Mercurial > repos > iuc > biobox_add_taxid

--- a/biobox_add_taxid.xml	Sun Sep 08 14:37:41 2024 +0000
+++ b/biobox_add_taxid.xml	Sat Feb 08 11:33:03 2025 +0000
@@ -1,68 +1,59 @@
-<tool id="biobox_add_taxid" name="Biobox add taxid" version="@SCRIPT_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
+<tool id="biobox_add_taxid" name="Biobox add taxid" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
     <description>Add taxid output from BAT or GTDB to biobox binning data</description>
     <macros>
-        <import>macros.xml</import>
-        <token name="@SCRIPT_VERSION@">0.6</token>
+        <token name="@TOOL_VERSION@">1.2</token>
+        <token name="@VERSION_SUFFIX@">0</token>
+        <token name="@PROFILE@">24.1</token>
     </macros>
     <requirements>
-        <requirement type="package" version="@SCRIPT_VERSION@">biobox_add_taxid</requirement>
+        <requirement type="package" version="@TOOL_VERSION@">biobox_add_taxid</requirement>
     </requirements>
     <command detect_errors="exit_code">
     <![CDATA[

-        mkdir -p input taxonkit gtdb_to_taxdump &&
-
-        ln -s '${biobox_file}' '$biobox_file.element_identifier' &&
-
-        #for $i, $f in enumerate($tool_type.input):
-            ln -s '$f' 'input/${i}.tsv' &&
-        #end for
+    ln -s '$biobox_file' 'biobox.tsv' &&

-        #if $tool_type.is_select == 'GTDB':
-            #for $i, $f in enumerate($gtdb_to_taxdump):
-                ln -s '$f' 'gtdb_to_taxdump/gtdb_to_taxdump_${i}.tsv' &&
-            #end for
-            #for $i, $f in enumerate($taxonkit):
-                ln -s '$f' 'taxonkit/taxonkit_${i}.tsv' &&
-            #end for
-        #end if
+    #if $input.is_select == 'contig':
+        ln -s '$contig2taxid' 'contig.tsv' &&
+    #else:
+        ln -s '$binid2taxid' 'bin.tsv' &&
+    #end if

-        biobox_add_taxid.py
-        '$biobox_file.element_identifier'
-        '$tool_type.is_select'
-        'input'
-        #if $tool_type.is_select == 'GTDB':
-            -g 'gtdb_to_taxdump'
-            -t 'taxonkit'
-            -c $column
-        #end if
-        &&
+    biobox_add_taxid.py
+    'biobox.tsv'
+    #if $input.is_select == 'contig':
+        -c 'contig.tsv'
+    #else:
+        -b 'bin.tsv'
+    #end if
+    -k_c ${key_col}
+    -t_c ${taxid_col}

-        #if $tool_type.is_select == 'GTDB':
-            cp *_add_taxid_GTDB* $output
-        #else:
-            cp *_add_taxid_BAT* $output
-        #end if
+    &&
+
+    cp 'modified_biobox_file.tsv' '$output'

     ]]>
     </command>
     <inputs>
-        <param name="biobox_file" type="data" format="tabular" label="CAMI amber biobox file input" help="Input the CAMI amber biobox file here which are corespond with the biner and the BAT/GTDB output which did used the biner as input! "/>
-        <conditional name="tool_type">
-            <param name="is_select" type="select" label="Select the tool which output should be used here" help="Select BAT when you use the bin2classifier file(s) or select GTDB when using the summary file(s)">
-                <option value="BAT">BAT</option>
-                <option value="GTDB">GTDB</option>
+        <param name="biobox_file" type="data" format="tabular" label="Input biobox file"
+            help="This file can be generated with the utility tool from CAMI AMBER named convert to biobox"/>
+        <conditional name="input">
+            <param name="is_select" type="select" label="Select typ of input">
+                <option value="contig">ContigID2TaxID</option>
+                <option value="bin">BinID2TaxID</option>
             </param>
-            <when value="GTDB">
-                <param argument="--gtdb_to_taxdump" type="data" multiple="true" format="tabular" label="Input the output from gtdb_to_taxdump here" help="Use the output from gtdb_to_taxdump here since we need the mapped names from GTDB to NCBI to get the arcoding taxids from NCBI"/>
-                <param argument="--taxonkit" type="data" format="tabular" multiple="true" label="Input the output from Taxonkit here" help="Use the output from Taxonkit here since the need the mapped NCBI names to the arcording taxids"/>
-                <param argument="--column" type="data_column" data_ref="taxonkit" label="Input the colum with the NCBI names"/>
-                <param name="input" type="data" multiple="true" format="tabular" label="Input the GTDB-Tk summary file(s) here"
-                    help="Use the GTDB-Tk file(s) which are coresponding with the binning file!"/>
+            <when value="contig">
+                <param argument="--contig2taxid" type="data" format="tabular" label="Input ConitgID2TaxID file"
+                    help="This input comes from Kraken2"/>
+                <param argument="--key_col" type="data_column" data_ref="contig2taxid" label="Select the column where the ContigID are stated"/>
+                <param argument="--taxid_col" type="data_column" data_ref="contig2taxid" label="Select the column where the TaxID are stated"/>
             </when>
-            <when value="BAT">
-                <param name="input" type="data" multiple="true" format="tabular" label="Input bin2classifier file(s) from BAT here"
-                    help="Use the BAT file(s) which are coresponding with the binning file!"/>
+            <when value="bin">
+                <param argument="--binid2taxid" type="data" format="tabular" label="Input BinID2TaxID file"
+                    help="This input comes from Kraken2"/>
+                <param argument="--key_col" type="data_column" data_ref="binid2taxid" label="Select the column where the BinID are stated"/>
+                <param argument="--taxid_col" type="data_column" data_ref="binid2taxid" label="Select the column where the TaxID are stated"/>
             </when>
         </conditional>
     </inputs>
@@ -70,48 +61,52 @@
         <data name="output" format="tabular" label="${tool.name}: BIOBOX ADD TAXID COLUMN"/>
     </outputs>
     <tests>
-        <test expect_num_outputs="1">
-            <param name="biobox_file" ftype="tabular" value="test_biobox_file.tsv"/>
-            <conditional name="tool_type">
-                <param name="is_select" value="BAT"/>
-                <param name="input" ftype="tabular" value="test_bat_file.tsv"/>
+        <test>
+            <param name="biobox_file" value="biobox_file.tsv" ftype="tabular"/>
+            <conditional name="input">
+                <param name="is_select" value="bin"/>
+                <param name="binid2taxid" value="binid2taxid.tsv" ftype="tabular"/>
+                <param name="key_col" value="1"/>
+                <param name="taxid_col" value="2"/>
             </conditional>
-            <output name="output" file="test_biobox_file_add_taxid_bat.tsv"/>
+            <output name="output" file="modified_biobox_file_bin.tsv"/>
         </test>
-        <test expect_num_outputs="1">
-            <param name="biobox_file" ftype="tabular" value="test_biobox_file.tsv"/>
-            <conditional name="tool_type">
-                <param name="is_select" value="GTDB"/>
-                <param name="gtdb_to_taxdump" ftype="tabular" value="test_gtdb_to_taxdump_file.tsv"/>
-                <param name="taxonkit" ftype="tabular" value="test_taxonkit_file_1.tsv,test_taxonkit_file_2.tsv"/>
-                <param name="column" value="1"/>
-                <param name="input" ftype="tabular" value="test_gtdb_file.tsv"/>
+        <test>
+            <param name="biobox_file" value="biobox_file.tsv" ftype="tabular"/>
+            <conditional name="input">
+                <param name="is_select" value="contig"/>
+                <param name="contig2taxid" value="kraken2.tsv" ftype="tabular"/>
+                <param name="key_col" value="2"/>
+                <param name="taxid_col" value="3"/>
             </conditional>
-            <output name="output" file="test_biobox_file_add_taxid_gtdb.tsv"/>
+            <output name="output" file="modified_biobox_file_contig.tsv"/>
         </test>
     </tests>
     <help>
     <![CDATA[

         **USAGE OF THIS TOOL**
-
-        This tool was desgin for using the BAT/GTDB-Tk output to expand the CAMI amber biobox file with the taxid column to access taxa evaluation with amber!
-
-        **IMPORTAND NOTE WHEN USING GTDB OUTPUT**
-
-        Befor using GTDB-Tk output you have to use 2 other tools to map the GTDB names to the NCBI names and then map the NCBI names to there taxids.
-        To map the GTDB names to the NCBI names you extract the GTDB names from the summary file and with them you can now use the gtdb_to_taxdum tool!
-        After using the gtdb_to_taxdum tool you have the extract the NCBI names here and then use the tool Taxonkit[name2taxid] to finaly get the taxids.
+
+        This tool can be used to add the TaxID column to a biobox file.

         **INPUTS**
-        - The CAMI amber biobox file
-        - BAT[bin2classifier] file(s) OR GTDB-Tk[Summary] file(s)
-        - The gtdb_to_taxdum output[WHEN USING GTDB-Tk]
-        - The Taxonkit[name2taxid] output[WHEN USING GTDB-Tk]
+
+        - A biobox file. This file can be generated with the CAMI AMBER utility Tool named 'convert to biobox'
+        - Either a Contig2TaxID file which is generated from Kraken2 (the classification file from Kraken2) or a BinID2TaxID which has to be done manualy
+
+        Example for a BinID2TaxID file
+
+        ::
+
+            #BinID   TaxID
+            test1   11056
+            test2   444944
+            ABC 888

         **OUTPUT**

-        A CAMI amber biobox file with a taxid colum
+        - A CAMI AMBER biobox file with a taxid column
+
     ]]>
     </help>
     <citations>
@@ -121,8 +116,7 @@
             journal = {GitHub},
             year = {2024},
             month = aug,
-            note = {[Online; accessed 22. Aug. 2024]},
-            url = {https://github.com/SantaMcCloud/biobox_add_taxid/tree/release-0.3}
+            url = {https://github.com/SantaMcCloud/biobox_add_taxid/tree/release-1.0}
         }</citation>
     </citations>
 </tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/binid2taxid.tsv	Sat Feb 08 11:33:03 2025 +0000
@@ -0,0 +1,39 @@
+#BinID	NCBI_TaxID
+SemiBin_SemiBin_234	12908
+SemiBin_SemiBin_78_sub	12908
+SemiBin_SemiBin_79	12908
+SemiBin_SemiBin_54	226
+SemiBin_SemiBin_56	226
+MetaBAT2_69	2234
+SemiBin_SemiBin_80	191412
+SemiBin_SemiBin_448	100716
+CONCOCT_117	1485
+CONCOCT_136_sub	897
+CONCOCT_73_sub	1263979
+SemiBin_SemiBin_1072	1263979
+CONCOCT_45_sub	39960
+CONCOCT_170	1188228
+MetaBAT2_13_sub	2745
+CONCOCT_60	54248
+MetaBAT2_42	12908
+CONCOCT_87	467094
+CONCOCT_2_sub	1124597
+CONCOCT_93	186192
+CONCOCT_8	936476
+SemiBin_SemiBin_50	2198
+CONCOCT_192	38027
+SemiBin_SemiBin_159	168695
+CONCOCT_62	133539
+CONCOCT_198	1229
+CONCOCT_17	971279
+SemiBin_SemiBin_93	497
+CONCOCT_166_sub	1335757
+MetaBAT2_7	1335746
+CONCOCT_27	1292
+CONCOCT_214	265570
+MetaBAT2_46	1129
+SemiBin_SemiBin_374	80679
+MetaBAT2_9_sub	171436
+SemiBin_SemiBin_19	662
+SemiBin_SemiBin_75	662
+MetaBAT2_24	29497
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/biobox_file.tsv	Sat Feb 08 11:33:03 2025 +0000
@@ -0,0 +1,321 @@
+#CAMI Format for Binning
+@Version:0.9.0
+@SampleID:_SAMPLEID_
+@@SEQUENCEID	BINID
+S0C67443	CONCOCT_117
+S0C145665	CONCOCT_117
+S0C179008	CONCOCT_117
+S0C285214	CONCOCT_117
+S0C309108	CONCOCT_117
+S0C310129	CONCOCT_117
+S0C336019	CONCOCT_117
+S0C388550	CONCOCT_117
+S0C495394	CONCOCT_117
+S0C511360	CONCOCT_117
+S0C577842	CONCOCT_117
+S0C596918	CONCOCT_117
+S0C603398	CONCOCT_117
+S0C754713	CONCOCT_117
+S0C938786	CONCOCT_117
+S0C967914	CONCOCT_117
+S0C974893	CONCOCT_117
+S0C1006901	CONCOCT_117
+S0C1018235	CONCOCT_117
+S0C1018552	CONCOCT_117
+S0C1049501	CONCOCT_117
+S0C1067275	CONCOCT_117
+S0C1069633	CONCOCT_117
+S0C1089023	CONCOCT_117
+S0C1146406	CONCOCT_117
+S0C1154753	CONCOCT_117
+S0C1194005	CONCOCT_117
+S0C1226618	CONCOCT_117
+S0C1282023	CONCOCT_117
+S0C1332000	CONCOCT_117
+S0C1359995	CONCOCT_117
+S0C1396765	CONCOCT_117
+S0C1472996	CONCOCT_117
+S0C1475640	CONCOCT_117
+S0C2285	CONCOCT_136_sub
+S0C12513	CONCOCT_136_sub
+S0C13841	CONCOCT_136_sub
+S0C15954	CONCOCT_136_sub
+S0C33046	CONCOCT_136_sub
+S0C38240	CONCOCT_136_sub
+S0C40714	CONCOCT_136_sub
+S0C67745	CONCOCT_136_sub
+S0C96249	CONCOCT_136_sub
+S0C105628	CONCOCT_136_sub
+S0C121147	CONCOCT_136_sub
+S0C123278	CONCOCT_136_sub
+S0C128492	CONCOCT_136_sub
+S0C142447	CONCOCT_136_sub
+S0C143656	CONCOCT_136_sub
+S0C146090	CONCOCT_136_sub
+S0C146468	CONCOCT_136_sub
+S0C148477	CONCOCT_136_sub
+S0C154116	CONCOCT_136_sub
+S0C154853	CONCOCT_136_sub
+S0C183450	CONCOCT_136_sub
+S0C206740	CONCOCT_136_sub
+S0C217759	CONCOCT_136_sub
+S0C218807	CONCOCT_136_sub
+S0C232692	CONCOCT_136_sub
+S0C241720	CONCOCT_136_sub
+S0C254412	CONCOCT_136_sub
+S0C255416	CONCOCT_136_sub
+S0C257539	CONCOCT_136_sub
+S0C271698	CONCOCT_136_sub
+S0C273417	CONCOCT_136_sub
+S0C277828	CONCOCT_136_sub
+S0C292193	CONCOCT_136_sub
+S0C317783	CONCOCT_136_sub
+S0C325310	CONCOCT_136_sub
+S0C328828	CONCOCT_136_sub
+S0C329977	CONCOCT_136_sub
+S0C333294	CONCOCT_136_sub
+S0C368301	CONCOCT_136_sub
+S0C383465	CONCOCT_136_sub
+S0C394511	CONCOCT_136_sub
+S0C398856	CONCOCT_136_sub
+S0C403250	CONCOCT_136_sub
+S0C425442	CONCOCT_136_sub
+S0C452562	CONCOCT_136_sub
+S0C456710	CONCOCT_136_sub
+S0C463745	CONCOCT_136_sub
+S0C528906	CONCOCT_136_sub
+S0C537221	CONCOCT_136_sub
+S0C544925	CONCOCT_136_sub
+S0C561693	CONCOCT_136_sub
+S0C600277	CONCOCT_136_sub
+S0C604275	CONCOCT_136_sub
+S0C605807	CONCOCT_136_sub
+S0C637735	CONCOCT_136_sub
+S0C638781	CONCOCT_136_sub
+S0C649134	CONCOCT_136_sub
+S0C652655	CONCOCT_136_sub
+S0C660528	CONCOCT_136_sub
+S0C677873	CONCOCT_136_sub
+S0C680313	CONCOCT_136_sub
+S0C687459	CONCOCT_136_sub
+S0C692321	CONCOCT_136_sub
+S0C713693	CONCOCT_136_sub
+S0C714168	CONCOCT_136_sub
+S0C733252	CONCOCT_136_sub
+S0C776530	CONCOCT_136_sub
+S0C783755	CONCOCT_136_sub
+S0C795045	CONCOCT_136_sub
+S0C800057	CONCOCT_136_sub
+S0C813055	CONCOCT_136_sub
+S0C899262	CONCOCT_136_sub
+S0C913746	CONCOCT_136_sub
+S0C918289	CONCOCT_136_sub
+S0C938734	CONCOCT_136_sub
+S0C975726	CONCOCT_136_sub
+S0C979641	CONCOCT_136_sub
+S0C983123	CONCOCT_136_sub
+S0C997065	CONCOCT_136_sub
+S0C1002112	CONCOCT_136_sub
+S0C1021820	CONCOCT_136_sub
+S0C1025488	CONCOCT_136_sub
+S0C1065828	CONCOCT_136_sub
+S0C1070236	CONCOCT_136_sub
+S0C1073934	CONCOCT_136_sub
+S0C1113098	CONCOCT_136_sub
+S0C1114754	CONCOCT_136_sub
