Mercurial > repos > cpt > cpt_disruptin_finder

changeset 1:b973bc75693d draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
author cpt
date Mon, 05 Jun 2023 02:40:49 +0000
parents 3f0d07a10405
children f046c58687a2
files cpt-macros.xml cpt_disruptin_finder/cpt-macros.xml cpt_disruptin_finder/disruptin_finder.py cpt_disruptin_finder/disruptin_finder.xml cpt_disruptin_finder/macros.xml disruptin_finder.py disruptin_finder.xml macros.xml
diffstat 8 files changed, 333 insertions(+), 285 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt-macros.xml	Mon Jun 05 02:40:49 2023 +0000
@@ -0,0 +1,115 @@
+<macros>
+    <xml name="gff_requirements">
+        <requirements>
+            <requirement type="package" version="2.7">python</requirement>
+            <requirement type="package" version="1.65">biopython</requirement>
+            <requirement type="package" version="2.12.1">requests</requirement>
+			<requirement type="package" version="1.2.2">cpt_gffparser</requirement>
+            <yield/>
+        </requirements>
+        <version_command>
+		<![CDATA[
+			cd '$__tool_directory__' && git rev-parse HEAD
+		]]>
+		</version_command>
+    </xml>
+    <xml name="citation/mijalisrasche">
+        <citation type="doi">10.1371/journal.pcbi.1008214</citation>
+        <citation type="bibtex">@unpublished{galaxyTools,
+		author = {E. Mijalis, H. Rasche},
+		title = {CPT Galaxy Tools},
+		year = {2013-2017},
+		note = {https://github.com/tamu-cpt/galaxy-tools/}
+		}
+		</citation>
+    </xml>
+    <xml name="citations">
+        <citations>
+            <citation type="doi">10.1371/journal.pcbi.1008214</citation>
+            <citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {E. Mijalis, H. Rasche},
+				title = {CPT Galaxy Tools},
+				year = {2013-2017},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+			</citation>
+            <yield/>
+        </citations>
+    </xml>
+    <xml name="citations-crr">
+        <citations>
+            <citation type="doi">10.1371/journal.pcbi.1008214</citation>
+            <citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {C. Ross},
+				title = {CPT Galaxy Tools},
+				year = {2020-},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+			</citation>
+            <yield/>
+        </citations>
+    </xml>
+    <xml name="citations-2020">
+        <citations>
+            <citation type="doi">10.1371/journal.pcbi.1008214</citation>
+            <citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {E. Mijalis, H. Rasche},
+				title = {CPT Galaxy Tools},
+				year = {2013-2017},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+			</citation>
+            <citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {A. Criscione},
+				title = {CPT Galaxy Tools},
+				year = {2019-2021},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+                        </citation>
+            <yield/>
+        </citations>
+    </xml>
+    <xml name="citations-2020-AJC-solo">
+        <citations>
+            <citation type="doi">10.1371/journal.pcbi.1008214</citation>
+            <citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {A. Criscione},
+				title = {CPT Galaxy Tools},
+				year = {2019-2021},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+                        </citation>
+            <yield/>
+        </citations>
+    </xml>
+    <xml name="citations-clm">
+        <citations>
+            <citation type="doi">10.1371/journal.pcbi.1008214</citation>
+            <citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {C. Maughmer},
+				title = {CPT Galaxy Tools},
+				year = {2017-2020},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+			</citation>
+            <yield/>
+        </citations>
+    </xml>
+    <xml name="sl-citations-clm">
+        <citation type="bibtex">
+			@unpublished{galaxyTools,
+				author = {C. Maughmer},
