.79, 89.98, 0.727; GCF_002929225.1, s__Stutzerimonas stutzeri_U, 97.04, 89.97, 0.743; GCF_000935215.1, s__Stutzerimonas stutzeri_AD, 96.98, 89.84, 0.723; GCF_000495915.1, s__Stutzerimonas chloritidismutans, 96.78, 89.84, 0.717; GCA_018823765.1, s__Stutzerimonas sp018823765, 97.02, 89.77, 0.71; GCA_003488145.1, s__Stutzerimonas sp003488145, 96.59, 89.74, 0.666; GCF_000341615.1, s__Stutzerimonas stutzeri_G, 95.0, 89.32, 0.697; GCF_002890795.1, s__Stutzerimonas stutzeri_AA, 95.0, 89.28, 0.735; GCF_024448335.1, s__Stutzerimonas frequens, 95.0, 88.75, 0.714; GCF_015291885.1, s__Stutzerimonas stutzeri_AC, 95.0, 88.59, 0.662; GCF_000219605.1, s__Stutzerimonas stutzeri, 95.0, 88.34, 0.673; GCF_002909485.1, s__Stutzerimonas stutzeri_AH, 95.0, 88.19, 0.688; GCF_000307775.2, s__Stutzerimonas stutzeri_B, 95.0, 86.95, 0.549; GCF_002890915.1, s__Stutzerimonas stutzeri_AF, 95.0, 85.91, 0.472; GCF_025966695.1, s__Stutzerimonas sp025966695, 95.0, 85.39, 0.44; GCA_000263395.1, s__Stutzerimonas stutzeri_C, 95.0, 85.38, 0.392; GCF_024448505.1, s__Stutzerimonas degradans, 96.08, 85.26, 0.426; GCF_021432765.1, s__Stutzerimonas phenolilytica, 95.0, 85.11, 0.435; GCF_015070855.1, s__Stutzerimonas lopnurensis, 95.0, 85.07, 0.41; GCF_021726475.1, s__Stutzerimonas oligotrophica, 95.0, 84.76, 0.419; GCF_000818015.1, s__Stutzerimonas balearica, 95.0, 83.88, 0.33; GCF_003696285.1, s__Stutzerimonas nitrititolerans, 95.0, 82.51, 0.26; GCF_018138085.1, s__Stutzerimonas stutzeri_AI, 95.0, 82.03, 0.245; GCF_005876855.1, s__Stutzerimonas nosocomialis, 95.0, 81.99, 0.242; GCF_019090095.1, s__Stutzerimonas stutzeri_AN, 95.0, 81.91, 0.245; GCF_013522825.1, s__Stutzerimonas stutzeri_AK, 95.0, 81.91, 0.2; GCA_002339675.1, s__Stutzerimonas stutzeri_O, 95.0, 81.89, 0.253; GCF_019355055.1, s__Stutzerimonas sp004331835, 95.0, 81.83, 0.222; GCF_024448955.1, s__Stutzerimonas stutzeri_AQ, 95.0, 81.79, 0.232; GCF_024448695.1, s__Stutzerimonas stutzeri_T, 95.0, 81.71, 0.242; GCF_022810315.1, s__Stutzerimonas marianensis, 95.0, 81.66, 0.218; GCF_024448935.1, s__Stutzerimonas stutzeri_AO, 95.0, 81.57, 0.177; GCF_009789555.1, s__Stutzerimonas stutzeri_R, 95.0, 81.41, 0.22; GCA_022448005.1, s__Stutzerimonas sp022448005, 95.0, 81.35, 0.194; GCF_003325755.1, s__Stutzerimonas sp003325755, 95.0, 81.28, 0.206; GCA_004010935.1, s__Stutzerimonas sp004010935, 95.0, 81.27, 0.216; GCA_002387205.1, s__Stutzerimonas stutzeri_N, 95.0, 81.26, 0.195; GCF_024448985.1, s__Stutzerimonas stutzeri_AP, 95.0, 81.22, 0.203; GCF_000425625.1, s__Stutzerimonas azotifigens, 95.0, 81.18, 0.187; GCF_000756775.1, s__Stutzerimonas saudiphocaensis, 95.0, 81.13, 0.219; GCF_000952685.1, s__Stutzerimonas stutzeri_E, 95.0, 81.08, 0.216; GCF_000235745.1, s__Stutzerimonas stutzeri_H, 95.0, 81.07, 0.199; GCF_013522725.1, s__Stutzerimonas azotifigens_A, 95.0, 80.99, 0.203; GCA_900766265.1, s__Stutzerimonas sp900766265, 95.0, 80.94, 0.196; GCF_024448895.1, s__Stutzerimonas stutzeri_Q, 95.0, 80.91, 0.193; GCF_900129835.1, s__Stutzerimonas xanthomarina, 95.0, 80.89, 0.2; GCF_002890895.1, s__Stutzerimonas stutzeri_AB, 95.0, 80.87, 0.198; GCF_019880365.1, s__Stutzerimonas stutzeri_P, 95.0, 80.81, 0.187; GCA_002345575.1, s__Stutzerimonas stutzeri_S, 95.0, 80.74, 0.191; GCF_013620795.1, s__Stutzerimonas sp013620795, 95.0, 80.74, 0.187; GCF_024448715.1, s__Stutzerimonas stutzeri_AR, 95.0, 80.6, 0.18; GCF_000590475.1, s__Stutzerimonas stutzeri_D, 95.0, 80.4, 0.167; GCF_003696365.1, s__Stutzerimonas zhaodongensis, 95.0, 79.95, 0.152	97.72	11	N/A	N/A
+NC_021184	d__Bacteria;p__Bacillota_B;c__Desulfotomaculia;o__Desulfotomaculales;f__Desulfallaceae;g__Sporotomaculum;s__Sporotomaculum gibsoniae	GCF_000233715.2	95.0	d__Bacteria;p__Bacillota_B;c__Desulfotomaculia;o__Desulfotomaculales;f__Desulfallaceae;g__Sporotomaculum;s__Sporotomaculum gibsoniae	100.0	1.0	GCF_000233715.2	95.0	d__Bacteria;p__Bacillota_B;c__Desulfotomaculia;o__Desulfotomaculales;f__Desulfallaceae;g__Sporotomaculum;s__Sporotomaculum gibsoniae	100.0	1.0	d__Bacteria;p__Bacillota_B;c__Desulfotomaculia;o__Desulfotomaculales;f__Desulfallaceae;g__Sporotomaculum;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	N/A	95.73	11	N/A	N/A