# HG changeset patch
# User iuc
# Date 1652188685 0
# Node ID c840a1c77a0a71f4799e8ebc4513515cdde6f762

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/prot-scriber commit 8b58f3f03d6430689d228029bb2eb46c16cfff23

diff -r 000000000000 -r c840a1c77a0a prot-scriber.xml
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/prot-scriber.xml	Tue May 10 13:18:05 2022 +0000
@@ -0,0 +1,310 @@
+<tool id="prot_scriber" name="prot-scriber" version="@TOOL_VERSION@" profile="21.05">
+  <description>Protein annotation of short human readable descriptions</description>
+  <macros>
+    <token name="@TOOL_VERSION@">0.1.1</token>
+  </macros>
+  <requirements>
+    <requirement type="package" version="@TOOL_VERSION@">prot-scriber</requirement>
+  </requirements>
+  <stdio>
+    <regex match="panicked" level="fatal" source="stderr" />
+  </stdio>
+  <command>
+    <![CDATA['prot-scriber'
+    #if str($input_config.input_config_selector) == "basic"
+      #for $sst in $input_config.seq_sim_table
+        -s '$sst'
+      #end for
+    #else if str($input_config.input_config_selector) == "advanced"
+      #for $ssr in $input_config.advanced_input_repeat
+        -s '$ssr.seq_sim_table'
+        #if $ssr.header
+          -e '$ssr.header'
+        #end if
+        #if $ssr.field_separator
+          -p '$ssr.field_separator'
+        #end if
+        #if $ssr.blacklist_regexs
+          -b '$ssr.blacklist_regexs'
+        #end if
+        #if $ssr.capture_replace_pairs
+          -c '$ssr.capture_replace_pairs'
+        #end if
+        #if $ssr.filter_regexs
+          -l '$ssr.filter_regexs'
+        #end if
+      #end for   
+      #if $input_config.expert_options.non_informative_words_regexs
+        -w '$input_config.expert_options.non_informative_words_regexs'
+      #end if
+      #if $input_config.expert_options.description_split_regex
+        -r "$input_config.expert_options.description_split_regex"
+      #end if
+      #if $input_config.expert_options.center_inverse_word_information_content_at_quantile
+        -q $input_config.expert_options.center_inverse_word_information_content_at_quantile
+      #end if
+    #end if
+    #if $seq_family.seq_families
+      -f '$seq_families'
+    #end if
+    #if $seq_family.annotate_non_family_queries
+      -a
+    #end if
+    #if $seq_family.seq_family_gene_ids_separator
+      -g "$seq_family_gene_ids_separator"
+    #end if
+    #if $seq_family.seq_family_id_genes_separator
+      -i '$seq_family_id_genes_separator'
+    #end if
+    -o '$output'
+    ]]>
+  </command>
+  <inputs>
+    <conditional name="input_config">
+      <param type="select" name="input_config_selector" label="Choose input configuration options">
+        <option value="basic" selected="true">Basic</option>
+        <option value="advanced">Advanced</option>
+      </param>
+      <when value="basic">
+        <param type="data" multiple="true" name="seq_sim_table" argument="-s" format="tabular" label="Sequence similarity search results in tabular format (-s)" help="Files in which to find sequence similarity search results in tabular format (SSST). Use e.g. Blast or Diamond to produce them.
+        Required columns are: 'qacc sacc stitle' (Blast) or 'qseqid sseqid stitle' (Diamond)." /> 
+      </when>
+      <when value="advanced">
+        <repeat name="advanced_input_repeat" title="Sequence similarity table" min="1" default="1">
+          <param type="data" name="seq_sim_table" argument="-s" format="tabular" label="Sequence similarity search result in tabular format (-s)" help="File in which to find sequence similarity search results in tabular format (SSST). Use e.g. Blast or Diamond to produce them.
+          Required columns are: 'qacc sacc stitle' (Blast) or 'qseqid sseqid stitle' (Diamond)." /> 
+          <param type="text" optional="true" name="field_separator" argument="-p" label="Field separator (-p)" help="Field-Separator of the (-s) sequence similarity table. The default value is the 'TAB' character. Set to 'default' to use the hard coded default">
+            <sanitizer>
+              <valid initial="default">
+                <add preset="string.printable" />
+              </valid>
+            </sanitizer>
+          </param>
+          <param type="text" optional="true" name="header" argument="-e" label="Header of the sequence similarity tables (-e)" help="Header of the (-s) sequence similarity table. Separated by space (' ') the names of the
+            in order of appearance in the respective table. Required and default columns are 'qacc sacc stitle'. Set to 'default' to use the hard coded default" />
+          <param type="data" optional="true" name="blacklist_regexs" argument="-b" format="tabular" label="Blacklist Regexs (-b)" help="A file with regular expressions, one per line. Any match to any of these
+            regular expressions causes sequence similarity search result descriptions ('stitle' in Blast terminology) to be discarded from the prot-scriber annotation process. Set to 'default' to use the hard coded default" />
+          <param type="data" optional="true" name="capture_replace_pairs" argument="-c" format="tabular" label="Capture replace pairs (-c)" help="A file with pairs of lines. Within each pair the first line is a regular expressions
+            defining one or more capture groups. The second line of a pair is the string used to replace the match in the regular expression with. Set to 'default' to use the hard coded default" />
+          <param type="data" optional="true" name="filter_regexs" argument="-l" format="tabular" label="Filter regexs (-l)" help="A file with regular expressions, one per line. Any match to any of these
+            regular expressions causes the matched sub-string to be deleted, i.e. filtered out. Set to 'default' to use the hard coded default" /> 
+        </repeat>
+        <section title="Expert options" name="expert_options">
+          <param type="data" optional="true" name="non_informative_words_regexs" argument="-w" format="tabular" label="Non informative words regexs (-w)" help="A file in which regular expressions (regexs) are stored, one per line. These
+            regexs are used to recognize non-informative words, which will only receive a minimum score in the prot-scriber process that generates human readable description." />
+          <param type="text" optional="true" name="description_split_regex" argument="-r" label="Description split regex (-r)" help="A regular expression to be used to split descriptions (`stitle` in Blast
+            terminology) into words. Default is '([~_\-/|\;,':.\s]+)'.">
+            <sanitizer>
+              <valid initial="default">
+                <add preset="string.printable" />
+              </valid>
+            </sanitizer>
+          </param>
+          <param type="integer" optional="true" name="center_inverse_word_information_content_at_quantile" argument="-q" label="Center inverse word-information-content at quantile (-q)" help="The quantile (percentile) to be subtracted from calculated inverse word information
+            content to center these values. Value between 0 and 1." />
+        </section>
+      </when>
+    </conditional>
+    <section title="Sequence family annotation" name="seq_family">
+      <param type="data" optional="true" name="seq_families" argument="-f" format="tabular" label="Families of biological sequences (-f)" help="A file in which families of biological sequences are stored, one family per line. Each
+        line must have format 'fam_name TAB gene1,gene2,gene3'. Make sure no gene appears in
+        more than one family." />
+      <param type="boolean" optional="true" name="annotate_non_family_queries" argument="-a" label="Annotate non family query sequences (-a)" help="Set this to true to also annotate sequences are not member of a sequence family." />
+      <param type="text" optional="true" name="seq_family_gene_ids_separator" argument="-g" label="Sequence family file gene-id separator (-g)" help=" A regular expression used to split the list of gene_identifiers in the
+        argument --seq-families (-f) gene families file. Default is '(\s*,\s*|\s+)'.">
+        <sanitizer>
+          <valid initial="default">
+            <add preset="string.printable" />
+          </valid>
+        </sanitizer>
+      </param>
+      <param type="text" optional="true" name="seq_family_id_genes_separator" argument="-i" label="Sequence family file family - gene-id separator (-i)" help="A string used as separator in the argument --seq-families (-f) gene families file. This
+        string separates the gene_family_identifier (name) from the gene_identifier list that family comprises. Default is 'TAB'.">
+        <sanitizer>
+          <valid initial="default">
+            <add preset="string.printable" />
+          </valid>
+        </sanitizer>
+      </param>
+    </section>
+  </inputs>
+  <outputs>
+    <data format="tabular" name="output" />
+  </outputs>
+  <tests>
+    <test>
+      <param name="input_config_selector" value="basic"/>
+      <param name="seq_sim_table" value="8_Proteins_vs_Swissprot_blastp.txt" />
+      <param name="seq_sim_table" value="8_Proteins_vs_Trembl_blastp.txt" />
+      <output name="output" file="8_Proteins_prot-scriber.out" sort="true" />
+    </test>
+    <test>
+      <param name="input_config_selector" value="advanced" />
+      <repeat name="advanced_input_repeat">
+        <param name="seq_sim_table" value="8_Proteins_vs_Swissprot_blastp.txt" />
+        <param name="field_separator" value="default" />
+        <param name="header" value="qacc sacc stitle" />
+      </repeat>
+      <repeat name="advanced_input_repeat">
+        <param name="seq_sim_table" value="8_Proteins_vs_Trembl_blastp.txt" />
+        <param name="field_separator" value="default" />
+        <param name="header" value="qacc sacc stitle" />
+      </repeat>
+      <output name="output" file="8_Proteins_prot-scriber.out" sort="true" />
+    </test>
+    <test>
+      <param name="input_config_selector" value="advanced" />
+      <repeat name="advanced_input_repeat">
+        <param name="seq_sim_table" value="8_Proteins_vs_Swissprot_blastp.txt" />
+        <param name="blacklist_regexs" value="blacklist_stitle_regexs.txt" />
+      </repeat>
+      <repeat name="advanced_input_repeat">
+        <param name="seq_sim_table" value="8_Proteins_vs_Trembl_blastp.txt" />
+        <param name="blacklist_regexs" value="blacklist_stitle_regexs.txt" />
+      </repeat>
+      <param name="description_split_regex" value="([~_\-/|;,':.\s]+)" />
+      <param name="center_inverse_word_information_content_at_quantile" value="50" />
+      <output name="output" file="8_Proteins_prot-scriber.out" sort="true" />
+    </test>
+  </tests>
+  <help>
+    <![CDATA[
+
+**What it does**
+    
+prot-scriber_ assigns short human readable descriptions (HRD) to query biological sequences using reference candidate descriptions.
+In this, prot-scriber consumes sequence similarity search (Blast or Diamond or similar) results in tabular format.
+customized lexical analysis is carried out on the descriptions of these Blast Hits and a resulting HRD is assigned to the query sequences.
+For more information, examples and how to use the prot-scriber commandline tool refer to the prot-scriber README_ and MANUAL_.
+
+.. _prot-scriber: http://github.com/usadellab/prot-scriber
+.. _README: https://github.com/usadellab/prot-scriber/blob/master/README.md
+.. _MANUAL: https://github.com/usadellab/prot-scriber/blob/master/README.md#manual
+
+----
+
+**Input**
+
+The input file is one or multiple tabular output(s) of a sequence similarity search (Blast, Diamon or similar).