+				title = {CPT Galaxy Tools},
+				year = {2017-2020},
+				note = {https://github.com/tamu-cpt/galaxy-tools/}
+			}
+			</citation>
+        <yield/>
+    </xml>
+</macros>
--- a/cpt_disruptin_finder/cpt-macros.xml	Fri Jun 17 12:22:15 2022 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,115 +0,0 @@
-<?xml version="1.0"?>
-<macros>
-	<xml name="gff_requirements">
-		<requirements>
-			<requirement type="package" version="2.7">python</requirement>
-			<requirement type="package" version="1.65">biopython</requirement>
-			<requirement type="package" version="2.12.1">requests</requirement>
-			<yield/>
-		</requirements>
-		<version_command>
-		<![CDATA[
-			cd $__tool_directory__ && git rev-parse HEAD
-		]]>
-		</version_command>
-	</xml>
-	<xml name="citation/mijalisrasche">
-		<citation type="doi">10.1371/journal.pcbi.1008214</citation>
-		<citation type="bibtex">@unpublished{galaxyTools,
-		author = {E. Mijalis, H. Rasche},
-		title = {CPT Galaxy Tools},
-		year = {2013-2017},
-		note = {https://github.com/tamu-cpt/galaxy-tools/}
-		}
-		</citation>
-	</xml>
-	<xml name="citations">
-		<citations>
-			<citation type="doi">10.1371/journal.pcbi.1008214</citation>
-			<citation type="bibtex">
-			@unpublished{galaxyTools,
-				author = {E. Mijalis, H. Rasche},
-				title = {CPT Galaxy Tools},
-				year = {2013-2017},
-				note = {https://github.com/tamu-cpt/galaxy-tools/}
-			}
-			</citation> 
-		<yield/>
-		</citations>
-	</xml>
-    	<xml name="citations-crr">
-		<citations>
-			<citation type="doi">10.1371/journal.pcbi.1008214</citation>
-			<citation type="bibtex">
-			@unpublished{galaxyTools,
-				author = {C. Ross},
-				title = {CPT Galaxy Tools},
-				year = {2020-},
-				note = {https://github.com/tamu-cpt/galaxy-tools/}
-			}
-			</citation>
-		<yield/>
-		</citations>
-	</xml>
-        <xml name="citations-2020">
-		<citations>
-			<citation type="doi">10.1371/journal.pcbi.1008214</citation>
-			<citation type="bibtex">
-			@unpublished{galaxyTools,
-				author = {E. Mijalis, H. Rasche},
-				title = {CPT Galaxy Tools},
-				year = {2013-2017},
-				note = {https://github.com/tamu-cpt/galaxy-tools/}
-			}
-			</citation>
-                        <citation type="bibtex">
-			@unpublished{galaxyTools,
-				author = {A. Criscione},
-				title = {CPT Galaxy Tools},
-				year = {2019-2021},
-				note = {https://github.com/tamu-cpt/galaxy-tools/}
-			}
-                        </citation>
-                        <yield/>
-		</citations>
-	</xml>
-        <xml name="citations-2020-AJC-solo">
-		<citations>
-			<citation type="doi">10.1371/journal.pcbi.1008214</citation>
-                        <citation type="bibtex">
-			@unpublished{galaxyTools,
-				author = {A. Criscione},
-				title = {CPT Galaxy Tools},
-				year = {2019-2021},
-				note = {https://github.com/tamu-cpt/galaxy-tools/}
-			}
-                        </citation>
-                        <yield/>
-		</citations>
-	</xml>
-        <xml name="citations-clm">
-		<citations>
-			<citation type="doi">10.1371/journal.pcbi.1008214</citation>
-			<citation type="bibtex">
-			@unpublished{galaxyTools,
-				author = {C. Maughmer},
-				title = {CPT Galaxy Tools},
-				year = {2017-2020},
-				note = {https://github.com/tamu-cpt/galaxy-tools/}
-			}
-			</citation>
-                        <yield/>
-		</citations>
-	</xml>
-        <xml name="sl-citations-clm">
-			<citation type="bibtex">
-			@unpublished{galaxyTools,
-				author = {C. Maughmer},
-				title = {CPT Galaxy Tools},
-				year = {2017-2020},
-				note = {https://github.com/tamu-cpt/galaxy-tools/}
-			}
-			</citation>
-                        <yield/>
-	</xml>
-</macros>
--- a/cpt_disruptin_finder/disruptin_finder.py	Fri Jun 17 12:22:15 2022 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,93 +0,0 @@
-"""
-This program is intended to find gene products that would be acceptable disruptin candidates.
