Allow mmCIF inputs

frontend/multifoxs/submit_page.py

@@ -59,17 +59,22 @@ def handle_new_job():
 def handle_pdb(pdb_code, pdb_file, job):
     """Handle input PDB code or file. Return file name."""
     if pdb_file:
-        fname = 'input.pdb'
+        if pdb_file.filename.endswith('.cif'):
+            fname = 'input.cif'
+        else:
+            fname = 'input.pdb'
         full_fname = job.get_path(fname)
         pdb_file.save(full_fname)
-        saliweb.frontend.check_pdb(full_fname)
+        saliweb.frontend.check_pdb_or_mmcif(
+            full_fname, show_filename=os.path.basename(pdb_file.filename))
         return fname
     elif pdb_code:
-        fname = saliweb.frontend.get_pdb_chains(pdb_code, job.directory)
+        fname = saliweb.frontend.get_pdb_chains(
+            pdb_code, job.directory, formats=["PDB", "MMCIF", "IHM"])
         return os.path.basename(fname)
     else:
         raise InputValidationError("Error in protein input: please specify "
-                                   "PDB code or upload file")
+                                   "PDB code or upload PDB/mmCIF file")
 
 
 def handle_uploaded_file(fh, job, output_file, description,

frontend/multifoxs/templates/download.html

@@ -14,7 +14,7 @@ <h3><font color='#B22222'>Download</font></h3>
 
 <ol> 
 
-<li><p>Conformational sampling. Prepare your input PDB file and flexible residues file as explained in <a href="help.cgi?type=help#protein"> Help </a>:</p>
+<li><p>Conformational sampling. Prepare your input PDB or mmCIF file and flexible residues file as explained in <a href="help.cgi?type=help#protein"> Help </a>:</p>
 
 <div class="imp-code notranslate htmlHigh">
 <br /> rrt_sample protein_PDB flexible_residues_file -i 1000000 -n 10000 <br />

frontend/multifoxs/templates/help.html

@@ -9,8 +9,8 @@ <h3><font color='#B22222'>Input Fields</font></h3>
 
 <ul>
 <li><a name="protein"></a><b>Input protein:</b> it is possible to
-specify the PDB code of the input protein <b>or</b> upload a file in PDB
-format. Each code is a four character PDB ID, followed by a colon and
+specify the PDB code of the input protein <b>or</b> upload a file in PDB or
+mmCIF format. Each code is a four character PDB ID, followed by a colon and
 a comma-separated list of chain IDs, e.g. 2pka:A,B. If no chain IDs are given,
 all the chains of the PDB file are used.
 

frontend/multifoxs/templates/index.html

@@ -8,7 +8,7 @@
 
   <table cellpadding="5" cellspacing="0">
     <tr>
-      <td>Type PDB code for protein or upload file in PDB format  <a href="{{ url_for("help", _anchor="sampleinput") }}">sample input files</a></td>
+      <td>Type PDB code for protein or upload file in PDB or mmCIF format  <a href="{{ url_for("help", _anchor="sampleinput") }}">sample input files</a></td>
     </tr>
   </table>
   <table border="0" cellpadding="5" cellspacing="0" width="99%">

test/frontend/test_submit.py

@@ -2,13 +2,71 @@
 import saliweb.test
 import tempfile
 import os
+import gzip
 import re
 
 # Import the multifoxs frontend with mocks
 multifoxs = saliweb.test.import_mocked_frontend("multifoxs", __file__,
                                                 '../../frontend')
 