+S0C1114940	CONCOCT_136_sub
+S0C1147832	CONCOCT_136_sub
+S0C1152832	CONCOCT_136_sub
+S0C1163944	CONCOCT_136_sub
+S0C1165074	CONCOCT_136_sub
+S0C1169186	CONCOCT_136_sub
+S0C1169264	CONCOCT_136_sub
+S0C1171688	CONCOCT_136_sub
+S0C1176365	CONCOCT_136_sub
+S0C1185051	CONCOCT_136_sub
+S0C1186809	CONCOCT_136_sub
+S0C1210700	CONCOCT_136_sub
+S0C1214131	CONCOCT_136_sub
+S0C1221620	CONCOCT_136_sub
+S0C1234807	CONCOCT_136_sub
+S0C1239526	CONCOCT_136_sub
+S0C1254841	CONCOCT_136_sub
+S0C1285320	CONCOCT_136_sub
+S0C1293224	CONCOCT_136_sub
+S0C1295836	CONCOCT_136_sub
+S0C1304758	CONCOCT_136_sub
+S0C1304844	CONCOCT_136_sub
+S0C1325299	CONCOCT_136_sub
+S0C1352093	CONCOCT_136_sub
+S0C1379815	CONCOCT_136_sub
+S0C1383473	CONCOCT_136_sub
+S0C1392056	CONCOCT_136_sub
+S0C1393578	CONCOCT_136_sub
+S0C1393787	CONCOCT_136_sub
+S0C1463756	CONCOCT_136_sub
+S0C1473393	CONCOCT_136_sub
+S0C105857	CONCOCT_166_sub
+S0C388714	CONCOCT_17
+S0C813	CONCOCT_170
+S0C3376	CONCOCT_170
+S0C3946	CONCOCT_170
+S0C4598	CONCOCT_170
+S0C5801	CONCOCT_170
+S0C6129	CONCOCT_170
+S0C6683	CONCOCT_170
+S0C7348	CONCOCT_170
+S0C8735	CONCOCT_170
+S0C9580	CONCOCT_170
+S0C9975	CONCOCT_170
+S0C13152	CONCOCT_170
+S0C13440	CONCOCT_170
+S0C17036	CONCOCT_170
+S0C18177	CONCOCT_170
+S0C19017	CONCOCT_170
+S0C23506	CONCOCT_170
+S0C26465	CONCOCT_170
+S0C26897	CONCOCT_170
+S0C27778	CONCOCT_170
+S0C29092	CONCOCT_170
+S0C29873	CONCOCT_170
+S0C31104	CONCOCT_170
+S0C32058	CONCOCT_170
+S0C33000	CONCOCT_170
+S0C36793	CONCOCT_170
+S0C38649	CONCOCT_170
+S0C42734	CONCOCT_170
+S0C43766	CONCOCT_170
+S0C43907	CONCOCT_170
+S0C46070	CONCOCT_170
+S0C48380	CONCOCT_170
+S0C52799	CONCOCT_170
+S0C53306	CONCOCT_170
+S0C56322	CONCOCT_170
+S0C56380	CONCOCT_170
+S0C57389	CONCOCT_170
+S0C58396	CONCOCT_170
+S0C60056	CONCOCT_170
+S0C61727	CONCOCT_170
+S0C68023	CONCOCT_170
+S0C74410	CONCOCT_170
+S0C74790	CONCOCT_170
+S0C74939	CONCOCT_170
+S0C75897	CONCOCT_170
+S0C78941	CONCOCT_170
+S0C85952	CONCOCT_170
+S0C87085	CONCOCT_170
+S0C87881	CONCOCT_170
+S0C88932	CONCOCT_170
+S0C89448	CONCOCT_170
+S0C89868	CONCOCT_170
+S0C90415	CONCOCT_170
+S0C90716	CONCOCT_170
+S0C93293	CONCOCT_170
+S0C102816	CONCOCT_170
+S0C103662	CONCOCT_170
+S0C104694	CONCOCT_170
+S0C107175	CONCOCT_170
+S0C107697	CONCOCT_170
+S0C107933	CONCOCT_170
+S0C111037	CONCOCT_170
+S0C114385	CONCOCT_170
+S0C117906	CONCOCT_170
+S0C123235	CONCOCT_170
+S0C124089	CONCOCT_170
+S0C129769	CONCOCT_170
+S0C131077	CONCOCT_170
+S0C131919	CONCOCT_170
+S0C136538	CONCOCT_170
+S0C137113	CONCOCT_170
+S0C139193	CONCOCT_170
+S0C140030	CONCOCT_170
+S0C143099	CONCOCT_170
+S0C143812	CONCOCT_170
+S0C146859	CONCOCT_170
+S0C148933	CONCOCT_170
+S0C152340	CONCOCT_170
+S0C152505	CONCOCT_170
+S0C152600	CONCOCT_170
+S0C153465	CONCOCT_170
+S0C153977	CONCOCT_170
+S0C156191	CONCOCT_170
+S0C163440	CONCOCT_170
+S0C164900	CONCOCT_170
+S0C165431	CONCOCT_170
+S0C165600	CONCOCT_170
+S0C167514	CONCOCT_170
+S0C170731	CONCOCT_170
+S0C171275	CONCOCT_170
+S0C172053	CONCOCT_170
+S0C172143	CONCOCT_170
+S0C173871	CONCOCT_170
+S0C176168	CONCOCT_170
+S0C176457	CONCOCT_170
+S0C177012	CONCOCT_170
+S0C177016	CONCOCT_170
+S0C180505	CONCOCT_170
+S0C184052	CONCOCT_170
+S0C187627	CONCOCT_170
+S0C189589	CONCOCT_170
+S0C190286	CONCOCT_170
+S0C190997	CONCOCT_170
+S0C192169	CONCOCT_170
+S0C192913	CONCOCT_170
+S0C193235	CONCOCT_170
+S0C197282	CONCOCT_170
+S0C199440	CONCOCT_170
+S0C200742	CONCOCT_170
+S0C202327	CONCOCT_170
+S0C203916	CONCOCT_170
+S0C207418	CONCOCT_170
+S0C214076	CONCOCT_170
+S0C214145	CONCOCT_170
+S0C214674	CONCOCT_170
+S0C215796	CONCOCT_170
+S0C218011	CONCOCT_170
+S0C223793	CONCOCT_170
+S0C224911	CONCOCT_170
+S0C226616	CONCOCT_170
+S0C226964	CONCOCT_170
+S0C232179	CONCOCT_170
+S0C233703	CONCOCT_170
+S0C235269	CONCOCT_170
+S0C244843	CONCOCT_170
+S0C245988	CONCOCT_170
+S0C247775	CONCOCT_170
+S0C248142	CONCOCT_170
+S0C248525	CONCOCT_170
+S0C250249	CONCOCT_170
+S0C250769	CONCOCT_170
+S0C261957	CONCOCT_170
+S0C267920	CONCOCT_170
+S0C268515	CONCOCT_170
+S0C271398	CONCOCT_170
+S0C273474	CONCOCT_170
+S0C273642	CONCOCT_170
+S0C273909	CONCOCT_170
+S0C282614	CONCOCT_170
+S0C284421	CONCOCT_170
+S0C284529	CONCOCT_170
+S0C286800	CONCOCT_170
+S0C289235	CONCOCT_170
+S0C290438	CONCOCT_170
+S0C291627	CONCOCT_170
+S0C296643	CONCOCT_170
+S0C297219	CONCOCT_170
+S0C302272	CONCOCT_170
+S0C303794	CONCOCT_170
+S0C307970	CONCOCT_170
+S0C310701	CONCOCT_170
+S0C310818	CONCOCT_170
+S0C313722	CONCOCT_170
+S0C313791	CONCOCT_170
+S0C315247	CONCOCT_170
+S0C316931	CONCOCT_170
+S0C317968	CONCOCT_170
+S0C319375	CONCOCT_170
+S0C320040	CONCOCT_170
+S0C320442	CONCOCT_170
+S0C328161	CONCOCT_170
+S0C328842	CONCOCT_170
+S0C329759	CONCOCT_170
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/kraken2.tsv	Sat Feb 08 11:33:03 2025 +0000
@@ -0,0 +1,317 @@
+C	S0C67443	1415774
+U	S0C145665	0
+U	S0C179008	0
+U	S0C285214	0
+C	S0C309108	1415774
+U	S0C310129	0
+C	S0C336019	1415774
+U	S0C388550	0
+C	S0C495394	1415774
+C	S0C511360	1415774
+C	S0C577842	1415774
+C	S0C596918	1415774
+U	S0C603398	0
+U	S0C754713	0
+U	S0C938786	0
+C	S0C967914	1415774
+C	S0C974893	1415774
+U	S0C1006901	0
+U	S0C1018235	0
+U	S0C1018552	0
+C	S0C1049501	1415774
+C	S0C1067275	1415774
+U	S0C1069633	0
+U	S0C1089023	0
+U	S0C1146406	0
+U	S0C1154753	0
+U	S0C1194005	0
+U	S0C1226618	0
+C	S0C1282023	1415774
+C	S0C1332000	1415774
+C	S0C1359995	1415774
+U	S0C1396765	0
+U	S0C1472996	0
+U	S0C1475640	0
+C	S0C2285	897
+C	S0C12513	897
+C	S0C13841	897
+C	S0C15954	897
+C	S0C33046	897
+C	S0C38240	897
+C	S0C40714	897
+C	S0C67745	897
+C	S0C96249	897
+C	S0C105628	897
+C	S0C121147	897
+C	S0C123278	897
+C	S0C128492	897
+C	S0C142447	897
+C	S0C143656	897
+C	S0C146090	897
+C	S0C146468	897
+C	S0C148477	897
+C	S0C154116	897
+C	S0C154853	897
+C	S0C183450	897
+C	S0C206740	897
+C	S0C217759	897
+C	S0C218807	897
+C	S0C232692	897
+C	S0C241720	897
+C	S0C254412	897
+C	S0C255416	897
+C	S0C257539	897
+C	S0C271698	897
+C	S0C273417	897
+C	S0C277828	897
+C	S0C292193	897
+C	S0C317783	897
+C	S0C325310	897
+C	S0C328828	897
+C	S0C329977	897
+C	S0C333294	897
+C	S0C368301	897
+C	S0C383465	897
+C	S0C394511	897
+C	S0C398856	897
+C	S0C403250	897
+C	S0C425442	897
+C	S0C452562	897
+C	S0C456710	897
+C	S0C463745	897
+C	S0C528906	897
+C	S0C537221	897
+C	S0C544925	897
+C	S0C561693	897
+C	S0C600277	897
+C	S0C604275	897
+C	S0C605807	897
+C	S0C637735	897
+C	S0C638781	897
+C	S0C649134	897
+C	S0C652655	897
+C	S0C660528	897
+C	S0C677873	897
+C	S0C680313	897
+C	S0C687459	897
+C	S0C692321	897
+C	S0C713693	897
+C	S0C714168	897
+C	S0C733252	897
+C	S0C776530	897
+C	S0C783755	881
+C	S0C795045	897
+C	S0C800057	897
+C	S0C813055	897
+C	S0C899262	897
+C	S0C913746	897
+C	S0C918289	897
+C	S0C938734	897
+C	S0C975726	897
+C	S0C979641	897
+C	S0C983123	897
+C	S0C997065	897
+C	S0C1002112	897
+C	S0C1021820	897
+C	S0C1025488	897
+C	S0C1065828	897
+C	S0C1070236	897
+C	S0C1073934	897
+C	S0C1113098	897
+C	S0C1114754	897
+C	S0C1114940	897
+C	S0C1147832	897
+C	S0C1152832	897
+C	S0C1163944	897
+C	S0C1165074	897
+C	S0C1169186	897
+C	S0C1169264	897
+C	S0C1171688	897
+C	S0C1176365	897
+C	S0C1185051	897
+C	S0C1186809	897
+C	S0C1210700	897
+C	S0C1214131	897
+C	S0C1221620	897
+C	S0C1234807	897
+C	S0C1239526	897
+C	S0C1254841	562
+C	S0C1285320	897
+C	S0C1293224	897
+C	S0C1295836	897
+C	S0C1304758	897
+C	S0C1304844	897
+C	S0C1325299	897
+C	S0C1352093	897
+C	S0C1379815	897
+C	S0C1383473	897
+C	S0C1392056	897
+C	S0C1393578	897
+C	S0C1393787	897
+C	S0C1463756	897
+C	S0C1473393	897
+C	S0C105857	1335757
+C	S0C388714	1343739
+C	S0C813	1188229
+C	S0C3376	1188229
+C	S0C3946	1188229
+C	S0C4598	1188229
+C	S0C5801	1188229
+C	S0C6129	1188229
+C	S0C6683	1188229
+C	S0C7348	1188229
+C	S0C8735	1188229
+C	S0C9580	1188229
+C	S0C9975	1188229
+C	S0C13152	1188229
+C	S0C13440	1188229
+C	S0C17036	1188229
+C	S0C18177	1188229
+C	S0C19017	1188229
+C	S0C23506	1188229
+C	S0C26465	1188229
+C	S0C26897	1188229
+C	S0C27778	1188229
+C	S0C29092	1188229
+C	S0C29873	1188229
+C	S0C31104	1188229
+C	S0C32058	1188229
+C	S0C33000	1188229
+C	S0C36793	1188229
+C	S0C38649	1188229
+C	S0C42734	1188229
+C	S0C43766	1188229
+C	S0C43907	1188229
+C	S0C46070	1188229
+C	S0C48380	1188229
+C	S0C52799	1188229
+C	S0C53306	1188229
+C	S0C56322	1188229
+C	S0C56380	1188229
+C	S0C57389	1188229
+C	S0C58396	1188229
+C	S0C60056	1188229
+C	S0C61727	1188229
+C	S0C68023	1188229
+C	S0C74410	1188229
+C	S0C74790	1188229
+C	S0C74939	1188229
+C	S0C75897	1188229
+C	S0C78941	1188229
+C	S0C85952	1188229
+C	S0C87085	1188229
+C	S0C87881	1188229
+C	S0C88932	1188229
+C	S0C89448	1188229
+C	S0C89868	1188229
+C	S0C90415	1188229
+C	S0C90716	1188229
+C	S0C93293	1188229
+C	S0C102816	1188229
+C	S0C103662	1188229
+C	S0C104694	1188229
+C	S0C107175	1188229
+C	S0C107697	1188229
+C	S0C107933	1188229
+C	S0C111037	1188229
+C	S0C114385	1188229
+C	S0C117906	1188229
+C	S0C123235	1188229
+C	S0C124089	1188229
+C	S0C129769	1188229
+C	S0C131077	1188229
+C	S0C131919	1188229
+C	S0C136538	1188229
+C	S0C137113	1188229
+C	S0C139193	1188229
+C	S0C140030	1188229
+C	S0C143099	1188229
+C	S0C143812	1188229
+C	S0C146859	1188229
+C	S0C148933	1188229
+C	S0C152340	1188229
+C	S0C152505	1188229
+C	S0C152600	1188229
+C	S0C153465	1188229
+C	S0C153977	1188229
+C	S0C156191	1188229
+C	S0C163440	1188229
+C	S0C164900	1188229
+C	S0C165431	1188229
+C	S0C165600	1188229
+C	S0C167514	1188229
+C	S0C170731	1188229
+C	S0C171275	1188229
+C	S0C172053	1188229
+C	S0C172143	1188229
+C	S0C173871	1188229
+C	S0C176168	1188229
+C	S0C176457	1188229
+C	S0C177012	1188229
+C	S0C177016	1188229
+C	S0C180505	1188229
+C	S0C184052	1188229
+C	S0C187627	1188229
+C	S0C189589	1188229
+C	S0C190286	1188229
+C	S0C190997	1188229
+C	S0C192169	1188229
+C	S0C192913	1188229
+C	S0C193235	1188229
+C	S0C197282	1188229
+C	S0C199440	1188229
+C	S0C200742	1188229
+C	S0C202327	1188229
+C	S0C203916	1188229
+C	S0C207418	1188229
+C	S0C214076	1188229
+C	S0C214145	1188229
+C	S0C214674	1188229
+C	S0C215796	1188229
+C	S0C218011	1188229
+C	S0C223793	1188229
+C	S0C224911	1188229
+C	S0C226616	1188229
+C	S0C226964	1188229
+C	S0C232179	1188229
+C	S0C233703	1188229
+C	S0C235269	1188229
+C	S0C244843	1188229
+C	S0C245988	1188229
+C	S0C247775	1188229
+C	S0C248142	1188229
+C	S0C248525	1188229
+C	S0C250249	1188229
+C	S0C250769	1188229
+C	S0C261957	1188229
+C	S0C267920	1188229
+C	S0C268515	1188229
+C	S0C271398	1188229
+C	S0C273474	1188229
+C	S0C273642	1188229
+C	S0C273909	1188229
+C	S0C282614	1188229
+C	S0C284421	1188229
+C	S0C284529	1188229
+C	S0C286800	1188229
+C	S0C289235	1188229
+C	S0C290438	1188229
+C	S0C291627	1188229
+C	S0C296643	1188229
+C	S0C297219	1188229
+C	S0C302272	1188229
+C	S0C303794	1188229
+C	S0C307970	1188229
+C	S0C310701	1188229
+C	S0C310818	1188229
+C	S0C313722	1188229
+C	S0C313791	1188229
+C	S0C315247	1188229
+C	S0C316931	1188229
+C	S0C317968	1188229
+C	S0C319375	1188229
+C	S0C320040	1188229
+C	S0C320442	1188229
+C	S0C328161	1188229
+C	S0C328842	1188229
+C	S0C329759	1188229
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/modified_biobox_file_bin.tsv	Sat Feb 08 11:33:03 2025 +0000
@@ -0,0 +1,321 @@
+#CAMI Format for Binning
+@Version:0.9.0
+@SampleID:_SAMPLEID_
+@@SEQUENCEID	BINID	TAXID
+S0C67443	CONCOCT_117	1485
+S0C145665	CONCOCT_117	1485
+S0C179008	CONCOCT_117	1485
+S0C285214	CONCOCT_117	1485
+S0C309108	CONCOCT_117	1485
+S0C310129	CONCOCT_117	1485
+S0C336019	CONCOCT_117	1485
+S0C388550	CONCOCT_117	1485
+S0C495394	CONCOCT_117	1485
+S0C511360	CONCOCT_117	1485
+S0C577842	CONCOCT_117	1485
+S0C596918	CONCOCT_117	1485
+S0C603398	CONCOCT_117	1485
+S0C754713	CONCOCT_117	1485
+S0C938786	CONCOCT_117	1485
+S0C967914	CONCOCT_117	1485
+S0C974893	CONCOCT_117	1485
+S0C1006901	CONCOCT_117	1485
+S0C1018235	CONCOCT_117	1485
+S0C1018552	CONCOCT_117	1485
+S0C1049501	CONCOCT_117	1485
+S0C1067275	CONCOCT_117	1485
+S0C1069633	CONCOCT_117	1485
+S0C1089023	CONCOCT_117	1485
+S0C1146406	CONCOCT_117	1485
+S0C1154753	CONCOCT_117	1485
+S0C1194005	CONCOCT_117	1485
+S0C1226618	CONCOCT_117	1485
+S0C1282023	CONCOCT_117	1485
+S0C1332000	CONCOCT_117	1485
+S0C1359995	CONCOCT_117	1485
+S0C1396765	CONCOCT_117	1485
+S0C1472996	CONCOCT_117	1485
+S0C1475640	CONCOCT_117	1485
+S0C2285	CONCOCT_136_sub	897
+S0C12513	CONCOCT_136_sub	897
+S0C13841	CONCOCT_136_sub	897
+S0C15954	CONCOCT_136_sub	897
+S0C33046	CONCOCT_136_sub	897
+S0C38240	CONCOCT_136_sub	897
+S0C40714	CONCOCT_136_sub	897
+S0C67745	CONCOCT_136_sub	897
+S0C96249	CONCOCT_136_sub	897
+S0C105628	CONCOCT_136_sub	897
+S0C121147	CONCOCT_136_sub	897
+S0C123278	CONCOCT_136_sub	897
+S0C128492	CONCOCT_136_sub	897
+S0C142447	CONCOCT_136_sub	897
+S0C143656	CONCOCT_136_sub	897
+S0C146090	CONCOCT_136_sub	897
+S0C146468	CONCOCT_136_sub	897
+S0C148477	CONCOCT_136_sub	897
+S0C154116	CONCOCT_136_sub	897
+S0C154853	CONCOCT_136_sub	897
+S0C183450	CONCOCT_136_sub	897
+S0C206740	CONCOCT_136_sub	897
+S0C217759	CONCOCT_136_sub	897
+S0C218807	CONCOCT_136_sub	897
+S0C232692	CONCOCT_136_sub	897
+S0C241720	CONCOCT_136_sub	897
+S0C254412	CONCOCT_136_sub	897
+S0C255416	CONCOCT_136_sub	897
+S0C257539	CONCOCT_136_sub	897
+S0C271698	CONCOCT_136_sub	897
+S0C273417	CONCOCT_136_sub	897
+S0C277828	CONCOCT_136_sub	897
+S0C292193	CONCOCT_136_sub	897
+S0C317783	CONCOCT_136_sub	897
+S0C325310	CONCOCT_136_sub	897
+S0C328828	CONCOCT_136_sub	897
+S0C329977	CONCOCT_136_sub	897
+S0C333294	CONCOCT_136_sub	897
+S0C368301	CONCOCT_136_sub	897
+S0C383465	CONCOCT_136_sub	897
+S0C394511	CONCOCT_136_sub	897
+S0C398856	CONCOCT_136_sub	897
+S0C403250	CONCOCT_136_sub	897
+S0C425442	CONCOCT_136_sub	897
+S0C452562	CONCOCT_136_sub	897
+S0C456710	CONCOCT_136_sub	897
+S0C463745	CONCOCT_136_sub	897
+S0C528906	CONCOCT_136_sub	897
+S0C537221	CONCOCT_136_sub	897
+S0C544925	CONCOCT_136_sub	897
+S0C561693	CONCOCT_136_sub	897
+S0C600277	CONCOCT_136_sub	897
+S0C604275	CONCOCT_136_sub	897
+S0C605807	CONCOCT_136_sub	897
+S0C637735	CONCOCT_136_sub	897
+S0C638781	CONCOCT_136_sub	897
+S0C649134	CONCOCT_136_sub	897
+S0C652655	CONCOCT_136_sub	897
+S0C660528	CONCOCT_136_sub	897
+S0C677873	CONCOCT_136_sub	897
+S0C680313	CONCOCT_136_sub	897
+S0C687459	CONCOCT_136_sub	897
+S0C692321	CONCOCT_136_sub	897
+S0C713693	CONCOCT_136_sub	897
+S0C714168	CONCOCT_136_sub	897
+S0C733252	CONCOCT_136_sub	897
+S0C776530	CONCOCT_136_sub	897
+S0C783755	CONCOCT_136_sub	897
+S0C795045	CONCOCT_136_sub	897
+S0C800057	CONCOCT_136_sub	897
+S0C813055	CONCOCT_136_sub	897
+S0C899262	CONCOCT_136_sub	897
+S0C913746	CONCOCT_136_sub	897
+S0C918289	CONCOCT_136_sub	897
+S0C938734	CONCOCT_136_sub	897
+S0C975726	CONCOCT_136_sub	897
+S0C979641	CONCOCT_136_sub	897
+S0C983123	CONCOCT_136_sub	897
+S0C997065	CONCOCT_136_sub	897
+S0C1002112	CONCOCT_136_sub	897
