# HG changeset patch
# User artbio
# Date 1522513087 14400
# Node ID 39b8e13b1fc9785b93adf04d514e79d72ff3e18a
# Parent  78a1909aca3ee4e54e7340afbea5177c2c1954c3
planemo upload for repository https://github.com/artbio/tools-artbio/tree/master/tools/rsem commit f01c120abce1894ac9c6b298d301d4a2c740fc67

diff -r 78a1909aca3e -r 39b8e13b1fc9 datatypes_conf.xml
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/datatypes_conf.xml	Sat Mar 31 12:18:07 2018 -0400
@@ -0,0 +1,14 @@
+<?xml version="1.0"?>
+<datatypes>
+    <datatype_files>
+        <datatype_file name="rsem.py"/>
+    </datatype_files>
+    <registration>
+        <datatype extension="rsem_ref" type="galaxy.datatypes.rsem:RsemReference" display_in_upload="true"/>
+        <datatype extension="rsem.genes.results" type="galaxy.datatypes.rsem:RsemGenesResults" display_in_upload="true"/>
+        <datatype extension="rsem.isoforms.results" type="galaxy.datatypes.rsem:RsemIsoformsResults" display_in_upload="true"/>
+        <datatype extension="rsem.ngvec" type="galaxy.datatypes.tabular:Tabular" subclass="True" display_in_upload="true"/>
+        <datatype extension="rsem.genemat" type="galaxy.datatypes.tabular:Tabular" subclass="True" display_in_upload="true"/>
+        <datatype extension="rsem.isomat" type="galaxy.datatypes.tabular:Tabular" subclass="True" display_in_upload="true"/>
+    </registration>
+</datatypes>
diff -r 78a1909aca3e -r 39b8e13b1fc9 extract_transcript_to_gene_map_from_trinity.xml
--- a/extract_transcript_to_gene_map_from_trinity.xml	Sat Mar 31 10:17:42 2018 -0400
+++ b/extract_transcript_to_gene_map_from_trinity.xml	Sat Mar 31 12:18:07 2018 -0400
@@ -1,4 +1,4 @@
-<tool id="extract_transcript_to_gene_map_from_trinity" name="RSEM trinity fasta to gene map" version="0.1.0">
+<tool id="extract_transcript_to_gene_map_from_trinity" name="RSEM trinity fasta to gene map" version="0.4.0">
   <description>extract transcript to gene map from trinity</description>
   <requirements>
     <requirement type="package" version="1.3.0">rsem</requirement>
@@ -38,4 +38,7 @@
  
 
   </help> 
+    <citations>
+      <citation type="doi">10.1038/nbt.1883</citation>
+    </citations>
 </tool> 
diff -r 78a1909aca3e -r 39b8e13b1fc9 rsem-bwt2.xml
--- a/rsem-bwt2.xml	Sat Mar 31 10:17:42 2018 -0400
+++ b/rsem-bwt2.xml	Sat Mar 31 12:18:07 2018 -0400
@@ -423,6 +423,7 @@
   </tests>
 
