Merge pull request #32 from danielparton/master

Version 1.0.3 release

docs/cli_docs.rst

@@ -41,3 +41,26 @@ PDB-format coordinate files in the directory ``templates/structures-resolved``.
 Each structure should be named XXX.pdb, where XXX matches the identifier in the
 fasta file. The residues in the coordinate files should also match the
 sequences in the fasta file.
+
+Additional Tools
+================
+
+Ensembler includes a ``tools`` submodule, which allows the user to conduct
+various useful tasks which are not considered core pipeline functions. The
+use-cases for many of these tools are quite specific, so they may not be
+applicable to every project, and should also be used with caution.
+
+Residue renumbering according to UniProt sequence coordinates
+-------------------------------------------------------------
+
+::
+
+  $ ensembler renumber_residues --target EGFR_HUMAN_D0
+
+The given target ID must begin with a UniProt mnemonic, e.g. "EGFR_HUMAN".
+This will output two files in the ``models/[target_id]`` directory:
+``topol-renumbered-implicit.pdb`` and ``topol-renumbered-explicit.pdb``.
+The coordinates are simply copied from the first example found for each of
+``refined-implicit.pdb.gz`` and ``refined-explicit.pdb.gz``. The residue
+numbers are renumbered according to the canonical isoform sequence coordinates
+in the UniProt entry.

ensembler/cli.py

@@ -42,4 +42,4 @@ def main():
 
     if not command_dispatched and args['--help']:
         print('\n'.join([ensembler.cli_commands.general.helpstring_header, ensembler.cli_commands.general.ensembler_helpstring]))
-        pass
+        pass

ensembler/cli_commands/__init__.py

@@ -12,6 +12,7 @@
     'refine_explicit',
     'package_models',
     'quickmodel',
+    'renumber_residues',
 ]
 
 from . import general
@@ -27,4 +28,5 @@
 from . import solvate
 from . import refine_explicit
 from . import package_models
-from . import quickmodel
+from . import quickmodel
+from . import renumber_residues

ensembler/cli_commands/general.py

@@ -36,13 +36,14 @@
       [--api_params <params>] [-v | --verbose]
   ensembler package_models [-h | --help] [--package_for <choice>] [--targets <target>]
       [--targetsfile <targetsfile>] [--templates <template>] [--templatesfile <templatesfile>]
-      [--template_seqid_cutoff <cutoff>] [--nfahclones <n>] [--archivefahproject] [-v | --verbose]
+      [--template_seqid_cutoff <cutoff>] [--nfahclones <n>] [--compressruns] [-v | --verbose]
   ensembler testrun_pipeline [-h | --help]
   ensembler quickmodel [-h | --help] [--targetid <id>] [--templateids <ids>]
       [--target_uniprot_entry_name <entry_name>] [--uniprot_domain_regex <regex>]
       [--template_pdbids <pdbids>] [--template_chainids <chainids>]
       [--template_uniprot_query <query>] [--template_seqid_cutoff <cutoff>] [--no-loopmodel]
       [--package_for_fah] [--nfahclones <nfahclones>] [--structure_dirs <structure_dirs>]
+  ensembler renumber_residues [-h | --help] [--target <targetid>] [-v | --verbose]
 
 Commands:
   init                          Initialize a new Ensembler project

ensembler/cli_commands/package_models.py

@@ -22,8 +22,8 @@
                                         to use for each model [default: 1].""",
 
     """\
-  --archivefahproject                   If packaging for Folding@Home, choose whether to compress
-                                        the results into a .tgz file.""",
+  --compressruns                        If packaging for Folding@Home, choose whether to compress
+                                        each RUN into a .tgz file.""",
 ]
 
 helpstring_nonunique_options = [
@@ -86,7 +86,7 @@ def dispatch(args):
     else:
         n_fah_clones = 1
 
-    if args['--archivefahproject']:
+    if args['--compressruns']:
         archive = True
     else:
         archive = False
@@ -109,5 +109,5 @@ def dispatch(args):
             template_seqid_cutoff=template_seqid_cutoff,
             nclones=n_fah_clones,
             archive=archive,
-            verbose=args['--verbose'],
+            loglevel=loglevel,
         )

ensembler/cli_commands/refine_explicit.py

@@ -75,6 +75,7 @@
 helpstring = '\n\n'.join([helpstring_header, '\n\n'.join(helpstring_unique_options), '\n\n'.join(helpstring_nonunique_options)])
 docopt_helpstring = '\n\n'.join(helpstring_unique_options)
 
+
 def dispatch(args):
     if args['--targetsfile']:
         with open(args['--targetsfile'], 'r') as targetsfile:

ensembler/cli_commands/renumber_residues.py

@@ -0,0 +1,30 @@
+from ensembler.tools.renumber_residues import RenumberResidues
+
+helpstring_header = """Renumber residues using the canonical UniProt sequence coordinates.
+Target IDs must start with the UniProt mnemonic, e.g. 'ABL1_HUMAN'
+"""
+
+helpstring_unique_options = [
+    """\
+  --target <targetid>          ID for target to work, e.g. 'ABL1_HUMAN_D0'""",
+]
+
+helpstring_nonunique_options = [
+    """\
+  -v --verbose                 """,
+]
+
+helpstring = '\n\n'.join([helpstring_header, '\n\n'.join(helpstring_unique_options), '\n\n'.join(helpstring_nonunique_options)])
+docopt_helpstring = '\n\n'.join(helpstring_unique_options)
+
+
+def dispatch(args):
+    if args['--verbose']:
+        log_level = 'debug'
+    else:
+        log_level = 'info'
+
+    RenumberResidues(
+        targetid=args['--target'],
+        log_level=log_level
+    )

ensembler/initproject.py

@@ -11,6 +11,7 @@
 from Bio.SeqRecord import SeqRecord
 
 import ensembler
+import ensembler.version
 import ensembler.targetexplorer
 import ensembler.uniprot
 import ensembler.pdb