+Required columns are: 'qacc sacc stitle' (Blast) or 'qseqid sseqid stitle' (Diamond). The input is done via the -s parameter::
+
+    -s, --seq-sim-table
+            File in which to find sequence similarity search results in tabular format (SSST). Use
+            e.g. Blast or Diamond to produce them. Required columns are: 'qacc sacc stitle' (Blast)
+            or 'qseqid sseqid stitle' (Diamond). If the required columns, or more, appear in different order than
+            shown here you must use the --header (-e) argument. If any of the input SSSTs uses a
+            different field-separator than the '<TAB>' character, you must provide the --field-
+            separator (-p) argument. You can provide multiple SSSTs for your query proteins whose information
+            will be combined and evaluated by the tool.
+
+**Input parameters**
+
+prot-scriber gives the user the opportunity to fine tune parameters for the provided input tables.
+To do so turn on the *input configuration* switch. Those are optional, as the tool also provides sensible defaults.
+In case you decide to customize your inputs using below parameters, be advised that prot-scriber expects the
+customized parameter for all input tables - the number of tables and e.g. *--header* parameters have to match.
+You can set the values to 'default' if you want to use the default value for a given input table::
+  
+    -e, --header
+            Header of the --seq-sim-table (-s) arg. Separated by space (' ') the names of the
+            columns in order of appearance in the respective table. Required and default columns are
+            'qacc sacc stitle'. Note that this option only understands Blast terminology, i.e. even
+            if you ran Diamond, please provide 'qacc' instead of 'qseqid' and 'sacc' instead of
+            'sseqid'. Luckily 'stitle' is 'stitle' in Diamond, too. You can have additional columns
+            that will be ignored, as long as the required columns appear in the correct order.
+            Consider this example: 'qacc sacc evalue bitscore stitle'. Set to 'default' to use the hard coded default.
+  
+    -p, --field-separator
+            Field-Separator of the --seq-sim-table (-s) arg. The default value is the '<TAB>' character.
+            Consider this example: ','. You can provide 'default' to use the hard coded default (TAB).
+
+    -b, --blacklist-regexs (Expert option)
+            A file with regular expressions, one per line. Any match to any of these
+            regular expressions causes sequence similarity search result descriptions ('stitle' in
+            Blast terminology) to be discarded from the prot-scriber annotation process. Set to 'default' to use the hard
+            coded default. An example file can be downloaded here:
+            https://raw.githubusercontent.com/usadellab/prot-scriber/master/misc/blacklist_stitle_regexs.txt.
+
+    -l, --filter-regexs (Expert option)
+            A file with regular expressions, one per line. Any match to any of these
+            regular expressions causes the matched sub-string to be deleted, i.e. filtered out.
+            Filtering is used to process descriptions ('stitle' in Blast terminology) and prepare
+            the descriptions for the prot-scriber annotation process. In case of UniProt sequence
+            similarity search results (Blast result tables), this removes the Blast Hit identifier
+            (`sacc`) from the description (`stitle`) and also removes the taxonomic information
+            starting with e.g. 'OS=' at the end of the `stitle` strings. Set to 'default' to use 
+            hard coded default. Anexample file can be downloaded here:
+            https://raw.githubusercontent.com/usadellab/prot-scriber/master/misc/filter_stitle_regexs.txt.
+
+    -c, --capture-replace-pairs (Expert option)
+            A file with pairs of lines. Within each pair the first line is a regular expressions
+            defining one or more capture groups. The second line of a pair is the
+            string used to replace the match in the regular expression with. This means the second
+            line contains the capture groups. These pairs are used to further filter
+            the sequence similarity search result descriptions ('stitle' in Blast terminology). In
+            contrast to the --filter-regex (-l) matches are not deleted, but replaced with the
+            second line of the pair. Filtering is used to process descriptions ('stitle' in Blast
+            terminology) and prepare the descriptions for the prot-scriber annotation process.
+            Set to 'default' to use the hard coded default. An example file can be downloaded here:
+            https://raw.githubusercontent.com/usadellab/prot-scriber/master/misc/capture_replace_pairs.txt.
+
+----
+
+**Gene family annotation**
+
+prot-scriber can also apply the same methodology to produce HRDs for sets of biological sequences, i.e. gene families::
+
+    -f, --seq-families
+            A file in which families of biological sequences are stored, one family per line. Each
+            line must have format 'fam-name TAB gene1,gene2,gene3'. Make sure no gene appears in
+            more than one family.
+
+    -g, --seq-family-gene-ids-separator 
+            A regular expression used to split the list of gene-identifiers in the
+            argument --seq-families (-f) gene families file. Default is '(\s*,\s*|\s+)'.
+
+    -a, --annotate-non-family-queries
+            Use this option only in combination with --seq-families (-f), i.e. when prot-scriber is
+            used to generate human readable descriptions for gene families. If in that context this
+            flag is given, queries for which there are sequence similarity search (Blast) results
+            but that are NOT member of a sequence family will receive an annotation (human readable
+            description) in the output file, too. Default value of this setting is 'OFF' (false).
+
+----
+
+**Expert options**
+
+Some additional optional configuration. Only use when you know what you are doing::
+
+    -w, --non-informative-words-regexs
+            A file in which regular expressions (regexs) are stored, one per line. These
+            regexs are used to recognize non-informative words, which will only receive a minimun
+            score in the prot-scriber process that generates human readable description. There is a
+            default list hard-coded into prot-scriber. An example file can be downloaded here:
+            https://raw.githubusercontent.com/usadellab/prot-scriber/master/misc/non_informative_words_regexs.txt.
+
+    -r, --description-split-regex
+            A regular expression to be used to split descriptions (`stitle` in Blast
+            terminology) into words. Default is '([~_\-/|\;,':.\s]+)'.
+
+    -q, --center-inverse-word-information-content-at-quantile
+            The quantile (percentile) to be subtracted from calculated inverse word information
+            content to center these values. Consequently, this must be a value between zero and one
+            or literal 50, which is interpreted as mean instead of a quantile. Default is 50,
+            implying centering at the mean.
+
+----
+
+**Output**
+
+prot-scriber outputs a single tab-separated text file with the annotated sequences or gene-families, depending on how you ran the program, one result per line::
+
+    Annotee-Identifier	Human-Readable-Description
+    Soltu.DM.02G020600.1	arath strubbelig receptor family
+    Soltu.DM.S001650.1	germin member
+    Soltu.DM.03G011280.1	increased dna methylation
+    ...
+
+    ]]>
+  </help>
+</tool>
diff -r 000000000000 -r c840a1c77a0a test-data/8_Proteins_prot-scriber.out