-
-The criteria can be toggled between selecting for proteins with:
-    - net charge above a give threshold (default = +4) and length less than given threshold (default = 100 aa)
-    OR
-    - ratio of number of charged residues to length of the sequence above a given threshold (default = 0.25 residue/aa)
-    and length less than given threshold (default = 100 aa)
-    OR
-    - net charge above a give threshold (default = +4), ratio of number of charged residues to length of the sequence
-    above a given threshold (default = 0.25 residue/aa), and length less than given threshold (default = 100 aa)
-
-Net charge of a sequence is calculated so that for every R or K residue the net charge increases by one, and for every
-D or E residue the net charge decreases by one. The ratio of charged residues to length is calculated in a similar manner.
-The residues R, K, D, and E each increase the number of charged residues by one, and total for the sequence is then
-divided by the length to get the ratio.
-
-Input a multi fasta file with all of the predicted protein sequences from the genome as well as a threshold
-sequence length, net charge, and charge residue to length ratio. The program outputs another fasta file.
-The output fasta file includes records for all the sequences meeting the size and charge criteria.
-
-"""
-
-from Bio import SeqIO
-import argparse
-import sys
-
-
-def disruptin_finder(
-    fasta_file, thresh_size, thresh_net_charge, thresh_charge_ratio, selection_criteria
-):
-    # Iterable variables
-    net_charge = 0
-    charge_res = 0
-
-    # Create record variable to store record information
-    total_record = []
-
-    # Parse the .fasta file and get the sequence
-    for rec in SeqIO.parse(fasta_file, "fasta"):
-        sequence = str(rec.seq)
-
-        if len(sequence) <= thresh_size:
-            for aa in sequence:
-                # For R and K residues a positive charge is given
-                if aa in "RK":
-                    net_charge += 1
-                    charge_res += 1
-                # For D and E residues a negative charge is given
-                elif aa in "DE":
-                    net_charge -= 1
-                    charge_res += 1
-
-            # Charge (total charged residues) to size ratio is calculated
-            Length = len(sequence)
-            charge_ratio = float(charge_res) / float(Length)
-
-            # Based on the user-specified selection criteria a list of records is compiled
-            if selection_criteria == "net":
-                if net_charge >= thresh_net_charge:
-                    total_record = total_record + [rec]
-            elif selection_criteria == "ratio":
-                if charge_ratio >= thresh_charge_ratio:
-                    total_record = total_record + [rec]
-            elif selection_criteria == "both":
-                if (
-                    charge_ratio >= thresh_charge_ratio
-                    and net_charge >= thresh_net_charge
-                ):
-                    total_record = total_record + [rec]
-
-            # Reset the iterable variables
-            net_charge = 0
-            charge_res = 0
-
-    # The total list of records is returned by the function
-    yield total_record
-
-
-if __name__ == "__main__":
-    # Grab all of the filters from our plugin loader
-    parser = argparse.ArgumentParser(description="Disruptin Finder")
-    parser.add_argument(
-        "fasta_file", type=argparse.FileType("r"), help="Multi-FASTA Input"
-    )
-    parser.add_argument("--thresh_net_charge", type=int, default=4)
-    parser.add_argument("--thresh_size", type=int, default=100)
-    parser.add_argument("--thresh_charge_ratio", type=float, default=0.25)
-    parser.add_argument("--selection_criteria", action="store")
-    args = parser.parse_args()
-
-    for seq in disruptin_finder(**vars(args)):
-        SeqIO.write(seq, sys.stdout, "fasta")
--- a/cpt_disruptin_finder/disruptin_finder.xml	Fri Jun 17 12:22:15 2022 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,54 +0,0 @@
-<?xml version="1.1"?>
-<tool id="edu.tamu.cpt2.phage.disruptin_finder" name="Disruptin Finder" version="1.1">
-    <description>finds proteins with size and charge criteria</description>
-    <macros>