 
+def make_test_pdb(pdbf, compressed=False):
+    def write(fh):
+        fh.write(
+            "REMARK\n"
+            "ATOM      2  CA  ALA C   1      26.711  14.576   5.091\n")
+
+    if compressed:
+        with gzip.open(pdbf, 'wt') as fh:
+            write(fh)
+    else:
+        with open(pdbf, 'w') as fh:
+            write(fh)
+
+
+def make_test_mmcif(fname, compressed=False):
+    def write(fh):
+        fh.write("""
+loop_
+_atom_site.group_PDB
+_atom_site.type_symbol
+_atom_site.label_atom_id
+_atom_site.label_alt_id
+_atom_site.label_comp_id
+_atom_site.label_asym_id
+_atom_site.auth_asym_id
+_atom_site.label_seq_id
+_atom_site.auth_seq_id
+_atom_site.pdbx_PDB_ins_code
+_atom_site.Cartn_x
+_atom_site.Cartn_y
+_atom_site.Cartn_z
+_atom_site.occupancy
+_atom_site.B_iso_or_equiv
+_atom_site.label_entity_id
+_atom_site.id
+_atom_site.pdbx_PDB_model_num
+ATOM N N . ALA A C 1 1 ? 27.932 14.488 4.257 1.000 23.91 1 1 1
+ATOM N N . ALA B D 1 1 ? 27.932 14.488 4.257 1.000 23.91 1 2 1
+""")
+
+    if compressed:
+        with gzip.open(fname, 'wt') as fh:
+            write(fh)
+    else:
+        with open(fname, 'w') as fh:
+            write(fh)
+
+
+def make_test_profile(saxsf):
+    with open(saxsf, 'w') as fh:
+        fh.write("# sample profile\n"
+                 "garbage\n"
+                 "more garbage, ignored\n"
+                 "0.1 -0.5\n"
+                 "0.00000    9656627.00000000 2027.89172363\n")
+
+
 class Tests(saliweb.test.TestCase):
     """Check submit page"""
 
@@ -27,8 +85,9 @@ def test_submit_page_pdb_no_atoms(self):
                 '/job', data={'pdbfile': open(pdbfile, 'rb'),
                               'modelsnumber': "5", "units": "unknown"})
             self.assertEqual(rv.status_code, 400)
-            self.assertIn(b'PDB file contains no ATOM or HETATM records',
-                          rv.data)
+            self.assertIn(
+                b'PDB file test.pdb contains no ATOM or HETATM records',
+                rv.data)
 
     def test_submit_page_bad_profile(self):
         """Test submit page with invalid profile"""
@@ -38,9 +97,7 @@ def test_submit_page_bad_profile(self):
             multifoxs.app.config['DIRECTORIES_INCOMING'] = incoming
             c = multifoxs.app.test_client()
             pdbfile = os.path.join(tmpdir, 'test.pdb')
-            with open(pdbfile, 'w') as fh:
-                fh.write(
-                    "ATOM      2  CA  ALA     1      26.711  14.576   5.091\n")
+            make_test_pdb(pdbfile)
             saxsf = os.path.join(tmpdir, 'test.profile')
             with open(saxsf, 'w') as fh:
                 fh.write("garbage\n")
@@ -52,26 +109,18 @@ def test_submit_page_bad_profile(self):
             self.assertEqual(rv.status_code, 400)
             self.assertIn(b'Invalid profile uploaded', rv.data)
 
-    def test_submit_page(self):
-        """Test submit page"""
+    def test_submit_page_pdb(self):
+        """Test submit page, PDB format"""
         with tempfile.TemporaryDirectory() as tmpdir:
             incoming = os.path.join(tmpdir, 'incoming')
             os.mkdir(incoming)
             multifoxs.app.config['DIRECTORIES_INCOMING'] = incoming
             c = multifoxs.app.test_client()
 
             pdbf = os.path.join(tmpdir, 'test.pdb')
-            with open(pdbf, 'w') as fh:
-                fh.write(
-                    "REMARK\n"
-                    "ATOM      2  CA  ALA     1      26.711  14.576   5.091\n")
+            make_test_pdb(pdbf)
             saxsf = os.path.join(tmpdir, 'test.profile')
-            with open(saxsf, 'w') as fh:
-                fh.write("# sample profile\n"
-                         "garbage\n"
-                         "more garbage, ignored\n"
-                         "0.1 -0.5\n"
-                         "0.00000    9656627.00000000 2027.89172363\n")
+            make_test_profile(saxsf)
             emptyf = os.path.join(tmpdir, 'emptyf')
             with open(emptyf, 'w') as fh:
                 pass
@@ -98,7 +147,8 @@ def test_submit_page(self):
                     'hingefile': open(linkf, 'rb'), 'jobname': 'foobar'}
             rv = c.post('/job', data=data)
             self.assertEqual(rv.status_code, 400)
-            self.assertIn(b'please specify PDB code or upload file', rv.data)
+            self.assertIn(b'please specify PDB code or upload PDB/mmCIF file',
+                          rv.data)
 
             # Missing SAXS file
             data = {'modelsnumber': '100', 'units': 'unknown',
@@ -148,6 +198,93 @@ def test_submit_page(self):
                            re.MULTILINE | re.DOTALL)
             self.assertRegex(rv.data, r)
 