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/8_Proteins_prot-scriber.out	Tue May 10 13:18:05 2022 +0000
@@ -0,0 +1,9 @@
+Annotee-Identifier	Human-Readable-Description
+Soltu.DM.02G020600.1	arath strubbelig receptor family
+Soltu.DM.S001650.1	germin member
+Soltu.DM.03G011280.1	increased dna methylation
+Soltu.DM.02G015700.1	lrr receptor serine threonine kinase
+Soltu.DM.07G016620.1	gdsl esterase lipase
+Soltu.DM.04G035790.1	phosphatidylinositol phosphatidylcholine transfer sfh
+Soltu.DM.01G022510.1	5 amp activated kinase subunit gamma
+Soltu.DM.01G045390.1	hva
diff -r 000000000000 -r c840a1c77a0a test-data/8_Proteins_vs_Swissprot_blastp.txt
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/8_Proteins_vs_Swissprot_blastp.txt	Tue May 10 13:18:05 2022 +0000
@@ -0,0 +1,136 @@
+Soltu.DM.02G015700.1	sp|Q1MX30|XA21_ORYSI	sp|Q1MX30|XA21_ORYSI Receptor kinase-like protein Xa21 OS=Oryza sativa subsp. indica OX=39946 GN=XA21 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|Q2R2D5|XA21_ORYSJ	sp|Q2R2D5|XA21_ORYSJ Receptor kinase-like protein Xa21 OS=Oryza sativa subsp. japonica OX=39947 GN=XA21 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|C0LGP4|Y3475_ARATH	sp|C0LGP4|Y3475_ARATH Probable LRR receptor-like serine/threonine-protein kinase At3g47570 OS=Arabidopsis thaliana OX=3702 GN=At3g47570 PE=2 SV=1
+Soltu.DM.02G015700.1	sp|C0LGT6|EFR_ARATH	sp|C0LGT6|EFR_ARATH LRR receptor-like serine/threonine-protein kinase EFR OS=Arabidopsis thaliana OX=3702 GN=EFR PE=1 SV=1
+Soltu.DM.02G015700.1	sp|Q9SD62|Y3471_ARATH	sp|Q9SD62|Y3471_ARATH Putative receptor-like protein kinase At3g47110 OS=Arabidopsis thaliana OX=3702 GN=At3g47110 PE=3 SV=1
+Soltu.DM.02G015700.1	sp|Q9ZUI0|Y2241_ARATH	sp|Q9ZUI0|Y2241_ARATH Putative leucine-rich repeat receptor-like serine/threonine-protein kinase At2g24130 OS=Arabidopsis thaliana OX=3702 GN=At2g24130 PE=3 SV=1
+Soltu.DM.02G015700.1	sp|Q9FL28|FLS2_ARATH	sp|Q9FL28|FLS2_ARATH LRR receptor-like serine/threonine-protein kinase FLS2 OS=Arabidopsis thaliana OX=3702 GN=FLS2 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|Q9SJG2|Y2296_ARATH	sp|Q9SJG2|Y2296_ARATH Probable receptor-like protein kinase At2g42960 OS=Arabidopsis thaliana OX=3702 GN=At2g42960 PE=3 SV=1
+Soltu.DM.02G015700.1	sp|Q9LRP3|Y3174_ARATH	sp|Q9LRP3|Y3174_ARATH Probable receptor-like protein kinase At3g17420 OS=Arabidopsis thaliana OX=3702 GN=At3g17420 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|Q9LYN8|EMS1_ARATH	sp|Q9LYN8|EMS1_ARATH Leucine-rich repeat receptor protein kinase EMS1 OS=Arabidopsis thaliana OX=3702 GN=EMS1 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|Q3EDL4|Y1154_ARATH	sp|Q3EDL4|Y1154_ARATH Probable serine/threonine-protein kinase At1g01540 OS=Arabidopsis thaliana OX=3702 GN=At1g01540 PE=1 SV=2
+Soltu.DM.02G015700.1	sp|C0LGF4|FEI1_ARATH	sp|C0LGF4|FEI1_ARATH LRR receptor-like serine/threonine-protein kinase FEI 1 OS=Arabidopsis thaliana OX=3702 GN=FEI1 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|C0LGQ5|GSO1_ARATH	sp|C0LGQ5|GSO1_ARATH LRR receptor-like serine/threonine-protein kinase GSO1 OS=Arabidopsis thaliana OX=3702 GN=GSO1 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|C0LGJ1|Y1743_ARATH	sp|C0LGJ1|Y1743_ARATH Probable LRR receptor-like serine/threonine-protein kinase At1g74360 OS=Arabidopsis thaliana OX=3702 GN=At1g74360 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|Q9FZB1|Y5188_ARATH	sp|Q9FZB1|Y5188_ARATH Probable LRR receptor-like serine/threonine-protein kinase At1g51880 OS=Arabidopsis thaliana OX=3702 GN=At1g51880 PE=2 SV=1
+Soltu.DM.02G015700.1	sp|Q9SHI2|Y1723_ARATH	sp|Q9SHI2|Y1723_ARATH Leucine-rich repeat receptor-like serine/threonine-protein kinase At1g17230 OS=Arabidopsis thaliana OX=3702 GN=At1g17230 PE=1 SV=2
+Soltu.DM.02G015700.1	sp|Q9C7S5|PSYR1_ARATH	sp|Q9C7S5|PSYR1_ARATH Tyrosine-sulfated glycopeptide receptor 1 OS=Arabidopsis thaliana OX=3702 GN=PSY1R PE=1 SV=1
+Soltu.DM.02G015700.1	sp|O49564|CRK27_ARATH	sp|O49564|CRK27_ARATH Cysteine-rich receptor-like protein kinase 27 OS=Arabidopsis thaliana OX=3702 GN=CRK27 PE=3 SV=2
+Soltu.DM.02G015700.1	sp|Q0JA29|FLS2_ORYSJ	sp|Q0JA29|FLS2_ORYSJ LRR receptor-like serine/threonine-protein kinase FLS2 OS=Oryza sativa subsp. japonica OX=39947 GN=FLS2 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|Q7G768|BRL2_ORYSJ	sp|Q7G768|BRL2_ORYSJ Brassinosteroid LRR receptor kinase BRL2 OS=Oryza sativa subsp. japonica OX=39947 GN=BRL2 PE=2 SV=1
+Soltu.DM.02G015700.1	sp|Q9FGL5|CEPR1_ARATH	sp|Q9FGL5|CEPR1_ARATH Receptor protein-tyrosine kinase CEPR1 OS=Arabidopsis thaliana OX=3702 GN=CEPR1 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|Q8LPB4|PSKR1_DAUCA	sp|Q8LPB4|PSKR1_DAUCA Phytosulfokine receptor 1 OS=Daucus carota OX=4039 GN=PSKR PE=1 SV=1
+Soltu.DM.02G015700.1	sp|C0LGL9|FEI2_ARATH	sp|C0LGL9|FEI2_ARATH LRR receptor-like serine/threonine-protein kinase FEI 2 OS=Arabidopsis thaliana OX=3702 GN=FEI2 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|O22476|BRI1_ARATH	sp|O22476|BRI1_ARATH Protein BRASSINOSTEROID INSENSITIVE 1 OS=Arabidopsis thaliana OX=3702 GN=BRI1 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|Q9LJF3|BRL3_ARATH	sp|Q9LJF3|BRL3_ARATH Receptor-like protein kinase BRI1-like 3 OS=Arabidopsis thaliana OX=3702 GN=BRL3 PE=1 SV=1
+Soltu.DM.04G035790.1	sp|F4JVA6|SFH6_ARATH	sp|F4JVA6|SFH6_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH6 OS=Arabidopsis thaliana OX=3702 GN=SFH6 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|F4HP88|SFH4_ARATH	sp|F4HP88|SFH4_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH4 OS=Arabidopsis thaliana OX=3702 GN=SFH4 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|Q94A34|SFH12_ARATH	sp|Q94A34|SFH12_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH12 OS=Arabidopsis thaliana OX=3702 GN=SFH12 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|F4JVA9|SFH2_ARATH	sp|F4JVA9|SFH2_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH2 OS=Arabidopsis thaliana OX=3702 GN=SFH2 PE=3 SV=1
+Soltu.DM.04G035790.1	sp|Q93ZE9|SFH3_ARATH	sp|Q93ZE9|SFH3_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH3 OS=Arabidopsis thaliana OX=3702 GN=SFH3 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|Q8GXC6|SFH5_ARATH	sp|Q8GXC6|SFH5_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH5 OS=Arabidopsis thaliana OX=3702 GN=SFH5 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|Q9SI13|SFH10_ARATH	sp|Q9SI13|SFH10_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH10 OS=Arabidopsis thaliana OX=3702 GN=SFH10 PE=3 SV=1
+Soltu.DM.04G035790.1	sp|F4JLE5|SFH1_ARATH	sp|F4JLE5|SFH1_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH1 OS=Arabidopsis thaliana OX=3702 GN=SFH1 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|Q9SIW3|SFH7_ARATH	sp|Q9SIW3|SFH7_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH7 OS=Arabidopsis thaliana OX=3702 GN=SFH7 PE=2 SV=2
+Soltu.DM.04G035790.1	sp|F4IHJ0|SFH8_ARATH	sp|F4IHJ0|SFH8_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH8 OS=Arabidopsis thaliana OX=3702 GN=SFH8 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|F4J7S8|SFH9_ARATH	sp|F4J7S8|SFH9_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH9 OS=Arabidopsis thaliana OX=3702 GN=SFH9 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|F4K6D3|SFH14_ARATH	sp|F4K6D3|SFH14_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH14 OS=Arabidopsis thaliana OX=3702 GN=SFH14 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|Q501H5|SFH13_ARATH	sp|Q501H5|SFH13_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH13 OS=Arabidopsis thaliana OX=3702 GN=SFH13 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|F4JYJ3|SFH11_ARATH	sp|F4JYJ3|SFH11_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH11 OS=Arabidopsis thaliana OX=3702 GN=SFH11 PE=3 SV=1