-		<import>macros.xml</import>
-		<import>cpt-macros.xml</import>
-    </macros>
-    <expand macro="requirements"/>
-    <command detect_errors="aggressive"><![CDATA[
-python $__tool_directory__/disruptin_finder.py
-$fasta_file
---thresh_net_charge $thresh_net_charge
---thresh_size $thresh_size
---thresh_charge_ratio $thresh_charge_ratio
---selection_criteria $selection_criteria
-
-> $output]]></command>
-    <inputs>
-        <param label="Fasta" name="fasta_file" type="data" format="fasta" />
-	<param label="Minimum Net Charge" name="thresh_net_charge" type="integer" value="4" />
-        <param label="Maximum Length" name="thresh_size" type="integer" value="100" />
-	<param label="Minimum Charge to Length Ratio" name="thresh_charge_ratio" type="float" value="0.25" />
-		
-	<param type="select" label="Type of selection criteria" name="selection_criteria">
-		<option value="net">Net charge</option>
-		<option value="ratio">Ratio of charged residues to sequence length</option>
-		<option value="both" selected="true">Both net charge and ratio</option>
-	</param>
-
-    </inputs>
-    <outputs>
-		<data format="fasta" name="output"/>
-    </outputs>
-    <help><![CDATA[
-**What it does**
-This program finds proteins sequences based on given selection criteria: net charge, sequence length, 
-and/or number of charged residues per amino acid. Inputs include a multi fasta file of protein sequences,
-thresholds for size, charge, and charge-to-size ratio criteria.
-
-This tool returns the selected sequences in a fasta format.
-
-        ]]></help>
-    <citations>
-      <citation type="doi">10.1371/journal.pcbi.1008214</citation>
-      <citation type="bibtex">
-      @unpublished{galaxyTools, 
-          author = {A. Holt},
-          title = {CPT Galaxy Tools},
-          year = {2020},
-          note = {https://github.com/tamu-cpt/galaxy-tools/}
-      }
-      </citation>
-    </citations>
-</tool>
--- a/cpt_disruptin_finder/macros.xml	Fri Jun 17 12:22:15 2022 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,23 +0,0 @@
-<?xml version="1.0"?>
-<macros>
-  <xml name="requirements">
-    <requirements>
-		<requirement type="package" version="3.8.13">python</requirement>
-		<requirement type="package" version="1.79">biopython</requirement>
-		<requirement type="package" version="1.2.2">cpt_gffparser</requirement>  
-		<yield/>
-    </requirements>
-  </xml>
-  <xml name="genome_selector">
-	    <param name="genome_fasta" type="data" format="fasta" label="Source FASTA Sequence"/>
-  </xml>
-  <xml name="gff3_input">
-    <param label="GFF3 Annotations" name="gff3_data" type="data" format="gff3"/>
-  </xml>
-  <token name="@GENOME_SELECTOR_PRE@">
-		ln -s $genome_fasta genomeref.fa;
-	</token>
-	<token name="@GENOME_SELECTOR@">
-		genomeref.fa
-	</token>
-</macros>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/disruptin_finder.py	Mon Jun 05 02:40:49 2023 +0000
@@ -0,0 +1,93 @@
+"""
+This program is intended to find gene products that would be acceptable disruptin candidates.
+
+The criteria can be toggled between selecting for proteins with:
+    - net charge above a give threshold (default = +4) and length less than given threshold (default = 100 aa)
+    OR
+    - ratio of number of charged residues to length of the sequence above a given threshold (default = 0.25 residue/aa)
+    and length less than given threshold (default = 100 aa)
+    OR
+    - net charge above a give threshold (default = +4), ratio of number of charged residues to length of the sequence
+    above a given threshold (default = 0.25 residue/aa), and length less than given threshold (default = 100 aa)
+
+Net charge of a sequence is calculated so that for every R or K residue the net charge increases by one, and for every
+D or E residue the net charge decreases by one. The ratio of charged residues to length is calculated in a similar manner.
+The residues R, K, D, and E each increase the number of charged residues by one, and total for the sequence is then
+divided by the length to get the ratio.
+
+Input a multi fasta file with all of the predicted protein sequences from the genome as well as a threshold
+sequence length, net charge, and charge residue to length ratio. The program outputs another fasta file.