+S0C1021820	CONCOCT_136_sub	897
+S0C1025488	CONCOCT_136_sub	897
+S0C1065828	CONCOCT_136_sub	897
+S0C1070236	CONCOCT_136_sub	897
+S0C1073934	CONCOCT_136_sub	897
+S0C1113098	CONCOCT_136_sub	897
+S0C1114754	CONCOCT_136_sub	897
+S0C1114940	CONCOCT_136_sub	897
+S0C1147832	CONCOCT_136_sub	897
+S0C1152832	CONCOCT_136_sub	897
+S0C1163944	CONCOCT_136_sub	897
+S0C1165074	CONCOCT_136_sub	897
+S0C1169186	CONCOCT_136_sub	897
+S0C1169264	CONCOCT_136_sub	897
+S0C1171688	CONCOCT_136_sub	897
+S0C1176365	CONCOCT_136_sub	897
+S0C1185051	CONCOCT_136_sub	897
+S0C1186809	CONCOCT_136_sub	897
+S0C1210700	CONCOCT_136_sub	897
+S0C1214131	CONCOCT_136_sub	897
+S0C1221620	CONCOCT_136_sub	897
+S0C1234807	CONCOCT_136_sub	897
+S0C1239526	CONCOCT_136_sub	897
+S0C1254841	CONCOCT_136_sub	897
+S0C1285320	CONCOCT_136_sub	897
+S0C1293224	CONCOCT_136_sub	897
+S0C1295836	CONCOCT_136_sub	897
+S0C1304758	CONCOCT_136_sub	897
+S0C1304844	CONCOCT_136_sub	897
+S0C1325299	CONCOCT_136_sub	897
+S0C1352093	CONCOCT_136_sub	897
+S0C1379815	CONCOCT_136_sub	897
+S0C1383473	CONCOCT_136_sub	897
+S0C1392056	CONCOCT_136_sub	897
+S0C1393578	CONCOCT_136_sub	897
+S0C1393787	CONCOCT_136_sub	897
+S0C1463756	CONCOCT_136_sub	897
+S0C1473393	CONCOCT_136_sub	897
+S0C105857	CONCOCT_166_sub	1335757
+S0C388714	CONCOCT_17	971279
+S0C813	CONCOCT_170	1188228
+S0C3376	CONCOCT_170	1188228
+S0C3946	CONCOCT_170	1188228
+S0C4598	CONCOCT_170	1188228
+S0C5801	CONCOCT_170	1188228
+S0C6129	CONCOCT_170	1188228
+S0C6683	CONCOCT_170	1188228
+S0C7348	CONCOCT_170	1188228
+S0C8735	CONCOCT_170	1188228
+S0C9580	CONCOCT_170	1188228
+S0C9975	CONCOCT_170	1188228
+S0C13152	CONCOCT_170	1188228
+S0C13440	CONCOCT_170	1188228
+S0C17036	CONCOCT_170	1188228
+S0C18177	CONCOCT_170	1188228
+S0C19017	CONCOCT_170	1188228
+S0C23506	CONCOCT_170	1188228
+S0C26465	CONCOCT_170	1188228
+S0C26897	CONCOCT_170	1188228
+S0C27778	CONCOCT_170	1188228
+S0C29092	CONCOCT_170	1188228
+S0C29873	CONCOCT_170	1188228
+S0C31104	CONCOCT_170	1188228
+S0C32058	CONCOCT_170	1188228
+S0C33000	CONCOCT_170	1188228
+S0C36793	CONCOCT_170	1188228
+S0C38649	CONCOCT_170	1188228
+S0C42734	CONCOCT_170	1188228
+S0C43766	CONCOCT_170	1188228
+S0C43907	CONCOCT_170	1188228
+S0C46070	CONCOCT_170	1188228
+S0C48380	CONCOCT_170	1188228
+S0C52799	CONCOCT_170	1188228
+S0C53306	CONCOCT_170	1188228
+S0C56322	CONCOCT_170	1188228
+S0C56380	CONCOCT_170	1188228
+S0C57389	CONCOCT_170	1188228
+S0C58396	CONCOCT_170	1188228
+S0C60056	CONCOCT_170	1188228
+S0C61727	CONCOCT_170	1188228
+S0C68023	CONCOCT_170	1188228
+S0C74410	CONCOCT_170	1188228
+S0C74790	CONCOCT_170	1188228
+S0C74939	CONCOCT_170	1188228
+S0C75897	CONCOCT_170	1188228
+S0C78941	CONCOCT_170	1188228
+S0C85952	CONCOCT_170	1188228
+S0C87085	CONCOCT_170	1188228
+S0C87881	CONCOCT_170	1188228
+S0C88932	CONCOCT_170	1188228
+S0C89448	CONCOCT_170	1188228
+S0C89868	CONCOCT_170	1188228
+S0C90415	CONCOCT_170	1188228
+S0C90716	CONCOCT_170	1188228
+S0C93293	CONCOCT_170	1188228
+S0C102816	CONCOCT_170	1188228
+S0C103662	CONCOCT_170	1188228
+S0C104694	CONCOCT_170	1188228
+S0C107175	CONCOCT_170	1188228
+S0C107697	CONCOCT_170	1188228
+S0C107933	CONCOCT_170	1188228
+S0C111037	CONCOCT_170	1188228
+S0C114385	CONCOCT_170	1188228
+S0C117906	CONCOCT_170	1188228
+S0C123235	CONCOCT_170	1188228
+S0C124089	CONCOCT_170	1188228
+S0C129769	CONCOCT_170	1188228
+S0C131077	CONCOCT_170	1188228
+S0C131919	CONCOCT_170	1188228
+S0C136538	CONCOCT_170	1188228
+S0C137113	CONCOCT_170	1188228
+S0C139193	CONCOCT_170	1188228
+S0C140030	CONCOCT_170	1188228
+S0C143099	CONCOCT_170	1188228
+S0C143812	CONCOCT_170	1188228
+S0C146859	CONCOCT_170	1188228
+S0C148933	CONCOCT_170	1188228
+S0C152340	CONCOCT_170	1188228
+S0C152505	CONCOCT_170	1188228
+S0C152600	CONCOCT_170	1188228
+S0C153465	CONCOCT_170	1188228
+S0C153977	CONCOCT_170	1188228
+S0C156191	CONCOCT_170	1188228
+S0C163440	CONCOCT_170	1188228
+S0C164900	CONCOCT_170	1188228
+S0C165431	CONCOCT_170	1188228
+S0C165600	CONCOCT_170	1188228
+S0C167514	CONCOCT_170	1188228
+S0C170731	CONCOCT_170	1188228
+S0C171275	CONCOCT_170	1188228
+S0C172053	CONCOCT_170	1188228
+S0C172143	CONCOCT_170	1188228
+S0C173871	CONCOCT_170	1188228
+S0C176168	CONCOCT_170	1188228
+S0C176457	CONCOCT_170	1188228
+S0C177012	CONCOCT_170	1188228
+S0C177016	CONCOCT_170	1188228
+S0C180505	CONCOCT_170	1188228
+S0C184052	CONCOCT_170	1188228
+S0C187627	CONCOCT_170	1188228
+S0C189589	CONCOCT_170	1188228
+S0C190286	CONCOCT_170	1188228
+S0C190997	CONCOCT_170	1188228
+S0C192169	CONCOCT_170	1188228
+S0C192913	CONCOCT_170	1188228
+S0C193235	CONCOCT_170	1188228
+S0C197282	CONCOCT_170	1188228
+S0C199440	CONCOCT_170	1188228
+S0C200742	CONCOCT_170	1188228
+S0C202327	CONCOCT_170	1188228
+S0C203916	CONCOCT_170	1188228
+S0C207418	CONCOCT_170	1188228
+S0C214076	CONCOCT_170	1188228
+S0C214145	CONCOCT_170	1188228
+S0C214674	CONCOCT_170	1188228
+S0C215796	CONCOCT_170	1188228
+S0C218011	CONCOCT_170	1188228
+S0C223793	CONCOCT_170	1188228
+S0C224911	CONCOCT_170	1188228
+S0C226616	CONCOCT_170	1188228
+S0C226964	CONCOCT_170	1188228
+S0C232179	CONCOCT_170	1188228
+S0C233703	CONCOCT_170	1188228
+S0C235269	CONCOCT_170	1188228
+S0C244843	CONCOCT_170	1188228
+S0C245988	CONCOCT_170	1188228
+S0C247775	CONCOCT_170	1188228
+S0C248142	CONCOCT_170	1188228
+S0C248525	CONCOCT_170	1188228
+S0C250249	CONCOCT_170	1188228
+S0C250769	CONCOCT_170	1188228
+S0C261957	CONCOCT_170	1188228
+S0C267920	CONCOCT_170	1188228
+S0C268515	CONCOCT_170	1188228
+S0C271398	CONCOCT_170	1188228
+S0C273474	CONCOCT_170	1188228
+S0C273642	CONCOCT_170	1188228
+S0C273909	CONCOCT_170	1188228
+S0C282614	CONCOCT_170	1188228
+S0C284421	CONCOCT_170	1188228
+S0C284529	CONCOCT_170	1188228
+S0C286800	CONCOCT_170	1188228
+S0C289235	CONCOCT_170	1188228
+S0C290438	CONCOCT_170	1188228
+S0C291627	CONCOCT_170	1188228
+S0C296643	CONCOCT_170	1188228
+S0C297219	CONCOCT_170	1188228
+S0C302272	CONCOCT_170	1188228
+S0C303794	CONCOCT_170	1188228
+S0C307970	CONCOCT_170	1188228
+S0C310701	CONCOCT_170	1188228
+S0C310818	CONCOCT_170	1188228
+S0C313722	CONCOCT_170	1188228
+S0C313791	CONCOCT_170	1188228
+S0C315247	CONCOCT_170	1188228
+S0C316931	CONCOCT_170	1188228
+S0C317968	CONCOCT_170	1188228
+S0C319375	CONCOCT_170	1188228
+S0C320040	CONCOCT_170	1188228
+S0C320442	CONCOCT_170	1188228
+S0C328161	CONCOCT_170	1188228
+S0C328842	CONCOCT_170	1188228
+S0C329759	CONCOCT_170	1188228
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/modified_biobox_file_contig.tsv	Sat Feb 08 11:33:03 2025 +0000
@@ -0,0 +1,321 @@
+#CAMI Format for Binning
+@Version:0.9.0
+@SampleID:_SAMPLEID_
+@@SEQUENCEID	BINID	TAXID
+S0C67443	CONCOCT_117	1415774
+S0C145665	CONCOCT_117	0
+S0C179008	CONCOCT_117	0
+S0C285214	CONCOCT_117	0
+S0C309108	CONCOCT_117	1415774
+S0C310129	CONCOCT_117	0
+S0C336019	CONCOCT_117	1415774
+S0C388550	CONCOCT_117	0
+S0C495394	CONCOCT_117	1415774
+S0C511360	CONCOCT_117	1415774
+S0C577842	CONCOCT_117	1415774
+S0C596918	CONCOCT_117	1415774
+S0C603398	CONCOCT_117	0
+S0C754713	CONCOCT_117	0
+S0C938786	CONCOCT_117	0
+S0C967914	CONCOCT_117	1415774
+S0C974893	CONCOCT_117	1415774
+S0C1006901	CONCOCT_117	0
+S0C1018235	CONCOCT_117	0
+S0C1018552	CONCOCT_117	0
+S0C1049501	CONCOCT_117	1415774
+S0C1067275	CONCOCT_117	1415774
+S0C1069633	CONCOCT_117	0
+S0C1089023	CONCOCT_117	0
+S0C1146406	CONCOCT_117	0
+S0C1154753	CONCOCT_117	0
+S0C1194005	CONCOCT_117	0
+S0C1226618	CONCOCT_117	0
+S0C1282023	CONCOCT_117	1415774
+S0C1332000	CONCOCT_117	1415774
+S0C1359995	CONCOCT_117	1415774
+S0C1396765	CONCOCT_117	0
+S0C1472996	CONCOCT_117	0
+S0C1475640	CONCOCT_117	0
+S0C2285	CONCOCT_136_sub	897
+S0C12513	CONCOCT_136_sub	897
+S0C13841	CONCOCT_136_sub	897
+S0C15954	CONCOCT_136_sub	897
+S0C33046	CONCOCT_136_sub	897
+S0C38240	CONCOCT_136_sub	897
+S0C40714	CONCOCT_136_sub	897
+S0C67745	CONCOCT_136_sub	897
+S0C96249	CONCOCT_136_sub	897
+S0C105628	CONCOCT_136_sub	897
+S0C121147	CONCOCT_136_sub	897
+S0C123278	CONCOCT_136_sub	897
+S0C128492	CONCOCT_136_sub	897
+S0C142447	CONCOCT_136_sub	897
+S0C143656	CONCOCT_136_sub	897
+S0C146090	CONCOCT_136_sub	897
+S0C146468	CONCOCT_136_sub	897
+S0C148477	CONCOCT_136_sub	897
+S0C154116	CONCOCT_136_sub	897
+S0C154853	CONCOCT_136_sub	897
+S0C183450	CONCOCT_136_sub	897
+S0C206740	CONCOCT_136_sub	897
+S0C217759	CONCOCT_136_sub	897
+S0C218807	CONCOCT_136_sub	897
+S0C232692	CONCOCT_136_sub	897
+S0C241720	CONCOCT_136_sub	897
+S0C254412	CONCOCT_136_sub	897
+S0C255416	CONCOCT_136_sub	897
+S0C257539	CONCOCT_136_sub	897
+S0C271698	CONCOCT_136_sub	897
+S0C273417	CONCOCT_136_sub	897
+S0C277828	CONCOCT_136_sub	897
+S0C292193	CONCOCT_136_sub	897
+S0C317783	CONCOCT_136_sub	897
+S0C325310	CONCOCT_136_sub	897
+S0C328828	CONCOCT_136_sub	897
+S0C329977	CONCOCT_136_sub	897
+S0C333294	CONCOCT_136_sub	897
+S0C368301	CONCOCT_136_sub	897
+S0C383465	CONCOCT_136_sub	897
+S0C394511	CONCOCT_136_sub	897
+S0C398856	CONCOCT_136_sub	897
+S0C403250	CONCOCT_136_sub	897
+S0C425442	CONCOCT_136_sub	897
+S0C452562	CONCOCT_136_sub	897
+S0C456710	CONCOCT_136_sub	897
+S0C463745	CONCOCT_136_sub	897
+S0C528906	CONCOCT_136_sub	897
+S0C537221	CONCOCT_136_sub	897
+S0C544925	CONCOCT_136_sub	897
+S0C561693	CONCOCT_136_sub	897
+S0C600277	CONCOCT_136_sub	897
+S0C604275	CONCOCT_136_sub	897
+S0C605807	CONCOCT_136_sub	897
+S0C637735	CONCOCT_136_sub	897
+S0C638781	CONCOCT_136_sub	897
+S0C649134	CONCOCT_136_sub	897
+S0C652655	CONCOCT_136_sub	897
+S0C660528	CONCOCT_136_sub	897
+S0C677873	CONCOCT_136_sub	897
+S0C680313	CONCOCT_136_sub	897
+S0C687459	CONCOCT_136_sub	897
+S0C692321	CONCOCT_136_sub	897
+S0C713693	CONCOCT_136_sub	897
+S0C714168	CONCOCT_136_sub	897
+S0C733252	CONCOCT_136_sub	897
+S0C776530	CONCOCT_136_sub	897
+S0C783755	CONCOCT_136_sub	881
+S0C795045	CONCOCT_136_sub	897
+S0C800057	CONCOCT_136_sub	897
+S0C813055	CONCOCT_136_sub	897
+S0C899262	CONCOCT_136_sub	897
+S0C913746	CONCOCT_136_sub	897
+S0C918289	CONCOCT_136_sub	897
+S0C938734	CONCOCT_136_sub	897
+S0C975726	CONCOCT_136_sub	897
+S0C979641	CONCOCT_136_sub	897
+S0C983123	CONCOCT_136_sub	897
+S0C997065	CONCOCT_136_sub	897
+S0C1002112	CONCOCT_136_sub	897
+S0C1021820	CONCOCT_136_sub	897
+S0C1025488	CONCOCT_136_sub	897
+S0C1065828	CONCOCT_136_sub	897
+S0C1070236	CONCOCT_136_sub	897
+S0C1073934	CONCOCT_136_sub	897
+S0C1113098	CONCOCT_136_sub	897
+S0C1114754	CONCOCT_136_sub	897
+S0C1114940	CONCOCT_136_sub	897
+S0C1147832	CONCOCT_136_sub	897
+S0C1152832	CONCOCT_136_sub	897
+S0C1163944	CONCOCT_136_sub	897
+S0C1165074	CONCOCT_136_sub	897
+S0C1169186	CONCOCT_136_sub	897
+S0C1169264	CONCOCT_136_sub	897
+S0C1171688	CONCOCT_136_sub	897
+S0C1176365	CONCOCT_136_sub	897
+S0C1185051	CONCOCT_136_sub	897
+S0C1186809	CONCOCT_136_sub	897
+S0C1210700	CONCOCT_136_sub	897
+S0C1214131	CONCOCT_136_sub	897
+S0C1221620	CONCOCT_136_sub	897
+S0C1234807	CONCOCT_136_sub	897
+S0C1239526	CONCOCT_136_sub	897
+S0C1254841	CONCOCT_136_sub	562
+S0C1285320	CONCOCT_136_sub	897
+S0C1293224	CONCOCT_136_sub	897
+S0C1295836	CONCOCT_136_sub	897
+S0C1304758	CONCOCT_136_sub	897
+S0C1304844	CONCOCT_136_sub	897
+S0C1325299	CONCOCT_136_sub	897
+S0C1352093	CONCOCT_136_sub	897
+S0C1379815	CONCOCT_136_sub	897
+S0C1383473	CONCOCT_136_sub	897
+S0C1392056	CONCOCT_136_sub	897
+S0C1393578	CONCOCT_136_sub	897
+S0C1393787	CONCOCT_136_sub	897
+S0C1463756	CONCOCT_136_sub	897
+S0C1473393	CONCOCT_136_sub	897
+S0C105857	CONCOCT_166_sub	1335757
+S0C388714	CONCOCT_17	1343739
+S0C813	CONCOCT_170	1188229
+S0C3376	CONCOCT_170	1188229
+S0C3946	CONCOCT_170	1188229
+S0C4598	CONCOCT_170	1188229
+S0C5801	CONCOCT_170	1188229
+S0C6129	CONCOCT_170	1188229
+S0C6683	CONCOCT_170	1188229
+S0C7348	CONCOCT_170	1188229
+S0C8735	CONCOCT_170	1188229
+S0C9580	CONCOCT_170	1188229
+S0C9975	CONCOCT_170	1188229
+S0C13152	CONCOCT_170	1188229
+S0C13440	CONCOCT_170	1188229
+S0C17036	CONCOCT_170	1188229
+S0C18177	CONCOCT_170	1188229
+S0C19017	CONCOCT_170	1188229
+S0C23506	CONCOCT_170	1188229
+S0C26465	CONCOCT_170	1188229
+S0C26897	CONCOCT_170	1188229
+S0C27778	CONCOCT_170	1188229
+S0C29092	CONCOCT_170	1188229
+S0C29873	CONCOCT_170	1188229
+S0C31104	CONCOCT_170	1188229
+S0C32058	CONCOCT_170	1188229
+S0C33000	CONCOCT_170	1188229
+S0C36793	CONCOCT_170	1188229
+S0C38649	CONCOCT_170	1188229
+S0C42734	CONCOCT_170	1188229
+S0C43766	CONCOCT_170	1188229
+S0C43907	CONCOCT_170	1188229
+S0C46070	CONCOCT_170	1188229
+S0C48380	CONCOCT_170	1188229
+S0C52799	CONCOCT_170	1188229
+S0C53306	CONCOCT_170	1188229
+S0C56322	CONCOCT_170	1188229
+S0C56380	CONCOCT_170	1188229
+S0C57389	CONCOCT_170	1188229
+S0C58396	CONCOCT_170	1188229
+S0C60056	CONCOCT_170	1188229
+S0C61727	CONCOCT_170	1188229
+S0C68023	CONCOCT_170	1188229
+S0C74410	CONCOCT_170	1188229
+S0C74790	CONCOCT_170	1188229
+S0C74939	CONCOCT_170	1188229
+S0C75897	CONCOCT_170	1188229
+S0C78941	CONCOCT_170	1188229
+S0C85952	CONCOCT_170	1188229
+S0C87085	CONCOCT_170	1188229
+S0C87881	CONCOCT_170	1188229
+S0C88932	CONCOCT_170	1188229
+S0C89448	CONCOCT_170	1188229
+S0C89868	CONCOCT_170	1188229
+S0C90415	CONCOCT_170	1188229
+S0C90716	CONCOCT_170	1188229
+S0C93293	CONCOCT_170	1188229
+S0C102816	CONCOCT_170	1188229
+S0C103662	CONCOCT_170	1188229
+S0C104694	CONCOCT_170	1188229
+S0C107175	CONCOCT_170	1188229
+S0C107697	CONCOCT_170	1188229
+S0C107933	CONCOCT_170	1188229
+S0C111037	CONCOCT_170	1188229
+S0C114385	CONCOCT_170	1188229
+S0C117906	CONCOCT_170	1188229
+S0C123235	CONCOCT_170	1188229
+S0C124089	CONCOCT_170	1188229
+S0C129769	CONCOCT_170	1188229
+S0C131077	CONCOCT_170	1188229
+S0C131919	CONCOCT_170	1188229
+S0C136538	CONCOCT_170	1188229
+S0C137113	CONCOCT_170	1188229
+S0C139193	CONCOCT_170	1188229
+S0C140030	CONCOCT_170	1188229
+S0C143099	CONCOCT_170	1188229
+S0C143812	CONCOCT_170	1188229
+S0C146859	CONCOCT_170	1188229
+S0C148933	CONCOCT_170	1188229
+S0C152340	CONCOCT_170	1188229
+S0C152505	CONCOCT_170	1188229
+S0C152600	CONCOCT_170	1188229
+S0C153465	CONCOCT_170	1188229
+S0C153977	CONCOCT_170	1188229
+S0C156191	CONCOCT_170	1188229
+S0C163440	CONCOCT_170	1188229
+S0C164900	CONCOCT_170	1188229
+S0C165431	CONCOCT_170	1188229
+S0C165600	CONCOCT_170	1188229
+S0C167514	CONCOCT_170	1188229
+S0C170731	CONCOCT_170	1188229
+S0C171275	CONCOCT_170	1188229
+S0C172053	CONCOCT_170	1188229
+S0C172143	CONCOCT_170	1188229
+S0C173871	CONCOCT_170	1188229
+S0C176168	CONCOCT_170	1188229
+S0C176457	CONCOCT_170	1188229
+S0C177012	CONCOCT_170	1188229
+S0C177016	CONCOCT_170	1188229
+S0C180505	CONCOCT_170	1188229
+S0C184052	CONCOCT_170	1188229
+S0C187627	CONCOCT_170	1188229
+S0C189589	CONCOCT_170	1188229
+S0C190286	CONCOCT_170	1188229
+S0C190997	CONCOCT_170	1188229
+S0C192169	CONCOCT_170	1188229
+S0C192913	CONCOCT_170	1188229
+S0C193235	CONCOCT_170	1188229
+S0C197282	CONCOCT_170	1188229