+    def test_submit_page_mmcif(self):
+        """Test submit page, mmCIF format"""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            incoming = os.path.join(tmpdir, 'incoming')
+            os.mkdir(incoming)
+            multifoxs.app.config['DIRECTORIES_INCOMING'] = incoming
+            c = multifoxs.app.test_client()
+
+            pdbf = os.path.join(tmpdir, 'test.cif')
+            make_test_mmcif(pdbf)
+            saxsf = os.path.join(tmpdir, 'test.profile')
+            make_test_profile(saxsf)
+            linkf = os.path.join(tmpdir, 'test.linkers')
+            with open(linkf, 'w') as fh:
+                fh.write("189 A\n")
+
+            data = {'modelsnumber': '100', 'units': 'unknown',
+                    'pdbfile': open(pdbf, 'rb'), 'saxsfile': open(saxsf, 'rb'),
+                    'hingefile': open(linkf, 'rb'), 'jobname': 'foobar'}
+            rv = c.post('/job', data=data)
+            self.assertEqual(rv.status_code, 200)
+            r = re.compile(b'Your job <b>foobar</b> has been submitted.*'
+                           b'Results will be found at',
+                           re.MULTILINE | re.DOTALL)
+            self.assertRegex(rv.data, r)
+
+    def test_submit_pdb_code_pdb(self):
+        """Test submit with a PDB code (PDB format)"""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            incoming = os.path.join(tmpdir, 'incoming')
+            os.mkdir(incoming)
+            pdb_root = os.path.join(tmpdir, 'pdb')
+            os.mkdir(pdb_root)
+            multifoxs.app.config['DIRECTORIES_INCOMING'] = incoming
+            multifoxs.app.config['PDB_ROOT'] = pdb_root
+            c = multifoxs.app.test_client()
+
+            os.mkdir(os.path.join(pdb_root, 'xy'))
+            pdbf = os.path.join(pdb_root, 'xy', 'pdb1xyz.ent.gz')
+            make_test_pdb(pdbf, compressed=True)
+            saxsf = os.path.join(tmpdir, 'test.profile')
+            make_test_profile(saxsf)
+            linkf = os.path.join(tmpdir, 'test.linkers')
+            with open(linkf, 'w') as fh:
+                fh.write("189 A\n")
+
+            data = {'modelsnumber': '100', 'units': 'unknown',
+                    'pdbcode': '1xyz:C', 'saxsfile': open(saxsf, 'rb'),
+                    'hingefile': open(linkf, 'rb'), 'jobname': 'foobar'}
+            rv = c.post('/job', data=data)
+            self.assertEqual(rv.status_code, 200)
+            r = re.compile(b'Your job <b>foobar</b> has been submitted.*'
+                           b'Results will be found at',
+                           re.MULTILINE | re.DOTALL)
+            self.assertRegex(rv.data, r)
+
+    def test_submit_pdb_code_mmcif(self):
+        """Test submit with a PDB code (mmCIF format)"""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            incoming = os.path.join(tmpdir, 'incoming')
+            os.mkdir(incoming)
+            pdb_root = os.path.join(tmpdir, 'pdb')
+            os.mkdir(pdb_root)
+            multifoxs.app.config['DIRECTORIES_INCOMING'] = incoming
+            multifoxs.app.config['PDB_ROOT'] = pdb_root
+            multifoxs.app.config['MMCIF_ROOT'] = pdb_root
+            c = multifoxs.app.test_client()
+
+            os.mkdir(os.path.join(pdb_root, 'xy'))
+            pdbf = os.path.join(pdb_root, 'xy', '1xyz.cif.gz')
+            make_test_mmcif(pdbf, compressed=True)
+            saxsf = os.path.join(tmpdir, 'test.profile')
+            make_test_profile(saxsf)
+            linkf = os.path.join(tmpdir, 'test.linkers')
+            with open(linkf, 'w') as fh:
+                fh.write("189 A\n")
+
+            data = {'modelsnumber': '100', 'units': 'unknown',
+                    'pdbcode': '1xyz:C', 'saxsfile': open(saxsf, 'rb'),
+                    'hingefile': open(linkf, 'rb'), 'jobname': 'foobar'}
+            rv = c.post('/job', data=data)
+            self.assertEqual(rv.status_code, 200)
+            r = re.compile(b'Your job <b>foobar</b> has been submitted.*'
+                           b'Results will be found at',
+                           re.MULTILINE | re.DOTALL)
+            self.assertRegex(rv.data, r)
+
 
 if __name__ == '__main__':
     unittest.main()