+The output fasta file includes records for all the sequences meeting the size and charge criteria.
+
+"""
+
+from Bio import SeqIO
+import argparse
+import sys
+
+
+def disruptin_finder(
+    fasta_file, thresh_size, thresh_net_charge, thresh_charge_ratio, selection_criteria
+):
+    # Iterable variables
+    net_charge = 0
+    charge_res = 0
+
+    # Create record variable to store record information
+    total_record = []
+
+    # Parse the .fasta file and get the sequence
+    for rec in SeqIO.parse(fasta_file, "fasta"):
+        sequence = str(rec.seq)
+
+        if len(sequence) <= thresh_size:
+            for aa in sequence:
+                # For R and K residues a positive charge is given
+                if aa in "RK":
+                    net_charge += 1
+                    charge_res += 1
+                # For D and E residues a negative charge is given
+                elif aa in "DE":
+                    net_charge -= 1
+                    charge_res += 1
+
+            # Charge (total charged residues) to size ratio is calculated
+            Length = len(sequence)
+            charge_ratio = float(charge_res) / float(Length)
+
+            # Based on the user-specified selection criteria a list of records is compiled
+            if selection_criteria == "net":
+                if net_charge >= thresh_net_charge:
+                    total_record = total_record + [rec]
+            elif selection_criteria == "ratio":
+                if charge_ratio >= thresh_charge_ratio:
+                    total_record = total_record + [rec]
+            elif selection_criteria == "both":
+                if (
+                    charge_ratio >= thresh_charge_ratio
+                    and net_charge >= thresh_net_charge
+                ):
+                    total_record = total_record + [rec]
+
+            # Reset the iterable variables
+            net_charge = 0
+            charge_res = 0
+
+    # The total list of records is returned by the function
+    yield total_record
+
+
+if __name__ == "__main__":
+    # Grab all of the filters from our plugin loader
+    parser = argparse.ArgumentParser(description="Disruptin Finder")
+    parser.add_argument(
+        "fasta_file", type=argparse.FileType("r"), help="Multi-FASTA Input"
+    )
+    parser.add_argument("--thresh_net_charge", type=int, default=4)
+    parser.add_argument("--thresh_size", type=int, default=100)
+    parser.add_argument("--thresh_charge_ratio", type=float, default=0.25)
+    parser.add_argument("--selection_criteria", action="store")
+    args = parser.parse_args()
+
+    for seq in disruptin_finder(**vars(args)):
+        SeqIO.write(seq, sys.stdout, "fasta")
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/disruptin_finder.xml	Mon Jun 05 02:40:49 2023 +0000
@@ -0,0 +1,51 @@
+<tool id="edu.tamu.cpt2.phage.disruptin_finder" name="Disruptin Finder" version="1.1">
+  <description>finds proteins with size and charge criteria</description>
+  <macros>
+    <import>macros.xml</import>
+    <import>cpt-macros.xml</import>
+  </macros>
+  <expand macro="requirements"/>
+  <command detect_errors="aggressive"><![CDATA[
+python '$__tool_directory__/disruptin_finder.py'
+'$fasta_file'
+--thresh_net_charge '$thresh_net_charge'
+--thresh_size '$thresh_size'
+--thresh_charge_ratio '$thresh_charge_ratio'
+--selection_criteria '$selection_criteria'
+
+> '$output']]></command>
+  <inputs>
+    <param label="Fasta" name="fasta_file" type="data" format="fasta"/>
+    <param label="Minimum Net Charge" name="thresh_net_charge" type="integer" value="4"/>
+    <param label="Maximum Length" name="thresh_size" type="integer" value="100"/>
+    <param label="Minimum Charge to Length Ratio" name="thresh_charge_ratio" type="float" value="0.25"/>
+    <param type="select" label="Type of selection criteria" name="selection_criteria">
+      <option value="net">Net charge</option>
+      <option value="ratio">Ratio of charged residues to sequence length</option>
+      <option value="both" selected="true">Both net charge and ratio</option>
+    </param>
+  </inputs>
+  <outputs>
+    <data format="fasta" name="output"/>
+  </outputs>
+  <help><![CDATA[
+**What it does**
+This program finds proteins sequences based on given selection criteria: net charge, sequence length, 
+and/or number of charged residues per amino acid. Inputs include a multi fasta file of protein sequences,
+thresholds for size, charge, and charge-to-size ratio criteria.