+S0C199440	CONCOCT_170	1188229
+S0C200742	CONCOCT_170	1188229
+S0C202327	CONCOCT_170	1188229
+S0C203916	CONCOCT_170	1188229
+S0C207418	CONCOCT_170	1188229
+S0C214076	CONCOCT_170	1188229
+S0C214145	CONCOCT_170	1188229
+S0C214674	CONCOCT_170	1188229
+S0C215796	CONCOCT_170	1188229
+S0C218011	CONCOCT_170	1188229
+S0C223793	CONCOCT_170	1188229
+S0C224911	CONCOCT_170	1188229
+S0C226616	CONCOCT_170	1188229
+S0C226964	CONCOCT_170	1188229
+S0C232179	CONCOCT_170	1188229
+S0C233703	CONCOCT_170	1188229
+S0C235269	CONCOCT_170	1188229
+S0C244843	CONCOCT_170	1188229
+S0C245988	CONCOCT_170	1188229
+S0C247775	CONCOCT_170	1188229
+S0C248142	CONCOCT_170	1188229
+S0C248525	CONCOCT_170	1188229
+S0C250249	CONCOCT_170	1188229
+S0C250769	CONCOCT_170	1188229
+S0C261957	CONCOCT_170	1188229
+S0C267920	CONCOCT_170	1188229
+S0C268515	CONCOCT_170	1188229
+S0C271398	CONCOCT_170	1188229
+S0C273474	CONCOCT_170	1188229
+S0C273642	CONCOCT_170	1188229
+S0C273909	CONCOCT_170	1188229
+S0C282614	CONCOCT_170	1188229
+S0C284421	CONCOCT_170	1188229
+S0C284529	CONCOCT_170	1188229
+S0C286800	CONCOCT_170	1188229
+S0C289235	CONCOCT_170	1188229
+S0C290438	CONCOCT_170	1188229
+S0C291627	CONCOCT_170	1188229
+S0C296643	CONCOCT_170	1188229
+S0C297219	CONCOCT_170	1188229
+S0C302272	CONCOCT_170	1188229
+S0C303794	CONCOCT_170	1188229
+S0C307970	CONCOCT_170	1188229
+S0C310701	CONCOCT_170	1188229
+S0C310818	CONCOCT_170	1188229
+S0C313722	CONCOCT_170	1188229
+S0C313791	CONCOCT_170	1188229
+S0C315247	CONCOCT_170	1188229
+S0C316931	CONCOCT_170	1188229
+S0C317968	CONCOCT_170	1188229
+S0C319375	CONCOCT_170	1188229
+S0C320040	CONCOCT_170	1188229
+S0C320442	CONCOCT_170	1188229
+S0C328161	CONCOCT_170	1188229
+S0C328842	CONCOCT_170	1188229
+S0C329759	CONCOCT_170	1188229
--- a/test-data/test_bat_file.tsv	Sun Sep 08 14:37:41 2024 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,39 +0,0 @@
-# bin	classification	reason	lineage	lineage scores
-1.FASTA	taxid assigned	based on 4161/4187 ORFs	1;131567;2;1783272;201174;1760;85007;182102;85043;1736349	1.00;1.00;1.00;1.00;1.00;1.00;0.99;0.99;0.99;0.31
-10.FASTA	taxid assigned	based on 1895/1915 ORFs	1;131567;2;1224;1236;135614;32033;2370;2371	1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;0.94
-11.FASTA	taxid assigned	based on 4793/4923 ORFs	1;131567;2;1783272;1239;186801;186802;31979;1884934;191027*	1.00;1.00;1.00;0.99;0.99;0.98;0.98;0.83;0.81;0.81
-12.FASTA	taxid assigned	based on 4056/4136 ORFs	1;131567;2;1783270;68336;976;1853228;1853229;563835;398041;462367	1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;0.99;0.99
-13.FASTA	taxid assigned	based on 3575/3644 ORFs	1;131567;2;1783272;544448;31969;186332;186333;2086;2088	1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00
-14.FASTA	taxid assigned	based on 245/248 ORFs	1;131567;2;1224;28216;80840;75682;149698;1736522	1.00;1.00;1.00;0.99;0.91;0.91;0.91;0.89;0.35
-15.FASTA	taxid assigned	based on 3834/3853 ORFs	1;131567;2;1224;28211;204455;31989;1097466;404881	1.00;1.00;1.00;1.00;1.00;0.99;0.97;0.96;0.96
-16.FASTA	taxid assigned	based on 2824/2869 ORFs	1;131567;2;1783272;544448;31969;186332;186333;2086;2088	1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00
-17.FASTA	taxid assigned	based on 2646/2678 ORFs	1;131567;2;1783272;1239;186801;186802;186804;214904;227138	1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;0.90
-18.FASTA	taxid assigned	based on 6183/6302 ORFs	1;131567;2;1783272;200795;388447;388448;768649;768650*	1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00
-19.FASTA	taxid assigned	based on 8855/8930 ORFs	1;131567;2;1783272;1239;91061;1385;539002;539742;33986*	1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00
-2.FASTA	taxid assigned	based on 3440/3461 ORFs	1;131567;2;1783272;1239;91061;1385;539002;539742;33986*	1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00
-20.FASTA	taxid assigned	based on 4264/4287 ORFs	1;131567;2;1224;28216;206351;1499392;397275;1121000	1.00;1.00;1.00;1.00;1.00;1.00;0.99;0.99;0.97
-21.FASTA	taxid assigned	based on 5835/5867 ORFs	1;131567;2;1224;28216;80840;75682;149698;1736522	1.00;1.00;1.00;1.00;0.98;0.98;0.98;0.97;0.59
-22.FASTA	taxid assigned	based on 2576/2598 ORFs	1;131567;2;1783270;68336;976;117743;200644;49546;363408;328515	1.00;1.00;1.00;1.00;1.00;1.00;1.00;0.97;0.97;0.96;0.89
-23.FASTA	taxid assigned	based on 5759/5763 ORFs	1;131567;2	1.00;0.74;0.73
-24.FASTA	taxid assigned	based on 6458/6478 ORFs	1;131567;2;1224;28211;204455;31989;265;266	1.00;1.00;1.00;1.00;1.00;0.99;0.99;0.95;0.46
-25.FASTA	taxid assigned	based on 4145/4341 ORFs	1;131567;2;1783270;68336;976;1853228;1853229;563835;398041;462367	1.00;1.00;1.00;0.99;0.99;0.99;0.93;0.93;0.93;0.89;0.88
-26.FASTA	taxid assigned	based on 2208/2231 ORFs	1;131567;2;1783272;1239;186801;186802;1491775;42447;182411	1.00;1.00;1.00;1.00;1.00;1.00;1.00;0.97;0.97;0.72
-27.FASTA	taxid assigned	based on 4557/4633 ORFs	1;131567;2;1783270;68336;976;1853228;1853229;563835;1004300;1004304	1.00;1.00;1.00;1.00;1.00;1.00;0.89;0.89;0.89;0.89;0.88
-28.FASTA	taxid assigned	based on 1856/1860 ORFs	1;131567;2;1783272;1239;91061;1385;539002;539742;33986*	1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00
-29.FASTA	taxid assigned	based on 3780/3817 ORFs	1;131567;2;1783272;1239;91061;1385;539002;539742;33986*	1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00
-3.FASTA	taxid assigned	based on 205/207 ORFs	1;131567;2;1783272;1239;909932;909929;1843491;55506;55507*	1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;0.99;0.99
-30.FASTA	taxid assigned	based on 6218/6259 ORFs	1;131567;2;1224;28216;80840;75682;149698;1736532	1.00;1.00;1.00;1.00;0.98;0.98;0.98;0.97;0.57
-31.FASTA	taxid assigned	based on 2720/2744 ORFs	1;131567;2;1224;28216;80840;80864;198705;198706	1.00;1.00;1.00;1.00;0.99;0.99;0.98;0.97;0.97
-32.FASTA	taxid assigned	based on 3222/3245 ORFs	1;131567;2;1783272;201174;1760;85006;85021;99479;1736399	1.00;1.00;1.00;1.00;1.00;1.00;1.00;0.99;0.96;0.53
-33.FASTA	taxid assigned	based on 292/297 ORFs	1;131567;2;1224;28211;204455;31989	1.00;1.00;0.99;0.89;0.84;0.50;0.49
-34.FASTA	taxid assigned	based on 3557/3604 ORFs	1;131567;2;1783272;1239;186801;186802;186803;653683;264463*	1.00;1.00;1.00;1.00;1.00;1.00;1.00;0.99;0.99;0.99
-35.FASTA	taxid assigned	based on 2175/2205 ORFs	1;131567;2;1783272;1239;909932;909929;1843491;55506;55507*	1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;0.99;0.99
-36.FASTA	taxid assigned	based on 3370/3422 ORFs	1;131567;2;1783270;68336;976;1853228;1853229;563835;1004300;1004304	1.00;1.00;1.00;1.00;1.00;1.00;0.89;0.89;0.89;0.89;0.87
-37.FASTA	taxid assigned	based on 4212/4264 ORFs	1;131567;2;1783270;68336;976;1853228;1853229;563835;1004300;1004304	1.00;1.00;1.00;1.00;1.00;1.00;0.92;0.92;0.92;0.92;0.91
-38.FASTA	taxid assigned	based on 8008/8038 ORFs	1;131567;2;1224;28211;204455;31989;265;266	1.00;1.00;1.00;1.00;1.00;0.99;0.99;0.98;0.40
-4.FASTA	taxid assigned	based on 8568/8682 ORFs	1;131567;2;1783270;68336;976;1853228;1853229;563835;1004300;1004304	1.00;1.00;1.00;1.00;1.00;1.00;0.92;0.92;0.92;0.92;0.90
-5.FASTA	taxid assigned	based on 2948/2952 ORFs	1;131567;2;1224;28211;204455;31989;205889;990712	1.00;1.00;1.00;1.00;1.00;0.87;0.87;0.86;0.86
-6.FASTA	taxid assigned	based on 2846/2901 ORFs	1;131567;2;1224;1236;135614;32033;68;1736549	1.00;1.00;1.00;0.96;0.94;0.92;0.85;0.65;0.52
-7.FASTA	taxid assigned	based on 5030/5081 ORFs	1;131567;2;1224;68525;28221;213118;213119;218207;259354	1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;0.38
-8.FASTA	taxid assigned	based on 2537/2579 ORFs	1;131567;2;1783272;544448;31969;186332;186333;2086;2088	1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00
-9.FASTA	taxid assigned	based on 1648/1673 ORFs	1;131567;2;1783272;544448;31969;186332;186333;2086;2088	1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00;1.00
\ No newline at end of file
--- a/test-data/test_biobox_file.tsv	Sun Sep 08 14:37:41 2024 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,13 +0,0 @@
-#CAMI Format for Binning
-@Version:0.9.0
-@SampleID:gsa
-@@SEQUENCEID	BINID
-RL|S1|C1198	1
-RL|S1|C3912	1
-RL|S1|C131	10
-RL|S1|C1410	10
-RL|S1|C2929	10
-RL|S1|C3754	10
-RL|S1|C1335	11
-RL|S1|C1344	11
-RL|S1|C1352	11
\ No newline at end of file
--- a/test-data/test_biobox_file_add_taxid_bat.tsv	Sun Sep 08 14:37:41 2024 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,13 +0,0 @@
-#CAMI Format for Binning
-@Version:0.9.0
-@SampleID:_SAMPLEID_
-@@SEQUENCEID	BINID	TAXID
-RL|S1|C1198	1	1736349
-RL|S1|C3912	1	1736349
-RL|S1|C131	10	2371
-RL|S1|C1410	10	2371
-RL|S1|C2929	10	2371
-RL|S1|C3754	10	2371
-RL|S1|C1335	11	191027
-RL|S1|C1344	11	191027
-RL|S1|C1352	11	191027
--- a/test-data/test_biobox_file_add_taxid_gtdb.tsv	Sun Sep 08 14:37:41 2024 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,13 +0,0 @@
-#CAMI Format for Binning
-@Version:0.9.0
-@SampleID:_SAMPLEID_
-@@SEQUENCEID	BINID	TAXID
-RL|S1|C1198	1	12908
-RL|S1|C3912	1	12908
-RL|S1|C131	10	2371
-RL|S1|C1410	10	2371
-RL|S1|C2929	10	2371
-RL|S1|C3754	10	2371
-RL|S1|C1335	11	191027
-RL|S1|C1344	11	191027
-RL|S1|C1352	11	191027
--- a/test-data/test_gtdb_file.tsv	Sun Sep 08 14:37:41 2024 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,39 +0,0 @@
-user_genome	classification	fastani_reference	fastani_reference_radius	fastani_taxonomy	fastani_ani	fastani_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
-1	d__Bacteria;p__Actinobacteriota;c__Actinomycetia;o__Mycobacteriales;f__Mycobacteriaceae;g__Williamsia_A;s__Williamsia_A herbipolensis	GCF_000964005.1	95.0	d__Bacteria;p__Actinobacteriota;c__Actinomycetia;o__Mycobacteriales;f__Mycobacteriaceae;g__Williamsia_A;s__Williamsia_A herbipolensis	95.01	0.891	GCF_000964005.1	95.0	d__Bacteria;p__Actinobacteriota;c__Actinomycetia;o__Mycobacteriales;f__Mycobacteriaceae;g__Williamsia_A;s__Williamsia_A herbipolensis	95.01	0.891	d__Bacteria;p__Actinobacteriota;c__Actinomycetia;o__Mycobacteriales;f__Mycobacteriaceae;g__Williamsia_A;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_014635305.1, s__Williamsia_A phyllosphaerae, 95.0, 82.43, 0.702; GCA_016462415.1, s__Williamsia_A sp016462415, 95.0, 82.15, 0.649; GCF_018474015.1, s__Williamsia_A sp018474015, 95.0, 80.23, 0.523	96.49	11	N/A	N/A
-10	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Xanthomonadales;f__Xanthomonadaceae;g__Xylella;s__Xylella fastidiosa	GCF_011801475.1	95.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Xanthomonadales;f__Xanthomonadaceae;g__Xylella;s__Xylella fastidiosa	99.99	1.0	GCF_011801475.1	95.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Xanthomonadales;f__Xanthomonadaceae;g__Xylella;s__Xylella fastidiosa	99.99	1.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Xanthomonadales;f__Xanthomonadaceae;g__Xylella;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_013177435.1, s__Xylella taiwanensis, 95.0, 82.85, 0.849	85.13	11	N/A	N/A
-11	d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Peptostreptococcales;f__Caminicellaceae;g__Paramaledivibacter;s__Paramaledivibacter caminithermalis	GCF_900142245.1	95.0	d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Peptostreptococcales;f__Caminicellaceae;g__Paramaledivibacter;s__Paramaledivibacter caminithermalis	99.97	0.872	GCF_900142245.1	95.0	d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Peptostreptococcales;f__Caminicellaceae;g__Paramaledivibacter;s__Paramaledivibacter caminithermalis	99.97	0.872	d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Peptostreptococcales;f__Caminicellaceae;g__;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	N/A	78.49	11	N/A	Genome has more than 10.0% of markers with multiple hits
-12	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Flavisolibacter;s__Flavisolibacter ginsengisoli	GCF_900129295.1	95.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Flavisolibacter;s__Flavisolibacter ginsengisoli	100.0	0.999	GCF_900129295.1	95.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Flavisolibacter;s__Flavisolibacter ginsengisoli	100.0	0.999	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Flavisolibacter;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCA_017745135.1, s__Flavisolibacter sp017745135, 95.0, 77.32, 0.1; GCA_013327885.1, s__Flavisolibacter sp013327885, 95.0, 77.25, 0.081; GCF_007970805.1, s__Flavisolibacter ginsenosidimutans, 95.0, 76.92, 0.056; GCF_003628535.1, s__Flavisolibacter nicotianae, 95.0, 76.88, 0.08; GCA_014163555.1, s__Flavisolibacter sp014163555, 95.0, 76.86, 0.077; GCA_002050435.1, s__Flavisolibacter sp002050435, 95.0, 76.62, 0.139	97.8	11	N/A	N/A
-13	d__Bacteria;p__Firmicutes;c__Bacilli;o__Acholeplasmatales;f__Anaeroplasmataceae;g__Anaeroplasma;s__Anaeroplasma bactoclasticum	GCF_003550015.1	95.0	d__Bacteria;p__Firmicutes;c__Bacilli;o__Acholeplasmatales;f__Anaeroplasmataceae;g__Anaeroplasma;s__Anaeroplasma bactoclasticum	97.96	0.859	GCF_003550015.1	95.0	d__Bacteria;p__Firmicutes;c__Bacilli;o__Acholeplasmatales;f__Anaeroplasmataceae;g__Anaeroplasma;s__Anaeroplasma bactoclasticum	97.96	0.859	d__Bacteria;p__Firmicutes;c__Bacilli;o__Acholeplasmatales;f__Anaeroplasmataceae;g__Anaeroplasma;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCA_017388605.1, s__Anaeroplasma sp017388605, 95.0, 83.32, 0.715; GCA_016280975.1, s__Anaeroplasma sp016280975, 95.0, 78.46, 0.241; GCA_017449215.1, s__Anaeroplasma sp017449215, 95.0, 77.98, 0.251; GCA_002449755.1, s__Anaeroplasma sp002449755, 95.0, 77.78, 0.249; GCA_017441525.1, s__Anaeroplasma sp017441525, 95.0, 77.67, 0.269; GCA_016282815.1, s__Anaeroplasma sp016282815, 95.0, 77.61, 0.204; GCA_017524905.1, s__Anaeroplasma sp017524905, 95.0, 77.59, 0.242; GCA_900770055.1, s__Anaeroplasma sp900770055, 95.0, 77.45, 0.176; GCA_015059145.1, s__Anaeroplasma sp015059145, 95.0, 77.44, 0.194; GCA_017542485.1, s__Anaeroplasma sp017542485, 95.0, 77.44, 0.199; GCA_017462645.1, s__Anaeroplasma sp017462645, 95.0, 77.4, 0.236; GCA_016288855.1, s__Anaeroplasma sp016288855, 95.0, 77.33, 0.203; GCA_017444645.1, s__Anaeroplasma sp017444645, 95.0, 77.24, 0.231; GCA_017454375.1, s__Anaeroplasma sp017454375, 95.0, 77.07, 0.14; GCA_902783745.1, s__Anaeroplasma sp902783745, 95.0, 77.01, 0.214; GCA_018715825.1, s__Anaeroplasma faecigallinarum, 95.0, 76.96, 0.115; GCA_900767915.1, s__Anaeroplasma sp900767915, 95.0, 76.92, 0.173; GCA_902796895.1, s__Anaeroplasma sp902796895, 95.0, 76.82, 0.227; GCA_905236105.1, s__Anaeroplasma sp905236105, 95.0, 76.14, 0.118; GCA_905236965.1, s__Anaeroplasma sp905236965, 95.0, 75.89, 0.176	55.08	11	N/A	Genome has more than 19.2% of markers with multiple hits
