diff rsem.py @ 1:49795544dac7 draft

planemo upload for repository https://github.com/artbio/tools-artbio/tree/master/tools/rsem commit 62e8088d5f73cbb9b2f93e23a74636c77a06b492
author artbio
date Sun, 01 Apr 2018 18:28:24 -0400
parents e5e836936d60
children e00a79cf5f8c
line wrap: on
line diff
--- a/rsem.py	Sat Mar 31 21:30:07 2018 -0400
+++ b/rsem.py	Sun Apr 01 18:28:24 2018 -0400
@@ -172,3 +172,115 @@
                 dataset.metadata.reference_name = fname[:-4]
                 break
         self.regenerate_primary_file(dataset)
+
+
+class RsemBt2Reference(Html):
+    """Class describing an RSEM reference"""
+    MetadataElement(name='reference_name', default='rsem_bt2_ref',
+                    desc='RSEM Bowtie2 Reference Name', readonly=True,
+                    visible=True, set_in_upload=True, no_value='rsem_bt2_ref')
+    file_ext = 'rsem_bt2_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>.n2g.idx.fa
+        extra_files_path/<reference_name>.1.bt2
+        extra_files_path/<reference_name>.2.bt2
+        extra_files_path/<reference_name>.3.bt2
+        extra_files_path/<reference_name>.4.bt2
+        extra_files_path/<reference_name>.rev.1.bt2
+        extra_files_path/<reference_name>.rev.2.bt2
+        """
+        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.n2g.idx.fa', description='',
+                                substitute_name_with_metadata='reference_name',
+                                is_binary=False, optional=True)
+        self.add_composite_file('%s.1.bt2', description='',
+                                substitute_name_with_metadata='reference_name',
+                                is_binary=True, optional=True)
+        self.add_composite_file('%s.2.bt2', description='',
+                                substitute_name_with_metadata='reference_name',
+                                is_binary=True, optional=True)
+        self.add_composite_file('%s.3.bt2', description='',
+                                substitute_name_with_metadata='reference_name',
+                                is_binary=True, optional=True)
+        self.add_composite_file('%s.4.bt2', description='',
+                                substitute_name_with_metadata='reference_name',
+                                is_binary=True, optional=True)
+        self.add_composite_file('%s.rev.1.bt2', description='',
+                                substitute_name_with_metadata='reference_name',
+                                is_binary=True, optional=True)
+        self.add_composite_file('%s.rev.2.bt2', 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)