comparison gene_family_scaffold_loader.py @ 10:11a36e425c94 draft

Uploaded

9:1a5fecd8e5c1

        1. Parse all of the *.list files in the same directory to populate
        self.scaffold_genes_dict.
        """
        scaffold_id = os.path.basename(self.args.scaffold_path)
        file_dir = os.path.join(self.args.scaffold_path, 'annot')
        # The scaffol naming convention must follow this pattern:
        # <integer1>Gv<integer2>.<integer3>
        # where integer 1 is the number of genomes in the scaffold_id.  For example:
        # 22Gv1.1 -> 22 genomes
        # 12Gv1.0 -> 12 genomes
        # 26Gv2.0 -> 26 genomes, etc.

                i = 0
                for i2, line in enumerate(fh):
                    if i2 == 0:
                        # Skip first line.
                        continue
                    num_genes = 0
                    num_species = 0
                    items = line.split("\t")
                    orthogroup_id = int(items[0])
                    # Zero based items 1 to num_genomes consists of the

10:11a36e425c94

        1. Parse all of the *.list files in the same directory to populate
        self.scaffold_genes_dict.
        """
        scaffold_id = os.path.basename(self.args.scaffold_path)
        file_dir = os.path.join(self.args.scaffold_path, 'annot')
        # The scaffold naming convention must follow this pattern:
        # <integer1>Gv<integer2>.<integer3>
        # where integer 1 is the number of genomes in the scaffold_id.  For example:
        # 22Gv1.1 -> 22 genomes
        # 12Gv1.0 -> 12 genomes
        # 26Gv2.0 -> 26 genomes, etc.

                i = 0
                for i2, line in enumerate(fh):
                    if i2 == 0:
                        # Skip first line.
                        continue
                    line = line.rstrip('\n')
                    num_genes = 0
                    num_species = 0
                    items = line.split("\t")
                    orthogroup_id = int(items[0])
                    # Zero based items 1 to num_genomes consists of the