-14	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Burkholderiaceae;g__Pseudoduganella;s__Pseudoduganella sp001425045	GCF_001425045.1	95.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Burkholderiaceae;g__Pseudoduganella;s__Pseudoduganella sp001425045	100.0	1.0	GCF_001425045.1	95.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Burkholderiaceae;g__Pseudoduganella;s__Pseudoduganella sp001425045	100.0	1.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Burkholderiaceae;g__Pseudoduganella;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_001425265.1, s__Pseudoduganella sp001425265, 95.0, 92.95, 0.957; GCF_003053665.1, s__Pseudoduganella sp003053665, 95.0, 91.93, 0.891; GCF_009857595.1, s__Pseudoduganella aquatica_A, 95.0, 91.22, 0.978; GCF_900116645.1, s__Pseudoduganella namucuonensis, 95.0, 87.85, 0.913; GCF_014191875.1, s__Pseudoduganella violacea, 95.0, 84.06, 0.761; GCF_013369485.1, s__Pseudoduganella sp013369485, 95.0, 84.01, 0.804; GCF_009674485.1, s__Pseudoduganella sp009674485, 95.0, 83.86, 0.804; GCF_000425385.1, s__Pseudoduganella violaceinigra, 95.0, 83.6, 0.804; GCF_001191005.1, s__Pseudoduganella sp001191005, 95.0, 83.48, 0.848; GCF_004421005.1, s__Pseudoduganella plicata, 95.0, 83.23, 0.717; GCF_003028855.1, s__Pseudoduganella armeniaca, 95.0, 83.18, 0.804; GCA_008011715.1, s__Pseudoduganella haloabium, 95.0, 83.0, 0.848; GCF_007830455.1, s__Pseudoduganella lurida, 95.0, 82.99, 0.761; GCF_009720865.1, s__Pseudoduganella ginsengisoli, 95.0, 82.96, 0.848; GCF_001427305.1, s__Pseudoduganella sp001427305, 95.0, 82.81, 0.761; GCF_004322755.1, s__Pseudoduganella albidiflava, 95.0, 82.76, 0.826; GCF_009720835.1, s__Pseudoduganella buxea, 95.0, 82.6, 0.804; GCF_009857475.1, s__Pseudoduganella guangdongensis, 95.0, 82.56, 0.783; GCF_004217275.1, s__Pseudoduganella sp004217275, 95.0, 82.55, 0.761; GCF_900113115.1, s__Pseudoduganella sp900113115, 95.0, 82.37, 0.739; GCA_002454505.1, s__Pseudoduganella sp002454505, 95.0, 82.35, 0.783; GCF_009727155.1, s__Pseudoduganella dura, 95.0, 82.31, 0.848; GCF_014192225.1, s__Pseudoduganella umbonata, 95.0, 82.27, 0.826; GCF_001425005.1, s__Pseudoduganella sp001425005, 95.0, 82.22, 0.783; GCF_004209755.1, s__Pseudoduganella lutea, 95.0, 82.18, 0.826; GCF_007830495.1, s__Pseudoduganella flava, 95.0, 82.17, 0.804; GCF_009720745.1, s__Pseudoduganella eburnea, 95.0, 81.81, 0.848	12.39	11	N/A	N/A
-15	d__Bacteria;p__Proteobacteria;c__Alphaproteobacteria;o__Rhodobacterales;f__Rhodobacteraceae;g__Albidovulum;s__Albidovulum denitrificans	GCF_002973535.1	95.0	d__Bacteria;p__Proteobacteria;c__Alphaproteobacteria;o__Rhodobacterales;f__Rhodobacteraceae;g__Albidovulum;s__Albidovulum denitrificans	100.0	0.998	GCF_002973535.1	95.0	d__Bacteria;p__Proteobacteria;c__Alphaproteobacteria;o__Rhodobacterales;f__Rhodobacteraceae;g__Albidovulum;s__Albidovulum denitrificans	100.0	0.998	d__Bacteria;p__Proteobacteria;c__Alphaproteobacteria;o__Rhodobacterales;f__Rhodobacteraceae;g__Albidovulum;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCA_002440625.1, s__Albidovulum sp002440625, 95.0, 81.59, 0.611; GCA_002280515.1, s__Albidovulum sp002280515, 95.0, 81.47, 0.618; GCA_011620265.1, s__Albidovulum sp011620265, 95.0, 81.18, 0.602; GCA_008933605.1, s__Albidovulum sp008933605, 95.0, 80.63, 0.571; GCA_002841115.1, s__Albidovulum sp002841115, 95.0, 80.51, 0.565; GCF_900302475.1, s__Albidovulum aquaemixtae, 95.0, 79.33, 0.459; GCF_002927635.1, s__Albidovulum inexpectatum, 95.0, 79.06, 0.482	89.91	11	N/A	N/A
-16	d__Bacteria;p__Firmicutes;c__Bacilli;o__Acholeplasmatales;f__Anaeroplasmataceae;g__Anaeroplasma;s__Anaeroplasma bactoclasticum	GCF_003550015.1	95.0	d__Bacteria;p__Firmicutes;c__Bacilli;o__Acholeplasmatales;f__Anaeroplasmataceae;g__Anaeroplasma;s__Anaeroplasma bactoclasticum	98.99	0.916	GCF_003550015.1	95.0	d__Bacteria;p__Firmicutes;c__Bacilli;o__Acholeplasmatales;f__Anaeroplasmataceae;g__Anaeroplasma;s__Anaeroplasma bactoclasticum	98.99	0.916	d__Bacteria;p__Firmicutes;c__Bacilli;o__Acholeplasmatales;f__Anaeroplasmataceae;g__Anaeroplasma;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCA_017388605.1, s__Anaeroplasma sp017388605, 95.0, 83.71, 0.719; GCA_017449215.1, s__Anaeroplasma sp017449215, 95.0, 78.26, 0.268; GCA_017441525.1, s__Anaeroplasma sp017441525, 95.0, 78.17, 0.276; GCA_017524905.1, s__Anaeroplasma sp017524905, 95.0, 77.95, 0.238; GCA_002449755.1, s__Anaeroplasma sp002449755, 95.0, 77.9, 0.268; GCA_016280975.1, s__Anaeroplasma sp016280975, 95.0, 77.81, 0.257; GCA_017462645.1, s__Anaeroplasma sp017462645, 95.0, 77.8, 0.236; GCA_017542485.1, s__Anaeroplasma sp017542485, 95.0, 77.55, 0.195; GCA_017444645.1, s__Anaeroplasma sp017444645, 95.0, 77.47, 0.262; GCA_900770055.1, s__Anaeroplasma sp900770055, 95.0, 77.41, 0.184; GCA_902783745.1, s__Anaeroplasma sp902783745, 95.0, 77.4, 0.217; GCA_016288855.1, s__Anaeroplasma sp016288855, 95.0, 77.38, 0.218; GCA_016282815.1, s__Anaeroplasma sp016282815, 95.0, 77.33, 0.221; GCA_015059145.1, s__Anaeroplasma sp015059145, 95.0, 77.32, 0.197; GCA_017454375.1, s__Anaeroplasma sp017454375, 95.0, 77.22, 0.13; GCA_900767915.1, s__Anaeroplasma sp900767915, 95.0, 77.2, 0.183; GCA_018715825.1, s__Anaeroplasma faecigallinarum, 95.0, 76.96, 0.111; GCA_902796895.1, s__Anaeroplasma sp902796895, 95.0, 76.93, 0.242; GCA_905236965.1, s__Anaeroplasma sp905236965, 95.0, 76.16, 0.185; GCA_905236105.1, s__Anaeroplasma sp905236105, 95.0, 76.08, 0.131	50.77	11	N/A	Genome has more than 15.8% of markers with multiple hits
-17	d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Peptostreptococcales;f__Peptostreptococcaceae;g__Tepidibacter;s__Tepidibacter formicigenes	GCF_900142235.1	95.0	d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Peptostreptococcales;f__Peptostreptococcaceae;g__Tepidibacter;s__Tepidibacter formicigenes	100.0	0.999	GCF_900142235.1	95.0	d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Peptostreptococcales;f__Peptostreptococcaceae;g__Tepidibacter;s__Tepidibacter formicigenes	100.0	0.999	d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Peptostreptococcales;f__Peptostreptococcaceae;g__Tepidibacter;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_900129915.1, s__Tepidibacter thalassicus, 95.0, 86.9, 0.78	77.03	11	N/A	N/A
-18	d__Bacteria;p__Chloroflexota;c__Ktedonobacteria;o__Ktedonobacterales;f__Ktedonobacteraceae;g__Thermosporothrix;s__Thermosporothrix hazakensis	GCF_003253565.1	95.0	d__Bacteria;p__Chloroflexota;c__Ktedonobacteria;o__Ktedonobacterales;f__Ktedonobacteraceae;g__Thermosporothrix;s__Thermosporothrix hazakensis	100.0	0.999	GCF_003253565.1	95.0	d__Bacteria;p__Chloroflexota;c__Ktedonobacteria;o__Ktedonobacterales;f__Ktedonobacteraceae;g__Thermosporothrix;s__Thermosporothrix hazakensis	100.0	0.999	d__Bacteria;p__Chloroflexota;c__Ktedonobacteria;o__Ktedonobacterales;f__Ktedonobacteraceae;g__;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	N/A	84.41	11	N/A	Genome has more than 11.7% of markers with multiple hits
-19	d__Bacteria;p__Firmicutes;c__Bacilli;o__Exiguobacterales;f__Exiguobacteraceae;g__Exiguobacterium_A;s__Exiguobacterium_A sp001423965	GCF_001423965.1	95.0	d__Bacteria;p__Firmicutes;c__Bacilli;o__Exiguobacterales;f__Exiguobacteraceae;g__Exiguobacterium_A;s__Exiguobacterium_A sp001423965	99.76	0.989	GCF_001423965.1	95.0	d__Bacteria;p__Firmicutes;c__Bacilli;o__Exiguobacterales;f__Exiguobacteraceae;g__Exiguobacterium_A;s__Exiguobacterium_A sp001423965	99.76	0.989	d__Bacteria;p__Firmicutes;c__Bacilli;o__Exiguobacterales;f__Exiguobacteraceae;g__Exiguobacterium_A;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_000702605.1, s__Exiguobacterium_A acetylicum, 95.0, 90.87, 0.853; GCF_001939065.1, s__Exiguobacterium_A indicum, 95.0, 90.72, 0.833; GCF_001275385.1, s__Exiguobacterium_A sp001275385, 95.0, 89.22, 0.814; GCF_018618755.1, s__Exiguobacterium_A sp018618755, 95.0, 80.92, 0.543; GCF_000702625.1, s__Exiguobacterium_A oxidotolerans, 95.0, 80.85, 0.548; GCF_000019905.1, s__Exiguobacterium_A sibiricum, 95.0, 80.84, 0.552; GCF_000620865.1, s__Exiguobacterium_A sibiricum_A, 95.0, 80.82, 0.534; GCA_902363455.1, s__Exiguobacterium_A sp902363455, 95.0, 80.8, 0.51; GCF_003339585.1, s__Exiguobacterium_A sp003339585, 95.0, 80.75, 0.542; GCF_000620805.1, s__Exiguobacterium_A undae, 95.0, 80.72, 0.516; GCF_000685865.1, s__Exiguobacterium_A antarcticum, 95.0, 80.66, 0.512; GCF_014524545.1, s__Exiguobacterium_A sp004339505, 95.0, 80.64, 0.522; GCF_001870785.1, s__Exiguobacterium_A sp001870785, 95.0, 80.58, 0.531; GCF_003344535.1, s__Exiguobacterium_A flavidum, 95.0, 79.37, 0.3	16.18	11	N/A	Genome has more than 82.5% of markers with multiple hits
-2	d__Bacteria;p__Firmicutes;c__Bacilli;o__Exiguobacterales;f__Exiguobacteraceae;g__Exiguobacterium_A;s__Exiguobacterium_A sp001423965	GCF_001423965.1	95.0	d__Bacteria;p__Firmicutes;c__Bacilli;o__Exiguobacterales;f__Exiguobacteraceae;g__Exiguobacterium_A;s__Exiguobacterium_A sp001423965	99.23	0.971	GCF_001423965.1	95.0	d__Bacteria;p__Firmicutes;c__Bacilli;o__Exiguobacterales;f__Exiguobacteraceae;g__Exiguobacterium_A;s__Exiguobacterium_A sp001423965	99.23	0.971	d__Bacteria;p__Firmicutes;c__Bacilli;o__Exiguobacterales;f__Exiguobacteraceae;g__Exiguobacterium_A;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_000702605.1, s__Exiguobacterium_A acetylicum, 95.0, 90.41, 0.883; GCF_001939065.1, s__Exiguobacterium_A indicum, 95.0, 90.37, 0.852; GCF_001275385.1, s__Exiguobacterium_A sp001275385, 95.0, 88.8, 0.834; GCF_018618755.1, s__Exiguobacterium_A sp018618755, 95.0, 80.82, 0.518; GCA_902363455.1, s__Exiguobacterium_A sp902363455, 95.0, 80.82, 0.478; GCF_000702625.1, s__Exiguobacterium_A oxidotolerans, 95.0, 80.81, 0.511; GCF_000620865.1, s__Exiguobacterium_A sibiricum_A, 95.0, 80.77, 0.523; GCF_000620805.1, s__Exiguobacterium_A undae, 95.0, 80.74, 0.5; GCF_003339585.1, s__Exiguobacterium_A sp003339585, 95.0, 80.63, 0.504; GCF_000019905.1, s__Exiguobacterium_A sibiricum, 95.0, 80.61, 0.502; GCF_000685865.1, s__Exiguobacterium_A antarcticum, 95.0, 80.57, 0.501; GCF_014524545.1, s__Exiguobacterium_A sp004339505, 95.0, 80.55, 0.514; GCF_001870785.1, s__Exiguobacterium_A sp001870785, 95.0, 80.52, 0.514; GCF_003344535.1, s__Exiguobacterium_A flavidum, 95.0, 79.14, 0.277	86.16	11	N/A	N/A
-20	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Chitinibacteraceae;g__Andreprevotia;s__Andreprevotia lacus	GCF_900176275.1	95.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Chitinibacteraceae;g__Andreprevotia;s__Andreprevotia lacus	100.0	1.0	GCF_900176275.1	95.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Chitinibacteraceae;g__Andreprevotia;s__Andreprevotia lacus	100.0	1.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Chitinibacteraceae;g__Andreprevotia;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_009848685.1, s__Andreprevotia sp009848685, 95.0, 82.66, 0.616; GCF_000711875.1, s__Andreprevotia chitinilytica, 95.0, 80.35, 0.45	92.83	11	N/A	N/A
-21	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Burkholderiaceae;g__Pseudoduganella;s__Pseudoduganella sp001425045	GCF_001425045.1	95.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Burkholderiaceae;g__Pseudoduganella;s__Pseudoduganella sp001425045	100.0	1.0	GCF_001425045.1	95.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Burkholderiaceae;g__Pseudoduganella;s__Pseudoduganella sp001425045	100.0	1.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Burkholderiaceae;g__Pseudoduganella;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_001425265.1, s__Pseudoduganella sp001425265, 95.0, 90.09, 0.928; GCF_003053665.1, s__Pseudoduganella sp003053665, 95.0, 89.99, 0.888; GCF_009857595.1, s__Pseudoduganella aquatica_A, 95.0, 88.9, 0.843; GCF_900116645.1, s__Pseudoduganella namucuonensis, 95.0, 85.3, 0.781; GCF_014191875.1, s__Pseudoduganella violacea, 95.0, 82.17, 0.604; GCF_001191005.1, s__Pseudoduganella sp001191005, 95.0, 82.07, 0.612; GCF_013369485.1, s__Pseudoduganella sp013369485, 95.0, 82.03, 0.605; GCA_008011715.1, s__Pseudoduganella haloabium, 95.0, 81.49, 0.621; GCF_009674485.1, s__Pseudoduganella sp009674485, 95.0, 81.47, 0.689; GCF_009720835.1, s__Pseudoduganella buxea, 95.0, 81.41, 0.6; GCF_009857475.1, s__Pseudoduganella guangdongensis, 95.0, 81.4, 0.581; GCF_003028855.1, s__Pseudoduganella armeniaca, 95.0, 81.39, 0.619; GCF_000425385.1, s__Pseudoduganella violaceinigra, 95.0, 81.23, 0.526; GCF_007830455.1, s__Pseudoduganella lurida, 95.0, 81.11, 0.574; GCF_900113115.1, s__Pseudoduganella sp900113115, 95.0, 81.1, 0.541; GCF_004217275.1, s__Pseudoduganella sp004217275, 95.0, 81.1, 0.555; GCF_009720745.1, s__Pseudoduganella eburnea, 95.0, 81.0, 0.551; GCA_002454505.1, s__Pseudoduganella sp002454505, 95.0, 81.0, 0.579; GCF_001425005.1, s__Pseudoduganella sp001425005, 95.0, 80.95, 0.557; GCF_014192225.1, s__Pseudoduganella umbonata, 95.0, 80.88, 0.602; GCF_009727155.1, s__Pseudoduganella dura, 95.0, 80.84, 0.597; GCF_004322755.1, s__Pseudoduganella albidiflava, 95.0, 80.82, 0.628; GCF_001427305.1, s__Pseudoduganella sp001427305, 95.0, 80.8, 0.562; GCF_004421005.1, s__Pseudoduganella plicata, 95.0, 80.7, 0.553; GCF_004209755.1, s__Pseudoduganella lutea, 95.0, 80.57, 0.569; GCF_007830495.1, s__Pseudoduganella flava, 95.0, 80.5, 0.617; GCF_009720865.1, s__Pseudoduganella ginsengisoli, 95.0, 80.45, 0.545	43.37	11	N/A	N/A
-22	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Flavobacteriales;f__Flavobacteriaceae;g__Nonlabens;s__Nonlabens dokdonensis	GCF_000332115.1	95.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Flavobacteriales;f__Flavobacteriaceae;g__Nonlabens;s__Nonlabens dokdonensis	100.0	1.0	GCF_000332115.1	95.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Flavobacteriales;f__Flavobacteriaceae;g__Nonlabens;s__Nonlabens dokdonensis	100.0	1.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Flavobacteriales;f__Flavobacteriaceae;g__Nonlabens;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCA_002162835.1, s__Nonlabens dokdonensis_B, 95.0, 86.47, 0.762; GCF_000732625.1, s__Nonlabens ulvanivorans, 95.0, 79.63, 0.287; GCF_002934445.1, s__Nonlabens xylanidelens, 95.0, 79.33, 0.543; GCF_002831625.1, s__Nonlabens sp002831625, 95.0, 79.02, 0.461; GCF_012974865.1, s__Nonlabens sp012974865, 95.0, 78.76, 0.472; GCA_000153385.1, s__Nonlabens sp000153385, 95.0, 78.67, 0.259; GCF_000755285.1, s__Nonlabens ulvanivorans_A, 95.0, 78.48, 0.316; GCF_002954765.1, s__Nonlabens arenilitoris, 95.0, 78.4, 0.305; GCA_018401815.1, s__Nonlabens sp018401815, 95.0, 78.16, 0.397; GCF_003966335.1, s__Nonlabens ponticola, 95.0, 77.67, 0.152; GCF_900101765.1, s__Nonlabens sp900101765, 95.0, 77.65, 0.156; GCF_000831385.1, s__Nonlabens marinus, 95.0, 77.49, 0.16; GCF_002994045.1, s__Nonlabens agnitus, 95.0, 77.34, 0.184; GCF_001413925.1, s__Nonlabens sp001413925, 95.0, 76.88, 0.17; GCF_002954355.1, s__Nonlabens tegetincola, 95.0, 76.75, 0.152; GCF_002117125.1, s__Nonlabens spongiae, 95.0, 76.63, 0.121; GCF_003865345.1, s__Nonlabens xiamenensis, 95.0, 76.61, 0.138; GCF_015356755.1, s__Nonlabens antarcticus, 95.0, 76.38, 0.163	47.56	11	N/A	N/A