+Soltu.DM.04G035790.1	sp|P24859|SEC14_KLULA	sp|P24859|SEC14_KLULA SEC14 cytosolic factor OS=Kluyveromyces lactis (strain ATCC 8585 / CBS 2359 / DSM 70799 / NBRC 1267 / NRRL Y-1140 / WM37) OX=284590 GN=SEC14 PE=3 SV=2
+Soltu.DM.04G035790.1	sp|P24280|SEC14_YEAST	sp|P24280|SEC14_YEAST SEC14 cytosolic factor OS=Saccharomyces cerevisiae (strain ATCC 204508 / S288c) OX=559292 GN=SEC14 PE=1 SV=3
+Soltu.DM.04G035790.1	sp|P53989|SEC14_CANGA	sp|P53989|SEC14_CANGA SEC14 cytosolic factor OS=Candida glabrata (strain ATCC 2001 / CBS 138 / JCM 3761 / NBRC 0622 / NRRL Y-65) OX=284593 GN=SEC14 PE=3 SV=1
+Soltu.DM.04G035790.1	sp|Q10137|SEC14_SCHPO	sp|Q10137|SEC14_SCHPO Sec14 cytosolic factor OS=Schizosaccharomyces pombe (strain 972 / ATCC 24843) OX=284812 GN=sec14 PE=4 SV=1
+Soltu.DM.04G035790.1	sp|P45816|SEC14_YARLI	sp|P45816|SEC14_YARLI SEC14 cytosolic factor OS=Yarrowia lipolytica (strain CLIB 122 / E 150) OX=284591 GN=SEC14 PE=3 SV=2
+Soltu.DM.04G035790.1	sp|Q75DK1|SEC14_ASHGO	sp|Q75DK1|SEC14_ASHGO SEC14 cytosolic factor OS=Ashbya gossypii (strain ATCC 10895 / CBS 109.51 / FGSC 9923 / NRRL Y-1056) OX=284811 GN=SEC14 PE=3 SV=2
+Soltu.DM.04G035790.1	sp|P46250|SEC14_CANAL	sp|P46250|SEC14_CANAL SEC14 cytosolic factor OS=Candida albicans (strain SC5314 / ATCC MYA-2876) OX=237561 GN=SEC14 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|P33324|YKJ1_YEAST	sp|P33324|YKJ1_YEAST CRAL-TRIO domain-containing protein YKL091C OS=Saccharomyces cerevisiae (strain ATCC 204508 / S288c) OX=559292 GN=YKL091C PE=1 SV=2
+Soltu.DM.04G035790.1	sp|Q92503|S14L1_HUMAN	sp|Q92503|S14L1_HUMAN SEC14-like protein 1 OS=Homo sapiens OX=9606 GN=SEC14L1 PE=1 SV=2
+Soltu.DM.04G035790.1	sp|A8Y5H7|S14L1_MOUSE	sp|A8Y5H7|S14L1_MOUSE SEC14-like protein 1 OS=Mus musculus OX=10090 GN=Sec14l1 PE=1 SV=1
+Soltu.DM.04G035790.1	sp|Q29JQ0|RETM_DROPS	sp|Q29JQ0|RETM_DROPS Protein real-time OS=Drosophila pseudoobscura pseudoobscura OX=46245 GN=retm PE=3 SV=1
+Soltu.DM.01G022510.1	sp|Q944A6|SNF4_ARATH	sp|Q944A6|SNF4_ARATH Sucrose nonfermenting 4-like protein OS=Arabidopsis thaliana OX=3702 GN=SNF4 PE=1 SV=1
+Soltu.DM.01G022510.1	sp|Q8BGM7|AAKG3_MOUSE	sp|Q8BGM7|AAKG3_MOUSE 5'-AMP-activated protein kinase subunit gamma-3 OS=Mus musculus OX=10090 GN=Prkag3 PE=1 SV=1
+Soltu.DM.01G022510.1	sp|Q9UGI9|AAKG3_HUMAN	sp|Q9UGI9|AAKG3_HUMAN 5'-AMP-activated protein kinase subunit gamma-3 OS=Homo sapiens OX=9606 GN=PRKAG3 PE=1 SV=3
+Soltu.DM.01G022510.1	sp|Q10343|AAKG_SCHPO	sp|Q10343|AAKG_SCHPO 5'-AMP-activated protein kinase subunit gamma OS=Schizosaccharomyces pombe (strain 972 / ATCC 24843) OX=284812 GN=cbs2 PE=1 SV=2
+Soltu.DM.01G022510.1	sp|Q9SCY5|KINB2_ARATH	sp|Q9SCY5|KINB2_ARATH SNF1-related protein kinase regulatory subunit beta-2 OS=Arabidopsis thaliana OX=3702 GN=KINB2 PE=1 SV=1
+Soltu.DM.01G022510.1	sp|Q9C5D0|CBSX2_ARATH	sp|Q9C5D0|CBSX2_ARATH CBS domain-containing protein CBSX2, chloroplastic OS=Arabidopsis thaliana OX=3702 GN=CBSX2 PE=1 SV=1
+Soltu.DM.S001650.1	sp|Q9FMA9|GL110_ARATH	sp|Q9FMA9|GL110_ARATH Germin-like protein subfamily 1 member 10 OS=Arabidopsis thaliana OX=3702 GN=At5g38930 PE=3 SV=1
+Soltu.DM.S001650.1	sp|Q9FMA8|GL111_ARATH	sp|Q9FMA8|GL111_ARATH Germin-like protein subfamily 1 member 11 OS=Arabidopsis thaliana OX=3702 GN=At5g38940 PE=2 SV=1
+Soltu.DM.S001650.1	sp|Q9LEA7|GL18_ARATH	sp|Q9LEA7|GL18_ARATH Germin-like protein subfamily 1 member 8 OS=Arabidopsis thaliana OX=3702 GN=GLP9 PE=2 SV=2
+Soltu.DM.S001650.1	sp|Q9SFF9|GL17_ARATH	sp|Q9SFF9|GL17_ARATH Germin-like protein subfamily 1 member 7 OS=Arabidopsis thaliana OX=3702 GN=At3g05950 PE=2 SV=1
+Soltu.DM.S001650.1	sp|Q9FMA6|GL112_ARATH	sp|Q9FMA6|GL112_ARATH Putative germin-like protein subfamily 1 member 12 OS=Arabidopsis thaliana OX=3702 GN=At5g38960 PE=3 SV=1
+Soltu.DM.S001650.1	sp|Q9FMB0|GL19_ARATH	sp|Q9FMB0|GL19_ARATH Putative germin-like protein subfamily 1 member 9 OS=Arabidopsis thaliana OX=3702 GN=At5g38910 PE=3 SV=1
+Soltu.DM.S001650.1	sp|Q7XSN6|GL41_ORYSJ	sp|Q7XSN6|GL41_ORYSJ Germin-like protein 4-1 OS=Oryza sativa subsp. japonica OX=39947 GN=Os04g0617900 PE=2 SV=2
+Soltu.DM.S001650.1	sp|Q6K5P9|GL22_ORYSJ	sp|Q6K5P9|GL22_ORYSJ Putative germin-like protein 2-2 OS=Oryza sativa subsp. japonica OX=39947 GN=Os02g0491700 PE=3 SV=1
+Soltu.DM.S001650.1	sp|Q2QXJ4|GL121_ORYSJ	sp|Q2QXJ4|GL121_ORYSJ Germin-like protein 12-1 OS=Oryza sativa subsp. japonica OX=39947 GN=Os12g0154700 PE=2 SV=1
+Soltu.DM.S001650.1	sp|Q2QXJ0|GL124_ORYSJ	sp|Q2QXJ0|GL124_ORYSJ Putative germin-like protein 12-4 OS=Oryza sativa subsp. japonica OX=39947 GN=Os12g0155000 PE=3 SV=2
+Soltu.DM.S001650.1	sp|Q2QXJ1|GL123_ORYSJ	sp|Q2QXJ1|GL123_ORYSJ Putative germin-like protein 12-3 OS=Oryza sativa subsp. japonica OX=39947 GN=Os12g0154900 PE=3 SV=1
+Soltu.DM.S001650.1	sp|Q2QXJ2|GL122_ORYSJ	sp|Q2QXJ2|GL122_ORYSJ Germin-like protein 12-2 OS=Oryza sativa subsp. japonica OX=39947 GN=Os12g0154800 PE=2 SV=1
+Soltu.DM.S001650.1	sp|Q6K5P8|GL23_ORYSJ	sp|Q6K5P8|GL23_ORYSJ Putative germin-like protein 2-3 OS=Oryza sativa subsp. japonica OX=39947 GN=Os02g0491800 PE=3 SV=1
+Soltu.DM.S001650.1	sp|Q6K5Q0|GL21_ORYSJ	sp|Q6K5Q0|GL21_ORYSJ Putative germin-like protein 2-1 OS=Oryza sativa subsp. japonica OX=39947 GN=Os02g0491600 PE=3 SV=1
+Soltu.DM.S001650.1	sp|Q9FIC9|GL115_ARATH	sp|Q9FIC9|GL115_ARATH Germin-like protein subfamily 1 member 15 OS=Arabidopsis thaliana OX=3702 GN=At5g39120 PE=2 SV=1
+Soltu.DM.S001650.1	sp|Q9FIC6|GL117_ARATH	sp|Q9FIC6|GL117_ARATH Germin-like protein subfamily 1 member 17 OS=Arabidopsis thaliana OX=3702 GN=At5g39150 PE=2 SV=1
+Soltu.DM.S001650.1	sp|Q9FID0|GL114_ARATH	sp|Q9FID0|GL114_ARATH Germin-like protein subfamily 1 member 14 OS=Arabidopsis thaliana OX=3702 GN=At5g39110 PE=3 SV=1
+Soltu.DM.S001650.1	sp|Q9M8X3|GL13_ARATH	sp|Q9M8X3|GL13_ARATH Germin-like protein subfamily 1 member 3 OS=Arabidopsis thaliana OX=3702 GN=At3g04170 PE=2 SV=1
+Soltu.DM.S001650.1	sp|Q9FL89|GL119_ARATH	sp|Q9FL89|GL119_ARATH Germin-like protein subfamily 1 member 19 OS=Arabidopsis thaliana OX=3702 GN=At5g39180 PE=2 SV=1
+Soltu.DM.S001650.1	sp|Q9M8X6|GL16_ARATH	sp|Q9M8X6|GL16_ARATH Germin-like protein subfamily 1 member 6 OS=Arabidopsis thaliana OX=3702 GN=At3g04200 PE=2 SV=1
+Soltu.DM.S001650.1	sp|Q6YZZ2|GL87_ORYSJ	sp|Q6YZZ2|GL87_ORYSJ Germin-like protein 8-7 OS=Oryza sativa subsp. japonica OX=39947 GN=GER6 PE=2 SV=1
+Soltu.DM.S001650.1	sp|Q6YZA9|GL82_ORYSJ	sp|Q6YZA9|GL82_ORYSJ Germin-like protein 8-2 OS=Oryza sativa subsp. japonica OX=39947 GN=GER3 PE=2 SV=1
+Soltu.DM.S001650.1	sp|P92997|GL113_ARATH	sp|P92997|GL113_ARATH Germin-like protein subfamily 1 member 13 OS=Arabidopsis thaliana OX=3702 GN=GLP6 PE=2 SV=2
+Soltu.DM.S001650.1	sp|Q6YZY5|GL811_ORYSJ	sp|Q6YZY5|GL811_ORYSJ Germin-like protein 8-11 OS=Oryza sativa subsp. japonica OX=39947 GN=Os08g0190100 PE=1 SV=1
+Soltu.DM.S001650.1	sp|Q6YZA6|GL85_ORYSJ	sp|Q6YZA6|GL85_ORYSJ Germin-like protein 8-5 OS=Oryza sativa subsp. japonica OX=39947 GN=Os08g0189400 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q9SJB4|GDL34_ARATH	sp|Q9SJB4|GDL34_ARATH GDSL esterase/lipase At2g04570 OS=Arabidopsis thaliana OX=3702 GN=At2g04570 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q8VY93|GDL66_ARATH	sp|Q8VY93|GDL66_ARATH GDSL esterase/lipase At4g26790 OS=Arabidopsis thaliana OX=3702 GN=At4g26790 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q67ZI9|GDL48_ARATH	sp|Q67ZI9|GDL48_ARATH GDSL esterase/lipase At2g42990 OS=Arabidopsis thaliana OX=3702 GN=At2g42990 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q9FHW9|GDL90_ARATH	sp|Q9FHW9|GDL90_ARATH GDSL esterase/lipase At5g42170 OS=Arabidopsis thaliana OX=3702 GN=At5g42170/At5g42160 PE=3 SV=2
+Soltu.DM.07G016620.1	sp|Q9FFN0|GDL72_ARATH	sp|Q9FFN0|GDL72_ARATH GDSL esterase/lipase At5g03810 OS=Arabidopsis thaliana OX=3702 GN=At5g03810 PE=3 SV=1
+Soltu.DM.07G016620.1	sp|Q94CH6|EXL3_ARATH	sp|Q94CH6|EXL3_ARATH GDSL esterase/lipase EXL3 OS=Arabidopsis thaliana OX=3702 GN=EXL3 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q9LZC5|GDL73_ARATH	sp|Q9LZC5|GDL73_ARATH GDSL esterase/lipase At5g03820 OS=Arabidopsis thaliana OX=3702 GN=At5g03820 PE=3 SV=1