   <help>
+.. class:: infomark
 
 RSEM HOME PAGE - http://deweylab.biostat.wisc.edu/rsem/
 
diff -r 78a1909aca3e -r 39b8e13b1fc9 rsem.py
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/rsem.py	Sat Mar 31 12:18:07 2018 -0400
@@ -0,0 +1,174 @@
+"""
+RSEM datatypes
+"""
+import logging
+import os
+import os.path
+
+from galaxy.datatypes.images import Html
+from galaxy.datatypes.metadata import MetadataElement
+from galaxy.datatypes.sniff import get_headers
+from galaxy.datatypes.tabular import Tabular
+
+
+log = logging.getLogger(__name__)
+
+
+class RsemIsoformsResults(Tabular):
+    file_ext = "rsem.isoforms.results"
+    """
+    required columns:
+    transcript_id gene_id length effective_length expected_count TPM
+    FPKM IsoPct
+    optional columns:
+    pme_expected_count pme_TPM pme_FPKM IsoPct_from_pme_TPM TPM_ci_lower_bound
+    TPM_ci_upper_bound FPKM_ci_lower_bound FPKM_ci_upper_bound
+    """
+
+    def __init__(self, **kwd):
+        Tabular.__init__(self, **kwd)
+        """Initialize RsemResults datatype"""
+        self.comment_lines = 1
+
+    def sniff(self, filename):
+        headers = get_headers(filename, '\n', count=1)
+        return (len(headers) > 0 and len(headers[0]) >= 8 and
+                headers[0][0] == "transcript_id" and
+                headers[0][1] == "gene_id" and headers[0][6] == "FPKM")
+
+    def set_meta(self, dataset, **kwd):
+        Tabular.set_meta(self, dataset, skip=None, **kwd)
+
+
+class RsemGenesResults(Tabular):
+    file_ext = "rsem.genes.results"
+    """
+    required columns:
+    gene_id transcript_id(s) length effective_length expected_count TPM FPKM
+    optional columns:
+    pme_expected_count pme_TPM pme_FPKM TPM_ci_lower_bound TPM_ci_upper_bound
+    FPKM_ci_lower_bound FPKM_ci_upper_bound
+    """
+
+    def __init__(self, **kwd):
+        Tabular.__init__(self, **kwd)
+        """Initialize RsemResults datatype"""
+        self.comment_lines = 1
+
+    def sniff(self, filename):
+        headers = get_headers(filename, '\n', count=1)
+        return (len(headers) > 0 and len(headers[0]) >= 7 and
+                headers[0][0] == "gene_id" and
+                headers[0][1].startswith("transcript_id") and
+                headers[0][6] == "FPKM")
+
+    def set_meta(self, dataset, **kwd):
+        Tabular.set_meta(self, dataset, skip=None, **kwd)
+
+
+class RsemReference(Html):
+    """Class describing an RSEM reference"""
+    MetadataElement(name='reference_name', default='rsem_ref',
+                    desc='RSEM Reference Name', readonly=True, visible=True,
+                    set_in_upload=True, no_value='rsem_ref')
+    file_ext = 'rsem_ref'
+    allow_datatype_change = False
+    composite_type = 'auto_primary_file'
+
+    def __init__(self, **kwd):
+        Html.__init__(self, **kwd)
+        """
+        Expecting files:
+        extra_files_path/<reference_name>.grp
+        extra_files_path/<reference_name>.ti
+        extra_files_path/<reference_name>.seq
+        extra_files_path/<reference_name>.transcripts.fa
+        Optionally includes files:
+        extra_files_path/<reference_name>.chrlist
+        extra_files_path/<reference_name>.idx.fa
+        extra_files_path/<reference_name>.1.ebwt
+        extra_files_path/<reference_name>.2.ebwt
+        extra_files_path/<reference_name>.3.ebwt
+        extra_files_path/<reference_name>.4.ebwt
+        extra_files_path/<reference_name>.rev.1.ebwt
+        extra_files_path/<reference_name>.rev.2.ebwt
+        """
+        self.add_composite_file('%s.grp', description='Group File',
+                                substitute_name_with_metadata='reference_name',
+                                is_binary=False)
+        self.add_composite_file('%s.ti', description='',
+                                substitute_name_with_metadata='reference_name',
+                                is_binary=False)
+        self.add_composite_file('%s.seq', description='',
+                                substitute_name_with_metadata='reference_name',
+                                is_binary=False)
+        self.add_composite_file('%s.transcripts.fa', description='',
+                                substitute_name_with_metadata='reference_name',
+                                is_binary=False)
+        self.add_composite_file('%s.chrlist', description='',
+                                substitute_name_with_metadata='reference_name',
+                                is_binary=False, optional=True)
+        self.add_composite_file('%s.idx.fa', description='',
+                                substitute_name_with_metadata='reference_name',
+                                is_binary=False, optional=True)
+        self.add_composite_file('%s.1.ebwt', description='',
+                                substitute_name_with_metadata='reference_name',
+                                is_binary=True, optional=True)
+        self.add_composite_file('%s.2.ebwt', description='',
+                                substitute_name_with_metadata='reference_name',
+                                is_binary=True, optional=True)
+        self.add_composite_file('%s.3.ebwt', description='',
+                                substitute_name_with_metadata='reference_name',
+                                is_binary=True, optional=True)
+        self.add_composite_file('%s.4.ebwt', description='',
+                                substitute_name_with_metadata='reference_name',
+                                is_binary=True, optional=True)
+        self.add_composite_file('%s.rev.1.ebwt', description='',
+                                substitute_name_with_metadata='reference_name',
+                                is_binary=True, optional=True)
+        self.add_composite_file('%s.rev.2.ebwt', description='',
+                                substitute_name_with_metadata='reference_name',
+                                is_binary=True, optional=True)
+
+    def generate_primary_file(self, dataset=None):
+        """
+        This is called only at upload to write the file
+        cannot rename the datasets here - they come with
+        the default unfortunately
+        """
+
+    def regenerate_primary_file(self, dataset):
+        """
+        cannot do this until we are setting metadata
+        """
+        link_to_exts = ['.grp', '.ti', '.seq', '.fa', '.chrlist', '.log']
+        ref_name = dataset.metadata.reference_name
+        efp = dataset.extra_files_path
+        flist = os.listdir(efp)
+        rval = ['<html><head><title>%s</title></head><body><p/>RSEM \
+                 Reference   %s   files:<p/><ul>' % (dataset.name, ref_name)]
+        rvalb = []
+        for i, fname in enumerate(flist):
+            sfname = os.path.split(fname)[-1]
+            f, e = os.path.splitext(fname)
+            if e in link_to_exts:
+                rval.append('<li><a href="%s">%s</a></li>' % (sfname, sfname))
+            else:
+                rvalb.append('<li>%s</li>' % (sfname))
+        if len(rvalb) > 0:
+            rval += rvalb
+        rval.append('</ul></body></html>')
+        fh = file(dataset.file_name, 'w')
+        fh.write("\n".join(rval))
+        fh.write('\n')
+        fh.close()
+
+    def set_meta(self, dataset, **kwd):
+        Html.set_meta(self, dataset, **kwd)
+        efp = dataset.extra_files_path
+        flist = os.listdir(efp)
+        for i, fname in enumerate(flist):
+            if fname.endswith('.grp'):
+                dataset.metadata.reference_name = fname[:-4]
+                break
+        self.regenerate_primary_file(dataset)
diff -r 78a1909aca3e -r 39b8e13b1fc9 rsem.xml
--- a/rsem.xml	Sat Mar 31 10:17:42 2018 -0400
+++ b/rsem.xml	Sat Mar 31 12:18:07 2018 -0400
@@ -417,6 +417,7 @@
   </tests>
 
   <help>
+.. class:: infomark
 
 RSEM HOME PAGE - http://deweylab.biostat.wisc.edu/rsem/