-23	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Pseudomonadales;f__Pseudomonadaceae;g__Pseudomonas;s__Pseudomonas aeruginosa	GCF_001457615.1	95.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Pseudomonadales;f__Pseudomonadaceae;g__Pseudomonas;s__Pseudomonas aeruginosa	100.0	1.0	GCF_001457615.1	95.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Pseudomonadales;f__Pseudomonadaceae;g__Pseudomonas;s__Pseudomonas aeruginosa	100.0	1.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Pseudomonadales;f__Pseudomonadaceae;g__Pseudomonas;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_000017205.1, s__Pseudomonas aeruginosa_A, 95.0, 94.08, 0.898; GCF_900187975.1, s__Pseudomonas delhiensis, 95.078, 84.72, 0.657; GCF_900103845.1, s__Pseudomonas jinjuensis, 95.0, 84.68, 0.586; GCF_900112375.1, s__Pseudomonas citronellolis, 95.078, 84.65, 0.657; GCF_017589465.1, s__Pseudomonas sp017589465, 95.0, 84.16, 0.606; GCF_000349845.1, s__Pseudomonas sp000349845, 95.0, 83.98, 0.654; GCF_017491605.1, s__Pseudomonas sp017491605, 95.0, 83.93, 0.609; GCF_014204515.1, s__Pseudomonas nitritireducens_A, 95.0, 83.89, 0.64; GCA_002452115.1, s__Pseudomonas nitroreducens_B, 95.0, 83.87, 0.623; GCF_000689415.1, s__Pseudomonas knackmussii, 95.0, 83.83, 0.579; GCF_900099785.1, s__Pseudomonas panipatensis, 95.0, 83.79, 0.609; GCF_000955805.1, s__Pseudomonas sp000955805, 95.0, 83.72, 0.626; GCF_008807415.1, s__Pseudomonas sp002079985, 95.0, 83.68, 0.631; GCF_009189165.1, s__Pseudomonas sp009189165, 95.0, 83.63, 0.584; GCF_002091755.1, s__Pseudomonas nitroreducens, 95.0, 83.55, 0.618; GCA_002796985.1, s__Pseudomonas sp002796985, 95.0, 83.47, 0.604; GCF_014852585.1, s__Pseudomonas sp014852585, 95.0, 83.39, 0.608; GCF_000313755.1, s__Pseudomonas nitroreducens_A, 95.0, 83.37, 0.611; GCF_016919445.1, s__Pseudomonas sp016919445, 95.0, 83.35, 0.614; GCF_005877905.1, s__Pseudomonas nicosulfuronedens, 95.0, 83.35, 0.613	90.35	11	N/A	N/A
-24	d__Bacteria;p__Proteobacteria;c__Alphaproteobacteria;o__Rhodobacterales;f__Rhodobacteraceae;g__Paracoccus;s__Paracoccus denitrificans	GCF_900100045.1	95.0	d__Bacteria;p__Proteobacteria;c__Alphaproteobacteria;o__Rhodobacterales;f__Rhodobacteraceae;g__Paracoccus;s__Paracoccus denitrificans	100.0	0.85	GCF_900100045.1	95.0	d__Bacteria;p__Proteobacteria;c__Alphaproteobacteria;o__Rhodobacterales;f__Rhodobacteraceae;g__Paracoccus;s__Paracoccus denitrificans	100.0	0.85	d__Bacteria;p__Proteobacteria;c__Alphaproteobacteria;o__Rhodobacterales;f__Rhodobacteraceae;g__Paracoccus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_001447385.1, s__Paracoccus sp001447385, 95.0, 91.66, 0.582; GCF_008824185.1, s__Paracoccus pantotrophus, 95.0, 91.28, 0.634; GCF_000518925.1, s__Paracoccus sp000518925, 95.0, 90.94, 0.62; GCF_000763885.1, s__Paracoccus versutus, 95.0, 90.85, 0.57; GCF_016446475.1, s__Paracoccus binzhouensis, 95.0, 88.9, 0.547; GCF_900156255.1, s__Paracoccus thiocyanatus, 95.0, 88.81, 0.661; GCF_016919705.1, s__Paracoccus sp002359815, 95.0, 87.13, 0.614; GCF_001546115.1, s__Paracoccus aminovorans_B, 95.0, 86.89, 0.534; GCF_900005615.1, s__Paracoccus aminovorans, 95.0, 86.71, 0.557; GCF_000622145.1, s__Paracoccus yeei, 96.0533, 84.29, 0.492; GCF_009301415.1, s__Paracoccus kondratievae, 95.0, 84.29, 0.567; GCF_003285265.1, s__Paracoccus mutanolyticus, 96.0533, 84.23, 0.54; GCF_003337565.1, s__Paracoccus lutimaris, 95.0, 84.16, 0.5; GCF_000763905.1, s__Paracoccus halophilus, 95.0, 84.01, 0.499; GCA_018056045.1, s__Paracoccus sp018056045, 95.0, 83.99, 0.546; GCF_009711185.1, s__Paracoccus limosus, 95.0, 83.56, 0.528; GCF_009696685.1, s__Paracoccus sp009696685, 95.0, 83.34, 0.592; GCF_003709565.1, s__Paracoccus siganidrum, 95.0, 83.3, 0.476; GCF_009711205.1, s__Paracoccus litorisediminis, 95.0, 82.54, 0.387; GCF_009711265.1, s__Paracoccus sp009711265, 95.0, 82.45, 0.476; GCF_004522175.1, s__Paracoccus ravus, 95.0, 82.05, 0.419; GCF_900142875.1, s__Paracoccus solventivorans, 95.0, 81.92, 0.487; GCF_018860165.1, s__Paracoccus sp018860165, 95.0, 81.79, 0.441; GCF_007830335.1, s__Paracoccus sulfuroxidans, 95.0, 81.77, 0.452; GCF_900182695.1, s__Paracoccus laeviglucosivorans, 95.0, 81.62, 0.457; GCF_900631945.1, s__Paracoccus haematequi, 95.0, 81.4, 0.457; GCF_017356265.1, s__Paracoccus fontiphilus, 95.0, 81.21, 0.448; GCF_000763805.1, s__Paracoccus sphaerophysae, 95.0, 81.21, 0.486; GCF_017315735.1, s__Paracoccus sp017315735, 95.0, 81.15, 0.457; GCF_900110285.1, s__Paracoccus alcaliphilus, 95.0, 81.14, 0.422; GCF_009711225.1, s__Paracoccus aestuariivivens, 95.0, 81.1, 0.383; GCF_900108405.1, s__Paracoccus alkenifer, 95.0, 81.07, 0.499; GCF_009708075.1, s__Paracoccus lichenicola, 95.0, 81.07, 0.444; GCF_014642735.1, s__Paracoccus acridae, 95.0, 80.96, 0.429; GCF_003594815.1, s__Paracoccus aestuarii, 95.0, 80.95, 0.461; GCF_002287065.1, s__Paracoccus salipaludis, 95.0, 80.84, 0.451; GCF_900102885.1, s__Paracoccus chinensis, 95.0, 80.73, 0.442; GCF_004683865.2, s__Paracoccus liaowanqingii, 95.0, 80.72, 0.332; GCF_014656455.1, s__Paracoccus aerius, 95.0, 80.7, 0.405; GCF_002847445.1, s__Paracoccus zhejiangensis, 95.0, 80.7, 0.402; GCF_005048225.1, s__Paracoccus gahaiensis, 95.0, 80.69, 0.401; GCF_019061185.1, s__Paracoccus sp019061185, 95.0, 80.68, 0.461; GCF_004522155.1, s__Paracoccus luteus, 95.0, 80.66, 0.494; GCF_016617715.1, s__Paracoccus sp014164625, 95.0, 80.62, 0.431; GCF_003286075.1, s__Paracoccus endophyticus, 95.0, 80.58, 0.488; GCF_900106665.1, s__Paracoccus sanguinis, 95.0, 80.52, 0.462; GCF_000420145.1, s__Paracoccus zeaxanthinifaciens, 95.0, 80.43, 0.469; GCF_900102505.1, s__Paracoccus tibetensis, 95.0, 80.39, 0.408; GCF_006151785.1, s__Paracoccus marcusii, 95.0, 80.38, 0.404; GCF_900188295.1, s__Paracoccus sediminis, 95.0, 80.37, 0.423; GCF_003007735.2, s__Paracoccus marinus_A, 95.0, 80.34, 0.35; GCF_005048265.1, s__Paracoccus hibiscisoli, 95.0, 80.26, 0.425; GCF_002865605.1, s__Paracoccus jeotgali, 95.0, 80.23, 0.449; GCA_002294185.1, s__Paracoccus sp002294185, 95.0, 80.16, 0.432; GCF_013868135.1, s__Paracoccus sp013868135, 95.0, 80.14, 0.412; GCF_002105555.1, s__Paracoccus contaminans, 95.0, 80.12, 0.474; GCF_000444995.1, s__Paracoccus aminophilus, 95.0, 80.1, 0.334; GCF_004310345.1, s__Paracoccus subflavus, 95.0, 80.08, 0.465; GCF_004923205.2, s__Paracoccus aeridis, 95.0, 80.04, 0.421; GCF_000787695.1, s__Paracoccus sp000787695, 95.0, 80.03, 0.366; GCF_007096355.1, s__Paracoccus sp007096355, 95.0, 79.99, 0.371; GCF_007018965.1, s__Paracoccus marinus, 95.0, 79.94, 0.448; GCF_011308835.1, s__Paracoccus xiamenensis, 95.0, 79.84, 0.416; GCF_016629665.1, s__Paracoccus caeni, 95.0, 79.83, 0.368; GCF_018860625.1, s__Paracoccus sp018860625, 95.0, 79.83, 0.403; GCA_003255745.1, s__Paracoccus saliphilus_A, 95.0, 79.82, 0.388; GCF_003697785.1, s__Paracoccus alkanivorans, 95.0, 79.77, 0.339; GCF_003056335.1, s__Paracoccus indicus, 95.0, 79.77, 0.412; GCF_009674885.1, s__Paracoccus sp009674885, 95.0, 79.76, 0.378; GCF_017744015.1, s__Paracoccus sp002732665, 95.0, 79.74, 0.365; GCF_003259195.1, s__Paracoccus sediminilitoris, 95.0, 79.7, 0.398; GCA_900156835.1, s__Paracoccus saliphilus, 95.0, 79.65, 0.301; GCF_900101865.1, s__Paracoccus isoporae, 95.0, 79.64, 0.403; GCF_900111675.1, s__Paracoccus homiensis, 95.0, 79.63, 0.369; GCA_016869875.1, s__Paracoccus sp016869875, 95.0, 79.53, 0.311; GCF_004335005.1, s__Paracoccus sp004335005, 95.0, 79.5, 0.361; GCF_003324675.1, s__Paracoccus suum, 95.0, 79.1, 0.398; GCF_007993065.1, s__Paracoccus aurantiacus, 95.0, 78.95, 0.298; GCA_005768755.1, s__Paracoccus denitrificans_B, 95.0, 78.88, 0.289; GCF_002847305.1, s__Paracoccus sp002847305, 95.0, 78.88, 0.311; GCF_900199195.1, s__Paracoccus seriniphilus, 95.0, 78.66, 0.294; GCF_014490725.1, s__Paracoccus amoyensis, 95.0, 78.59, 0.301; GCA_003240735.1, s__Paracoccus denitrificans_A, 95.0, 78.52, 0.338; GCF_003591515.1, s__Paracoccus sp003591515, 95.0, 78.33, 0.268; GCF_003590715.1, s__Paracoccus sp003590715, 95.0, 77.93, 0.247	65.41	11	N/A	N/A
-25	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Flavisolibacter;s__	N/A	N/A	N/A	N/A	N/A	GCF_900129295.1	95.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Flavisolibacter;s__Flavisolibacter ginsengisoli	84.4	0.777	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Flavisolibacter;s__	taxonomic classification defined by topology and ANI	classification based on placement in class-level tree	GCA_002050435.1, s__Flavisolibacter sp002050435, 95.0, 77.03, 0.153; GCA_017745135.1, s__Flavisolibacter sp017745135, 95.0, 76.9, 0.111; GCF_003628535.1, s__Flavisolibacter nicotianae, 95.0, 76.85, 0.074; GCA_013327885.1, s__Flavisolibacter sp013327885, 95.0, 76.81, 0.084; GCA_014163555.1, s__Flavisolibacter sp014163555, 95.0, 76.57, 0.096; GCF_007970805.1, s__Flavisolibacter ginsenosidimutans, 95.0, 76.56, 0.057	98.29	11	0.98734	Genome not assigned to closest species as it falls outside its pre-defined ANI radius
-26	d__Bacteria;p__Firmicutes_D;c__Proteinivoracia;o__Proteinivoracales;f__Proteinivoraceae;g__Anaerobranca;s__Anaerobranca californiensis	GCF_900142275.1	95.0	d__Bacteria;p__Firmicutes_D;c__Proteinivoracia;o__Proteinivoracales;f__Proteinivoraceae;g__Anaerobranca;s__Anaerobranca californiensis	100.0	0.977	GCF_900142275.1	95.0	d__Bacteria;p__Firmicutes_D;c__Proteinivoracia;o__Proteinivoracales;f__Proteinivoraceae;g__Anaerobranca;s__Anaerobranca californiensis	100.0	0.977	d__Bacteria;p__Firmicutes_D;c__Proteinivoracia;o__Proteinivoracales;f__Proteinivoraceae;g__Anaerobranca;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_900111575.1, s__Anaerobranca gottschalkii, 95.0, 86.04, 0.802	87.59	11	N/A	N/A
-27	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Hydrotalea;s__Hydrotalea sandarakina	GCF_003254115.1	95.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Hydrotalea;s__Hydrotalea sandarakina	97.48	0.867	GCF_003254115.1	95.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Hydrotalea;s__Hydrotalea sandarakina	97.48	0.867	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Hydrotalea;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCA_011362875.1, s__Hydrotalea flava_A, 95.0, 92.3, 0.83; GCA_001623405.1, s__Hydrotalea flava, 95.0, 78.35, 0.428	49.05	11	N/A	Genome has more than 13.3% of markers with multiple hits
-28	d__Bacteria;p__Firmicutes;c__Bacilli;o__Exiguobacterales;f__Exiguobacteraceae;g__Exiguobacterium_A;s__Exiguobacterium_A sp001423965	GCF_001423965.1	95.0	d__Bacteria;p__Firmicutes;c__Bacilli;o__Exiguobacterales;f__Exiguobacteraceae;g__Exiguobacterium_A;s__Exiguobacterium_A sp001423965	100.0	0.993	GCF_001423965.1	95.0	d__Bacteria;p__Firmicutes;c__Bacilli;o__Exiguobacterales;f__Exiguobacteraceae;g__Exiguobacterium_A;s__Exiguobacterium_A sp001423965	100.0	0.993	d__Bacteria;p__Firmicutes;c__Bacilli;o__Exiguobacterales;f__Exiguobacteraceae;g__Exiguobacterium_A;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_000702605.1, s__Exiguobacterium_A acetylicum, 95.0, 91.58, 0.944; GCF_001939065.1, s__Exiguobacterium_A indicum, 95.0, 91.28, 0.89; GCF_001275385.1, s__Exiguobacterium_A sp001275385, 95.0, 90.06, 0.899; GCA_902363455.1, s__Exiguobacterium_A sp902363455, 95.0, 81.7, 0.601; GCF_000620865.1, s__Exiguobacterium_A sibiricum_A, 95.0, 81.66, 0.637; GCF_014524545.1, s__Exiguobacterium_A sp004339505, 95.0, 81.61, 0.661; GCF_000702625.1, s__Exiguobacterium_A oxidotolerans, 95.0, 81.6, 0.65; GCF_018618755.1, s__Exiguobacterium_A sp018618755, 95.0, 81.59, 0.643; GCF_000019905.1, s__Exiguobacterium_A sibiricum, 95.0, 81.56, 0.64; GCF_003339585.1, s__Exiguobacterium_A sp003339585, 95.0, 81.55, 0.64; GCF_000620805.1, s__Exiguobacterium_A undae, 95.0, 81.4, 0.653; GCF_001870785.1, s__Exiguobacterium_A sp001870785, 95.0, 81.31, 0.624; GCF_000685865.1, s__Exiguobacterium_A antarcticum, 95.0, 81.27, 0.633; GCF_003344535.1, s__Exiguobacterium_A flavidum, 95.0, 79.69, 0.349	84.09	11	N/A	N/A
-29	d__Bacteria;p__Firmicutes;c__Bacilli;o__Exiguobacterales;f__Exiguobacteraceae;g__Exiguobacterium_A;s__Exiguobacterium_A sp001423965	GCF_001423965.1	95.0	d__Bacteria;p__Firmicutes;c__Bacilli;o__Exiguobacterales;f__Exiguobacteraceae;g__Exiguobacterium_A;s__Exiguobacterium_A sp001423965	98.66	0.951	GCF_001423965.1	95.0	d__Bacteria;p__Firmicutes;c__Bacilli;o__Exiguobacterales;f__Exiguobacteraceae;g__Exiguobacterium_A;s__Exiguobacterium_A sp001423965	98.66	0.951	d__Bacteria;p__Firmicutes;c__Bacilli;o__Exiguobacterales;f__Exiguobacteraceae;g__Exiguobacterium_A;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_000702605.1, s__Exiguobacterium_A acetylicum, 95.0, 89.97, 0.827; GCF_001939065.1, s__Exiguobacterium_A indicum, 95.0, 89.81, 0.795; GCF_001275385.1, s__Exiguobacterium_A sp001275385, 95.0, 88.32, 0.779; GCF_018618755.1, s__Exiguobacterium_A sp018618755, 95.0, 80.5, 0.481; GCF_000702625.1, s__Exiguobacterium_A oxidotolerans, 95.0, 80.47, 0.469; GCF_000620865.1, s__Exiguobacterium_A sibiricum_A, 95.0, 80.45, 0.467; GCF_000620805.1, s__Exiguobacterium_A undae, 95.0, 80.4, 0.466; GCA_902363455.1, s__Exiguobacterium_A sp902363455, 95.0, 80.39, 0.45; GCF_000685865.1, s__Exiguobacterium_A antarcticum, 95.0, 80.33, 0.451; GCF_000019905.1, s__Exiguobacterium_A sibiricum, 95.0, 80.31, 0.484; GCF_003339585.1, s__Exiguobacterium_A sp003339585, 95.0, 80.29, 0.477; GCF_014524545.1, s__Exiguobacterium_A sp004339505, 95.0, 80.22, 0.47; GCF_001870785.1, s__Exiguobacterium_A sp001870785, 95.0, 80.18, 0.481; GCF_003344535.1, s__Exiguobacterium_A flavidum, 95.0, 79.0, 0.248	73.13	11	N/A	Genome has more than 13.3% of markers with multiple hits