+Soltu.DM.07G016620.1	sp|Q9C653|GDL24_ARATH	sp|Q9C653|GDL24_ARATH GDSL esterase/lipase At1g58525 OS=Arabidopsis thaliana OX=3702 GN=At1g58525 PE=3 SV=2
+Soltu.DM.07G016620.1	sp|P0DKJ6|GDL4_ARATH	sp|P0DKJ6|GDL4_ARATH GDSL esterase/lipase At1g20120 OS=Arabidopsis thaliana OX=3702 GN=At1g20120 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q3ECM4|GDL25_ARATH	sp|Q3ECM4|GDL25_ARATH GDSL esterase/lipase At1g58725 OS=Arabidopsis thaliana OX=3702 GN=At1g58725 PE=2 SV=2
+Soltu.DM.07G016620.1	sp|F4IBF0|GDL26_ARATH	sp|F4IBF0|GDL26_ARATH GDSL esterase/lipase At1g59030 OS=Arabidopsis thaliana OX=3702 GN=At1g59030 PE=3 SV=2
+Soltu.DM.07G016620.1	sp|P0DI15|GDL27_ARATH	sp|P0DI15|GDL27_ARATH GDSL esterase/lipase At1g59406 OS=Arabidopsis thaliana OX=3702 GN=At1g59406 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q9LU14|APG2_ARATH	sp|Q9LU14|APG2_ARATH GDSL esterase/lipase APG OS=Arabidopsis thaliana OX=3702 GN=APG PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q9FFC6|GDL78_ARATH	sp|Q9FFC6|GDL78_ARATH GDSL esterase/lipase At5g22810 OS=Arabidopsis thaliana OX=3702 GN=At5g22810 PE=3 SV=3
+Soltu.DM.07G016620.1	sp|Q9FJ40|GDL86_ARATH	sp|Q9FJ40|GDL86_ARATH GDSL esterase/lipase At5g45960 OS=Arabidopsis thaliana OX=3702 GN=At5g45960 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q94CH8|EXL1_ARATH	sp|Q94CH8|EXL1_ARATH GDSL esterase/lipase EXL1 OS=Arabidopsis thaliana OX=3702 GN=EXL1 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q9LMJ3|GDL1_ARATH	sp|Q9LMJ3|GDL1_ARATH GDSL esterase/lipase At1g06990 OS=Arabidopsis thaliana OX=3702 GN=At1g06990 PE=2 SV=2
+Soltu.DM.07G016620.1	sp|Q9SIQ3|GDL43_ARATH	sp|Q9SIQ3|GDL43_ARATH GDSL esterase/lipase At2g31540 OS=Arabidopsis thaliana OX=3702 GN=At2g31540 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q9SIQ2|GDL44_ARATH	sp|Q9SIQ2|GDL44_ARATH GDSL esterase/lipase At2g31550 OS=Arabidopsis thaliana OX=3702 GN=At2g31550 PE=3 SV=3
+Soltu.DM.07G016620.1	sp|Q9C648|GDL23_ARATH	sp|Q9C648|GDL23_ARATH GDSL esterase/lipase At1g58430 OS=Arabidopsis thaliana OX=3702 GN=At1g58430 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q9LH73|GDL52_ARATH	sp|Q9LH73|GDL52_ARATH GDSL esterase/lipase At3g14820 OS=Arabidopsis thaliana OX=3702 GN=At3g14820 PE=3 SV=2
+Soltu.DM.07G016620.1	sp|Q9SJA9|GDL39_ARATH	sp|Q9SJA9|GDL39_ARATH GDSL esterase/lipase At2g24560 OS=Arabidopsis thaliana OX=3702 GN=At2g24560 PE=2 SV=2
+Soltu.DM.07G016620.1	sp|Q0WPI9|GDL59_ARATH	sp|Q0WPI9|GDL59_ARATH GDSL esterase/lipase At3g53100 OS=Arabidopsis thaliana OX=3702 GN=At3g53100 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|O22927|GDL42_ARATH	sp|O22927|GDL42_ARATH GDSL esterase/lipase At2g30310 OS=Arabidopsis thaliana OX=3702 GN=At2g30310 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q9FYD3|GDL56_ARATH	sp|Q9FYD3|GDL56_ARATH GDSL esterase/lipase At3g43570 OS=Arabidopsis thaliana OX=3702 GN=At3g43570 PE=3 SV=1
+Soltu.DM.03G011280.1	sp|F4IXE7|IDM1_ARATH	sp|F4IXE7|IDM1_ARATH Increased DNA methylation 1 OS=Arabidopsis thaliana OX=3702 GN=IDM1 PE=1 SV=1
+Soltu.DM.01G045390.1	sp|Q9S7V4|HA22A_ARATH	sp|Q9S7V4|HA22A_ARATH HVA22-like protein a OS=Arabidopsis thaliana OX=3702 GN=HVA22A PE=2 SV=1
+Soltu.DM.01G045390.1	sp|Q9S784|HA22C_ARATH	sp|Q9S784|HA22C_ARATH HVA22-like protein c OS=Arabidopsis thaliana OX=3702 GN=HVA22C PE=2 SV=1
+Soltu.DM.01G045390.1	sp|Q682H0|HA22F_ARATH	sp|Q682H0|HA22F_ARATH HVA22-like protein f OS=Arabidopsis thaliana OX=3702 GN=HVA22F PE=2 SV=1
+Soltu.DM.01G045390.1	sp|Q9S760|HA22D_ARATH	sp|Q9S760|HA22D_ARATH HVA22-like protein d OS=Arabidopsis thaliana OX=3702 GN=HVA22D PE=2 SV=1
+Soltu.DM.02G020600.1	sp|Q6R2J8|SRF8_ARATH	sp|Q6R2J8|SRF8_ARATH Protein STRUBBELIG-RECEPTOR FAMILY 8 OS=Arabidopsis thaliana OX=3702 GN=SRF8 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q9LUL4|SRF7_ARATH	sp|Q9LUL4|SRF7_ARATH Protein STRUBBELIG-RECEPTOR FAMILY 7 OS=Arabidopsis thaliana OX=3702 GN=SRF7 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q9C8M9|SRF6_ARATH	sp|Q9C8M9|SRF6_ARATH Protein STRUBBELIG-RECEPTOR FAMILY 6 OS=Arabidopsis thaliana OX=3702 GN=SRF6 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q6R2K1|SRF5_ARATH	sp|Q6R2K1|SRF5_ARATH Protein STRUBBELIG-RECEPTOR FAMILY 5 OS=Arabidopsis thaliana OX=3702 GN=SRF5 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q06BH3|SRF1_ARATH	sp|Q06BH3|SRF1_ARATH Protein STRUBBELIG-RECEPTOR FAMILY 1 OS=Arabidopsis thaliana OX=3702 GN=SRF1 PE=1 SV=2
+Soltu.DM.02G020600.1	sp|Q9FG24|SRF2_ARATH	sp|Q9FG24|SRF2_ARATH Protein STRUBBELIG-RECEPTOR FAMILY 2 OS=Arabidopsis thaliana OX=3702 GN=SRF2 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q6R2K3|SRF3_ARATH	sp|Q6R2K3|SRF3_ARATH Protein STRUBBELIG-RECEPTOR FAMILY 3 OS=Arabidopsis thaliana OX=3702 GN=SRF3 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q6R2K2|SRF4_ARATH	sp|Q6R2K2|SRF4_ARATH Protein STRUBBELIG-RECEPTOR FAMILY 4 OS=Arabidopsis thaliana OX=3702 GN=SRF4 PE=2 SV=1
+Soltu.DM.02G020600.1	sp|Q8RWZ1|SUB_ARATH	sp|Q8RWZ1|SUB_ARATH Protein STRUBBELIG OS=Arabidopsis thaliana OX=3702 GN=SUB PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q9LDZ5|PBL21_ARATH	sp|Q9LDZ5|PBL21_ARATH Probable serine/threonine-protein kinase PBL21 OS=Arabidopsis thaliana OX=3702 GN=PBL21 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|O49339|PTI12_ARATH	sp|O49339|PTI12_ARATH PTI1-like tyrosine-protein kinase 2 OS=Arabidopsis thaliana OX=3702 GN=PTI12 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|B9DFG5|PTI13_ARATH	sp|B9DFG5|PTI13_ARATH PTI1-like tyrosine-protein kinase 3 OS=Arabidopsis thaliana OX=3702 GN=PTI13 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q41328|PTI1_SOLLC	sp|Q41328|PTI1_SOLLC Pto-interacting protein 1 OS=Solanum lycopersicum OX=4081 GN=PTI1 PE=1 SV=2
+Soltu.DM.02G020600.1	sp|Q9LUT0|CARK1_ARATH	sp|Q9LUT0|CARK1_ARATH Receptor-like cytoplasmic kinase 1 OS=Arabidopsis thaliana OX=3702 GN=CARK1 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q0WRY5|PBL7_ARATH	sp|Q0WRY5|PBL7_ARATH Probable serine/threonine-protein kinase PBL7 OS=Arabidopsis thaliana OX=3702 GN=PBL7 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|O80719|Y2706_ARATH	sp|O80719|Y2706_ARATH Probable receptor-like protein kinase At2g47060 OS=Arabidopsis thaliana OX=3702 GN=At2g47060 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|F4JEQ2|PBL23_ARATH	sp|F4JEQ2|PBL23_ARATH Probable serine/threonine-protein kinase PBL23 OS=Arabidopsis thaliana OX=3702 GN=PBL23 PE=2 SV=1
+Soltu.DM.02G020600.1	sp|Q8H1G6|PTI11_ARATH	sp|Q8H1G6|PTI11_ARATH PTI1-like tyrosine-protein kinase 1 OS=Arabidopsis thaliana OX=3702 GN=PTI11 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q9SFT7|PBL26_ARATH	sp|Q9SFT7|PBL26_ARATH Probable serine/threonine-protein kinase PBL26 OS=Arabidopsis thaliana OX=3702 GN=PBL26 PE=2 SV=1
+Soltu.DM.02G020600.1	sp|Q6I5Q6|RK185_ORYSJ	sp|Q6I5Q6|RK185_ORYSJ Receptor-like cytoplasmic kinase 185 OS=Oryza sativa subsp. japonica OX=39947 GN=RLCK185 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q9FE20|PBS1_ARATH	sp|Q9FE20|PBS1_ARATH Serine/threonine-protein kinase PBS1 OS=Arabidopsis thaliana OX=3702 GN=PBS1 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|P93749|Y2197_ARATH	sp|P93749|Y2197_ARATH Probable protein kinase At2g41970 OS=Arabidopsis thaliana OX=3702 GN=At2g41970 PE=2 SV=1
+Soltu.DM.02G020600.1	sp|Q1PE89|PBL24_ARATH	sp|Q1PE89|PBL24_ARATH Probable serine/threonine-protein kinase PBL24 OS=Arabidopsis thaliana OX=3702 GN=PBL24 PE=2 SV=1
+Soltu.DM.02G020600.1	sp|Q9LRY1|PBL25_ARATH	sp|Q9LRY1|PBL25_ARATH Probable serine/threonine-protein kinase PBL25 OS=Arabidopsis thaliana OX=3702 GN=PBL25 PE=2 SV=1
+Soltu.DM.02G020600.1	sp|Q9LQQ8|PBL5_ARATH	sp|Q9LQQ8|PBL5_ARATH Probable serine/threonine-protein kinase PBL5 OS=Arabidopsis thaliana OX=3702 GN=PBL5 PE=2 SV=1
