SBRG / ssbio

A Python framework for structural systems biology
http://ssbio.readthedocs.io/en/latest/
MIT License
104 stars 28 forks source link

Fail to read P00533 #47

Open bkellman opened 6 years ago

bkellman commented 6 years ago

My code:


PROJECT = 'GTspec_query'
LIST_OF_GENES = ['P01106','P01229','P01374']
PDB_FILE_TYPE = 'mmtf'

# Create the GEM-PRO project
my_gempro = GEMPRO(gem_name=PROJECT, root_dir=ROOT_DIR, genes_list=LIST_OF_GENES, pdb_file_type=PDB_FILE_TYPE)

# UniProt mapping
my_gempro.uniprot_mapping_and_metadata(model_gene_source='ACC+ID') 

fails and it appears to be due to a bad model in P00533. Error below

<ipython-input-2-d2f5408c2c3e> in <module>()
----> 1 execfile('02_structure_annote.py')

/media/ben/9c17f1c9-a45e-49ec-b547-8fbd2f25ccc6/GTspecificity/02_structure_annote.py in <module>()
    43
    44 # UniProt mapping
---> 45 my_gempro.uniprot_mapping_and_metadata(model_gene_source='ACC+ID')  ## [Nathan] can leave this as ACC+ID which means your list o
    46 print('Missing UniProt mapping: ', my_gempro.missing_uniprot_mapping)
    47 my_gempro.df_uniprot_metadata.head()

/home/ben/anaconda2/lib/python2.7/site-packages/ssbio/pipeline/gempro.pyc in uniprot_mapping_and_metadata(self, model_gene_source, custo
   546                         uniprot_prop = g.protein.load_uniprot(uniprot_id=mapped_uniprot, download=True, outdir=outdir,
   547                                                               set_as_representative=set_as_representative,
--> 548                                                               force_rerun=force_rerun)
   549                     except HTTPError as e:
   550                         log.error('{}, {}: unable to complete web request'.format(g.id, mapped_uniprot))

/home/ben/anaconda2/lib/python2.7/site-packages/ssbio/core/protein.pyc in load_uniprot(self, uniprot_id, uniprot_seq_file, uniprot_xml_f
   378             if download:
   379                 uniprot_prop.download_metadata_file(outdir=outdir, force_rerun=force_rerun)
--> 380                 uniprot_prop.download_seq_file(outdir=outdir, force_rerun=force_rerun)
   381
   382             # Also check if UniProt sequence matches a potentially set representative sequence

/home/ben/anaconda2/lib/python2.7/site-packages/ssbio/databases/uniprot.pyc in download_seq_file(self, outdir, force_rerun)
   183                                                    force_rerun=force_rerun)
   184
--> 185         self.sequence_path = uniprot_fasta_file
   186
   187     def download_metadata_file(self, outdir, force_rerun=False):

/home/ben/anaconda2/lib/python2.7/site-packages/ssbio/protein/sequence/seqprop.pyc in sequence_path(self, fasta_path)