+
+This tool returns the selected sequences in a fasta format.
+
+        ]]></help>
+  <citations>
+    <citation type="doi">10.1371/journal.pcbi.1008214</citation>
+    <citation type="bibtex">
+      @unpublished{galaxyTools, 
+          author = {A. Holt},
+          title = {CPT Galaxy Tools},
+          year = {2020},
+          note = {https://github.com/tamu-cpt/galaxy-tools/}
+      }
+      </citation>
+  </citations>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml	Mon Jun 05 02:40:49 2023 +0000
@@ -0,0 +1,74 @@
+<macros>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package">progressivemauve</requirement>
+            <!--<requirement type="package" version="2.7">python</requirement>-->
+            <requirement type="package" version="0.6.4">bcbiogff</requirement>
+            <yield/>
+        </requirements>
+    </xml>
+    <token name="@WRAPPER_VERSION@">2.4.0</token>
+    <xml name="citation/progressive_mauve">
+        <citation type="doi">10.1371/journal.pone.0011147</citation>
+    </xml>
+    <xml name="citation/gepard">
+        <citation type="doi">10.1093/bioinformatics/btm039</citation>
+    </xml>
+    <token name="@XMFA_INPUT@">
+		'$xmfa'
+	</token>
+    <xml name="xmfa_input" token_formats="xmfa">
+        <param type="data" format="@FORMATS@" name="xmfa" label="XMFA MSA"/>
+    </xml>
+    <token name="@XMFA_FA_INPUT@">
+		'$sequences'
+	</token>
+    <xml name="xmfa_fa_input">
+        <param type="data" format="fasta" name="sequences" label="Sequences in alignment" help="These sequences should be the SAME DATASET that was used in the progressiveMauve run. Failing that, they should be provided in the same order as in original progressiveMauve run"/>
+    </xml>
+    <xml name="genome_selector">
+        <conditional name="reference_genome">
+            <param name="reference_genome_source" type="select" label="Reference Genome">
+                <option value="history" selected="True">From History</option>
+                <option value="cached">Locally Cached</option>
+            </param>
+            <when value="cached">
+                <param name="fasta_indexes" type="select" label="Source FASTA Sequence">
+                    <options from_data_table="all_fasta"/>
+                </param>
+            </when>
+            <when value="history">
+                <param name="genome_fasta" type="data" format="fasta" label="Source FASTA Sequence"/>
+            </when>
+        </conditional>
+    </xml>
+    <xml name="gff3_input">
+        <param label="GFF3 Annotations" name="gff3_data" type="data" format="gff3"/>
+    </xml>
+    <xml name="input/gff3+fasta">
+        <expand macro="gff3_input"/>
+        <expand macro="genome_selector"/>
+    </xml>
+    <token name="@INPUT_GFF@">
+	    '$gff3_data'
+	</token>
+    <token name="@INPUT_FASTA@">
+    #if str($reference_genome.reference_genome_source) == 'cached':
+            '${reference_genome.fasta_indexes.fields.path}'
+    #else if str($reference_genome.reference_genome_source) == 'history':
+            genomeref.fa
+    #end if
+	</token>
+    <token name="@GENOME_SELECTOR_PRE@">
+    #if $reference_genome.reference_genome_source == 'history':
+            ln -s '$reference_genome.genome_fasta' genomeref.fa;
+    #end if
+	</token>
+    <token name="@GENOME_SELECTOR@">
+    #if str($reference_genome.reference_genome_source) == 'cached':
+            '${reference_genome.fasta_indexes.fields.path}'
+    #else if str($reference_genome.reference_genome_source) == 'history':
+            genomeref.fa
+    #end if
+	</token>
+</macros>