diff -r 000000000000 -r c840a1c77a0a test-data/8_Proteins_vs_Trembl_blastp.txt
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/8_Proteins_vs_Trembl_blastp.txt	Tue May 10 13:18:05 2022 +0000
@@ -0,0 +1,136 @@
+Soltu.DM.02G015700.1	sp|Q1MX30|XA21_ORYSI	sp|Q1MX30|XA21_ORYSI Receptor kinase-like protein Xa21 OS=Oryza sativa subsp. indica OX=39946 GN=XA21 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|Q2R2D5|XA21_ORYSJ	sp|Q2R2D5|XA21_ORYSJ Receptor kinase-like protein Xa21 OS=Oryza sativa subsp. japonica OX=39947 GN=XA21 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|C0LGP4|Y3475_ARATH	sp|C0LGP4|Y3475_ARATH Probable LRR receptor-like serine/threonine-protein kinase At3g47570 OS=Arabidopsis thaliana OX=3702 GN=At3g47570 PE=2 SV=1
+Soltu.DM.02G015700.1	sp|C0LGT6|EFR_ARATH	sp|C0LGT6|EFR_ARATH LRR receptor-like serine/threonine-protein kinase EFR OS=Arabidopsis thaliana OX=3702 GN=EFR PE=1 SV=1
+Soltu.DM.02G015700.1	sp|Q9SD62|Y3471_ARATH	sp|Q9SD62|Y3471_ARATH Putative receptor-like protein kinase At3g47110 OS=Arabidopsis thaliana OX=3702 GN=At3g47110 PE=3 SV=1
+Soltu.DM.02G015700.1	sp|Q9ZUI0|Y2241_ARATH	sp|Q9ZUI0|Y2241_ARATH Putative leucine-rich repeat receptor-like serine/threonine-protein kinase At2g24130 OS=Arabidopsis thaliana OX=3702 GN=At2g24130 PE=3 SV=1
+Soltu.DM.02G015700.1	sp|Q9FL28|FLS2_ARATH	sp|Q9FL28|FLS2_ARATH LRR receptor-like serine/threonine-protein kinase FLS2 OS=Arabidopsis thaliana OX=3702 GN=FLS2 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|Q9SJG2|Y2296_ARATH	sp|Q9SJG2|Y2296_ARATH Probable receptor-like protein kinase At2g42960 OS=Arabidopsis thaliana OX=3702 GN=At2g42960 PE=3 SV=1
+Soltu.DM.02G015700.1	sp|Q9LRP3|Y3174_ARATH	sp|Q9LRP3|Y3174_ARATH Probable receptor-like protein kinase At3g17420 OS=Arabidopsis thaliana OX=3702 GN=At3g17420 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|Q9LYN8|EMS1_ARATH	sp|Q9LYN8|EMS1_ARATH Leucine-rich repeat receptor protein kinase EMS1 OS=Arabidopsis thaliana OX=3702 GN=EMS1 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|Q3EDL4|Y1154_ARATH	sp|Q3EDL4|Y1154_ARATH Probable serine/threonine-protein kinase At1g01540 OS=Arabidopsis thaliana OX=3702 GN=At1g01540 PE=1 SV=2
+Soltu.DM.02G015700.1	sp|C0LGF4|FEI1_ARATH	sp|C0LGF4|FEI1_ARATH LRR receptor-like serine/threonine-protein kinase FEI 1 OS=Arabidopsis thaliana OX=3702 GN=FEI1 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|C0LGQ5|GSO1_ARATH	sp|C0LGQ5|GSO1_ARATH LRR receptor-like serine/threonine-protein kinase GSO1 OS=Arabidopsis thaliana OX=3702 GN=GSO1 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|C0LGJ1|Y1743_ARATH	sp|C0LGJ1|Y1743_ARATH Probable LRR receptor-like serine/threonine-protein kinase At1g74360 OS=Arabidopsis thaliana OX=3702 GN=At1g74360 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|Q9FZB1|Y5188_ARATH	sp|Q9FZB1|Y5188_ARATH Probable LRR receptor-like serine/threonine-protein kinase At1g51880 OS=Arabidopsis thaliana OX=3702 GN=At1g51880 PE=2 SV=1
+Soltu.DM.02G015700.1	sp|Q9SHI2|Y1723_ARATH	sp|Q9SHI2|Y1723_ARATH Leucine-rich repeat receptor-like serine/threonine-protein kinase At1g17230 OS=Arabidopsis thaliana OX=3702 GN=At1g17230 PE=1 SV=2
+Soltu.DM.02G015700.1	sp|Q9C7S5|PSYR1_ARATH	sp|Q9C7S5|PSYR1_ARATH Tyrosine-sulfated glycopeptide receptor 1 OS=Arabidopsis thaliana OX=3702 GN=PSY1R PE=1 SV=1
+Soltu.DM.02G015700.1	sp|O49564|CRK27_ARATH	sp|O49564|CRK27_ARATH Cysteine-rich receptor-like protein kinase 27 OS=Arabidopsis thaliana OX=3702 GN=CRK27 PE=3 SV=2
+Soltu.DM.02G015700.1	sp|Q0JA29|FLS2_ORYSJ	sp|Q0JA29|FLS2_ORYSJ LRR receptor-like serine/threonine-protein kinase FLS2 OS=Oryza sativa subsp. japonica OX=39947 GN=FLS2 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|Q7G768|BRL2_ORYSJ	sp|Q7G768|BRL2_ORYSJ Brassinosteroid LRR receptor kinase BRL2 OS=Oryza sativa subsp. japonica OX=39947 GN=BRL2 PE=2 SV=1
+Soltu.DM.02G015700.1	sp|Q9FGL5|CEPR1_ARATH	sp|Q9FGL5|CEPR1_ARATH Receptor protein-tyrosine kinase CEPR1 OS=Arabidopsis thaliana OX=3702 GN=CEPR1 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|Q8LPB4|PSKR1_DAUCA	sp|Q8LPB4|PSKR1_DAUCA Phytosulfokine receptor 1 OS=Daucus carota OX=4039 GN=PSKR PE=1 SV=1
+Soltu.DM.02G015700.1	sp|C0LGL9|FEI2_ARATH	sp|C0LGL9|FEI2_ARATH LRR receptor-like serine/threonine-protein kinase FEI 2 OS=Arabidopsis thaliana OX=3702 GN=FEI2 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|O22476|BRI1_ARATH	sp|O22476|BRI1_ARATH Protein BRASSINOSTEROID INSENSITIVE 1 OS=Arabidopsis thaliana OX=3702 GN=BRI1 PE=1 SV=1
+Soltu.DM.02G015700.1	sp|Q9LJF3|BRL3_ARATH	sp|Q9LJF3|BRL3_ARATH Receptor-like protein kinase BRI1-like 3 OS=Arabidopsis thaliana OX=3702 GN=BRL3 PE=1 SV=1
+Soltu.DM.04G035790.1	sp|F4JVA6|SFH6_ARATH	sp|F4JVA6|SFH6_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH6 OS=Arabidopsis thaliana OX=3702 GN=SFH6 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|F4HP88|SFH4_ARATH	sp|F4HP88|SFH4_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH4 OS=Arabidopsis thaliana OX=3702 GN=SFH4 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|Q94A34|SFH12_ARATH	sp|Q94A34|SFH12_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH12 OS=Arabidopsis thaliana OX=3702 GN=SFH12 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|F4JVA9|SFH2_ARATH	sp|F4JVA9|SFH2_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH2 OS=Arabidopsis thaliana OX=3702 GN=SFH2 PE=3 SV=1
+Soltu.DM.04G035790.1	sp|Q93ZE9|SFH3_ARATH	sp|Q93ZE9|SFH3_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH3 OS=Arabidopsis thaliana OX=3702 GN=SFH3 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|Q8GXC6|SFH5_ARATH	sp|Q8GXC6|SFH5_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH5 OS=Arabidopsis thaliana OX=3702 GN=SFH5 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|Q9SI13|SFH10_ARATH	sp|Q9SI13|SFH10_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH10 OS=Arabidopsis thaliana OX=3702 GN=SFH10 PE=3 SV=1
+Soltu.DM.04G035790.1	sp|F4JLE5|SFH1_ARATH	sp|F4JLE5|SFH1_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH1 OS=Arabidopsis thaliana OX=3702 GN=SFH1 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|Q9SIW3|SFH7_ARATH	sp|Q9SIW3|SFH7_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH7 OS=Arabidopsis thaliana OX=3702 GN=SFH7 PE=2 SV=2
+Soltu.DM.04G035790.1	sp|F4IHJ0|SFH8_ARATH	sp|F4IHJ0|SFH8_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH8 OS=Arabidopsis thaliana OX=3702 GN=SFH8 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|F4J7S8|SFH9_ARATH	sp|F4J7S8|SFH9_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH9 OS=Arabidopsis thaliana OX=3702 GN=SFH9 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|F4K6D3|SFH14_ARATH	sp|F4K6D3|SFH14_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH14 OS=Arabidopsis thaliana OX=3702 GN=SFH14 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|Q501H5|SFH13_ARATH	sp|Q501H5|SFH13_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH13 OS=Arabidopsis thaliana OX=3702 GN=SFH13 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|F4JYJ3|SFH11_ARATH	sp|F4JYJ3|SFH11_ARATH Phosphatidylinositol/phosphatidylcholine transfer protein SFH11 OS=Arabidopsis thaliana OX=3702 GN=SFH11 PE=3 SV=1
+Soltu.DM.04G035790.1	sp|P24859|SEC14_KLULA	sp|P24859|SEC14_KLULA SEC14 cytosolic factor OS=Kluyveromyces lactis (strain ATCC 8585 / CBS 2359 / DSM 70799 / NBRC 1267 / NRRL Y-1140 / WM37) OX=284590 GN=SEC14 PE=3 SV=2
+Soltu.DM.04G035790.1	sp|P24280|SEC14_YEAST	sp|P24280|SEC14_YEAST SEC14 cytosolic factor OS=Saccharomyces cerevisiae (strain ATCC 204508 / S288c) OX=559292 GN=SEC14 PE=1 SV=3
+Soltu.DM.04G035790.1	sp|P53989|SEC14_CANGA	sp|P53989|SEC14_CANGA SEC14 cytosolic factor OS=Candida glabrata (strain ATCC 2001 / CBS 138 / JCM 3761 / NBRC 0622 / NRRL Y-65) OX=284593 GN=SEC14 PE=3 SV=1