-3	d__Bacteria;p__Firmicutes_C;c__Negativicutes;o__Selenomonadales;f__Selenomonadaceae;g__Schwartzia;s__Schwartzia succinivorans	GCF_900129225.1	95.0	d__Bacteria;p__Firmicutes_C;c__Negativicutes;o__Selenomonadales;f__Selenomonadaceae;g__Schwartzia;s__Schwartzia succinivorans	100.0	1.0	GCF_900129225.1	95.0	d__Bacteria;p__Firmicutes_C;c__Negativicutes;o__Selenomonadales;f__Selenomonadaceae;g__Schwartzia;s__Schwartzia succinivorans	100.0	1.0	d__Bacteria;p__Firmicutes_C;c__Negativicutes;o__Selenomonadales;f__Selenomonadaceae;g__;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	N/A	16.46	11	N/A	N/A
-30	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Burkholderiaceae;g__Pseudoduganella;s__Pseudoduganella sp001425265	GCF_001425265.1	95.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Burkholderiaceae;g__Pseudoduganella;s__Pseudoduganella sp001425265	100.0	1.0	GCF_001425265.1	95.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Burkholderiaceae;g__Pseudoduganella;s__Pseudoduganella sp001425265	100.0	1.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Burkholderiaceae;g__Pseudoduganella;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_003053665.1, s__Pseudoduganella sp003053665, 95.0, 90.85, 0.868; GCF_001425045.1, s__Pseudoduganella sp001425045, 95.0, 90.63, 0.861; GCF_009857595.1, s__Pseudoduganella aquatica_A, 95.0, 89.77, 0.815; GCF_900116645.1, s__Pseudoduganella namucuonensis, 95.0, 85.71, 0.688; GCF_001191005.1, s__Pseudoduganella sp001191005, 95.0, 82.78, 0.593; GCF_014191875.1, s__Pseudoduganella violacea, 95.0, 82.72, 0.596; GCF_013369485.1, s__Pseudoduganella sp013369485, 95.0, 82.69, 0.586; GCA_008011715.1, s__Pseudoduganella haloabium, 95.0, 82.2, 0.58; GCF_009720835.1, s__Pseudoduganella buxea, 95.0, 82.11, 0.6; GCF_009857475.1, s__Pseudoduganella guangdongensis, 95.0, 82.09, 0.636; GCF_003028855.1, s__Pseudoduganella armeniaca, 95.0, 82.05, 0.601; GCF_009674485.1, s__Pseudoduganella sp009674485, 95.0, 81.97, 0.595; GCF_000425385.1, s__Pseudoduganella violaceinigra, 95.0, 81.81, 0.554; GCF_007830455.1, s__Pseudoduganella lurida, 95.0, 81.78, 0.586; GCF_004217275.1, s__Pseudoduganella sp004217275, 95.0, 81.75, 0.549; GCA_002454505.1, s__Pseudoduganella sp002454505, 95.0, 81.72, 0.592; GCF_009720745.1, s__Pseudoduganella eburnea, 95.0, 81.62, 0.569; GCF_001425005.1, s__Pseudoduganella sp001425005, 95.0, 81.59, 0.543; GCF_900113115.1, s__Pseudoduganella sp900113115, 95.0, 81.54, 0.555; GCF_001427305.1, s__Pseudoduganella sp001427305, 95.0, 81.37, 0.543; GCF_004322755.1, s__Pseudoduganella albidiflava, 95.0, 81.34, 0.549; GCF_014192225.1, s__Pseudoduganella umbonata, 95.0, 81.26, 0.528; GCF_009727155.1, s__Pseudoduganella dura, 95.0, 81.26, 0.541; GCF_004421005.1, s__Pseudoduganella plicata, 95.0, 81.21, 0.58; GCF_007830495.1, s__Pseudoduganella flava, 95.0, 81.1, 0.559; GCF_004209755.1, s__Pseudoduganella lutea, 95.0, 80.92, 0.516; GCF_009720865.1, s__Pseudoduganella ginsengisoli, 95.0, 80.7, 0.521	97.2	11	N/A	N/A
-31	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Burkholderiaceae;g__Lampropedia;s__Lampropedia hyalina	GCF_900129055.1	95.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Burkholderiaceae;g__Lampropedia;s__Lampropedia hyalina	100.0	1.0	GCF_900129055.1	95.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Burkholderiaceae;g__Lampropedia;s__Lampropedia hyalina	100.0	1.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Burkholderiaceae;g__Lampropedia;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_004217315.1, s__Lampropedia populi, 95.0, 79.06, 0.425; GCA_002285265.1, s__Lampropedia sp002285265, 95.0, 79.05, 0.389; GCA_002285285.1, s__Lampropedia sp002285285, 95.0, 78.85, 0.367; GCA_003703475.1, s__Lampropedia sp003703475, 95.0, 78.75, 0.327; GCF_001005215.1, s__Lampropedia cohaerens, 95.0, 78.15, 0.303; GCF_004803635.1, s__Lampropedia aestuarii, 95.0, 77.37, 0.192; GCF_004833285.1, s__Lampropedia puyangensis, 95.0, 76.97, 0.131	97.26	11	N/A	N/A
-32	d__Bacteria;p__Actinobacteriota;c__Actinomycetia;o__Actinomycetales;f__Dermatophilaceae;g__Phycicoccus;s__Phycicoccus sp001428065	GCF_001428065.1	95.0	d__Bacteria;p__Actinobacteriota;c__Actinomycetia;o__Actinomycetales;f__Dermatophilaceae;g__Phycicoccus;s__Phycicoccus sp001428065	99.99	0.997	GCF_001428065.1	95.0	d__Bacteria;p__Actinobacteriota;c__Actinomycetia;o__Actinomycetales;f__Dermatophilaceae;g__Phycicoccus;s__Phycicoccus sp001428065	99.99	0.997	d__Bacteria;p__Actinobacteriota;c__Actinomycetia;o__Actinomycetales;f__Dermatophilaceae;g__Phycicoccus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_002846495.1, s__Phycicoccus duodecadis, 95.0, 92.25, 0.859; GCF_011383005.1, s__Phycicoccus sp011383005, 95.0, 84.56, 0.741; GCF_016887965.1, s__Phycicoccus sp016887965, 95.0, 84.46, 0.714; GCF_000720925.1, s__Phycicoccus jejuensis, 95.0, 84.36, 0.722; GCF_013201035.1, s__Phycicoccus sp013201035, 95.0, 84.23, 0.736; GCA_014763705.1, s__Phycicoccus sp014763705, 95.0, 84.07, 0.661; GCF_004025965.2, s__Phycicoccus flavus, 95.0, 83.51, 0.697; GCF_011326735.1, s__Phycicoccus endophyticus, 95.0, 82.86, 0.667; GCF_016888005.1, s__Phycicoccus sp016888005, 95.0, 82.78, 0.656; GCF_018139485.1, s__Phycicoccus sp018139485, 95.0, 82.55, 0.623	96.03	11	N/A	N/A
-33	Unclassified Bacteria	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	N/A	Insufficient number of amino acids in MSA (6.6%)
-34	d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Lachnospirales;f__Lachnospiraceae;g__Anaerosporobacter;s__Anaerosporobacter mobilis	GCF_900142955.1	95.0	d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Lachnospirales;f__Lachnospiraceae;g__Anaerosporobacter;s__Anaerosporobacter mobilis	100.0	0.997	GCF_900142955.1	95.0	d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Lachnospirales;f__Lachnospiraceae;g__Anaerosporobacter;s__Anaerosporobacter mobilis	100.0	0.997	d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Lachnospirales;f__Lachnospiraceae;g__Anaerosporobacter;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCA_018372435.1, s__Anaerosporobacter sp018372435, 95.0, 94.7, 0.913; GCF_012070565.1, s__Anaerosporobacter sp012070565, 95.0, 79.12, 0.355	54.65	11	N/A	Genome has more than 11.7% of markers with multiple hits
-35	d__Bacteria;p__Firmicutes_C;c__Negativicutes;o__Selenomonadales;f__Selenomonadaceae;g__Schwartzia;s__Schwartzia succinivorans	GCF_900129225.1	95.0	d__Bacteria;p__Firmicutes_C;c__Negativicutes;o__Selenomonadales;f__Selenomonadaceae;g__Schwartzia;s__Schwartzia succinivorans	100.0	1.0	GCF_900129225.1	95.0	d__Bacteria;p__Firmicutes_C;c__Negativicutes;o__Selenomonadales;f__Selenomonadaceae;g__Schwartzia;s__Schwartzia succinivorans	100.0	1.0	d__Bacteria;p__Firmicutes_C;c__Negativicutes;o__Selenomonadales;f__Selenomonadaceae;g__;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	N/A	81.67	11	N/A	N/A
-36	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Hydrotalea;s__Hydrotalea sandarakina	GCF_003254115.1	95.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Hydrotalea;s__Hydrotalea sandarakina	97.73	0.846	GCF_003254115.1	95.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Hydrotalea;s__Hydrotalea sandarakina	97.73	0.846	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Hydrotalea;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCA_011362875.1, s__Hydrotalea flava_A, 95.0, 92.52, 0.741; GCA_001623405.1, s__Hydrotalea flava, 95.0, 78.56, 0.446	38.4	11	N/A	Genome has more than 12.5% of markers with multiple hits
-37	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Hydrotalea;s__Hydrotalea sandarakina	GCF_003254115.1	95.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Hydrotalea;s__Hydrotalea sandarakina	99.13	0.933	GCF_003254115.1	95.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Hydrotalea;s__Hydrotalea sandarakina	99.13	0.933	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Hydrotalea;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCA_011362875.1, s__Hydrotalea flava_A, 95.0, 93.75, 0.894; GCA_001623405.1, s__Hydrotalea flava, 95.0, 78.83, 0.519	68.78	11	N/A	Genome has more than 15.0% of markers with multiple hits
-38	d__Bacteria;p__Proteobacteria;c__Alphaproteobacteria;o__Rhodobacterales;f__Rhodobacteraceae;g__Paracoccus;s__Paracoccus denitrificans	GCF_900100045.1	95.0	d__Bacteria;p__Proteobacteria;c__Alphaproteobacteria;o__Rhodobacterales;f__Rhodobacteraceae;g__Paracoccus;s__Paracoccus denitrificans	99.47	0.878	GCF_900100045.1	95.0	d__Bacteria;p__Proteobacteria;c__Alphaproteobacteria;o__Rhodobacterales;f__Rhodobacteraceae;g__Paracoccus;s__Paracoccus denitrificans	99.47	0.878	d__Bacteria;p__Proteobacteria;c__Alphaproteobacteria;o__Rhodobacterales;f__Rhodobacteraceae;g__Paracoccus;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_001447385.1, s__Paracoccus sp001447385, 95.0, 92.4, 0.686; GCF_008824185.1, s__Paracoccus pantotrophus, 95.0, 91.75, 0.773; GCF_000518925.1, s__Paracoccus sp000518925, 95.0, 91.5, 0.76; GCF_000763885.1, s__Paracoccus versutus, 95.0, 91.37, 0.686; GCF_016446475.1, s__Paracoccus binzhouensis, 95.0, 89.81, 0.692; GCF_900156255.1, s__Paracoccus thiocyanatus, 95.0, 89.57, 0.812; GCF_016919705.1, s__Paracoccus sp002359815, 95.0, 87.44, 0.75; GCF_900005615.1, s__Paracoccus aminovorans, 95.0, 87.41, 0.693; GCF_001546115.1, s__Paracoccus aminovorans_B, 95.0, 87.27, 0.674; GCF_000622145.1, s__Paracoccus yeei, 96.0533, 84.9, 0.628; GCF_003337565.1, s__Paracoccus lutimaris, 95.0, 84.81, 0.638; GCF_003285265.1, s__Paracoccus mutanolyticus, 96.0533, 84.8, 0.689; GCF_009301415.1, s__Paracoccus kondratievae, 95.0, 84.68, 0.698; GCA_018056045.1, s__Paracoccus sp018056045, 95.0, 84.65, 0.696; GCF_000763905.1, s__Paracoccus halophilus, 95.0, 84.44, 0.631; GCF_009711185.1, s__Paracoccus limosus, 95.0, 84.27, 0.672; GCF_009696685.1, s__Paracoccus sp009696685, 95.0, 83.89, 0.751; GCF_003709565.1, s__Paracoccus siganidrum, 95.0, 83.61, 0.588; GCF_009711265.1, s__Paracoccus sp009711265, 95.0, 83.19, 0.594; GCF_009711205.1, s__Paracoccus litorisediminis, 95.0, 83.06, 0.496; GCF_004522175.1, s__Paracoccus ravus, 95.0, 82.44, 0.549; GCF_007830335.1, s__Paracoccus sulfuroxidans, 95.0, 82.23, 0.59; GCF_900182695.1, s__Paracoccus laeviglucosivorans, 95.0, 82.18, 0.589; GCF_900142875.1, s__Paracoccus solventivorans, 95.0, 82.17, 0.628; GCF_018860165.1, s__Paracoccus sp018860165, 95.0, 82.15, 0.554; GCF_900631945.1, s__Paracoccus haematequi, 95.0, 81.7, 0.572; GCF_000763805.1, s__Paracoccus sphaerophysae, 95.0, 81.61, 0.647; GCF_009708075.1, s__Paracoccus lichenicola, 95.0, 81.58, 0.568; GCF_017356265.1, s__Paracoccus fontiphilus, 95.0, 81.57, 0.555; GCF_017315735.1, s__Paracoccus sp017315735, 95.0, 81.56, 0.582; GCF_014642735.1, s__Paracoccus acridae, 95.0, 81.46, 0.531; GCF_009711225.1, s__Paracoccus aestuariivivens, 95.0, 81.45, 0.501; GCF_900110285.1, s__Paracoccus alcaliphilus, 95.0, 81.35, 0.518; GCF_900108405.1, s__Paracoccus alkenifer, 95.0, 81.32, 0.632; GCF_002847445.1, s__Paracoccus zhejiangensis, 95.0, 81.31, 0.521; GCF_014656455.1, s__Paracoccus aerius, 95.0, 81.25, 0.5; GCF_002287065.1, s__Paracoccus salipaludis, 95.0, 81.24, 0.59; GCF_003286075.1, s__Paracoccus endophyticus, 95.0, 81.19, 0.633; GCF_004522155.1, s__Paracoccus luteus, 95.0, 81.14, 0.64; GCF_019061185.1, s__Paracoccus sp019061185, 95.0, 81.1, 0.59; GCF_003594815.1, s__Paracoccus aestuarii, 95.0, 81.02, 0.562; GCF_005048225.1, s__Paracoccus gahaiensis, 95.0, 80.97, 0.51; GCF_900102885.1, s__Paracoccus chinensis, 95.0, 80.96, 0.568; GCF_016617715.1, s__Paracoccus sp014164625, 95.0, 80.89, 0.535; GCF_004683865.2, s__Paracoccus liaowanqingii, 95.0, 80.86, 0.427; GCF_900106665.1, s__Paracoccus sanguinis, 95.0, 80.78, 0.592; GCF_002865605.1, s__Paracoccus jeotgali, 95.0, 80.75, 0.541; GCF_900102505.1, s__Paracoccus tibetensis, 95.0, 80.74, 0.513; GCF_900188295.1, s__Paracoccus sediminis, 95.0, 80.67, 0.55; GCF_013868135.1, s__Paracoccus sp013868135, 95.0, 80.63, 0.53; GCF_000420145.1, s__Paracoccus zeaxanthinifaciens, 95.0, 80.6, 0.599; GCF_004310345.1, s__Paracoccus subflavus, 95.0, 80.57, 0.568; GCF_003007735.2, s__Paracoccus marinus_A, 95.0, 80.54, 0.46; GCF_005048265.1, s__Paracoccus hibiscisoli, 95.0, 80.54, 0.525; GCF_006151785.1, s__Paracoccus marcusii, 95.0, 80.51, 0.535; GCF_002105555.1, s__Paracoccus contaminans, 95.0, 80.5, 0.591; GCA_002294185.1, s__Paracoccus sp002294185, 95.0, 80.4, 0.553; GCF_000787695.1, s__Paracoccus sp000787695, 95.0, 80.39, 0.477; GCF_004923205.2, s__Paracoccus aeridis, 95.0, 80.31, 0.542; GCF_018860625.1, s__Paracoccus sp018860625, 95.0, 80.27, 0.506; GCF_007096355.1, s__Paracoccus sp007096355, 95.0, 80.26, 0.484; GCF_000444995.1, s__Paracoccus aminophilus, 95.0, 80.24, 0.428; GCF_007018965.1, s__Paracoccus marinus, 95.0, 80.24, 0.573; GCF_003056335.1, s__Paracoccus indicus, 95.0, 80.18, 0.534; GCF_011308835.1, s__Paracoccus xiamenensis, 95.0, 80.14, 0.509; GCF_900111675.1, s__Paracoccus homiensis, 95.0, 80.1, 0.465; GCF_017744015.1, s__Paracoccus sp002732665, 95.0, 80.09, 0.47; GCF_009674885.1, s__Paracoccus sp009674885, 95.0, 80.06, 0.484; GCF_900101865.1, s__Paracoccus isoporae, 95.0, 80.06, 0.506; GCA_003255745.1, s__Paracoccus saliphilus_A, 95.0, 80.05, 0.49; GCF_003697785.1, s__Paracoccus alkanivorans, 95.0, 80.0, 0.421; GCF_016629665.1, s__Paracoccus caeni, 95.0, 79.96, 0.482; GCF_003259195.1, s__Paracoccus sediminilitoris, 95.0, 79.92, 0.502; GCA_016869875.1, s__Paracoccus sp016869875, 95.0, 79.86, 0.406; GCF_004335005.1, s__Paracoccus sp004335005, 95.0, 79.84, 0.456; GCA_900156835.1, s__Paracoccus saliphilus, 95.0, 79.58, 0.378; GCF_003324675.1, s__Paracoccus suum, 95.0, 79.37, 0.5; GCF_002847305.1, s__Paracoccus sp002847305, 95.0, 79.07, 0.407; GCA_005768755.1, s__Paracoccus denitrificans_B, 95.0, 78.95, 0.364; GCF_900199195.1, s__Paracoccus seriniphilus, 95.0, 78.94, 0.373; GCF_007993065.1, s__Paracoccus aurantiacus, 95.0, 78.87, 0.377; GCF_014490725.1, s__Paracoccus amoyensis, 95.0, 78.85, 0.391; GCA_003240735.1, s__Paracoccus denitrificans_A, 95.0, 78.69, 0.439; GCF_003591515.1, s__Paracoccus sp003591515, 95.0, 78.33, 0.332; GCF_003590715.1, s__Paracoccus sp003590715, 95.0, 78.23, 0.32	65.59	11	N/A	Genome has more than 33.3% of markers with multiple hits
-4	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Hydrotalea;s__Hydrotalea sandarakina	GCF_003254115.1	95.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Hydrotalea;s__Hydrotalea sandarakina	99.99	0.99	GCF_003254115.1	95.0	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Hydrotalea;s__Hydrotalea sandarakina	99.99	0.99	d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Chitinophagales;f__Chitinophagaceae;g__Hydrotalea;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCA_011362875.1, s__Hydrotalea flava_A, 95.0, 94.51, 0.932; GCA_001623405.1, s__Hydrotalea flava, 95.0, 79.19, 0.591	26.13	11	N/A	Genome has more than 73.3% of markers with multiple hits