+Soltu.DM.04G035790.1	sp|Q10137|SEC14_SCHPO	sp|Q10137|SEC14_SCHPO Sec14 cytosolic factor OS=Schizosaccharomyces pombe (strain 972 / ATCC 24843) OX=284812 GN=sec14 PE=4 SV=1
+Soltu.DM.04G035790.1	sp|P45816|SEC14_YARLI	sp|P45816|SEC14_YARLI SEC14 cytosolic factor OS=Yarrowia lipolytica (strain CLIB 122 / E 150) OX=284591 GN=SEC14 PE=3 SV=2
+Soltu.DM.04G035790.1	sp|Q75DK1|SEC14_ASHGO	sp|Q75DK1|SEC14_ASHGO SEC14 cytosolic factor OS=Ashbya gossypii (strain ATCC 10895 / CBS 109.51 / FGSC 9923 / NRRL Y-1056) OX=284811 GN=SEC14 PE=3 SV=2
+Soltu.DM.04G035790.1	sp|P46250|SEC14_CANAL	sp|P46250|SEC14_CANAL SEC14 cytosolic factor OS=Candida albicans (strain SC5314 / ATCC MYA-2876) OX=237561 GN=SEC14 PE=2 SV=1
+Soltu.DM.04G035790.1	sp|P33324|YKJ1_YEAST	sp|P33324|YKJ1_YEAST CRAL-TRIO domain-containing protein YKL091C OS=Saccharomyces cerevisiae (strain ATCC 204508 / S288c) OX=559292 GN=YKL091C PE=1 SV=2
+Soltu.DM.04G035790.1	sp|Q92503|S14L1_HUMAN	sp|Q92503|S14L1_HUMAN SEC14-like protein 1 OS=Homo sapiens OX=9606 GN=SEC14L1 PE=1 SV=2
+Soltu.DM.04G035790.1	sp|A8Y5H7|S14L1_MOUSE	sp|A8Y5H7|S14L1_MOUSE SEC14-like protein 1 OS=Mus musculus OX=10090 GN=Sec14l1 PE=1 SV=1
+Soltu.DM.04G035790.1	sp|Q29JQ0|RETM_DROPS	sp|Q29JQ0|RETM_DROPS Protein real-time OS=Drosophila pseudoobscura pseudoobscura OX=46245 GN=retm PE=3 SV=1
+Soltu.DM.01G022510.1	sp|Q944A6|SNF4_ARATH	sp|Q944A6|SNF4_ARATH Sucrose nonfermenting 4-like protein OS=Arabidopsis thaliana OX=3702 GN=SNF4 PE=1 SV=1
+Soltu.DM.01G022510.1	sp|Q8BGM7|AAKG3_MOUSE	sp|Q8BGM7|AAKG3_MOUSE 5'-AMP-activated protein kinase subunit gamma-3 OS=Mus musculus OX=10090 GN=Prkag3 PE=1 SV=1
+Soltu.DM.01G022510.1	sp|Q9UGI9|AAKG3_HUMAN	sp|Q9UGI9|AAKG3_HUMAN 5'-AMP-activated protein kinase subunit gamma-3 OS=Homo sapiens OX=9606 GN=PRKAG3 PE=1 SV=3
+Soltu.DM.01G022510.1	sp|Q10343|AAKG_SCHPO	sp|Q10343|AAKG_SCHPO 5'-AMP-activated protein kinase subunit gamma OS=Schizosaccharomyces pombe (strain 972 / ATCC 24843) OX=284812 GN=cbs2 PE=1 SV=2
+Soltu.DM.01G022510.1	sp|Q9SCY5|KINB2_ARATH	sp|Q9SCY5|KINB2_ARATH SNF1-related protein kinase regulatory subunit beta-2 OS=Arabidopsis thaliana OX=3702 GN=KINB2 PE=1 SV=1
+Soltu.DM.01G022510.1	sp|Q9C5D0|CBSX2_ARATH	sp|Q9C5D0|CBSX2_ARATH CBS domain-containing protein CBSX2, chloroplastic OS=Arabidopsis thaliana OX=3702 GN=CBSX2 PE=1 SV=1
+Soltu.DM.S001650.1	sp|Q9FMA9|GL110_ARATH	sp|Q9FMA9|GL110_ARATH Germin-like protein subfamily 1 member 10 OS=Arabidopsis thaliana OX=3702 GN=At5g38930 PE=3 SV=1
+Soltu.DM.S001650.1	sp|Q9FMA8|GL111_ARATH	sp|Q9FMA8|GL111_ARATH Germin-like protein subfamily 1 member 11 OS=Arabidopsis thaliana OX=3702 GN=At5g38940 PE=2 SV=1
+Soltu.DM.S001650.1	sp|Q9LEA7|GL18_ARATH	sp|Q9LEA7|GL18_ARATH Germin-like protein subfamily 1 member 8 OS=Arabidopsis thaliana OX=3702 GN=GLP9 PE=2 SV=2
+Soltu.DM.S001650.1	sp|Q9SFF9|GL17_ARATH	sp|Q9SFF9|GL17_ARATH Germin-like protein subfamily 1 member 7 OS=Arabidopsis thaliana OX=3702 GN=At3g05950 PE=2 SV=1
+Soltu.DM.S001650.1	sp|Q9FMA6|GL112_ARATH	sp|Q9FMA6|GL112_ARATH Putative germin-like protein subfamily 1 member 12 OS=Arabidopsis thaliana OX=3702 GN=At5g38960 PE=3 SV=1
+Soltu.DM.S001650.1	sp|Q9FMB0|GL19_ARATH	sp|Q9FMB0|GL19_ARATH Putative germin-like protein subfamily 1 member 9 OS=Arabidopsis thaliana OX=3702 GN=At5g38910 PE=3 SV=1
+Soltu.DM.S001650.1	sp|Q7XSN6|GL41_ORYSJ	sp|Q7XSN6|GL41_ORYSJ Germin-like protein 4-1 OS=Oryza sativa subsp. japonica OX=39947 GN=Os04g0617900 PE=2 SV=2
+Soltu.DM.S001650.1	sp|Q6K5P9|GL22_ORYSJ	sp|Q6K5P9|GL22_ORYSJ Putative germin-like protein 2-2 OS=Oryza sativa subsp. japonica OX=39947 GN=Os02g0491700 PE=3 SV=1
+Soltu.DM.S001650.1	sp|Q2QXJ4|GL121_ORYSJ	sp|Q2QXJ4|GL121_ORYSJ Germin-like protein 12-1 OS=Oryza sativa subsp. japonica OX=39947 GN=Os12g0154700 PE=2 SV=1
+Soltu.DM.S001650.1	sp|Q2QXJ0|GL124_ORYSJ	sp|Q2QXJ0|GL124_ORYSJ Putative germin-like protein 12-4 OS=Oryza sativa subsp. japonica OX=39947 GN=Os12g0155000 PE=3 SV=2
+Soltu.DM.S001650.1	sp|Q2QXJ1|GL123_ORYSJ	sp|Q2QXJ1|GL123_ORYSJ Putative germin-like protein 12-3 OS=Oryza sativa subsp. japonica OX=39947 GN=Os12g0154900 PE=3 SV=1
+Soltu.DM.S001650.1	sp|Q2QXJ2|GL122_ORYSJ	sp|Q2QXJ2|GL122_ORYSJ Germin-like protein 12-2 OS=Oryza sativa subsp. japonica OX=39947 GN=Os12g0154800 PE=2 SV=1
+Soltu.DM.S001650.1	sp|Q6K5P8|GL23_ORYSJ	sp|Q6K5P8|GL23_ORYSJ Putative germin-like protein 2-3 OS=Oryza sativa subsp. japonica OX=39947 GN=Os02g0491800 PE=3 SV=1
+Soltu.DM.S001650.1	sp|Q6K5Q0|GL21_ORYSJ	sp|Q6K5Q0|GL21_ORYSJ Putative germin-like protein 2-1 OS=Oryza sativa subsp. japonica OX=39947 GN=Os02g0491600 PE=3 SV=1
+Soltu.DM.S001650.1	sp|Q9FIC9|GL115_ARATH	sp|Q9FIC9|GL115_ARATH Germin-like protein subfamily 1 member 15 OS=Arabidopsis thaliana OX=3702 GN=At5g39120 PE=2 SV=1
+Soltu.DM.S001650.1	sp|Q9FIC6|GL117_ARATH	sp|Q9FIC6|GL117_ARATH Germin-like protein subfamily 1 member 17 OS=Arabidopsis thaliana OX=3702 GN=At5g39150 PE=2 SV=1
+Soltu.DM.S001650.1	sp|Q9FID0|GL114_ARATH	sp|Q9FID0|GL114_ARATH Germin-like protein subfamily 1 member 14 OS=Arabidopsis thaliana OX=3702 GN=At5g39110 PE=3 SV=1
+Soltu.DM.S001650.1	sp|Q9M8X3|GL13_ARATH	sp|Q9M8X3|GL13_ARATH Germin-like protein subfamily 1 member 3 OS=Arabidopsis thaliana OX=3702 GN=At3g04170 PE=2 SV=1
+Soltu.DM.S001650.1	sp|Q9FL89|GL119_ARATH	sp|Q9FL89|GL119_ARATH Germin-like protein subfamily 1 member 19 OS=Arabidopsis thaliana OX=3702 GN=At5g39180 PE=2 SV=1
+Soltu.DM.S001650.1	sp|Q9M8X6|GL16_ARATH	sp|Q9M8X6|GL16_ARATH Germin-like protein subfamily 1 member 6 OS=Arabidopsis thaliana OX=3702 GN=At3g04200 PE=2 SV=1
+Soltu.DM.S001650.1	sp|Q6YZZ2|GL87_ORYSJ	sp|Q6YZZ2|GL87_ORYSJ Germin-like protein 8-7 OS=Oryza sativa subsp. japonica OX=39947 GN=GER6 PE=2 SV=1
+Soltu.DM.S001650.1	sp|Q6YZA9|GL82_ORYSJ	sp|Q6YZA9|GL82_ORYSJ Germin-like protein 8-2 OS=Oryza sativa subsp. japonica OX=39947 GN=GER3 PE=2 SV=1
+Soltu.DM.S001650.1	sp|P92997|GL113_ARATH	sp|P92997|GL113_ARATH Germin-like protein subfamily 1 member 13 OS=Arabidopsis thaliana OX=3702 GN=GLP6 PE=2 SV=2
+Soltu.DM.S001650.1	sp|Q6YZY5|GL811_ORYSJ	sp|Q6YZY5|GL811_ORYSJ Germin-like protein 8-11 OS=Oryza sativa subsp. japonica OX=39947 GN=Os08g0190100 PE=1 SV=1
+Soltu.DM.S001650.1	sp|Q6YZA6|GL85_ORYSJ	sp|Q6YZA6|GL85_ORYSJ Germin-like protein 8-5 OS=Oryza sativa subsp. japonica OX=39947 GN=Os08g0189400 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q9SJB4|GDL34_ARATH	sp|Q9SJB4|GDL34_ARATH GDSL esterase/lipase At2g04570 OS=Arabidopsis thaliana OX=3702 GN=At2g04570 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q8VY93|GDL66_ARATH	sp|Q8VY93|GDL66_ARATH GDSL esterase/lipase At4g26790 OS=Arabidopsis thaliana OX=3702 GN=At4g26790 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q67ZI9|GDL48_ARATH	sp|Q67ZI9|GDL48_ARATH GDSL esterase/lipase At2g42990 OS=Arabidopsis thaliana OX=3702 GN=At2g42990 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q9FHW9|GDL90_ARATH	sp|Q9FHW9|GDL90_ARATH GDSL esterase/lipase At5g42170 OS=Arabidopsis thaliana OX=3702 GN=At5g42170/At5g42160 PE=3 SV=2
+Soltu.DM.07G016620.1	sp|Q9FFN0|GDL72_ARATH	sp|Q9FFN0|GDL72_ARATH GDSL esterase/lipase At5g03810 OS=Arabidopsis thaliana OX=3702 GN=At5g03810 PE=3 SV=1
+Soltu.DM.07G016620.1	sp|Q94CH6|EXL3_ARATH	sp|Q94CH6|EXL3_ARATH GDSL esterase/lipase EXL3 OS=Arabidopsis thaliana OX=3702 GN=EXL3 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q9LZC5|GDL73_ARATH	sp|Q9LZC5|GDL73_ARATH GDSL esterase/lipase At5g03820 OS=Arabidopsis thaliana OX=3702 GN=At5g03820 PE=3 SV=1
+Soltu.DM.07G016620.1	sp|Q9C653|GDL24_ARATH	sp|Q9C653|GDL24_ARATH GDSL esterase/lipase At1g58525 OS=Arabidopsis thaliana OX=3702 GN=At1g58525 PE=3 SV=2
+Soltu.DM.07G016620.1	sp|P0DKJ6|GDL4_ARATH	sp|P0DKJ6|GDL4_ARATH GDSL esterase/lipase At1g20120 OS=Arabidopsis thaliana OX=3702 GN=At1g20120 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q3ECM4|GDL25_ARATH	sp|Q3ECM4|GDL25_ARATH GDSL esterase/lipase At1g58725 OS=Arabidopsis thaliana OX=3702 GN=At1g58725 PE=2 SV=2
+Soltu.DM.07G016620.1	sp|F4IBF0|GDL26_ARATH	sp|F4IBF0|GDL26_ARATH GDSL esterase/lipase At1g59030 OS=Arabidopsis thaliana OX=3702 GN=At1g59030 PE=3 SV=2
+Soltu.DM.07G016620.1	sp|P0DI15|GDL27_ARATH	sp|P0DI15|GDL27_ARATH GDSL esterase/lipase At1g59406 OS=Arabidopsis thaliana OX=3702 GN=At1g59406 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q9LU14|APG2_ARATH	sp|Q9LU14|APG2_ARATH GDSL esterase/lipase APG OS=Arabidopsis thaliana OX=3702 GN=APG PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q9FFC6|GDL78_ARATH	sp|Q9FFC6|GDL78_ARATH GDSL esterase/lipase At5g22810 OS=Arabidopsis thaliana OX=3702 GN=At5g22810 PE=3 SV=3
+Soltu.DM.07G016620.1	sp|Q9FJ40|GDL86_ARATH	sp|Q9FJ40|GDL86_ARATH GDSL esterase/lipase At5g45960 OS=Arabidopsis thaliana OX=3702 GN=At5g45960 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q94CH8|EXL1_ARATH	sp|Q94CH8|EXL1_ARATH GDSL esterase/lipase EXL1 OS=Arabidopsis thaliana OX=3702 GN=EXL1 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q9LMJ3|GDL1_ARATH	sp|Q9LMJ3|GDL1_ARATH GDSL esterase/lipase At1g06990 OS=Arabidopsis thaliana OX=3702 GN=At1g06990 PE=2 SV=2
+Soltu.DM.07G016620.1	sp|Q9SIQ3|GDL43_ARATH	sp|Q9SIQ3|GDL43_ARATH GDSL esterase/lipase At2g31540 OS=Arabidopsis thaliana OX=3702 GN=At2g31540 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q9SIQ2|GDL44_ARATH	sp|Q9SIQ2|GDL44_ARATH GDSL esterase/lipase At2g31550 OS=Arabidopsis thaliana OX=3702 GN=At2g31550 PE=3 SV=3
+Soltu.DM.07G016620.1	sp|Q9C648|GDL23_ARATH	sp|Q9C648|GDL23_ARATH GDSL esterase/lipase At1g58430 OS=Arabidopsis thaliana OX=3702 GN=At1g58430 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q9LH73|GDL52_ARATH	sp|Q9LH73|GDL52_ARATH GDSL esterase/lipase At3g14820 OS=Arabidopsis thaliana OX=3702 GN=At3g14820 PE=3 SV=2
+Soltu.DM.07G016620.1	sp|Q9SJA9|GDL39_ARATH	sp|Q9SJA9|GDL39_ARATH GDSL esterase/lipase At2g24560 OS=Arabidopsis thaliana OX=3702 GN=At2g24560 PE=2 SV=2
+Soltu.DM.07G016620.1	sp|Q0WPI9|GDL59_ARATH	sp|Q0WPI9|GDL59_ARATH GDSL esterase/lipase At3g53100 OS=Arabidopsis thaliana OX=3702 GN=At3g53100 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|O22927|GDL42_ARATH	sp|O22927|GDL42_ARATH GDSL esterase/lipase At2g30310 OS=Arabidopsis thaliana OX=3702 GN=At2g30310 PE=2 SV=1
+Soltu.DM.07G016620.1	sp|Q9FYD3|GDL56_ARATH	sp|Q9FYD3|GDL56_ARATH GDSL esterase/lipase At3g43570 OS=Arabidopsis thaliana OX=3702 GN=At3g43570 PE=3 SV=1
+Soltu.DM.03G011280.1	sp|F4IXE7|IDM1_ARATH	sp|F4IXE7|IDM1_ARATH Increased DNA methylation 1 OS=Arabidopsis thaliana OX=3702 GN=IDM1 PE=1 SV=1
+Soltu.DM.01G045390.1	sp|Q9S7V4|HA22A_ARATH	sp|Q9S7V4|HA22A_ARATH HVA22-like protein a OS=Arabidopsis thaliana OX=3702 GN=HVA22A PE=2 SV=1
+Soltu.DM.01G045390.1	sp|Q9S784|HA22C_ARATH	sp|Q9S784|HA22C_ARATH HVA22-like protein c OS=Arabidopsis thaliana OX=3702 GN=HVA22C PE=2 SV=1
+Soltu.DM.01G045390.1	sp|Q682H0|HA22F_ARATH	sp|Q682H0|HA22F_ARATH HVA22-like protein f OS=Arabidopsis thaliana OX=3702 GN=HVA22F PE=2 SV=1
+Soltu.DM.01G045390.1	sp|Q9S760|HA22D_ARATH	sp|Q9S760|HA22D_ARATH HVA22-like protein d OS=Arabidopsis thaliana OX=3702 GN=HVA22D PE=2 SV=1
+Soltu.DM.02G020600.1	sp|Q6R2J8|SRF8_ARATH	sp|Q6R2J8|SRF8_ARATH Protein STRUBBELIG-RECEPTOR FAMILY 8 OS=Arabidopsis thaliana OX=3702 GN=SRF8 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q9LUL4|SRF7_ARATH	sp|Q9LUL4|SRF7_ARATH Protein STRUBBELIG-RECEPTOR FAMILY 7 OS=Arabidopsis thaliana OX=3702 GN=SRF7 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q9C8M9|SRF6_ARATH	sp|Q9C8M9|SRF6_ARATH Protein STRUBBELIG-RECEPTOR FAMILY 6 OS=Arabidopsis thaliana OX=3702 GN=SRF6 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q6R2K1|SRF5_ARATH	sp|Q6R2K1|SRF5_ARATH Protein STRUBBELIG-RECEPTOR FAMILY 5 OS=Arabidopsis thaliana OX=3702 GN=SRF5 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q06BH3|SRF1_ARATH	sp|Q06BH3|SRF1_ARATH Protein STRUBBELIG-RECEPTOR FAMILY 1 OS=Arabidopsis thaliana OX=3702 GN=SRF1 PE=1 SV=2
+Soltu.DM.02G020600.1	sp|Q9FG24|SRF2_ARATH	sp|Q9FG24|SRF2_ARATH Protein STRUBBELIG-RECEPTOR FAMILY 2 OS=Arabidopsis thaliana OX=3702 GN=SRF2 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q6R2K3|SRF3_ARATH	sp|Q6R2K3|SRF3_ARATH Protein STRUBBELIG-RECEPTOR FAMILY 3 OS=Arabidopsis thaliana OX=3702 GN=SRF3 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q6R2K2|SRF4_ARATH	sp|Q6R2K2|SRF4_ARATH Protein STRUBBELIG-RECEPTOR FAMILY 4 OS=Arabidopsis thaliana OX=3702 GN=SRF4 PE=2 SV=1
+Soltu.DM.02G020600.1	sp|Q8RWZ1|SUB_ARATH	sp|Q8RWZ1|SUB_ARATH Protein STRUBBELIG OS=Arabidopsis thaliana OX=3702 GN=SUB PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q9LDZ5|PBL21_ARATH	sp|Q9LDZ5|PBL21_ARATH Probable serine/threonine-protein kinase PBL21 OS=Arabidopsis thaliana OX=3702 GN=PBL21 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|O49339|PTI12_ARATH	sp|O49339|PTI12_ARATH PTI1-like tyrosine-protein kinase 2 OS=Arabidopsis thaliana OX=3702 GN=PTI12 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|B9DFG5|PTI13_ARATH	sp|B9DFG5|PTI13_ARATH PTI1-like tyrosine-protein kinase 3 OS=Arabidopsis thaliana OX=3702 GN=PTI13 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q41328|PTI1_SOLLC	sp|Q41328|PTI1_SOLLC Pto-interacting protein 1 OS=Solanum lycopersicum OX=4081 GN=PTI1 PE=1 SV=2
+Soltu.DM.02G020600.1	sp|Q9LUT0|CARK1_ARATH	sp|Q9LUT0|CARK1_ARATH Receptor-like cytoplasmic kinase 1 OS=Arabidopsis thaliana OX=3702 GN=CARK1 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q0WRY5|PBL7_ARATH	sp|Q0WRY5|PBL7_ARATH Probable serine/threonine-protein kinase PBL7 OS=Arabidopsis thaliana OX=3702 GN=PBL7 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|O80719|Y2706_ARATH	sp|O80719|Y2706_ARATH Probable receptor-like protein kinase At2g47060 OS=Arabidopsis thaliana OX=3702 GN=At2g47060 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|F4JEQ2|PBL23_ARATH	sp|F4JEQ2|PBL23_ARATH Probable serine/threonine-protein kinase PBL23 OS=Arabidopsis thaliana OX=3702 GN=PBL23 PE=2 SV=1
+Soltu.DM.02G020600.1	sp|Q8H1G6|PTI11_ARATH	sp|Q8H1G6|PTI11_ARATH PTI1-like tyrosine-protein kinase 1 OS=Arabidopsis thaliana OX=3702 GN=PTI11 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q9SFT7|PBL26_ARATH	sp|Q9SFT7|PBL26_ARATH Probable serine/threonine-protein kinase PBL26 OS=Arabidopsis thaliana OX=3702 GN=PBL26 PE=2 SV=1
+Soltu.DM.02G020600.1	sp|Q6I5Q6|RK185_ORYSJ	sp|Q6I5Q6|RK185_ORYSJ Receptor-like cytoplasmic kinase 185 OS=Oryza sativa subsp. japonica OX=39947 GN=RLCK185 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|Q9FE20|PBS1_ARATH	sp|Q9FE20|PBS1_ARATH Serine/threonine-protein kinase PBS1 OS=Arabidopsis thaliana OX=3702 GN=PBS1 PE=1 SV=1
+Soltu.DM.02G020600.1	sp|P93749|Y2197_ARATH	sp|P93749|Y2197_ARATH Probable protein kinase At2g41970 OS=Arabidopsis thaliana OX=3702 GN=At2g41970 PE=2 SV=1
+Soltu.DM.02G020600.1	sp|Q1PE89|PBL24_ARATH	sp|Q1PE89|PBL24_ARATH Probable serine/threonine-protein kinase PBL24 OS=Arabidopsis thaliana OX=3702 GN=PBL24 PE=2 SV=1
+Soltu.DM.02G020600.1	sp|Q9LRY1|PBL25_ARATH	sp|Q9LRY1|PBL25_ARATH Probable serine/threonine-protein kinase PBL25 OS=Arabidopsis thaliana OX=3702 GN=PBL25 PE=2 SV=1
+Soltu.DM.02G020600.1	sp|Q9LQQ8|PBL5_ARATH	sp|Q9LQQ8|PBL5_ARATH Probable serine/threonine-protein kinase PBL5 OS=Arabidopsis thaliana OX=3702 GN=PBL5 PE=2 SV=1
diff -r 000000000000 -r c840a1c77a0a test-data/blacklist_stitle_regexs.txt
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/blacklist_stitle_regexs.txt	Tue May 10 13:18:05 2022 +0000
@@ -0,0 +1,11 @@
+(?i)\bsimilar\s+to
+(?i)\bprobable\b
+(?i)\bputative\b
+(?i)\bpredicted\b
+(?i)\buncharacterized\b
+(?i)\bunknown\b
+(?i)\bhypothetical\b
+(?i)\bunnamed\b
+(?i)\bfragment\b
+(?i)\bwhole\s+genome\s+shotgun\s+sequence\b
+(?i)\bclone\b
\ No newline at end of file