-5	d__Bacteria;p__Proteobacteria;c__Alphaproteobacteria;o__Rhodobacterales;f__Rhodobacteraceae;g__Meinhardsimonia;s__Meinhardsimonia xiamenensis	GCF_900102905.1	95.0	d__Bacteria;p__Proteobacteria;c__Alphaproteobacteria;o__Rhodobacterales;f__Rhodobacteraceae;g__Meinhardsimonia;s__Meinhardsimonia xiamenensis	100.0	0.999	GCF_900102905.1	95.0	d__Bacteria;p__Proteobacteria;c__Alphaproteobacteria;o__Rhodobacterales;f__Rhodobacteraceae;g__Meinhardsimonia;s__Meinhardsimonia xiamenensis	100.0	0.999	d__Bacteria;p__Proteobacteria;c__Alphaproteobacteria;o__Rhodobacterales;f__Rhodobacteraceae;g__;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	N/A	91.46	11	N/A	N/A
-6	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Xanthomonadales;f__Xanthomonadaceae;g__Lysobacter;s__	N/A	N/A	N/A	N/A	N/A	GCF_014489475.1	95.0	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Xanthomonadales;f__Xanthomonadaceae;g__Lysobacter;s__Lysobacter solisilvae	87.17	0.796	d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Xanthomonadales;f__Xanthomonadaceae;g__Lysobacter;s__	taxonomic classification defined by topology and ANI	classification based on placement in class-level tree	GCF_001427225.1, s__Lysobacter sp001427225, 95.0, 84.08, 0.726; GCF_016613535.2, s__Lysobacter solisilvae_A, 95.0, 82.93, 0.69; GCF_003814555.1, s__Lysobacter tengchongensis, 95.0, 82.62, 0.619; GCF_009765165.1, s__Lysobacter panacisoli, 95.0, 82.36, 0.64; GCF_003586305.1, s__Lysobacter tabacisoli, 95.0, 82.33, 0.649; GCF_016613475.2, s__Lysobacter arenosi, 95.0, 82.23, 0.643; GCF_009765215.1, s__Lysobacter prati, 95.0, 82.11, 0.618; GCF_017308985.1, s__Lysobacter sp017308985, 95.0, 82.08, 0.634; GCF_003382365.1, s__Lysobacter silvisoli, 95.0, 82.05, 0.664; GCF_900114355.1, s__Lysobacter sp900114355, 95.0, 82.04, 0.665; GCF_015453285.1, s__Lysobacter niastensis, 95.0, 82.04, 0.658; GCF_016735495.2, s__Lysobacter sp016735495, 95.0, 82.01, 0.647; GCA_013361435.1, s__Lysobacter sp013361435, 95.0, 81.93, 0.591; GCF_000768335.1, s__Lysobacter arseniciresistens, 95.0, 81.92, 0.555; GCF_003382285.1, s__Lysobacter soli, 95.0, 81.87, 0.642; GCF_001428685.1, s__Lysobacter sp001428685, 95.0, 81.87, 0.682; GCF_001429785.1, s__Lysobacter sp001429785, 95.0, 81.8, 0.669; GCF_900107375.1, s__Lysobacter sp900107375, 95.0, 81.79, 0.691; GCF_007923255.1, s__Lysobacter thermophilus, 95.0, 81.78, 0.578; GCF_001442515.1, s__Lysobacter enzymogenes_B, 95.0, 81.68, 0.712; GCF_017355525.1, s__Lysobacter enzymogenes_C, 95.0, 81.68, 0.672; GCF_000336385.2, s__Lysobacter antibioticus_A, 95.0, 81.66, 0.632; GCA_005503055.1, s__Lysobacter sp005503055, 95.0, 81.61, 0.628; GCF_000768355.1, s__Lysobacter daejeonensis, 95.0, 81.58, 0.548; GCF_018847975.1, s__Lysobacter sp018847975, 95.0, 81.55, 0.673; GCF_007830115.1, s__Lysobacter ruishenii, 95.0, 81.54, 0.556; GCF_900106525.1, s__Lysobacter enzymogenes, 95.0, 81.48, 0.687; GCF_001442535.1, s__Lysobacter antibioticus, 95.0, 81.4, 0.632; GCF_000731095.1, s__Lysobacter antibioticus_B, 95.0, 81.36, 0.618; GCF_003719825.1, s__Lysobacter psychrotolerans, 95.0, 81.34, 0.604; GCF_006546735.2, s__Lysobacter maris, 95.0, 81.34, 0.541; GCF_014651995.1, s__Lysobacter xinjiangensis, 95.0, 81.28, 0.546; GCF_014779555.1, s__Lysobacter capsici, 95.0, 81.21, 0.638; GCF_907164845.1, s__Lysobacter sp907164845, 95.0, 81.17, 0.576; GCF_001442805.1, s__Lysobacter gummosus, 95.0, 81.17, 0.642; GCF_018612875.1, s__Lysobacter sp018612875, 95.0, 81.13, 0.619; GCF_018732085.1, s__Lysobacter capsici_A, 95.0, 81.1, 0.67; GCA_001830245.1, s__Lysobacter sp001830245, 95.0, 81.08, 0.56; GCF_001427785.1, s__Lysobacter sp001427785, 95.0, 81.08, 0.623; GCF_014145325.1, s__Lysobacter spongiae, 95.0, 81.05, 0.553; GCF_004359965.1, s__Lysobacter segetis, 95.0, 81.01, 0.575; GCF_006546775.1, s__Lysobacter aestuarii, 95.0, 80.97, 0.546; GCF_006547045.1, s__Lysobacter alkalisoli, 95.0, 80.94, 0.566; GCF_000768345.1, s__Lysobacter concretionis, 95.0, 80.78, 0.518; GCF_014145395.1, s__Lysobacter penaei, 95.0, 80.76, 0.502; GCF_004361065.1, s__Lysobacter terrigena, 95.0, 80.55, 0.508; GCF_003367355.1, s__Lysobacter sp003367355, 95.0, 80.54, 0.516; GCF_000423325.1, s__Lysobacter defluvii, 95.0, 80.42, 0.515; GCF_000426005.1, s__Lysobacter sp000426005, 95.0, 80.4, 0.515; GCF_015209725.1, s__Lysobacter sp015209725, 95.0, 80.29, 0.481; GCF_900167055.1, s__Lysobacter spongiicola, 95.0, 80.25, 0.489; GCF_014652095.1, s__Lysobacter bugurensis, 95.0, 80.25, 0.522; GCF_008274655.1, s__Lysobacter lacus, 95.0, 80.01, 0.52; GCF_015209765.1, s__Lysobacter sp015209765, 95.0, 79.97, 0.484; GCA_004322525.1, s__Lysobacter sp004322525, 95.0, 79.81, 0.529; GCA_902805755.1, s__Lysobacter sp902805755, 95.0, 79.81, 0.544; GCF_000855665.1, s__Lysobacter sp000855665, 95.0, 79.58, 0.461	72.88	11	0.98425	Genome not assigned to closest species as it falls outside its pre-defined ANI radius
-7	d__Bacteria;p__Desulfobacterota;c__Desulfobacteria;o__Desulfobacterales;f__Desulfatibacillaceae;g__Desulfatibacillum;s__Desulfatibacillum alkenivorans	GCF_900142135.1	95.0	d__Bacteria;p__Desulfobacterota;c__Desulfobacteria;o__Desulfobacterales;f__Desulfatibacillaceae;g__Desulfatibacillum;s__Desulfatibacillum alkenivorans	100.0	1.0	GCF_900142135.1	95.0	d__Bacteria;p__Desulfobacterota;c__Desulfobacteria;o__Desulfobacterales;f__Desulfatibacillaceae;g__Desulfatibacillum;s__Desulfatibacillum alkenivorans	100.0	1.0	d__Bacteria;p__Desulfobacterota;c__Desulfobacteria;o__Desulfobacterales;f__Desulfatibacillaceae;g__Desulfatibacillum;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCF_000429905.1, s__Desulfatibacillum aliphaticivorans, 95.0, 93.06, 0.876; GCA_016342355.1, s__Desulfatibacillum sp016342355, 95.0, 79.44, 0.52	85.86	11	N/A	N/A
-8	d__Bacteria;p__Firmicutes;c__Bacilli;o__Acholeplasmatales;f__Anaeroplasmataceae;g__Anaeroplasma;s__Anaeroplasma bactoclasticum	GCF_003550015.1	95.0	d__Bacteria;p__Firmicutes;c__Bacilli;o__Acholeplasmatales;f__Anaeroplasmataceae;g__Anaeroplasma;s__Anaeroplasma bactoclasticum	99.22	0.892	GCF_003550015.1	95.0	d__Bacteria;p__Firmicutes;c__Bacilli;o__Acholeplasmatales;f__Anaeroplasmataceae;g__Anaeroplasma;s__Anaeroplasma bactoclasticum	99.22	0.892	d__Bacteria;p__Firmicutes;c__Bacilli;o__Acholeplasmatales;f__Anaeroplasmataceae;g__Anaeroplasma;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCA_017388605.1, s__Anaeroplasma sp017388605, 95.0, 83.89, 0.71; GCA_017449215.1, s__Anaeroplasma sp017449215, 95.0, 78.37, 0.262; GCA_017441525.1, s__Anaeroplasma sp017441525, 95.0, 78.17, 0.272; GCA_002449755.1, s__Anaeroplasma sp002449755, 95.0, 78.14, 0.275; GCA_017462645.1, s__Anaeroplasma sp017462645, 95.0, 78.0, 0.236; GCA_017524905.1, s__Anaeroplasma sp017524905, 95.0, 77.92, 0.242; GCA_016280975.1, s__Anaeroplasma sp016280975, 95.0, 77.86, 0.273; GCA_017444645.1, s__Anaeroplasma sp017444645, 95.0, 77.57, 0.26; GCA_900770055.1, s__Anaeroplasma sp900770055, 95.0, 77.54, 0.192; GCA_902783745.1, s__Anaeroplasma sp902783745, 95.0, 77.5, 0.231; GCA_016282815.1, s__Anaeroplasma sp016282815, 95.0, 77.44, 0.216; GCA_017542485.1, s__Anaeroplasma sp017542485, 95.0, 77.43, 0.189; GCA_016288855.1, s__Anaeroplasma sp016288855, 95.0, 77.42, 0.212; GCA_015059145.1, s__Anaeroplasma sp015059145, 95.0, 77.4, 0.199; GCA_900767915.1, s__Anaeroplasma sp900767915, 95.0, 77.38, 0.187; GCA_017454375.1, s__Anaeroplasma sp017454375, 95.0, 77.11, 0.128; GCA_902796895.1, s__Anaeroplasma sp902796895, 95.0, 76.99, 0.242; GCA_018715825.1, s__Anaeroplasma faecigallinarum, 95.0, 76.73, 0.118; GCA_905236965.1, s__Anaeroplasma sp905236965, 95.0, 76.07, 0.2; GCA_905236105.1, s__Anaeroplasma sp905236105, 95.0, 76.05, 0.133	57.15	11	N/A	Genome has more than 10.0% of markers with multiple hits
-9	d__Bacteria;p__Firmicutes;c__Bacilli;o__Acholeplasmatales;f__Anaeroplasmataceae;g__Anaeroplasma;s__Anaeroplasma bactoclasticum	GCF_003550015.1	95.0	d__Bacteria;p__Firmicutes;c__Bacilli;o__Acholeplasmatales;f__Anaeroplasmataceae;g__Anaeroplasma;s__Anaeroplasma bactoclasticum	100.0	1.0	GCF_003550015.1	95.0	d__Bacteria;p__Firmicutes;c__Bacilli;o__Acholeplasmatales;f__Anaeroplasmataceae;g__Anaeroplasma;s__Anaeroplasma bactoclasticum	100.0	1.0	d__Bacteria;p__Firmicutes;c__Bacilli;o__Acholeplasmatales;f__Anaeroplasmataceae;g__Anaeroplasma;s__	taxonomic classification defined by topology and ANI	topological placement and ANI have congruent species assignments	GCA_017388605.1, s__Anaeroplasma sp017388605, 95.0, 84.15, 0.658; GCA_002449755.1, s__Anaeroplasma sp002449755, 95.0, 78.65, 0.256; GCA_017441525.1, s__Anaeroplasma sp017441525, 95.0, 78.34, 0.265; GCA_017449215.1, s__Anaeroplasma sp017449215, 95.0, 78.33, 0.263; GCA_017524905.1, s__Anaeroplasma sp017524905, 95.0, 78.01, 0.244; GCA_017462645.1, s__Anaeroplasma sp017462645, 95.0, 78.0, 0.23; GCA_016280975.1, s__Anaeroplasma sp016280975, 95.0, 77.96, 0.23; GCA_017542485.1, s__Anaeroplasma sp017542485, 95.0, 77.74, 0.195; GCA_017444645.1, s__Anaeroplasma sp017444645, 95.0, 77.7, 0.258; GCA_900767915.1, s__Anaeroplasma sp900767915, 95.0, 77.52, 0.172; GCA_016288855.1, s__Anaeroplasma sp016288855, 95.0, 77.51, 0.196; GCA_902783745.1, s__Anaeroplasma sp902783745, 95.0, 77.5, 0.209; GCA_016282815.1, s__Anaeroplasma sp016282815, 95.0, 77.5, 0.201; GCA_900770055.1, s__Anaeroplasma sp900770055, 95.0, 77.43, 0.184; GCA_015059145.1, s__Anaeroplasma sp015059145, 95.0, 77.28, 0.183; GCA_902796895.1, s__Anaeroplasma sp902796895, 95.0, 77.2, 0.221; GCA_017454375.1, s__Anaeroplasma sp017454375, 95.0, 77.19, 0.129; GCA_018715825.1, s__Anaeroplasma faecigallinarum, 95.0, 76.79, 0.111; GCA_905236965.1, s__Anaeroplasma sp905236965, 95.0, 76.42, 0.19; GCA_905236105.1, s__Anaeroplasma sp905236105, 95.0, 76.12, 0.118	66.58	11	N/A	N/A
\ No newline at end of file
--- a/test-data/test_gtdb_to_taxdump_file.tsv	Sun Sep 08 14:37:41 2024 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,25 +0,0 @@
-ncbi_taxonomy	gtdb_taxonomy	lca_frac	target_tax_level	lineage
-s__Williamsia_A herbipolensis	unclassified	NA	NA	NA
-s__Xylella fastidiosa	s__Xylella fastidiosa	1.0	species	d__bacteria;p__pseudomonadota;c__gammaproteobacteria;o__xanthomonadales;f__xanthomonadaceae;g__xylella;s__xylella fastidiosa
-s__Paramaledivibacter caminithermalis	s__Paramaledivibacter caminithermalis	1.0	species	d__bacteria;p__bacillota_a;c__clostridia;o__peptostreptococcales;f__caminicellaceae;g__paramaledivibacter;s__paramaledivibacter caminithermalis
-s__Flavisolibacter ginsengisoli	s__Flavisolibacter ginsengisoli	1.0	species	d__bacteria;p__bacteroidota;c__bacteroidia;o__chitinophagales;f__chitinophagaceae;g__flavisolibacter;s__flavisolibacter ginsengisoli
-s__Anaeroplasma bactoclasticum	c__Bacilli	1.0	class	d__bacteria;p__bacillota;c__bacilli
-s__Pseudoduganella sp001425045	unclassified	NA	NA	NA
-s__Albidovulum denitrificans	unclassified	NA	NA	NA
-s__Tepidibacter formicigenes	s__Tepidibacter formicigenes	1.0	species	d__bacteria;p__bacillota_a;c__clostridia;o__peptostreptococcales;f__peptostreptococcaceae;g__tepidibacter;s__tepidibacter formicigenes
-s__Thermosporothrix hazakensis	unclassified	NA	NA	NA
-s__Exiguobacterium_A sp001423965	unclassified	NA	NA	NA
-s__Andreprevotia lacus	s__Andreprevotia lacus	1.0	species	d__bacteria;p__pseudomonadota;c__gammaproteobacteria;o__burkholderiales;f__chitinibacteraceae;g__andreprevotia;s__andreprevotia lacus
-s__Nonlabens dokdonensis	g__Nonlabens	1.0	genus	d__bacteria;p__bacteroidota;c__bacteroidia;o__flavobacteriales;f__flavobacteriaceae;g__nonlabens
-s__Pseudomonas aeruginosa	s__Pseudomonas aeruginosa	0.99	species	d__bacteria;p__pseudomonadota;c__gammaproteobacteria;o__pseudomonadales;f__pseudomonadaceae;g__pseudomonas;s__pseudomonas aeruginosa
-s__Paracoccus denitrificans	g__Paracoccus	1.0	genus	d__bacteria;p__pseudomonadota;c__alphaproteobacteria;o__rhodobacterales;f__rhodobacteraceae;g__paracoccus
-N/A	unclassified	NA	NA	NA
-s__Anaerobranca californiensis	s__Anaerobranca californiensis	1.0	species	d__bacteria;p__bacillota_d;c__proteinivoracia;o__proteinivoracales;f__proteinivoraceae;g__anaerobranca;s__anaerobranca californiensis
-s__Hydrotalea sandarakina	s__Hydrotalea sandarakina	1.0	species	d__bacteria;p__bacteroidota;c__bacteroidia;o__chitinophagales;f__chitinophagaceae;g__hydrotalea;s__hydrotalea sandarakina
-s__Schwartzia succinivorans	f__Selenomonadaceae	1.0	family	d__bacteria;p__bacillota_c;c__negativicutes;o__selenomonadales;f__selenomonadaceae
-s__Pseudoduganella sp001425265	unclassified	NA	NA	NA
-s__Lampropedia hyalina	s__Lampropedia hyalina	1.0	species	d__bacteria;p__pseudomonadota;c__gammaproteobacteria;o__burkholderiales;f__burkholderiaceae_b;g__lampropedia;s__lampropedia hyalina
-s__Phycicoccus sp001428065	unclassified	NA	NA	NA
-s__Anaerosporobacter mobilis	s__Anaerosporobacter mobilis	1.0	species	d__bacteria;p__bacillota_a;c__clostridia;o__lachnospirales;f__lachnospiraceae;g__anaerosporobacter;s__anaerosporobacter mobilis
-s__Meinhardsimonia xiamenensis	s__Meinhardsimonia xiamenensis	1.0	species	d__bacteria;p__pseudomonadota;c__alphaproteobacteria;o__rhodobacterales;f__rhodobacteraceae;g__meinhardsimonia;s__meinhardsimonia xiamenensis
-s__Desulfatibacillum alkenivorans	s__Desulfatibacillum alkenivorans	1.0	species	d__bacteria;p__desulfobacterota;c__desulfobacteria;o__desulfobacterales;f__desulfatibacillaceae;g__desulfatibacillum;s__desulfatibacillum alkenivorans
--- a/test-data/test_taxonkit_file_1.tsv	Sun Sep 08 14:37:41 2024 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,11 +0,0 @@
-unclassified	12908
-Xylella fastidiosa	2371
-Paramaledivibacter caminithermalis	191027
-Flavisolibacter ginsengisoli	462367
-Bacilli	91061
-unclassified	12908
-unclassified	12908
-Tepidibacter formicigenes	227138
-unclassified	12908
-unclassified	12908
-Andreprevotia lacus	1121000
--- a/test-data/test_taxonkit_file_2.tsv	Sun Sep 08 14:37:41 2024 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,14 +0,0 @@
-Nonlabens	363408
-Pseudomonas aeruginosa	287
-Paracoccus	265
-Paracoccus	249411
-unclassified	12908
-Anaerobranca californiensis	182411
-Hydrotalea sandarakina	1004304
-Selenomonadaceae	1843491
-unclassified	12908
-Lampropedia hyalina	198706
-unclassified	12908
-Anaerosporobacter mobilis	264463
-Meinhardsimonia xiamenensis	990712
-Desulfatibacillum alkenivorans	259354